openkylin
/
platform_kernel-5.15
mirror of https://gitee.com/openkylin/platform_kernel-5.15.git
9
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'upstream-master' into android-mainline 

This is an intermediate (mid-week) merge of Linus's tree into
android-mainline to take all of the "big" security fixes that went into
there into the android-mainline tree to get testing happening sooner.

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: Ie4d7914776ac1f917de0436061e46295ad919ead
This commit is contained in:
Greg Kroah-Hartman 2019-11-14 10:43:19 +08:00
parent 87d2866d54 0e3f1ad80f
commit 32815416dd
61 changed files with 2328 additions and 3608 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Documentation/ABI/testing/sysfs-devices-system-cpu
View File

@ -486,6 +486,8 @@ What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
/sys/devices/system/cpu/vulnerabilities/l1tf
/sys/devices/system/cpu/vulnerabilities/mds
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
/sys/devices/system/cpu/vulnerabilities/itlb_multihit
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities

2
Documentation/admin-guide/hw-vuln/index.rst
View File

@ -12,3 +12,5 @@ are configurable at compile, boot or run time.
spectre
l1tf
mds
tsx_async_abort
multihit.rst

163
Documentation/admin-guide/hw-vuln/multihit.rst Normal file
View File

@ -0,0 +1,163 @@
iTLB multihit
=============
iTLB multihit is an erratum where some processors may incur a machine check
error, possibly resulting in an unrecoverable CPU lockup, when an
instruction fetch hits multiple entries in the instruction TLB. This can
occur when the page size is changed along with either the physical address
or cache type. A malicious guest running on a virtualized system can
exploit this erratum to perform a denial of service attack.
Affected processors
-------------------
Variations of this erratum are present on most Intel Core and Xeon processor
models. The erratum is not present on:
- non-Intel processors
- Some Atoms (Airmont, Bonnell, Goldmont, GoldmontPlus, Saltwell, Silvermont)
- Intel processors that have the PSCHANGE_MC_NO bit set in the
IA32_ARCH_CAPABILITIES MSR.
Related CVEs
------------
The following CVE entry is related to this issue:
============== =================================================
CVE-2018-12207 Machine Check Error Avoidance on Page Size Change
============== =================================================
Problem
-------
Privileged software, including OS and virtual machine managers (VMM), are in
charge of memory management. A key component in memory management is the control
of the page tables. Modern processors use virtual memory, a technique that creates
the illusion of a very large memory for processors. This virtual space is split
into pages of a given size. Page tables translate virtual addresses to physical
addresses.
To reduce latency when performing a virtual to physical address translation,
processors include a structure, called TLB, that caches recent translations.
There are separate TLBs for instruction (iTLB) and data (dTLB).
Under this errata, instructions are fetched from a linear address translated
using a 4 KB translation cached in the iTLB. Privileged software modifies the
paging structure so that the same linear address using large page size (2 MB, 4
MB, 1 GB) with a different physical address or memory type. After the page
structure modification but before the software invalidates any iTLB entries for
the linear address, a code fetch that happens on the same linear address may
cause a machine-check error which can result in a system hang or shutdown.
Attack scenarios
----------------
Attacks against the iTLB multihit erratum can be mounted from malicious
guests in a virtualized system.
iTLB multihit system information
--------------------------------
The Linux kernel provides a sysfs interface to enumerate the current iTLB
multihit status of the system:whether the system is vulnerable and which
mitigations are active. The relevant sysfs file is:
/sys/devices/system/cpu/vulnerabilities/itlb_multihit
The possible values in this file are:
.. list-table::
* - Not affected
- The processor is not vulnerable.
* - KVM: Mitigation: Split huge pages
- Software changes mitigate this issue.
* - KVM: Vulnerable
- The processor is vulnerable, but no mitigation enabled
Enumeration of the erratum
--------------------------------
A new bit has been allocated in the IA32_ARCH_CAPABILITIES (PSCHANGE_MC_NO) msr
and will be set on CPU's which are mitigated against this issue.
======================================= =========== ===============================
IA32_ARCH_CAPABILITIES MSR Not present Possibly vulnerable,check model
IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '0' Likely vulnerable,check model
IA32_ARCH_CAPABILITIES[PSCHANGE_MC_NO] '1' Not vulnerable
======================================= =========== ===============================
Mitigation mechanism
-------------------------
This erratum can be mitigated by restricting the use of large page sizes to
non-executable pages. This forces all iTLB entries to be 4K, and removes
the possibility of multiple hits.
In order to mitigate the vulnerability, KVM initially marks all huge pages
as non-executable. If the guest attempts to execute in one of those pages,
the page is broken down into 4K pages, which are then marked executable.
If EPT is disabled or not available on the host, KVM is in control of TLB
flushes and the problematic situation cannot happen. However, the shadow
EPT paging mechanism used by nested virtualization is vulnerable, because
the nested guest can trigger multiple iTLB hits by modifying its own
(non-nested) page tables. For simplicity, KVM will make large pages
non-executable in all shadow paging modes.
Mitigation control on the kernel command line and KVM - module parameter
------------------------------------------------------------------------
The KVM hypervisor mitigation mechanism for marking huge pages as
non-executable can be controlled with a module parameter "nx_huge_pages=".
The kernel command line allows to control the iTLB multihit mitigations at
boot time with the option "kvm.nx_huge_pages=".
The valid arguments for these options are:
========== ================================================================
force Mitigation is enabled. In this case, the mitigation implements
non-executable huge pages in Linux kernel KVM module. All huge
pages in the EPT are marked as non-executable.
If a guest attempts to execute in one of those pages, the page is
broken down into 4K pages, which are then marked executable.
off Mitigation is disabled.
auto Enable mitigation only if the platform is affected and the kernel
was not booted with the "mitigations=off" command line parameter.
This is the default option.
========== ================================================================
Mitigation selection guide
--------------------------
1. No virtualization in use
^^^^^^^^^^^^^^^^^^^^^^^^^^^
The system is protected by the kernel unconditionally and no further
action is required.
2. Virtualization with trusted guests
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If the guest comes from a trusted source, you may assume that the guest will
not attempt to maliciously exploit these errata and no further action is
required.
3. Virtualization with untrusted guests
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If the guest comes from an untrusted source, the guest host kernel will need
to apply iTLB multihit mitigation via the kernel command line or kvm
module parameter.

276
Documentation/admin-guide/hw-vuln/tsx_async_abort.rst Normal file
View File

@ -0,0 +1,276 @@
.. SPDX-License-Identifier: GPL-2.0
TAA - TSX Asynchronous Abort
======================================
TAA is a hardware vulnerability that allows unprivileged speculative access to
data which is available in various CPU internal buffers by using asynchronous
aborts within an Intel TSX transactional region.
Affected processors
-------------------
This vulnerability only affects Intel processors that support Intel
Transactional Synchronization Extensions (TSX) when the TAA_NO bit (bit 8)
is 0 in the IA32_ARCH_CAPABILITIES MSR. On processors where the MDS_NO bit
(bit 5) is 0 in the IA32_ARCH_CAPABILITIES MSR, the existing MDS mitigations
also mitigate against TAA.
Whether a processor is affected or not can be read out from the TAA
vulnerability file in sysfs. See :ref:`tsx_async_abort_sys_info`.
Related CVEs
------------
The following CVE entry is related to this TAA issue:
============== ===== ===================================================
CVE-2019-11135 TAA TSX Asynchronous Abort (TAA) condition on some
microprocessors utilizing speculative execution may
allow an authenticated user to potentially enable
information disclosure via a side channel with
local access.
============== ===== ===================================================
Problem
-------
When performing store, load or L1 refill operations, processors write
data into temporary microarchitectural structures (buffers). The data in
those buffers can be forwarded to load operations as an optimization.
Intel TSX is an extension to the x86 instruction set architecture that adds
hardware transactional memory support to improve performance of multi-threaded
software. TSX lets the processor expose and exploit concurrency hidden in an
application due to dynamically avoiding unnecessary synchronization.
TSX supports atomic memory transactions that are either committed (success) or
aborted. During an abort, operations that happened within the transactional region
are rolled back. An asynchronous abort takes place, among other options, when a
different thread accesses a cache line that is also used within the transactional
region when that access might lead to a data race.
Immediately after an uncompleted asynchronous abort, certain speculatively
executed loads may read data from those internal buffers and pass it to dependent
operations. This can be then used to infer the value via a cache side channel
attack.
Because the buffers are potentially shared between Hyper-Threads cross
Hyper-Thread attacks are possible.
The victim of a malicious actor does not need to make use of TSX. Only the
attacker needs to begin a TSX transaction and raise an asynchronous abort
which in turn potenitally leaks data stored in the buffers.
More detailed technical information is available in the TAA specific x86
architecture section: :ref:`Documentation/x86/tsx_async_abort.rst <tsx_async_abort>`.
Attack scenarios
----------------
Attacks against the TAA vulnerability can be implemented from unprivileged
applications running on hosts or guests.
As for MDS, the attacker has no control over the memory addresses that can
be leaked. Only the victim is responsible for bringing data to the CPU. As
a result, the malicious actor has to sample as much data as possible and
then postprocess it to try to infer any useful information from it.
A potential attacker only has read access to the data. Also, there is no direct
privilege escalation by using this technique.
.. _tsx_async_abort_sys_info:
TAA system information
-----------------------
The Linux kernel provides a sysfs interface to enumerate the current TAA status
of mitigated systems. The relevant sysfs file is:
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
The possible values in this file are:
.. list-table::
* - 'Vulnerable'
- The CPU is affected by this vulnerability and the microcode and kernel mitigation are not applied.
* - 'Vulnerable: Clear CPU buffers attempted, no microcode'
- The system tries to clear the buffers but the microcode might not support the operation.
* - 'Mitigation: Clear CPU buffers'
- The microcode has been updated to clear the buffers. TSX is still enabled.
* - 'Mitigation: TSX disabled'
- TSX is disabled.
* - 'Not affected'
- The CPU is not affected by this issue.
.. _ucode_needed:
Best effort mitigation mode
^^^^^^^^^^^^^^^^^^^^^^^^^^^
If the processor is vulnerable, but the availability of the microcode-based
mitigation mechanism is not advertised via CPUID the kernel selects a best
effort mitigation mode. This mode invokes the mitigation instructions
without a guarantee that they clear the CPU buffers.
This is done to address virtualization scenarios where the host has the
microcode update applied, but the hypervisor is not yet updated to expose the
CPUID to the guest. If the host has updated microcode the protection takes
effect; otherwise a few CPU cycles are wasted pointlessly.
The state in the tsx_async_abort sysfs file reflects this situation
accordingly.
Mitigation mechanism
--------------------
The kernel detects the affected CPUs and the presence of the microcode which is
required. If a CPU is affected and the microcode is available, then the kernel
enables the mitigation by default.
The mitigation can be controlled at boot time via a kernel command line option.
See :ref:`taa_mitigation_control_command_line`.
.. _virt_mechanism:
Virtualization mitigation
^^^^^^^^^^^^^^^^^^^^^^^^^
Affected systems where the host has TAA microcode and TAA is mitigated by
having disabled TSX previously, are not vulnerable regardless of the status
of the VMs.
In all other cases, if the host either does not have the TAA microcode or
the kernel is not mitigated, the system might be vulnerable.
.. _taa_mitigation_control_command_line:
Mitigation control on the kernel command line
---------------------------------------------
The kernel command line allows to control the TAA mitigations at boot time with
the option "tsx_async_abort=". The valid arguments for this option are:
============ =============================================================
off This option disables the TAA mitigation on affected platforms.
If the system has TSX enabled (see next parameter) and the CPU
is affected, the system is vulnerable.
full TAA mitigation is enabled. If TSX is enabled, on an affected
system it will clear CPU buffers on ring transitions. On
systems which are MDS-affected and deploy MDS mitigation,
TAA is also mitigated. Specifying this option on those
systems will have no effect.
full,nosmt The same as tsx_async_abort=full, with SMT disabled on
vulnerable CPUs that have TSX enabled. This is the complete
mitigation. When TSX is disabled, SMT is not disabled because
CPU is not vulnerable to cross-thread TAA attacks.
============ =============================================================
Not specifying this option is equivalent to "tsx_async_abort=full".
The kernel command line also allows to control the TSX feature using the
parameter "tsx=" on CPUs which support TSX control. MSR_IA32_TSX_CTRL is used
to control the TSX feature and the enumeration of the TSX feature bits (RTM
and HLE) in CPUID.
The valid options are:
============ =============================================================
off Disables TSX on the system.
Note that this option takes effect only on newer CPUs which are
not vulnerable to MDS, i.e., have MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1
and which get the new IA32_TSX_CTRL MSR through a microcode
update. This new MSR allows for the reliable deactivation of
the TSX functionality.
on Enables TSX.
Although there are mitigations for all known security
vulnerabilities, TSX has been known to be an accelerator for
several previous speculation-related CVEs, and so there may be
unknown security risks associated with leaving it enabled.
auto Disables TSX if X86_BUG_TAA is present, otherwise enables TSX
on the system.
============ =============================================================
Not specifying this option is equivalent to "tsx=off".
The following combinations of the "tsx_async_abort" and "tsx" are possible. For
affected platforms tsx=auto is equivalent to tsx=off and the result will be:
========= ========================== =========================================
tsx=on tsx_async_abort=full The system will use VERW to clear CPU
buffers. Cross-thread attacks are still
possible on SMT machines.
tsx=on tsx_async_abort=full,nosmt As above, cross-thread attacks on SMT
mitigated.
tsx=on tsx_async_abort=off The system is vulnerable.
tsx=off tsx_async_abort=full TSX might be disabled if microcode
provides a TSX control MSR. If so,
system is not vulnerable.
tsx=off tsx_async_abort=full,nosmt Ditto
tsx=off tsx_async_abort=off ditto
========= ========================== =========================================
For unaffected platforms "tsx=on" and "tsx_async_abort=full" does not clear CPU
buffers. For platforms without TSX control (MSR_IA32_ARCH_CAPABILITIES.MDS_NO=0)
"tsx" command line argument has no effect.
For the affected platforms below table indicates the mitigation status for the
combinations of CPUID bit MD_CLEAR and IA32_ARCH_CAPABILITIES MSR bits MDS_NO
and TSX_CTRL_MSR.
======= ========= ============= ========================================
MDS_NO MD_CLEAR TSX_CTRL_MSR Status
======= ========= ============= ========================================
0 0 0 Vulnerable (needs microcode)
0 1 0 MDS and TAA mitigated via VERW
1 1 0 MDS fixed, TAA vulnerable if TSX enabled
because MD_CLEAR has no meaning and
VERW is not guaranteed to clear buffers
1 X 1 MDS fixed, TAA can be mitigated by
VERW or TSX_CTRL_MSR
======= ========= ============= ========================================
Mitigation selection guide
--------------------------
1. Trusted userspace and guests
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If all user space applications are from a trusted source and do not execute
untrusted code which is supplied externally, then the mitigation can be
disabled. The same applies to virtualized environments with trusted guests.
2. Untrusted userspace and guests
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If there are untrusted applications or guests on the system, enabling TSX
might allow a malicious actor to leak data from the host or from other
processes running on the same physical core.
If the microcode is available and the TSX is disabled on the host, attacks
are prevented in a virtualized environment as well, even if the VMs do not
explicitly enable the mitigation.
.. _taa_default_mitigations:
Default mitigations
-------------------
The kernel's default action for vulnerable processors is:
- Deploy TSX disable mitigation (tsx_async_abort=full tsx=off).

92
Documentation/admin-guide/kernel-parameters.txt
View File

@ -2055,6 +2055,25 @@
KVM MMU at runtime.
Default is 0 (off)
kvm.nx_huge_pages=
[KVM] Controls the software workaround for the
X86_BUG_ITLB_MULTIHIT bug.
force : Always deploy workaround.
off : Never deploy workaround.
auto : Deploy workaround based on the presence of
X86_BUG_ITLB_MULTIHIT.
Default is 'auto'.
If the software workaround is enabled for the host,
guests do need not to enable it for nested guests.
kvm.nx_huge_pages_recovery_ratio=
[KVM] Controls how many 4KiB pages are periodically zapped
back to huge pages. 0 disables the recovery, otherwise if
the value is N KVM will zap 1/Nth of the 4KiB pages every
minute. The default is 60.
kvm-amd.nested= [KVM,AMD] Allow nested virtualization in KVM/SVM.
Default is 1 (enabled)
@ -2636,6 +2655,13 @@
ssbd=force-off [ARM64]
l1tf=off [X86]
mds=off [X86]
tsx_async_abort=off [X86]
kvm.nx_huge_pages=off [X86]
Exceptions:
This does not have any effect on
kvm.nx_huge_pages when
kvm.nx_huge_pages=force.
auto (default)
Mitigate all CPU vulnerabilities, but leave SMT
@ -2651,6 +2677,7 @@
be fully mitigated, even if it means losing SMT.
Equivalent to: l1tf=flush,nosmt [X86]
mds=full,nosmt [X86]
tsx_async_abort=full,nosmt [X86]
mminit_loglevel=
[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@ -4854,6 +4881,71 @@
interruptions from clocksource watchdog are not
acceptable).
tsx= [X86] Control Transactional Synchronization
Extensions (TSX) feature in Intel processors that
support TSX control.
This parameter controls the TSX feature. The options are:
on - Enable TSX on the system. Although there are
mitigations for all known security vulnerabilities,
TSX has been known to be an accelerator for
several previous speculation-related CVEs, and
so there may be unknown security risks associated
with leaving it enabled.
off - Disable TSX on the system. (Note that this
option takes effect only on newer CPUs which are
not vulnerable to MDS, i.e., have
MSR_IA32_ARCH_CAPABILITIES.MDS_NO=1 and which get
the new IA32_TSX_CTRL MSR through a microcode
update. This new MSR allows for the reliable
deactivation of the TSX functionality.)
auto - Disable TSX if X86_BUG_TAA is present,
otherwise enable TSX on the system.
Not specifying this option is equivalent to tsx=off.
See Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
for more details.
tsx_async_abort= [X86,INTEL] Control mitigation for the TSX Async
Abort (TAA) vulnerability.
Similar to Micro-architectural Data Sampling (MDS)
certain CPUs that support Transactional
Synchronization Extensions (TSX) are vulnerable to an
exploit against CPU internal buffers which can forward
information to a disclosure gadget under certain
conditions.
In vulnerable processors, the speculatively forwarded
data can be used in a cache side channel attack, to
access data to which the attacker does not have direct
access.
This parameter controls the TAA mitigation. The
options are:
full - Enable TAA mitigation on vulnerable CPUs
if TSX is enabled.
full,nosmt - Enable TAA mitigation and disable SMT on
vulnerable CPUs. If TSX is disabled, SMT
is not disabled because CPU is not
vulnerable to cross-thread TAA attacks.
off - Unconditionally disable TAA mitigation
Not specifying this option is equivalent to
tsx_async_abort=full. On CPUs which are MDS affected
and deploy MDS mitigation, TAA mitigation is not
required and doesn't provide any additional
mitigation.
For details see:
Documentation/admin-guide/hw-vuln/tsx_async_abort.rst
turbografx.map[2|3]= [HW,JOY]
TurboGraFX parallel port interface
Format:

1
Documentation/x86/index.rst
View File

@ -27,6 +27,7 @@ x86-specific Documentation
mds
microcode
resctrl_ui
tsx_async_abort
usb-legacy-support
i386/index
x86_64/index

117
Documentation/x86/tsx_async_abort.rst Normal file
View File

@ -0,0 +1,117 @@
.. SPDX-License-Identifier: GPL-2.0
TSX Async Abort (TAA) mitigation
================================
.. _tsx_async_abort:
Overview
--------
TSX Async Abort (TAA) is a side channel attack on internal buffers in some
Intel processors similar to Microachitectural Data Sampling (MDS). In this
case certain loads may speculatively pass invalid data to dependent operations
when an asynchronous abort condition is pending in a Transactional
Synchronization Extensions (TSX) transaction. This includes loads with no
fault or assist condition. Such loads may speculatively expose stale data from
the same uarch data structures as in MDS, with same scope of exposure i.e.
same-thread and cross-thread. This issue affects all current processors that
support TSX.
Mitigation strategy
-------------------
a) TSX disable - one of the mitigations is to disable TSX. A new MSR
IA32_TSX_CTRL will be available in future and current processors after
microcode update which can be used to disable TSX. In addition, it
controls the enumeration of the TSX feature bits (RTM and HLE) in CPUID.
b) Clear CPU buffers - similar to MDS, clearing the CPU buffers mitigates this
vulnerability. More details on this approach can be found in
:ref:`Documentation/admin-guide/hw-vuln/mds.rst <mds>`.
Kernel internal mitigation modes
--------------------------------
============= ============================================================
off Mitigation is disabled. Either the CPU is not affected or
tsx_async_abort=off is supplied on the kernel command line.
tsx disabled Mitigation is enabled. TSX feature is disabled by default at
bootup on processors that support TSX control.
verw Mitigation is enabled. CPU is affected and MD_CLEAR is
advertised in CPUID.
ucode needed Mitigation is enabled. CPU is affected and MD_CLEAR is not
advertised in CPUID. That is mainly for virtualization
scenarios where the host has the updated microcode but the
hypervisor does not expose MD_CLEAR in CPUID. It's a best
effort approach without guarantee.
============= ============================================================
If the CPU is affected and the "tsx_async_abort" kernel command line parameter is
not provided then the kernel selects an appropriate mitigation depending on the
status of RTM and MD_CLEAR CPUID bits.
Below tables indicate the impact of tsx=on|off|auto cmdline options on state of
TAA mitigation, VERW behavior and TSX feature for various combinations of
MSR_IA32_ARCH_CAPABILITIES bits.
1. "tsx=off"
========= ========= ============ ============ ============== =================== ======================
MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=off
---------------------------------- -------------------------------------------------------------------------
TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation
after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full
========= ========= ============ ============ ============== =================== ======================
0 0 0 HW default Yes Same as MDS Same as MDS
0 0 1 Invalid case Invalid case Invalid case Invalid case
0 1 0 HW default No Need ucode update Need ucode update
0 1 1 Disabled Yes TSX disabled TSX disabled
1 X 1 Disabled X None needed None needed
========= ========= ============ ============ ============== =================== ======================
2. "tsx=on"
========= ========= ============ ============ ============== =================== ======================
MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=on
---------------------------------- -------------------------------------------------------------------------
TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation
after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full
========= ========= ============ ============ ============== =================== ======================
0 0 0 HW default Yes Same as MDS Same as MDS
0 0 1 Invalid case Invalid case Invalid case Invalid case
0 1 0 HW default No Need ucode update Need ucode update
0 1 1 Enabled Yes None Same as MDS
1 X 1 Enabled X None needed None needed
========= ========= ============ ============ ============== =================== ======================
3. "tsx=auto"
========= ========= ============ ============ ============== =================== ======================
MSR_IA32_ARCH_CAPABILITIES bits Result with cmdline tsx=auto
---------------------------------- -------------------------------------------------------------------------
TAA_NO MDS_NO TSX_CTRL_MSR TSX state VERW can clear TAA mitigation TAA mitigation
after bootup CPU buffers tsx_async_abort=off tsx_async_abort=full
========= ========= ============ ============ ============== =================== ======================
0 0 0 HW default Yes Same as MDS Same as MDS
0 0 1 Invalid case Invalid case Invalid case Invalid case
0 1 0 HW default No Need ucode update Need ucode update
0 1 1 Disabled Yes TSX disabled TSX disabled
1 X 1 Enabled X None needed None needed
========= ========= ============ ============ ============== =================== ======================
In the tables, TSX_CTRL_MSR is a new bit in MSR_IA32_ARCH_CAPABILITIES that
indicates whether MSR_IA32_TSX_CTRL is supported.
There are two control bits in IA32_TSX_CTRL MSR:
Bit 0: When set it disables the Restricted Transactional Memory (RTM)
sub-feature of TSX (will force all transactions to abort on the
XBEGIN instruction).
Bit 1: When set it disables the enumeration of the RTM and HLE feature
(i.e. it will make CPUID(EAX=7).EBX{bit4} and
CPUID(EAX=7).EBX{bit11} read as 0).

6
MAINTAINERS
View File

@ -17338,12 +17338,6 @@ F: include/linux/vbox_utils.h
F: include/uapi/linux/vbox*.h
F: drivers/virt/vboxguest/
VIRTUAL BOX SHARED FOLDER VFS DRIVER:
M: Hans de Goede <hdegoede@redhat.com>
L: linux-fsdevel@vger.kernel.org
S: Maintained
F: drivers/staging/vboxsf/*
VIRTUAL SERIO DEVICE DRIVER
M: Stephen Chandler Paul <thatslyude@gmail.com>
S: Maintained

45
arch/x86/Kconfig
View File

@ -1940,6 +1940,51 @@ config X86_INTEL_MEMORY_PROTECTION_KEYS
If unsure, say y.
choice
prompt "TSX enable mode"
depends on CPU_SUP_INTEL
default X86_INTEL_TSX_MODE_OFF
help
Intel's TSX (Transactional Synchronization Extensions) feature
allows to optimize locking protocols through lock elision which
can lead to a noticeable performance boost.
On the other hand it has been shown that TSX can be exploited
to form side channel attacks (e.g. TAA) and chances are there
will be more of those attacks discovered in the future.
Therefore TSX is not enabled by default (aka tsx=off). An admin
might override this decision by tsx=on the command line parameter.
Even with TSX enabled, the kernel will attempt to enable the best
possible TAA mitigation setting depending on the microcode available
for the particular machine.
This option allows to set the default tsx mode between tsx=on, =off
and =auto. See Documentation/admin-guide/kernel-parameters.txt for more
details.
Say off if not sure, auto if TSX is in use but it should be used on safe
platforms or on if TSX is in use and the security aspect of tsx is not
relevant.
config X86_INTEL_TSX_MODE_OFF
bool "off"
help
TSX is disabled if possible - equals to tsx=off command line parameter.
config X86_INTEL_TSX_MODE_ON
bool "on"
help
TSX is always enabled on TSX capable HW - equals the tsx=on command
line parameter.
config X86_INTEL_TSX_MODE_AUTO
bool "auto"
help
TSX is enabled on TSX capable HW that is believed to be safe against
side channel attacks- equals the tsx=auto command line parameter.
endchoice
config EFI
bool "EFI runtime service support"
depends on ACPI

2
arch/x86/include/asm/cpufeatures.h
View File

@ -399,5 +399,7 @@
#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
#endif /* _ASM_X86_CPUFEATURES_H */

6
arch/x86/include/asm/kvm_host.h
View File

@ -312,9 +312,12 @@ struct kvm_rmap_head {
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
struct list_head lpage_disallowed_link;
bool unsync;
u8 mmu_valid_gen;
bool mmio_cached;
bool lpage_disallowed; /* Can't be replaced by an equiv large page */
/*
* The following two entries are used to key the shadow page in the
@ -859,6 +862,7 @@ struct kvm_arch {
*/
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
struct list_head lpage_disallowed_mmu_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
@ -933,6 +937,7 @@ struct kvm_arch {
bool exception_payload_enabled;
struct kvm_pmu_event_filter *pmu_event_filter;
struct task_struct *nx_lpage_recovery_thread;
};
struct kvm_vm_stat {
@ -946,6 +951,7 @@ struct kvm_vm_stat {
ulong mmu_unsync;
ulong remote_tlb_flush;
ulong lpages;
ulong nx_lpage_splits;
ulong max_mmu_page_hash_collisions;
};

16
arch/x86/include/asm/msr-index.h
View File

@ -93,6 +93,18 @@
* Microarchitectural Data
* Sampling (MDS) vulnerabilities.
*/
#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /*
* The processor is not susceptible to a
* machine check error due to modifying the
* code page size along with either the
* physical address or cache type
* without TLB invalidation.
*/
#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */
#define ARCH_CAP_TAA_NO BIT(8) /*
* Not susceptible to
* TSX Async Abort (TAA) vulnerabilities.
*/
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
@ -103,6 +115,10 @@
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
#define MSR_IA32_TSX_CTRL 0x00000122
#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
#define MSR_IA32_SYSENTER_EIP 0x00000176

4
arch/x86/include/asm/nospec-branch.h
View File

@ -314,7 +314,7 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
#include <asm/segment.h>
/**
* mds_clear_cpu_buffers - Mitigation for MDS vulnerability
* mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
*
* This uses the otherwise unused and obsolete VERW instruction in
* combination with microcode which triggers a CPU buffer flush when the
@ -337,7 +337,7 @@ static inline void mds_clear_cpu_buffers(void)
}
/**
* mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
* mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
*
* Clear CPU buffers if the corresponding static key is enabled
*/

7
arch/x86/include/asm/processor.h
View File

@ -988,4 +988,11 @@ enum mds_mitigations {
MDS_MITIGATION_VMWERV,
};
enum taa_mitigations {
TAA_MITIGATION_OFF,
TAA_MITIGATION_UCODE_NEEDED,
TAA_MITIGATION_VERW,
TAA_MITIGATION_TSX_DISABLED,
};
#endif /* _ASM_X86_PROCESSOR_H */

2
arch/x86/kernel/cpu/Makefile
View File

@ -30,7 +30,7 @@ obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
ifdef CONFIG_CPU_SUP_INTEL
obj-y += intel.o intel_pconfig.o
obj-y += intel.o intel_pconfig.o tsx.o
obj-$(CONFIG_PM) += intel_epb.o
endif
obj-$(CONFIG_CPU_SUP_AMD) += amd.o

159
arch/x86/kernel/cpu/bugs.c
View File

@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
static void __init mds_select_mitigation(void);
static void __init taa_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
u64 x86_spec_ctrl_base;
@ -105,6 +106,7 @@ void __init check_bugs(void)
ssb_select_mitigation();
l1tf_select_mitigation();
mds_select_mitigation();
taa_select_mitigation();
arch_smt_update();
@ -268,6 +270,100 @@ static int __init mds_cmdline(char *str)
}
early_param("mds", mds_cmdline);
#undef pr_fmt
#define pr_fmt(fmt) "TAA: " fmt
/* Default mitigation for TAA-affected CPUs */
static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW;
static bool taa_nosmt __ro_after_init;
static const char * const taa_strings[] = {
[TAA_MITIGATION_OFF] = "Vulnerable",
[TAA_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode",
[TAA_MITIGATION_VERW] = "Mitigation: Clear CPU buffers",
[TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled",
};
static void __init taa_select_mitigation(void)
{
u64 ia32_cap;
if (!boot_cpu_has_bug(X86_BUG_TAA)) {
taa_mitigation = TAA_MITIGATION_OFF;
return;
}
/* TSX previously disabled by tsx=off */
if (!boot_cpu_has(X86_FEATURE_RTM)) {
taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
goto out;
}
if (cpu_mitigations_off()) {
taa_mitigation = TAA_MITIGATION_OFF;
return;
}
/* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
if (taa_mitigation == TAA_MITIGATION_OFF)
goto out;
if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
taa_mitigation = TAA_MITIGATION_VERW;
else
taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
/*
* VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
* A microcode update fixes this behavior to clear CPU buffers. It also
* adds support for MSR_IA32_TSX_CTRL which is enumerated by the
* ARCH_CAP_TSX_CTRL_MSR bit.
*
* On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
* update is required.
*/
ia32_cap = x86_read_arch_cap_msr();
if ( (ia32_cap & ARCH_CAP_MDS_NO) &&
!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR))
taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
/*
* TSX is enabled, select alternate mitigation for TAA which is
* the same as MDS. Enable MDS static branch to clear CPU buffers.
*
* For guests that can't determine whether the correct microcode is
* present on host, enable the mitigation for UCODE_NEEDED as well.
*/
static_branch_enable(&mds_user_clear);
if (taa_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
out:
pr_info("%s\n", taa_strings[taa_mitigation]);
}
static int __init tsx_async_abort_parse_cmdline(char *str)
{
if (!boot_cpu_has_bug(X86_BUG_TAA))
return 0;
if (!str)
return -EINVAL;
if (!strcmp(str, "off")) {
taa_mitigation = TAA_MITIGATION_OFF;
} else if (!strcmp(str, "full")) {
taa_mitigation = TAA_MITIGATION_VERW;
} else if (!strcmp(str, "full,nosmt")) {
taa_mitigation = TAA_MITIGATION_VERW;
taa_nosmt = true;
}
return 0;
}
early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V1 : " fmt
@ -786,13 +882,10 @@ static void update_mds_branch_idle(void)
}
#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
void cpu_bugs_smt_update(void)
{
/* Enhanced IBRS implies STIBP. No update required. */
if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
return;
mutex_lock(&spec_ctrl_mutex);
switch (spectre_v2_user) {
@ -819,6 +912,17 @@ void cpu_bugs_smt_update(void)
break;
}
switch (taa_mitigation) {
case TAA_MITIGATION_VERW:
case TAA_MITIGATION_UCODE_NEEDED:
if (sched_smt_active())
pr_warn_once(TAA_MSG_SMT);
break;
case TAA_MITIGATION_TSX_DISABLED:
case TAA_MITIGATION_OFF:
break;
}
mutex_unlock(&spec_ctrl_mutex);
}
@ -1149,6 +1253,9 @@ void x86_spec_ctrl_setup_ap(void)
x86_amd_ssb_disable();
}
bool itlb_multihit_kvm_mitigation;
EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
#undef pr_fmt
#define pr_fmt(fmt) "L1TF: " fmt
@ -1304,11 +1411,24 @@ static ssize_t l1tf_show_state(char *buf)
l1tf_vmx_states[l1tf_vmx_mitigation],
sched_smt_active() ? "vulnerable" : "disabled");
}
static ssize_t itlb_multihit_show_state(char *buf)
{
if (itlb_multihit_kvm_mitigation)
return sprintf(buf, "KVM: Mitigation: Split huge pages\n");
else
return sprintf(buf, "KVM: Vulnerable\n");
}
#else
static ssize_t l1tf_show_state(char *buf)
{
return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
}
static ssize_t itlb_multihit_show_state(char *buf)
{
return sprintf(buf, "Processor vulnerable\n");
}
#endif
static ssize_t mds_show_state(char *buf)
@ -1328,6 +1448,21 @@ static ssize_t mds_show_state(char *buf)
sched_smt_active() ? "vulnerable" : "disabled");
}
static ssize_t tsx_async_abort_show_state(char *buf)
{
if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) ||
(taa_mitigation == TAA_MITIGATION_OFF))
return sprintf(buf, "%s\n", taa_strings[taa_mitigation]);
if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
return sprintf(buf, "%s; SMT Host state unknown\n",
taa_strings[taa_mitigation]);
}
return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation],
sched_smt_active() ? "vulnerable" : "disabled");
}
static char *stibp_state(void)
{
if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@ -1398,6 +1533,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_MDS:
return mds_show_state(buf);
case X86_BUG_TAA:
return tsx_async_abort_show_state(buf);
case X86_BUG_ITLB_MULTIHIT:
return itlb_multihit_show_state(buf);
default:
break;
}
@ -1434,4 +1575,14 @@ ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *bu
{
return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
}
ssize_t cpu_show_tsx_async_abort(struct device *dev, struct device_attribute *attr, char *buf)
{
return cpu_show_common(dev, attr, buf, X86_BUG_TAA);
}
ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr, char *buf)
{
return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
}
#endif

97
arch/x86/kernel/cpu/common.c
View File

@ -1016,13 +1016,14 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#endif
}
#define NO_SPECULATION BIT(0)
#define NO_MELTDOWN BIT(1)
#define NO_SSB BIT(2)
#define NO_L1TF BIT(3)
#define NO_MDS BIT(4)
#define MSBDS_ONLY BIT(5)
#define NO_SWAPGS BIT(6)
#define NO_SPECULATION BIT(0)
#define NO_MELTDOWN BIT(1)
#define NO_SSB BIT(2)
#define NO_L1TF BIT(3)
#define NO_MDS BIT(4)
#define MSBDS_ONLY BIT(5)
#define NO_SWAPGS BIT(6)
#define NO_ITLB_MULTIHIT BIT(7)
#define VULNWL(_vendor, _family, _model, _whitelist) \
{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@ -1043,27 +1044,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL(NSC, 5, X86_MODEL_ANY, NO_SPECULATION),
/* Intel Family 6 */
VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION),
VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION),
VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION),
VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION),
VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION),
VULNWL_INTEL(ATOM_SALTWELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SALTWELL_TABLET, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SALTWELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_BONNELL, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_BONNELL_MID, NO_SPECULATION | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_SILVERMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SILVERMONT_D, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_SILVERMONT_MID, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_AIRMONT, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(XEON_PHI_KNL, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(XEON_PHI_KNM, NO_SSB | NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(CORE_YONAH, NO_SSB),
VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS),
VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_AIRMONT_MID, NO_L1TF | MSBDS_ONLY | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_AIRMONT_NP, NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS),
VULNWL_INTEL(ATOM_GOLDMONT, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_GOLDMONT_D, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_INTEL(ATOM_GOLDMONT_PLUS, NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
/*
* Technically, swapgs isn't serializing on AMD (despite it previously
@ -1073,15 +1074,17 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
* good enough for our purposes.
*/
VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT),
/* AMD Family 0xf - 0x12 */
VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS),
VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
{}
};
@ -1092,19 +1095,30 @@ static bool __init cpu_matches(unsigned long which)
return m && !!(m->driver_data & which);
}
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
u64 x86_read_arch_cap_msr(void)
{
u64 ia32_cap = 0;
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
return ia32_cap;
}
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = x86_read_arch_cap_msr();
/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
if (!cpu_matches(NO_ITLB_MULTIHIT) && !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO))
setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT);
if (cpu_matches(NO_SPECULATION))
return;
setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
setup_force_cpu_bug(X86_BUG_SPECTRE_V2);
if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
!cpu_has(c, X86_FEATURE_AMD_SSB_NO))
setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
@ -1121,6 +1135,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (!cpu_matches(NO_SWAPGS))
setup_force_cpu_bug(X86_BUG_SWAPGS);
/*
* When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when:
* - TSX is supported or
* - TSX_CTRL is present
*
* TSX_CTRL check is needed for cases when TSX could be disabled before
* the kernel boot e.g. kexec.
* TSX_CTRL check alone is not sufficient for cases when the microcode
* update is not present or running as guest that don't get TSX_CTRL.
*/
if (!(ia32_cap & ARCH_CAP_TAA_NO) &&
(cpu_has(c, X86_FEATURE_RTM) ||
(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)))
setup_force_cpu_bug(X86_BUG_TAA);
if (cpu_matches(NO_MELTDOWN))
return;
@ -1554,6 +1583,8 @@ void __init identify_boot_cpu(void)
#endif
cpu_detect_tlb(&boot_cpu_data);
setup_cr_pinning();
tsx_init();
}
void identify_secondary_cpu(struct cpuinfo_x86 *c)

18
arch/x86/kernel/cpu/cpu.h
View File

@ -44,6 +44,22 @@ struct _tlb_table {
extern const struct cpu_dev *const __x86_cpu_dev_start[],
*const __x86_cpu_dev_end[];
#ifdef CONFIG_CPU_SUP_INTEL
enum tsx_ctrl_states {
TSX_CTRL_ENABLE,
TSX_CTRL_DISABLE,
TSX_CTRL_NOT_SUPPORTED,
};
extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state;
extern void __init tsx_init(void);
extern void tsx_enable(void);
extern void tsx_disable(void);
#else
static inline void tsx_init(void) { }
#endif /* CONFIG_CPU_SUP_INTEL */
extern void get_cpu_cap(struct cpuinfo_x86 *c);
extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
@ -62,4 +78,6 @@ unsigned int aperfmperf_get_khz(int cpu);
extern void x86_spec_ctrl_setup_ap(void);
extern u64 x86_read_arch_cap_msr(void);
#endif /* ARCH_X86_CPU_H */

5
arch/x86/kernel/cpu/intel.c
View File

@ -762,6 +762,11 @@ static void init_intel(struct cpuinfo_x86 *c)
detect_tme(c);
init_intel_misc_features(c);
if (tsx_ctrl_state == TSX_CTRL_ENABLE)
tsx_enable();
if (tsx_ctrl_state == TSX_CTRL_DISABLE)
tsx_disable();
}
#ifdef CONFIG_X86_32

140
arch/x86/kernel/cpu/tsx.c Normal file
View File

@ -0,0 +1,140 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Intel Transactional Synchronization Extensions (TSX) control.
*
* Copyright (C) 2019 Intel Corporation
*
* Author:
* Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
*/
#include <linux/cpufeature.h>
#include <asm/cmdline.h>
#include "cpu.h"
enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED;
void tsx_disable(void)
{
u64 tsx;
rdmsrl(MSR_IA32_TSX_CTRL, tsx);
/* Force all transactions to immediately abort */
tsx |= TSX_CTRL_RTM_DISABLE;
/*
* Ensure TSX support is not enumerated in CPUID.
* This is visible to userspace and will ensure they
* do not waste resources trying TSX transactions that
* will always abort.
*/
tsx |= TSX_CTRL_CPUID_CLEAR;
wrmsrl(MSR_IA32_TSX_CTRL, tsx);
}
void tsx_enable(void)
{
u64 tsx;
rdmsrl(MSR_IA32_TSX_CTRL, tsx);
/* Enable the RTM feature in the cpu */
tsx &= ~TSX_CTRL_RTM_DISABLE;
/*
* Ensure TSX support is enumerated in CPUID.
* This is visible to userspace and will ensure they
* can enumerate and use the TSX feature.
*/
tsx &= ~TSX_CTRL_CPUID_CLEAR;
wrmsrl(MSR_IA32_TSX_CTRL, tsx);
}
static bool __init tsx_ctrl_is_supported(void)
{
u64 ia32_cap = x86_read_arch_cap_msr();
/*
* TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this
* MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES.
*
* TSX control (aka MSR_IA32_TSX_CTRL) is only available after a
* microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES
* bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get
* MSR_IA32_TSX_CTRL support even after a microcode update. Thus,
* tsx= cmdline requests will do nothing on CPUs without
* MSR_IA32_TSX_CTRL support.
*/
return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR);
}
static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
{
if (boot_cpu_has_bug(X86_BUG_TAA))
return TSX_CTRL_DISABLE;
return TSX_CTRL_ENABLE;
}
void __init tsx_init(void)
{
char arg[5] = {};
int ret;
if (!tsx_ctrl_is_supported())
return;
ret = cmdline_find_option(boot_command_line, "tsx", arg, sizeof(arg));
if (ret >= 0) {
if (!strcmp(arg, "on")) {
tsx_ctrl_state = TSX_CTRL_ENABLE;
} else if (!strcmp(arg, "off")) {
tsx_ctrl_state = TSX_CTRL_DISABLE;
} else if (!strcmp(arg, "auto")) {
tsx_ctrl_state = x86_get_tsx_auto_mode();
} else {
tsx_ctrl_state = TSX_CTRL_DISABLE;
pr_err("tsx: invalid option, defaulting to off\n");
}
} else {
/* tsx= not provided */
if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_AUTO))
tsx_ctrl_state = x86_get_tsx_auto_mode();
else if (IS_ENABLED(CONFIG_X86_INTEL_TSX_MODE_OFF))
tsx_ctrl_state = TSX_CTRL_DISABLE;
else
tsx_ctrl_state = TSX_CTRL_ENABLE;
}
if (tsx_ctrl_state == TSX_CTRL_DISABLE) {
tsx_disable();
/*
* tsx_disable() will change the state of the
* RTM CPUID bit. Clear it here since it is now
* expected to be not set.
*/
setup_clear_cpu_cap(X86_FEATURE_RTM);
} else if (tsx_ctrl_state == TSX_CTRL_ENABLE) {
/*
* HW defaults TSX to be enabled at bootup.
* We may still need the TSX enable support
* during init for special cases like
* kexec after TSX is disabled.
*/
tsx_enable();
/*
* tsx_enable() will change the state of the
* RTM CPUID bit. Force it here since it is now
* expected to be set.
*/
setup_force_cpu_cap(X86_FEATURE_RTM);
}
}

278
arch/x86/kvm/mmu.c
View File

@ -37,6 +37,7 @@
#include <linux/uaccess.h>
#include <linux/hash.h>
#include <linux/kern_levels.h>
#include <linux/kthread.h>
#include <asm/page.h>
#include <asm/pat.h>
@ -47,6 +48,30 @@
#include <asm/kvm_page_track.h>
#include "trace.h"
extern bool itlb_multihit_kvm_mitigation;
static int __read_mostly nx_huge_pages = -1;
static uint __read_mostly nx_huge_pages_recovery_ratio = 60;
static int set_nx_huge_pages(const char *val, const struct kernel_param *kp);
static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp);
static struct kernel_param_ops nx_huge_pages_ops = {
.set = set_nx_huge_pages,
.get = param_get_bool,
};
static struct kernel_param_ops nx_huge_pages_recovery_ratio_ops = {
.set = set_nx_huge_pages_recovery_ratio,
.get = param_get_uint,
};
module_param_cb(nx_huge_pages, &nx_huge_pages_ops, &nx_huge_pages, 0644);
__MODULE_PARM_TYPE(nx_huge_pages, "bool");
module_param_cb(nx_huge_pages_recovery_ratio, &nx_huge_pages_recovery_ratio_ops,
&nx_huge_pages_recovery_ratio, 0644);
__MODULE_PARM_TYPE(nx_huge_pages_recovery_ratio, "uint");
/*
* When setting this variable to true it enables Two-Dimensional-Paging
* where the hardware walks 2 page tables:
@ -352,6 +377,11 @@ static inline bool spte_ad_need_write_protect(u64 spte)
return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
}
static bool is_nx_huge_page_enabled(void)
{
return READ_ONCE(nx_huge_pages);
}
static inline u64 spte_shadow_accessed_mask(u64 spte)
{
MMU_WARN_ON(is_mmio_spte(spte));
@ -1190,6 +1220,17 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
if (sp->lpage_disallowed)
return;
++kvm->stat.nx_lpage_splits;
list_add_tail(&sp->lpage_disallowed_link,
&kvm->arch.lpage_disallowed_mmu_pages);
sp->lpage_disallowed = true;
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memslots *slots;
@ -1207,6 +1248,13 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
--kvm->stat.nx_lpage_splits;
sp->lpage_disallowed = false;
list_del(&sp->lpage_disallowed_link);
}
static bool __mmu_gfn_lpage_is_disallowed(gfn_t gfn, int level,
struct kvm_memory_slot *slot)
{
@ -2792,6 +2840,9 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
kvm_reload_remote_mmus(kvm);
}
if (sp->lpage_disallowed)
unaccount_huge_nx_page(kvm, sp);
sp->role.invalid = 1;
return list_unstable;
}
@ -3013,6 +3064,11 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
if (!speculative)
spte |= spte_shadow_accessed_mask(spte);
if (level > PT_PAGE_TABLE_LEVEL && (pte_access & ACC_EXEC_MASK) &&
is_nx_huge_page_enabled()) {
pte_access &= ~ACC_EXEC_MASK;
}
if (pte_access & ACC_EXEC_MASK)
spte |= shadow_x_mask;
else
@ -3233,9 +3289,32 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
__direct_pte_prefetch(vcpu, sp, sptep);
}
static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
gfn_t gfn, kvm_pfn_t *pfnp, int *levelp)
{
int level = *levelp;
u64 spte = *it.sptep;
if (it.level == level && level > PT_PAGE_TABLE_LEVEL &&
is_nx_huge_page_enabled() &&
is_shadow_present_pte(spte) &&
!is_large_pte(spte)) {
/*
* A small SPTE exists for this pfn, but FNAME(fetch)
* and __direct_map would like to create a large PTE
* instead: just force them to go down another level,
* patching back for them into pfn the next 9 bits of
* the address.
*/
u64 page_mask = KVM_PAGES_PER_HPAGE(level) - KVM_PAGES_PER_HPAGE(level - 1);
*pfnp |= gfn & page_mask;
(*levelp)--;
}
}
static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
int map_writable, int level, kvm_pfn_t pfn,
bool prefault)
bool prefault, bool lpage_disallowed)
{
struct kvm_shadow_walk_iterator it;
struct kvm_mmu_page *sp;
@ -3248,6 +3327,12 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
trace_kvm_mmu_spte_requested(gpa, level, pfn);
for_each_shadow_entry(vcpu, gpa, it) {
/*
* We cannot overwrite existing page tables with an NX
* large page, as the leaf could be executable.
*/
disallowed_hugepage_adjust(it, gfn, &pfn, &level);
base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
if (it.level == level)
break;
@ -3258,6 +3343,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
it.level - 1, true, ACC_ALL);
link_shadow_page(vcpu, it.sptep, sp);
if (lpage_disallowed)
account_huge_nx_page(vcpu->kvm, sp);
}
}
@ -3306,7 +3393,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
* here.
*/
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
!kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
PageTransCompoundMap(pfn_to_page(pfn)) &&
!mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
@ -3550,11 +3637,14 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
{
int r;
int level;
bool force_pt_level = false;
bool force_pt_level;
kvm_pfn_t pfn;
unsigned long mmu_seq;
bool map_writable, write = error_code & PFERR_WRITE_MASK;
bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
is_nx_huge_page_enabled();
force_pt_level = lpage_disallowed;
level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
/*
@ -3588,7 +3678,8 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
r = __direct_map(vcpu, v, write, map_writable, level, pfn, prefault);
r = __direct_map(vcpu, v, write, map_writable, level, pfn,
prefault, false);
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
@ -4174,6 +4265,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
unsigned long mmu_seq;
int write = error_code & PFERR_WRITE_MASK;
bool map_writable;
bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
is_nx_huge_page_enabled();
MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa));
@ -4184,8 +4277,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
if (r)
return r;
force_pt_level = !check_hugepage_cache_consistency(vcpu, gfn,
PT_DIRECTORY_LEVEL);
force_pt_level =
lpage_disallowed ||
!check_hugepage_cache_consistency(vcpu, gfn, PT_DIRECTORY_LEVEL);
level = mapping_level(vcpu, gfn, &force_pt_level);
if (likely(!force_pt_level)) {
if (level > PT_DIRECTORY_LEVEL &&
@ -4214,7 +4308,8 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
goto out_unlock;
if (likely(!force_pt_level))
transparent_hugepage_adjust(vcpu, gfn, &pfn, &level);
r = __direct_map(vcpu, gpa, write, map_writable, level, pfn, prefault);
r = __direct_map(vcpu, gpa, write, map_writable, level, pfn,
prefault, lpage_disallowed);
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
@ -5914,9 +6009,9 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
* the guest, and the guest page table is using 4K page size
* mapping if the indirect sp has level = 1.
*/
if (sp->role.direct &&
!kvm_is_reserved_pfn(pfn) &&
PageTransCompoundMap(pfn_to_page(pfn))) {
if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
!kvm_is_zone_device_pfn(pfn) &&
PageTransCompoundMap(pfn_to_page(pfn))) {
pte_list_remove(rmap_head, sptep);
if (kvm_available_flush_tlb_with_range())
@ -6155,10 +6250,60 @@ static void kvm_set_mmio_spte_mask(void)
kvm_mmu_set_mmio_spte_mask(mask, mask, ACC_WRITE_MASK | ACC_USER_MASK);
}
static bool get_nx_auto_mode(void)
{
/* Return true when CPU has the bug, and mitigations are ON */
return boot_cpu_has_bug(X86_BUG_ITLB_MULTIHIT) && !cpu_mitigations_off();
}
static void __set_nx_huge_pages(bool val)
{
nx_huge_pages = itlb_multihit_kvm_mitigation = val;
}
static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
{
bool old_val = nx_huge_pages;
bool new_val;
/* In "auto" mode deploy workaround only if CPU has the bug. */
if (sysfs_streq(val, "off"))
new_val = 0;
else if (sysfs_streq(val, "force"))
new_val = 1;
else if (sysfs_streq(val, "auto"))
new_val = get_nx_auto_mode();
else if (strtobool(val, &new_val) < 0)
return -EINVAL;
__set_nx_huge_pages(new_val);
if (new_val != old_val) {
struct kvm *kvm;
int idx;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
idx = srcu_read_lock(&kvm->srcu);
kvm_mmu_zap_all_fast(kvm);
srcu_read_unlock(&kvm->srcu, idx);
wake_up_process(kvm->arch.nx_lpage_recovery_thread);
}
mutex_unlock(&kvm_lock);
}
return 0;
}
int kvm_mmu_module_init(void)
{
int ret = -ENOMEM;
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
/*
* MMU roles use union aliasing which is, generally speaking, an
* undefined behavior. However, we supposedly know how compilers behave
@ -6238,3 +6383,116 @@ void kvm_mmu_module_exit(void)
unregister_shrinker(&mmu_shrinker);
mmu_audit_disable();
}
static int set_nx_huge_pages_recovery_ratio(const char *val, const struct kernel_param *kp)
{
unsigned int old_val;
int err;
old_val = nx_huge_pages_recovery_ratio;
err = param_set_uint(val, kp);
if (err)
return err;
if (READ_ONCE(nx_huge_pages) &&
!old_val && nx_huge_pages_recovery_ratio) {
struct kvm *kvm;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
wake_up_process(kvm->arch.nx_lpage_recovery_thread);
mutex_unlock(&kvm_lock);
}
return err;
}
static void kvm_recover_nx_lpages(struct kvm *kvm)
{
int rcu_idx;
struct kvm_mmu_page *sp;
unsigned int ratio;
LIST_HEAD(invalid_list);
ulong to_zap;
rcu_idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
/*
* We use a separate list instead of just using active_mmu_pages
* because the number of lpage_disallowed pages is expected to
* be relatively small compared to the total.
*/
sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
struct kvm_mmu_page,
lpage_disallowed_link);
WARN_ON_ONCE(!sp->lpage_disallowed);
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
WARN_ON_ONCE(sp->lpage_disallowed);
if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
kvm_mmu_commit_zap_page(kvm, &invalid_list);
if (to_zap)
cond_resched_lock(&kvm->mmu_lock);
}
}
spin_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, rcu_idx);
}
static long get_nx_lpage_recovery_timeout(u64 start_time)
{
return READ_ONCE(nx_huge_pages) && READ_ONCE(nx_huge_pages_recovery_ratio)
? start_time + 60 * HZ - get_jiffies_64()
: MAX_SCHEDULE_TIMEOUT;
}
static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
{
u64 start_time;
long remaining_time;
while (true) {
start_time = get_jiffies_64();
remaining_time = get_nx_lpage_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop() && remaining_time > 0) {
schedule_timeout(remaining_time);
remaining_time = get_nx_lpage_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
}
set_current_state(TASK_RUNNING);
if (kthread_should_stop())
return 0;
kvm_recover_nx_lpages(kvm);
}
}
int kvm_mmu_post_init_vm(struct kvm *kvm)
{
int err;
err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
"kvm-nx-lpage-recovery",
&kvm->arch.nx_lpage_recovery_thread);
if (!err)
kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
return err;
}
void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
{
if (kvm->arch.nx_lpage_recovery_thread)
kthread_stop(kvm->arch.nx_lpage_recovery_thread);
}

4
arch/x86/kvm/mmu.h
View File

@ -210,4 +210,8 @@ void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn);
int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
int kvm_mmu_post_init_vm(struct kvm *kvm);
void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
#endif

29
arch/x86/kvm/paging_tmpl.h
View File

@ -614,13 +614,14 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
struct guest_walker *gw,
int write_fault, int hlevel,
kvm_pfn_t pfn, bool map_writable, bool prefault)
kvm_pfn_t pfn, bool map_writable, bool prefault,
bool lpage_disallowed)
{
struct kvm_mmu_page *sp = NULL;
struct kvm_shadow_walk_iterator it;
unsigned direct_access, access = gw->pt_access;
int top_level, ret;
gfn_t base_gfn;
gfn_t gfn, base_gfn;
direct_access = gw->pte_access;
@ -665,13 +666,25 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
link_shadow_page(vcpu, it.sptep, sp);
}
base_gfn = gw->gfn;
/*
* FNAME(page_fault) might have clobbered the bottom bits of
* gw->gfn, restore them from the virtual address.
*/
gfn = gw->gfn | ((addr & PT_LVL_OFFSET_MASK(gw->level)) >> PAGE_SHIFT);
base_gfn = gfn;
trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
for (; shadow_walk_okay(&it); shadow_walk_next(&it)) {
clear_sp_write_flooding_count(it.sptep);
base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
/*
* We cannot overwrite existing page tables with an NX
* large page, as the leaf could be executable.
*/
disallowed_hugepage_adjust(it, gfn, &pfn, &hlevel);
base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
if (it.level == hlevel)
break;
@ -683,6 +696,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
it.level - 1, true, direct_access);
link_shadow_page(vcpu, it.sptep, sp);
if (lpage_disallowed)
account_huge_nx_page(vcpu->kvm, sp);
}
}
@ -759,9 +774,11 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
int r;
kvm_pfn_t pfn;
int level = PT_PAGE_TABLE_LEVEL;
bool force_pt_level = false;
unsigned long mmu_seq;
bool map_writable, is_self_change_mapping;
bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
is_nx_huge_page_enabled();
bool force_pt_level = lpage_disallowed;
pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@ -851,7 +868,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
if (!force_pt_level)
transparent_hugepage_adjust(vcpu, walker.gfn, &pfn, &level);
r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
level, pfn, map_writable, prefault);
level, pfn, map_writable, prefault, lpage_disallowed);
kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
out_unlock:

23
arch/x86/kvm/vmx/vmx.c
View File

@ -1268,6 +1268,18 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
return;
/*
* If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
* PI.NDST: pi_post_block is the one expected to change PID.NDST and the
* wakeup handler expects the vCPU to be on the blocked_vcpu_list that
* matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
* correctly.
*/
if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
pi_clear_sn(pi_desc);
goto after_clear_sn;
}
/* The full case. */
do {
old.control = new.control = pi_desc->control;
@ -1283,6 +1295,8 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
} while (cmpxchg64(&pi_desc->control, old.control,
new.control) != old.control);
after_clear_sn:
/*
* Clear SN before reading the bitmap. The VT-d firmware
* writes the bitmap and reads SN atomically (5.2.3 in the
@ -1291,7 +1305,7 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
*/
smp_mb__after_atomic();
if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS))
if (!pi_is_pir_empty(pi_desc))
pi_set_on(pi_desc);
}
@ -6137,7 +6151,7 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
if (pi_test_on(&vmx->pi_desc)) {
pi_clear_on(&vmx->pi_desc);
/*
* IOMMU can write to PIR.ON, so the barrier matters even on UP.
* IOMMU can write to PID.ON, so the barrier matters even on UP.
* But on x86 this is just a compiler barrier anyway.
*/
smp_mb__after_atomic();
@ -6167,7 +6181,10 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
return pi_test_on(vcpu_to_pi_desc(vcpu));
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
return pi_test_on(pi_desc) ||
(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
}
static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)

11
arch/x86/kvm/vmx/vmx.h
View File

@ -355,6 +355,11 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
}
static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
{
return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
}
static inline void pi_set_sn(struct pi_desc *pi_desc)
{
set_bit(POSTED_INTR_SN,
@ -373,6 +378,12 @@ static inline void pi_clear_on(struct pi_desc *pi_desc)
(unsigned long *)&pi_desc->control);
}
static inline void pi_clear_sn(struct pi_desc *pi_desc)
{
clear_bit(POSTED_INTR_SN,
(unsigned long *)&pi_desc->control);
}
static inline int pi_test_on(struct pi_desc *pi_desc)
{
return test_bit(POSTED_INTR_ON,

95
arch/x86/kvm/x86.c
View File

@ -213,6 +213,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "mmu_unsync", VM_STAT(mmu_unsync) },
{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
{ "largepages", VM_STAT(lpages, .mode = 0444) },
{ "nx_largepages_splitted", VM_STAT(nx_lpage_splits, .mode = 0444) },
{ "max_mmu_page_hash_collisions",
VM_STAT(max_mmu_page_hash_collisions) },
{ NULL }
@ -1132,13 +1133,15 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc);
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
* and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
*
* This list is modified at module load time to reflect the
* The three MSR lists(msrs_to_save, emulated_msrs, msr_based_features)
* extract the supported MSRs from the related const lists.
* msrs_to_save is selected from the msrs_to_save_all to reflect the
* capabilities of the host cpu. This capabilities test skips MSRs that are
* kvm-specific. Those are put in emulated_msrs; filtering of emulated_msrs
* kvm-specific. Those are put in emulated_msrs_all; filtering of emulated_msrs
* may depend on host virtualization features rather than host cpu features.
*/
static u32 msrs_to_save[] = {
static const u32 msrs_to_save_all[] = {
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_STAR,
#ifdef CONFIG_X86_64
@ -1179,9 +1182,10 @@ static u32 msrs_to_save[] = {
MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
};
static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)];
static unsigned num_msrs_to_save;
static u32 emulated_msrs[] = {
static const u32 emulated_msrs_all[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
@ -1220,7 +1224,7 @@ static u32 emulated_msrs[] = {
* by arch/x86/kvm/vmx/nested.c based on CPUID or other MSRs.
* We always support the "true" VMX control MSRs, even if the host
* processor does not, so I am putting these registers here rather
* than in msrs_to_save.
* than in msrs_to_save_all.
*/
MSR_IA32_VMX_BASIC,
MSR_IA32_VMX_TRUE_PINBASED_CTLS,
@ -1239,13 +1243,14 @@ static u32 emulated_msrs[] = {
MSR_KVM_POLL_CONTROL,
};
static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)];
static unsigned num_emulated_msrs;
/*
* List of msr numbers which are used to expose MSR-based features that
* can be used by a hypervisor to validate requested CPU features.
*/
static u32 msr_based_features[] = {
static const u32 msr_based_features_all[] = {
MSR_IA32_VMX_BASIC,
MSR_IA32_VMX_TRUE_PINBASED_CTLS,
MSR_IA32_VMX_PINBASED_CTLS,
@ -1270,6 +1275,7 @@ static u32 msr_based_features[] = {
MSR_IA32_ARCH_CAPABILITIES,
};
static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
static unsigned int num_msr_based_features;
static u64 kvm_get_arch_capabilities(void)
@ -1279,6 +1285,14 @@ static u64 kvm_get_arch_capabilities(void)
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
rdmsrl(MSR_IA32_ARCH_CAPABILITIES, data);
/*
* If nx_huge_pages is enabled, KVM's shadow paging will ensure that
* the nested hypervisor runs with NX huge pages. If it is not,
* L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
* L1 guests, so it need not worry about its own (L2) guests.
*/
data |= ARCH_CAP_PSCHANGE_MC_NO;
/*
* If we're doing cache flushes (either "always" or "cond")
* we will do one whenever the guest does a vmlaunch/vmresume.
@ -1298,6 +1312,25 @@ static u64 kvm_get_arch_capabilities(void)
if (!boot_cpu_has_bug(X86_BUG_MDS))
data |= ARCH_CAP_MDS_NO;
/*
* On TAA affected systems, export MDS_NO=0 when:
* - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
* - Updated microcode is present. This is detected by
* the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
* that VERW clears CPU buffers.
*
* When MDS_NO=0 is exported, guests deploy clear CPU buffer
* mitigation and don't complain:
*
* "Vulnerable: Clear CPU buffers attempted, no microcode"
*
* If TSX is disabled on the system, guests are also mitigated against
* TAA and clear CPU buffer mitigation is not required for guests.
*/
if (boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM) &&
(data & ARCH_CAP_TSX_CTRL_MSR))
data &= ~ARCH_CAP_MDS_NO;
return data;
}
@ -5090,22 +5123,22 @@ static void kvm_init_msr_list(void)
{
struct x86_pmu_capability x86_pmu;
u32 dummy[2];
unsigned i, j;
unsigned i;
BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
"Please update the fixed PMCs in msrs_to_save[]");
"Please update the fixed PMCs in msrs_to_saved_all[]");
perf_get_x86_pmu_capability(&x86_pmu);
for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) {
if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0)
continue;
/*
* Even MSRs that are valid in the host may not be exposed
* to the guests in some cases.
*/
switch (msrs_to_save[i]) {
switch (msrs_to_save_all[i]) {
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported())
continue;
@ -5133,17 +5166,17 @@ static void kvm_init_msr_list(void)
break;
case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: {
if (!kvm_x86_ops->pt_supported() ||
msrs_to_save[i] - MSR_IA32_RTIT_ADDR0_A >=
msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >=
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
continue;
break;
case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
continue;
break;
case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
continue;
}
@ -5151,34 +5184,25 @@ static void kvm_init_msr_list(void)
break;
}
if (j < i)
msrs_to_save[j] = msrs_to_save[i];
j++;
msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i];
}
num_msrs_to_save = j;
for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) {
if (!kvm_x86_ops->has_emulated_msr(emulated_msrs_all[i]))
continue;
if (j < i)
emulated_msrs[j] = emulated_msrs[i];
j++;
emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
}
num_emulated_msrs = j;
for (i = j = 0; i < ARRAY_SIZE(msr_based_features); i++) {
for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
struct kvm_msr_entry msr;
msr.index = msr_based_features[i];
msr.index = msr_based_features_all[i];
if (kvm_get_msr_feature(&msr))
continue;
if (j < i)
msr_based_features[j] = msr_based_features[i];
j++;
msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
}
num_msr_based_features = j;
}
static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
@ -9428,6 +9452,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
atomic_set(&kvm->arch.noncoherent_dma_count, 0);
@ -9456,6 +9481,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
return kvm_x86_ops->vm_init(kvm);
}
int kvm_arch_post_init_vm(struct kvm *kvm)
{
return kvm_mmu_post_init_vm(kvm);
}
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
{
vcpu_load(vcpu);
@ -9557,6 +9587,11 @@ int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
}
EXPORT_SYMBOL_GPL(x86_set_memory_region);
void kvm_arch_pre_destroy_vm(struct kvm *kvm)
{
kvm_mmu_pre_destroy_vm(kvm);
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
if (current->mm == kvm->mm) {

17
drivers/base/cpu.c
View File

@ -554,12 +554,27 @@ ssize_t __weak cpu_show_mds(struct device *dev,
return sprintf(buf, "Not affected\n");
}
ssize_t __weak cpu_show_tsx_async_abort(struct device *dev,
struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "Not affected\n");
}
ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "Not affected\n");
}
static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@ -568,6 +583,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_spec_store_bypass.attr,
&dev_attr_l1tf.attr,
&dev_attr_mds.attr,
&dev_attr_tsx_async_abort.attr,
&dev_attr_itlb_multihit.attr,
NULL
};

5
drivers/gpu/drm/i915/gem/i915_gem_context.c
View File

@ -319,6 +319,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
free_engines(rcu_access_pointer(ctx->engines));
mutex_destroy(&ctx->engines_mutex);
kfree(ctx->jump_whitelist);
if (ctx->timeline)
intel_timeline_put(ctx->timeline);
@ -441,6 +443,9 @@ __create_context(struct drm_i915_private *i915)
for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
ctx->jump_whitelist = NULL;
ctx->jump_whitelist_cmds = 0;
return ctx;
err_free:

7
drivers/gpu/drm/i915/gem/i915_gem_context_types.h
View File

@ -192,6 +192,13 @@ struct i915_gem_context {
* per vm, which may be one per context or shared with the global GTT)
*/
struct radix_tree_root handles_vma;
/** jump_whitelist: Bit array for tracking cmds during cmdparsing
* Guarded by struct_mutex
*/
unsigned long *jump_whitelist;
/** jump_whitelist_cmds: No of cmd slots available */
u32 jump_whitelist_cmds;
};
#endif /* __I915_GEM_CONTEXT_TYPES_H__ */

111
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
View File

@ -296,7 +296,9 @@ static inline u64 gen8_noncanonical_addr(u64 address)
static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
{
return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
return intel_engine_requires_cmd_parser(eb->engine) ||
(intel_engine_using_cmd_parser(eb->engine) &&
eb->args->batch_len);
}
static int eb_create(struct i915_execbuffer *eb)
@ -1955,40 +1957,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
return 0;
}
static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
static struct i915_vma *
shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
{
struct drm_i915_private *dev_priv = eb->i915;
struct i915_vma * const vma = *eb->vma;
struct i915_address_space *vm;
u64 flags;
/*
* PPGTT backed shadow buffers must be mapped RO, to prevent
* post-scan tampering
*/
if (CMDPARSER_USES_GGTT(dev_priv)) {
flags = PIN_GLOBAL;
vm = &dev_priv->ggtt.vm;
} else if (vma->vm->has_read_only) {
flags = PIN_USER;
vm = vma->vm;
i915_gem_object_set_readonly(obj);
} else {
DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
return ERR_PTR(-EINVAL);
}
return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
}
static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
{
struct intel_engine_pool_node *pool;
struct i915_vma *vma;
u64 batch_start;
u64 shadow_batch_start;
int err;
pool = intel_engine_pool_get(&eb->engine->pool, eb->batch_len);
if (IS_ERR(pool))
return ERR_CAST(pool);
err = intel_engine_cmd_parser(eb->engine,
vma = shadow_batch_pin(eb, pool->obj);
if (IS_ERR(vma))
goto err;
batch_start = gen8_canonical_addr(eb->batch->node.start) +
eb->batch_start_offset;
shadow_batch_start = gen8_canonical_addr(vma->node.start);
err = intel_engine_cmd_parser(eb->gem_context,
eb->engine,
eb->batch->obj,
pool->obj,
batch_start,
eb->batch_start_offset,
eb->batch_len,
is_master);
pool->obj,
shadow_batch_start);
if (err) {
if (err == -EACCES) /* unhandled chained batch */
i915_vma_unpin(vma);
/*
* Unsafe GGTT-backed buffers can still be submitted safely
* as non-secure.
* For PPGTT backing however, we have no choice but to forcibly
* reject unsafe buffers
*/
if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
/* Execute original buffer non-secure */
vma = NULL;
else
vma = ERR_PTR(err);
goto err;
}
vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
if (IS_ERR(vma))
goto err;
eb->vma[eb->buffer_count] = i915_vma_get(vma);
eb->flags[eb->buffer_count] =
__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
vma->exec_flags = &eb->flags[eb->buffer_count];
eb->buffer_count++;
eb->batch_start_offset = 0;
eb->batch = vma;
if (CMDPARSER_USES_GGTT(eb->i915))
eb->batch_flags |= I915_DISPATCH_SECURE;
/* eb->batch_len unchanged */
vma->private = pool;
return vma;
@ -2421,6 +2477,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
struct drm_i915_gem_exec_object2 *exec,
struct drm_syncobj **fences)
{
struct drm_i915_private *i915 = to_i915(dev);
struct i915_execbuffer eb;
struct dma_fence *in_fence = NULL;
struct dma_fence *exec_fence = NULL;
@ -2432,7 +2489,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
~__EXEC_OBJECT_UNKNOWN_FLAGS);
eb.i915 = to_i915(dev);
eb.i915 = i915;
eb.file = file;
eb.args = args;
if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
@ -2452,8 +2509,15 @@ i915_gem_do_execbuffer(struct drm_device *dev,
eb.batch_flags = 0;
if (args->flags & I915_EXEC_SECURE) {
if (INTEL_GEN(i915) >= 11)
return -ENODEV;
/* Return -EPERM to trigger fallback code on old binaries. */
if (!HAS_SECURE_BATCHES(i915))
return -EPERM;
if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
return -EPERM;
return -EPERM;
eb.batch_flags |= I915_DISPATCH_SECURE;
}
@ -2530,34 +2594,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
goto err_vma;
}
if (eb.batch_len == 0)
eb.batch_len = eb.batch->size - eb.batch_start_offset;
if (eb_use_cmdparser(&eb)) {
struct i915_vma *vma;
vma = eb_parse(&eb, drm_is_current_master(file));
vma = eb_parse(&eb);
if (IS_ERR(vma)) {
err = PTR_ERR(vma);
goto err_vma;
}
if (vma) {
/*
* Batch parsed and accepted:
*
* Set the DISPATCH_SECURE bit to remove the NON_SECURE
* bit from MI_BATCH_BUFFER_START commands issued in
* the dispatch_execbuffer implementations. We
* specifically don't want that set on batches the
* command parser has accepted.
*/
eb.batch_flags |= I915_DISPATCH_SECURE;
eb.batch_start_offset = 0;
eb.batch = vma;
}
}
if (eb.batch_len == 0)
eb.batch_len = eb.batch->size - eb.batch_start_offset;
/*
* snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
* batch" bit. Hence we need to pin secure batches into the global gtt.

13
drivers/gpu/drm/i915/gt/intel_engine_types.h
View File

@ -475,12 +475,13 @@ struct intel_engine_cs {
struct intel_engine_hangcheck hangcheck;
#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
#define I915_ENGINE_USING_CMD_PARSER BIT(0)
#define I915_ENGINE_SUPPORTS_STATS BIT(1)
#define I915_ENGINE_HAS_PREEMPTION BIT(2)
#define I915_ENGINE_HAS_SEMAPHORES BIT(3)
#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
#define I915_ENGINE_IS_VIRTUAL BIT(5)
#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
unsigned int flags;
/*
@ -541,9 +542,15 @@ struct intel_engine_cs {
};
static inline bool
intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
intel_engine_using_cmd_parser(const struct intel_engine_cs *engine)
{
return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
return engine->flags & I915_ENGINE_USING_CMD_PARSER;
}
static inline bool
intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine)
{
return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER;
}
static inline bool

8
drivers/gpu/drm/i915/gt/intel_gt_pm.c
View File

@ -38,6 +38,9 @@ static int __gt_unpark(struct intel_wakeref *wf)
gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
GEM_BUG_ON(!gt->awake);
if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
intel_enable_gt_powersave(i915);
i915_update_gfx_val(i915);
@ -67,6 +70,11 @@ static int __gt_park(struct intel_wakeref *wf)
if (INTEL_GEN(i915) >= 6)
gen6_rps_idle(i915);
if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
i915_rc6_ctx_wa_check(i915);
intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
}
/* Everything switched off, flush any residual interrupt just in case */
intel_synchronize_irq(i915);

439
drivers/gpu/drm/i915/i915_cmd_parser.c
View File

@ -53,13 +53,11 @@
* granting userspace undue privileges. There are three categories of privilege.
*
* First, commands which are explicitly defined as privileged or which should
* only be used by the kernel driver. The parser generally rejects such
* commands, though it may allow some from the drm master process.
* only be used by the kernel driver. The parser rejects such commands
*
* Second, commands which access registers. To support correct/enhanced
* userspace functionality, particularly certain OpenGL extensions, the parser
* provides a whitelist of registers which userspace may safely access (for both
* normal and drm master processes).
* provides a whitelist of registers which userspace may safely access
*
* Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
* The parser always rejects such commands.
@ -84,9 +82,9 @@
* in the per-engine command tables.
*
* Other command table entries map fairly directly to high level categories
* mentioned above: rejected, master-only, register whitelist. The parser
* implements a number of checks, including the privileged memory checks, via a
* general bitmasking mechanism.
* mentioned above: rejected, register whitelist. The parser implements a number
* of checks, including the privileged memory checks, via a general bitmasking
* mechanism.
*/
/*
@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor {
* CMD_DESC_REJECT: The command is never allowed
* CMD_DESC_REGISTER: The command should be checked against the
* register whitelist for the appropriate ring
* CMD_DESC_MASTER: The command is allowed if the submitting process
* is the DRM master
*/
u32 flags;
#define CMD_DESC_FIXED (1<<0)
@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor {
#define CMD_DESC_REJECT (1<<2)
#define CMD_DESC_REGISTER (1<<3)
#define CMD_DESC_BITMASK (1<<4)
#define CMD_DESC_MASTER (1<<5)
/*
* The command's unique identification bits and the bitmask to get them.
@ -194,7 +189,7 @@ struct drm_i915_cmd_table {
#define CMD(op, opm, f, lm, fl, ...) \
{ \
.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0), \
.cmd = { (op), ~0u << (opm) }, \
.cmd = { (op & ~0u << (opm)), ~0u << (opm) }, \
.length = { (lm) }, \
__VA_ARGS__ \
}
@ -209,14 +204,13 @@ struct drm_i915_cmd_table {
#define R CMD_DESC_REJECT
#define W CMD_DESC_REGISTER
#define B CMD_DESC_BITMASK
#define M CMD_DESC_MASTER
/* Command Mask Fixed Len Action
---------------------------------------------------------- */
static const struct drm_i915_cmd_descriptor common_cmds[] = {
static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
CMD( MI_NOOP, SMI, F, 1, S ),
CMD( MI_USER_INTERRUPT, SMI, F, 1, R ),
CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, M ),
CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, R ),
CMD( MI_ARB_CHECK, SMI, F, 1, S ),
CMD( MI_REPORT_HEAD, SMI, F, 1, S ),
CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ),
@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {
CMD( MI_BATCH_BUFFER_START, SMI, !F, 0xFF, S ),
};
static const struct drm_i915_cmd_descriptor render_cmds[] = {
static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
CMD( MI_FLUSH, SMI, F, 1, S ),
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_PREDICATE, SMI, F, 1, S ),
@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
CMD( MI_URB_ATOMIC_ALLOC, SMI, F, 1, S ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_RS_CONTEXT, SMI, F, 1, S ),
CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ),
CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W,
.reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ),
@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
CMD( GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS, S3D, !F, 0x1FF, S ),
};
static const struct drm_i915_cmd_descriptor video_cmds[] = {
static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B,
@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = {
CMD( MFX_WAIT, SMFX, F, 1, S ),
};
static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
CMD( MI_ARB_ON_OFF, SMI, F, 1, R ),
CMD( MI_SET_APPID, SMI, F, 1, S ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0xFF, B,
@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
}}, ),
};
static const struct drm_i915_cmd_descriptor blt_cmds[] = {
static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
CMD( MI_DISPLAY_FLIP, SMI, !F, 0xFF, R ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, B,
.bits = {{
@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = {
};
static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, M ),
CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, R ),
CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, R ),
};
/*
* For Gen9 we can still rely on the h/w to enforce cmd security, and only
* need to re-enforce the register access checks. We therefore only need to
* teach the cmdparser how to find the end of each command, and identify
* register accesses. The table doesn't need to reject any commands, and so
* the only commands listed here are:
* 1) Those that touch registers
* 2) Those that do not have the default 8-bit length
*
* Note that the default MI length mask chosen for this table is 0xFF, not
* the 0x3F used on older devices. This is because the vast majority of MI
* cmds on Gen9 use a standard 8-bit Length field.
* All the Gen9 blitter instructions are standard 0xFF length mask, and
* none allow access to non-general registers, so in fact no BLT cmds are
* included in the table at all.
*
*/
static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
CMD( MI_NOOP, SMI, F, 1, S ),
CMD( MI_USER_INTERRUPT, SMI, F, 1, S ),
CMD( MI_WAIT_FOR_EVENT, SMI, F, 1, S ),
CMD( MI_FLUSH, SMI, F, 1, S ),
CMD( MI_ARB_CHECK, SMI, F, 1, S ),
CMD( MI_REPORT_HEAD, SMI, F, 1, S ),
CMD( MI_ARB_ON_OFF, SMI, F, 1, S ),
CMD( MI_SUSPEND_FLUSH, SMI, F, 1, S ),
CMD( MI_LOAD_SCAN_LINES_INCL, SMI, !F, 0x3F, S ),
CMD( MI_LOAD_SCAN_LINES_EXCL, SMI, !F, 0x3F, S ),
CMD( MI_STORE_DWORD_IMM, SMI, !F, 0x3FF, S ),
CMD( MI_LOAD_REGISTER_IMM(1), SMI, !F, 0xFF, W,
.reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 } ),
CMD( MI_UPDATE_GTT, SMI, !F, 0x3FF, S ),
CMD( MI_STORE_REGISTER_MEM_GEN8, SMI, F, 4, W,
.reg = { .offset = 1, .mask = 0x007FFFFC } ),
CMD( MI_FLUSH_DW, SMI, !F, 0x3F, S ),
CMD( MI_LOAD_REGISTER_MEM_GEN8, SMI, F, 4, W,
.reg = { .offset = 1, .mask = 0x007FFFFC } ),
CMD( MI_LOAD_REGISTER_REG, SMI, !F, 0xFF, W,
.reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 } ),
/*
* We allow BB_START but apply further checks. We just sanitize the
* basic fields here.
*/
#define MI_BB_START_OPERAND_MASK GENMASK(SMI-1, 0)
#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
CMD( MI_BATCH_BUFFER_START_GEN8, SMI, !F, 0xFF, B,
.bits = {{
.offset = 0,
.mask = MI_BB_START_OPERAND_MASK,
.expected = MI_BB_START_OPERAND_EXPECT,
}}, ),
};
static const struct drm_i915_cmd_descriptor noop_desc =
CMD(MI_NOOP, SMI, F, 1, S);
@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc =
#undef R
#undef W
#undef B
#undef M
static const struct drm_i915_cmd_table gen7_render_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ render_cmds, ARRAY_SIZE(render_cmds) },
static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
};
static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ render_cmds, ARRAY_SIZE(render_cmds) },
static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
};
static const struct drm_i915_cmd_table gen7_video_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ video_cmds, ARRAY_SIZE(video_cmds) },
static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
};
static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ vecs_cmds, ARRAY_SIZE(vecs_cmds) },
static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
};
static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ blt_cmds, ARRAY_SIZE(blt_cmds) },
static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
};
static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
{ common_cmds, ARRAY_SIZE(common_cmds) },
{ blt_cmds, ARRAY_SIZE(blt_cmds) },
static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
};
static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
};
/*
* Register whitelists, sorted by increasing register offset.
*/
@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
};
static const struct drm_i915_reg_descriptor ivb_master_regs[] = {
REG32(FORCEWAKE_MT),
REG32(DERRMR),
REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)),
REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)),
REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)),
};
static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
REG32(FORCEWAKE_MT),
REG32(DERRMR),
static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
REG32(BCS_SWCTRL),
REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
REG64_IDX(BCS_GPR, 0),
REG64_IDX(BCS_GPR, 1),
REG64_IDX(BCS_GPR, 2),
REG64_IDX(BCS_GPR, 3),
REG64_IDX(BCS_GPR, 4),
REG64_IDX(BCS_GPR, 5),
REG64_IDX(BCS_GPR, 6),
REG64_IDX(BCS_GPR, 7),
REG64_IDX(BCS_GPR, 8),
REG64_IDX(BCS_GPR, 9),
REG64_IDX(BCS_GPR, 10),
REG64_IDX(BCS_GPR, 11),
REG64_IDX(BCS_GPR, 12),
REG64_IDX(BCS_GPR, 13),
REG64_IDX(BCS_GPR, 14),
REG64_IDX(BCS_GPR, 15),
};
#undef REG64
@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
struct drm_i915_reg_table {
const struct drm_i915_reg_descriptor *regs;
int num_regs;
bool master;
};
static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
};
static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
};
static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false },
{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
};
static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
};
static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
};
static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
return 0;
}
static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
{
u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
return 0xFF;
DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
return 0;
}
static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
const struct drm_i915_cmd_table *cmd_tables,
int cmd_table_count)
@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
int cmd_table_count;
int ret;
if (!IS_GEN(engine->i915, 7))
if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
engine->class == COPY_ENGINE_CLASS))
return;
switch (engine->class) {
case RENDER_CLASS:
if (IS_HASWELL(engine->i915)) {
cmd_tables = hsw_render_ring_cmds;
cmd_tables = hsw_render_ring_cmd_table;
cmd_table_count =
ARRAY_SIZE(hsw_render_ring_cmds);
ARRAY_SIZE(hsw_render_ring_cmd_table);
} else {
cmd_tables = gen7_render_cmds;
cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
cmd_tables = gen7_render_cmd_table;
cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
}
if (IS_HASWELL(engine->i915)) {
@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
engine->reg_tables = ivb_render_reg_tables;
engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
}
engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
break;
case VIDEO_DECODE_CLASS:
cmd_tables = gen7_video_cmds;
cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
cmd_tables = gen7_video_cmd_table;
cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
break;
case COPY_ENGINE_CLASS:
if (IS_HASWELL(engine->i915)) {
cmd_tables = hsw_blt_ring_cmds;
cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
if (IS_GEN(engine->i915, 9)) {
cmd_tables = gen9_blt_cmd_table;
cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
engine->get_cmd_length_mask =
gen9_blt_get_cmd_length_mask;
/* BCS Engine unsafe without parser */
engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
} else if (IS_HASWELL(engine->i915)) {
cmd_tables = hsw_blt_ring_cmd_table;
cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
} else {
cmd_tables = gen7_blt_cmds;
cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
cmd_tables = gen7_blt_cmd_table;
cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
}
if (IS_HASWELL(engine->i915)) {
if (IS_GEN(engine->i915, 9)) {
engine->reg_tables = gen9_blt_reg_tables;
engine->reg_table_count =
ARRAY_SIZE(gen9_blt_reg_tables);
} else if (IS_HASWELL(engine->i915)) {
engine->reg_tables = hsw_blt_reg_tables;
engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
} else {
engine->reg_tables = ivb_blt_reg_tables;
engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
}
engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
break;
case VIDEO_ENHANCEMENT_CLASS:
cmd_tables = hsw_vebox_cmds;
cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
cmd_tables = hsw_vebox_cmd_table;
cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
/* VECS can use the same length_mask function as VCS */
engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
break;
@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
return;
}
engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
engine->flags |= I915_ENGINE_USING_CMD_PARSER;
}
/**
@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
*/
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
{
if (!intel_engine_needs_cmd_parser(engine))
if (!intel_engine_using_cmd_parser(engine))
return;
fini_hash_table(engine);
@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
}
static const struct drm_i915_reg_descriptor *
find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
find_reg(const struct intel_engine_cs *engine, u32 addr)
{
const struct drm_i915_reg_table *table = engine->reg_tables;
const struct drm_i915_reg_descriptor *reg = NULL;
int count = engine->reg_table_count;
for (; count > 0; ++table, --count) {
if (!table->master || is_master) {
const struct drm_i915_reg_descriptor *reg;
for (; !reg && (count > 0); ++table, --count)
reg = __find_reg(table->regs, table->num_regs, addr);
reg = __find_reg(table->regs, table->num_regs, addr);
if (reg != NULL)
return reg;
}
}
return NULL;
return reg;
}
/* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
static bool check_cmd(const struct intel_engine_cs *engine,
const struct drm_i915_cmd_descriptor *desc,
const u32 *cmd, u32 length,
const bool is_master)
const u32 *cmd, u32 length)
{
if (desc->flags & CMD_DESC_SKIP)
return true;
@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine,
return false;
}
if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
*cmd);
return false;
}
if (desc->flags & CMD_DESC_REGISTER) {
/*
* Get the distance between individual register offset
@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
offset += step) {
const u32 reg_addr = cmd[offset] & desc->reg.mask;
const struct drm_i915_reg_descriptor *reg =
find_reg(engine, is_master, reg_addr);
find_reg(engine, reg_addr);
if (!reg) {
DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine,
return true;
}
static int check_bbstart(const struct i915_gem_context *ctx,
u32 *cmd, u32 offset, u32 length,
u32 batch_len,
u64 batch_start,
u64 shadow_batch_start)
{
u64 jump_offset, jump_target;
u32 target_cmd_offset, target_cmd_index;
/* For igt compatibility on older platforms */
if (CMDPARSER_USES_GGTT(ctx->i915)) {
DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
return -EACCES;
}
if (length != 3) {
DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
length);
return -EINVAL;
}
jump_target = *(u64*)(cmd+1);
jump_offset = jump_target - batch_start;
/*
* Any underflow of jump_target is guaranteed to be outside the range
* of a u32, so >= test catches both too large and too small
*/
if (jump_offset >= batch_len) {
DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
jump_target);
return -EINVAL;
}
/*
* This cannot overflow a u32 because we already checked jump_offset
* is within the BB, and the batch_len is a u32
*/
target_cmd_offset = lower_32_bits(jump_offset);
target_cmd_index = target_cmd_offset / sizeof(u32);
*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
if (target_cmd_index == offset)
return 0;
if (ctx->jump_whitelist_cmds <= target_cmd_index) {
DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
return -EINVAL;
} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
jump_target);
return -EINVAL;
}
return 0;
}
static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
{
const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
const u32 exact_size = BITS_TO_LONGS(batch_cmds);
u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
unsigned long *next_whitelist;
if (CMDPARSER_USES_GGTT(ctx->i915))
return;
if (batch_cmds <= ctx->jump_whitelist_cmds) {
bitmap_zero(ctx->jump_whitelist, batch_cmds);
return;
}
again:
next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
if (next_whitelist) {
kfree(ctx->jump_whitelist);
ctx->jump_whitelist = next_whitelist;
ctx->jump_whitelist_cmds =
next_size * BITS_PER_BYTE * sizeof(long);
return;
}
if (next_size > exact_size) {
next_size = exact_size;
goto again;
}
DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
return;
}
#define LENGTH_BIAS 2
/**
* i915_parse_cmds() - parse a submitted batch buffer for privilege violations
* @ctx: the context in which the batch is to execute
* @engine: the engine on which the batch is to execute
* @batch_obj: the batch buffer in question
* @shadow_batch_obj: copy of the batch buffer in question
* @batch_start: Canonical base address of batch
* @batch_start_offset: byte offset in the batch at which execution starts
* @batch_len: length of the commands in batch_obj
* @is_master: is the submitting process the drm master?
* @shadow_batch_obj: copy of the batch buffer in question
* @shadow_batch_start: Canonical base address of shadow_batch_obj
*
* Parses the specified batch buffer looking for privilege violations as
* described in the overview.
@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
* Return: non-zero if the parser finds violations or otherwise fails; -EACCES
* if the batch appears legal but should use hardware parsing
*/
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
int intel_engine_cmd_parser(struct i915_gem_context *ctx,
struct intel_engine_cs *engine,
struct drm_i915_gem_object *batch_obj,
struct drm_i915_gem_object *shadow_batch_obj,
u64 batch_start,
u32 batch_start_offset,
u32 batch_len,
bool is_master)
struct drm_i915_gem_object *shadow_batch_obj,
u64 shadow_batch_start)
{
u32 *cmd, *batch_end;
u32 *cmd, *batch_end, offset = 0;
struct drm_i915_cmd_descriptor default_desc = noop_desc;
const struct drm_i915_cmd_descriptor *desc = &default_desc;
bool needs_clflush_after = false;
@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
return PTR_ERR(cmd);
}
init_whitelist(ctx, batch_len);
/*
* We use the batch length as size because the shadow object is as
* large or larger and copy_batch() will write MI_NOPs to the extra
@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
do {
u32 length;
if (*cmd == MI_BATCH_BUFFER_END) {
if (needs_clflush_after) {
void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
drm_clflush_virt_range(ptr,
(void *)(cmd + 1) - ptr);
}
if (*cmd == MI_BATCH_BUFFER_END)
break;
}
desc = find_cmd(engine, *cmd, desc, &default_desc);
if (!desc) {
DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
*cmd);
ret = -EINVAL;
break;
}
/*
* If the batch buffer contains a chained batch, return an
* error that tells the caller to abort and dispatch the
* workload as a non-secure batch.
*/
if (desc->cmd.value == MI_BATCH_BUFFER_START) {
ret = -EACCES;
break;
goto err;
}
if (desc->flags & CMD_DESC_FIXED)
@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
length,
batch_end - cmd);
ret = -EINVAL;
goto err;
}
if (!check_cmd(engine, desc, cmd, length)) {
ret = -EACCES;
goto err;
}
if (desc->cmd.value == MI_BATCH_BUFFER_START) {
ret = check_bbstart(ctx, cmd, offset, length,
batch_len, batch_start,
shadow_batch_start);
if (ret)
goto err;
break;
}
if (!check_cmd(engine, desc, cmd, length, is_master)) {
ret = -EACCES;
break;
}
if (ctx->jump_whitelist_cmds > offset)
set_bit(offset, ctx->jump_whitelist);
cmd += length;
offset += length;
if (cmd >= batch_end) {
DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
ret = -EINVAL;
break;
goto err;
}
} while (1);
if (needs_clflush_after) {
void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
}
err:
i915_gem_object_unpin_map(shadow_batch_obj);
return ret;
}
@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
/* If the command parser is not enabled, report 0 - unsupported */
for_each_uabi_engine(engine, dev_priv) {
if (intel_engine_needs_cmd_parser(engine)) {
if (intel_engine_using_cmd_parser(engine)) {
active = true;
break;
}
@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
* the parser enabled.
* 9. Don't whitelist or handle oacontrol specially, as ownership
* for oacontrol state is moving to i915-perf.
* 10. Support for Gen9 BCS Parsing
*/
return 9;
return 10;
}

4
drivers/gpu/drm/i915/i915_drv.c
View File

@ -1850,6 +1850,8 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
i915_gem_suspend_late(dev_priv);
i915_rc6_ctx_wa_suspend(dev_priv);
intel_uncore_suspend(&dev_priv->uncore);
intel_power_domains_suspend(dev_priv,
@ -2053,6 +2055,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
intel_power_domains_resume(dev_priv);
i915_rc6_ctx_wa_resume(dev_priv);
intel_gt_sanitize(&dev_priv->gt, true);
enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);

31
drivers/gpu/drm/i915/i915_drv.h
View File

@ -593,6 +593,8 @@ struct intel_rps {
struct intel_rc6 {
bool enabled;
bool ctx_corrupted;
intel_wakeref_t ctx_corrupted_wakeref;
u64 prev_hw_residency[4];
u64 cur_residency[4];
};
@ -2075,9 +2077,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
#define VEBOX_MASK(dev_priv) \
ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS)
/*
* The Gen7 cmdparser copies the scanned buffer to the ggtt for execution
* All later gens can run the final buffer from the ppgtt
*/
#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7)
#define HAS_LLC(dev_priv) (INTEL_INFO(dev_priv)->has_llc)
#define HAS_SNOOP(dev_priv) (INTEL_INFO(dev_priv)->has_snoop)
#define HAS_EDRAM(dev_priv) ((dev_priv)->edram_size_mb)
#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6)
#define HAS_WT(dev_priv) ((IS_HASWELL(dev_priv) || \
IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv))
@ -2110,10 +2119,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
/* Early gen2 have a totally busted CS tlb and require pinned batches. */
#define HAS_BROKEN_CS_TLB(dev_priv) (IS_I830(dev_priv) || IS_I845G(dev_priv))
#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv) \
(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
/* WaRsDisableCoarsePowerGating:skl,cnl */
#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
(IS_CANNONLAKE(dev_priv) || \
IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
#define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
@ -2284,6 +2295,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
unsigned long flags);
#define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
struct i915_vma * __must_check
i915_gem_object_pin(struct drm_i915_gem_object *obj,
struct i915_address_space *vm,
const struct i915_ggtt_view *view,
u64 size,
u64 alignment,
u64 flags);
void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
static inline int __must_check
@ -2393,12 +2412,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
int intel_engine_cmd_parser(struct i915_gem_context *cxt,
struct intel_engine_cs *engine,
struct drm_i915_gem_object *batch_obj,
struct drm_i915_gem_object *shadow_batch_obj,
u64 user_batch_start,
u32 batch_start_offset,
u32 batch_len,
bool is_master);
struct drm_i915_gem_object *shadow_batch_obj,
u64 shadow_batch_start);
/* intel_device_info.c */
static inline struct intel_device_info *

16
drivers/gpu/drm/i915/i915_gem.c
View File

@ -964,6 +964,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
{
struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct i915_address_space *vm = &dev_priv->ggtt.vm;
return i915_gem_object_pin(obj, vm, view, size, alignment,
flags | PIN_GLOBAL);
}
struct i915_vma *
i915_gem_object_pin(struct drm_i915_gem_object *obj,
struct i915_address_space *vm,
const struct i915_ggtt_view *view,
u64 size,
u64 alignment,
u64 flags)
{
struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
struct i915_vma *vma;
int ret;
@ -1038,7 +1052,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
return ERR_PTR(ret);
}
ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
ret = i915_vma_pin(vma, size, alignment, flags);
if (ret)
return ERR_PTR(ret);

2
drivers/gpu/drm/i915/i915_getparam.c
View File

@ -62,7 +62,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES);
break;
case I915_PARAM_HAS_SECURE_BATCHES:
value = capable(CAP_SYS_ADMIN);
value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN);
break;
case I915_PARAM_CMD_PARSER_VERSION:
value = i915_cmd_parser_get_version(i915);

10
drivers/gpu/drm/i915/i915_reg.h
View File

@ -471,6 +471,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
#define ECOCHK_PPGTT_WT_HSW (0x2 << 3)
#define ECOCHK_PPGTT_WB_HSW (0x3 << 3)
#define GEN8_RC6_CTX_INFO _MMIO(0x8504)
#define GAC_ECO_BITS _MMIO(0x14090)
#define ECOBITS_SNB_BIT (1 << 13)
#define ECOBITS_PPGTT_CACHE64B (3 << 8)
@ -555,6 +557,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
*/
#define BCS_SWCTRL _MMIO(0x22200)
/* There are 16 GPR registers */
#define BCS_GPR(n) _MMIO(0x22600 + (n) * 8)
#define BCS_GPR_UDW(n) _MMIO(0x22600 + (n) * 8 + 4)
#define GPGPU_THREADS_DISPATCHED _MMIO(0x2290)
#define GPGPU_THREADS_DISPATCHED_UDW _MMIO(0x2290 + 4)
#define HS_INVOCATION_COUNT _MMIO(0x2300)
@ -7211,6 +7217,10 @@ enum {
#define TGL_DMC_DEBUG_DC5_COUNT _MMIO(0x101084)
#define TGL_DMC_DEBUG_DC6_COUNT _MMIO(0x101088)
/* Display Internal Timeout Register */
#define RM_TIMEOUT _MMIO(0x42060)
#define MMIO_TIMEOUT_US(us) ((us) << 0)
/* interrupts */
#define DE_MASTER_IRQ_CONTROL (1 << 31)
#define DE_SPRITEB_FLIP_DONE (1 << 29)

122
drivers/gpu/drm/i915/intel_pm.c
View File

@ -126,6 +126,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
*/
I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
PWM1_GATING_DIS | PWM2_GATING_DIS);
/*
* Lower the display internal timeout.
* This is needed to avoid any hard hangs when DSI port PLL
* is off and a MMIO access is attempted by any privilege
* application, using batch buffers or any other means.
*/
I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
}
static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@ -8544,6 +8552,100 @@ static void intel_init_emon(struct drm_i915_private *dev_priv)
dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
}
static bool i915_rc6_ctx_corrupted(struct drm_i915_private *dev_priv)
{
return !I915_READ(GEN8_RC6_CTX_INFO);
}
static void i915_rc6_ctx_wa_init(struct drm_i915_private *i915)
{
if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
return;
if (i915_rc6_ctx_corrupted(i915)) {
DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
i915->gt_pm.rc6.ctx_corrupted = true;
i915->gt_pm.rc6.ctx_corrupted_wakeref =
intel_runtime_pm_get(&i915->runtime_pm);
}
}
static void i915_rc6_ctx_wa_cleanup(struct drm_i915_private *i915)
{
if (i915->gt_pm.rc6.ctx_corrupted) {
intel_runtime_pm_put(&i915->runtime_pm,
i915->gt_pm.rc6.ctx_corrupted_wakeref);
i915->gt_pm.rc6.ctx_corrupted = false;
}
}
/**
* i915_rc6_ctx_wa_suspend - system suspend sequence for the RC6 CTX WA
* @i915: i915 device
*
* Perform any steps needed to clean up the RC6 CTX WA before system suspend.
*/
void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915)
{
if (i915->gt_pm.rc6.ctx_corrupted)
intel_runtime_pm_put(&i915->runtime_pm,
i915->gt_pm.rc6.ctx_corrupted_wakeref);
}
/**
* i915_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
* @i915: i915 device
*
* Perform any steps needed to re-init the RC6 CTX WA after system resume.
*/
void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915)
{
if (!i915->gt_pm.rc6.ctx_corrupted)
return;
if (i915_rc6_ctx_corrupted(i915)) {
i915->gt_pm.rc6.ctx_corrupted_wakeref =
intel_runtime_pm_get(&i915->runtime_pm);
return;
}
DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
i915->gt_pm.rc6.ctx_corrupted = false;
}
static void intel_disable_rc6(struct drm_i915_private *dev_priv);
/**
* i915_rc6_ctx_wa_check - check for a new RC6 CTX corruption
* @i915: i915 device
*
* Check if an RC6 CTX corruption has happened since the last check and if so
* disable RC6 and runtime power management.
*
* Return false if no context corruption has happened since the last call of
* this function, true otherwise.
*/
bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915)
{
if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
return false;
if (i915->gt_pm.rc6.ctx_corrupted)
return false;
if (!i915_rc6_ctx_corrupted(i915))
return false;
DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
intel_disable_rc6(i915);
i915->gt_pm.rc6.ctx_corrupted = true;
i915->gt_pm.rc6.ctx_corrupted_wakeref =
intel_runtime_pm_get_noresume(&i915->runtime_pm);
return true;
}
void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
{
struct intel_rps *rps = &dev_priv->gt_pm.rps;
@ -8557,6 +8659,8 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
pm_runtime_get(&dev_priv->drm.pdev->dev);
}
i915_rc6_ctx_wa_init(dev_priv);
/* Initialize RPS limits (for userspace) */
if (IS_CHERRYVIEW(dev_priv))
cherryview_init_gt_powersave(dev_priv);
@ -8595,6 +8699,8 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
if (IS_VALLEYVIEW(dev_priv))
valleyview_cleanup_gt_powersave(dev_priv);
i915_rc6_ctx_wa_cleanup(dev_priv);
if (!HAS_RC6(dev_priv))
pm_runtime_put(&dev_priv->drm.pdev->dev);
}
@ -8623,7 +8729,7 @@ static inline void intel_disable_llc_pstate(struct drm_i915_private *i915)
i915->gt_pm.llc_pstate.enabled = false;
}
static void intel_disable_rc6(struct drm_i915_private *dev_priv)
static void __intel_disable_rc6(struct drm_i915_private *dev_priv)
{
lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@ -8642,6 +8748,15 @@ static void intel_disable_rc6(struct drm_i915_private *dev_priv)
dev_priv->gt_pm.rc6.enabled = false;
}
static void intel_disable_rc6(struct drm_i915_private *dev_priv)
{
struct intel_rps *rps = &dev_priv->gt_pm.rps;
mutex_lock(&rps->lock);
__intel_disable_rc6(dev_priv);
mutex_unlock(&rps->lock);
}
static void intel_disable_rps(struct drm_i915_private *dev_priv)
{
lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
@ -8667,7 +8782,7 @@ void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
{
mutex_lock(&dev_priv->gt_pm.rps.lock);
intel_disable_rc6(dev_priv);
__intel_disable_rc6(dev_priv);
intel_disable_rps(dev_priv);
if (HAS_LLC(dev_priv))
intel_disable_llc_pstate(dev_priv);
@ -8694,6 +8809,9 @@ static void intel_enable_rc6(struct drm_i915_private *dev_priv)
if (dev_priv->gt_pm.rc6.enabled)
return;
if (dev_priv->gt_pm.rc6.ctx_corrupted)
return;
if (IS_CHERRYVIEW(dev_priv))
cherryview_enable_rc6(dev_priv);
else if (IS_VALLEYVIEW(dev_priv))

3
drivers/gpu/drm/i915/intel_pm.h
View File

@ -36,6 +36,9 @@ void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv);
void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
bool i915_rc6_ctx_wa_check(struct drm_i915_private *i915);
void i915_rc6_ctx_wa_suspend(struct drm_i915_private *i915);
void i915_rc6_ctx_wa_resume(struct drm_i915_private *i915);
void gen6_rps_busy(struct drm_i915_private *dev_priv);
void gen6_rps_idle(struct drm_i915_private *dev_priv);
void gen6_rps_boost(struct i915_request *rq);

8
drivers/scsi/qla2xxx/qla_mid.c
View File

@ -76,9 +76,11 @@ qla24xx_deallocate_vp_id(scsi_qla_host_t *vha)
* ensures no active vp_list traversal while the vport is removed
* from the queue)
*/
for (i = 0; i < 10 && atomic_read(&vha->vref_count); i++)
wait_event_timeout(vha->vref_waitq,
atomic_read(&vha->vref_count), HZ);
for (i = 0; i < 10; i++) {
if (wait_event_timeout(vha->vref_waitq,
!atomic_read(&vha->vref_count), HZ) > 0)
break;
}
spin_lock_irqsave(&ha->vport_slock, flags);
if (atomic_read(&vha->vref_count)) {

8
drivers/scsi/qla2xxx/qla_os.c
View File

@ -1119,9 +1119,11 @@ qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha)
qla2x00_mark_all_devices_lost(vha, 0);
for (i = 0; i < 10; i++)
wait_event_timeout(vha->fcport_waitQ, test_fcport_count(vha),
HZ);
for (i = 0; i < 10; i++) {
if (wait_event_timeout(vha->fcport_waitQ,
test_fcport_count(vha), HZ) > 0)
break;
}
flush_workqueue(vha->hw->wq);
}

3
drivers/scsi/scsi_lib.c
View File

@ -1883,7 +1883,8 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost)
{
unsigned int cmd_size, sgl_size;
sgl_size = scsi_mq_inline_sgl_size(shost);
sgl_size = max_t(unsigned int, sizeof(struct scatterlist),
scsi_mq_inline_sgl_size(shost));
cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size + sgl_size;
if (scsi_host_get_prot(shost))
cmd_size += sizeof(struct scsi_data_buffer) +

29
drivers/scsi/sd_zbc.c
View File

@ -263,25 +263,16 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
int result = cmd->result;
struct request *rq = cmd->request;
switch (req_op(rq)) {
case REQ_OP_ZONE_RESET:
case REQ_OP_ZONE_RESET_ALL:
if (result &&
sshdr->sense_key == ILLEGAL_REQUEST &&
sshdr->asc == 0x24)
/*
* INVALID FIELD IN CDB error: reset of a conventional
* zone was attempted. Nothing to worry about, so be
* quiet about the error.
*/
rq->rq_flags |= RQF_QUIET;
break;
case REQ_OP_WRITE:
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
break;
if (req_op(rq) == REQ_OP_ZONE_RESET &&
result &&
sshdr->sense_key == ILLEGAL_REQUEST &&
sshdr->asc == 0x24) {
/*
* INVALID FIELD IN CDB error: reset of a conventional
* zone was attempted. Nothing to worry about, so be
* quiet about the error.
*/
rq->rq_flags |= RQF_QUIET;
}
}

2
drivers/staging/Kconfig
View File

@ -125,6 +125,4 @@ source "drivers/staging/exfat/Kconfig"
source "drivers/staging/qlge/Kconfig"
source "drivers/staging/vboxsf/Kconfig"
endif # STAGING

1
drivers/staging/Makefile
View File

@ -53,4 +53,3 @@ obj-$(CONFIG_UWB) += uwb/
obj-$(CONFIG_USB_WUSB) += wusbcore/
obj-$(CONFIG_EXFAT_FS) += exfat/
obj-$(CONFIG_QLGE) += qlge/
obj-$(CONFIG_VBOXSF_FS) += vboxsf/

10
drivers/staging/vboxsf/Kconfig
View File

@ -1,10 +0,0 @@
config VBOXSF_FS
tristate "VirtualBox guest shared folder (vboxsf) support"
depends on X86 && VBOXGUEST
select NLS
help
VirtualBox hosts can share folders with guests, this driver
implements the Linux-guest side of this allowing folders exported
by the host to be mounted under Linux.
If you want to use shared folders in VirtualBox guests, answer Y or M.

5
drivers/staging/vboxsf/Makefile
View File

@ -1,5 +0,0 @@
# SPDX-License-Identifier: MIT
obj-$(CONFIG_VBOXSF_FS) += vboxsf.o
vboxsf-y := dir.o file.o utils.o vboxsf_wrappers.o super.o

7
drivers/staging/vboxsf/TODO
View File

@ -1,7 +0,0 @@
TODO:
- Find a file-system developer to review this and give their Reviewed-By
- Address any items coming up during review
- Move to fs/vboxfs
Please send any patches to Greg Kroah-Hartman <gregkh@linuxfoundation.org>
and Hans de Goede <hdegoede@redhat.com>

418
drivers/staging/vboxsf/dir.c
View File

@ -1,418 +0,0 @@
// SPDX-License-Identifier: MIT
/*
* VirtualBox Guest Shared Folders support: Directory inode and file operations
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#include <linux/namei.h>
#include <linux/vbox_utils.h>
#include "vfsmod.h"
static int vboxsf_dir_open(struct inode *inode, struct file *file)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
struct shfl_createparms params = {};
struct vboxsf_dir_info *sf_d;
int err;
sf_d = vboxsf_dir_info_alloc();
if (!sf_d)
return -ENOMEM;
params.handle = SHFL_HANDLE_NIL;
params.create_flags = SHFL_CF_DIRECTORY | SHFL_CF_ACT_OPEN_IF_EXISTS |
SHFL_CF_ACT_FAIL_IF_NEW | SHFL_CF_ACCESS_READ;
err = vboxsf_create_at_dentry(file_dentry(file), &params);
if (err)
goto err_free_dir_info;
if (params.result != SHFL_FILE_EXISTS) {
err = -ENOENT;
goto err_close;
}
err = vboxsf_dir_read_all(sbi, sf_d, params.handle);
if (err)
goto err_close;
vboxsf_close(sbi->root, params.handle);
file->private_data = sf_d;
return 0;
err_close:
vboxsf_close(sbi->root, params.handle);
err_free_dir_info:
vboxsf_dir_info_free(sf_d);
return err;
}
static int vboxsf_dir_release(struct inode *inode, struct file *file)
{
if (file->private_data)
vboxsf_dir_info_free(file->private_data);
return 0;
}
static unsigned int vboxsf_get_d_type(u32 mode)
{
unsigned int d_type;
switch (mode & SHFL_TYPE_MASK) {
case SHFL_TYPE_FIFO:
d_type = DT_FIFO;
break;
case SHFL_TYPE_DEV_CHAR:
d_type = DT_CHR;
break;
case SHFL_TYPE_DIRECTORY:
d_type = DT_DIR;
break;
case SHFL_TYPE_DEV_BLOCK:
d_type = DT_BLK;
break;
case SHFL_TYPE_FILE:
d_type = DT_REG;
break;
case SHFL_TYPE_SYMLINK:
d_type = DT_LNK;
break;
case SHFL_TYPE_SOCKET:
d_type = DT_SOCK;
break;
case SHFL_TYPE_WHITEOUT:
d_type = DT_WHT;
break;
default:
d_type = DT_UNKNOWN;
break;
}
return d_type;
}
static bool vboxsf_dir_emit(struct file *dir, struct dir_context *ctx)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(file_inode(dir)->i_sb);
struct vboxsf_dir_info *sf_d = dir->private_data;
struct shfl_dirinfo *info;
struct vboxsf_dir_buf *b;
unsigned int d_type;
loff_t i, cur = 0;
ino_t fake_ino;
size_t size;
int err;
list_for_each_entry(b, &sf_d->info_list, head) {
try_next_entry:
if (ctx->pos >= cur + b->entries) {
cur += b->entries;
continue;
}
/*
* Note the vboxsf_dir_info objects we are iterating over here
* are variable sized, so the info pointer may end up being
* unaligned. This is how we get the data from the host.
* Since vboxsf is only supported on x86 machines this is not
* a problem.
*/
for (i = 0, info = b->buf; i < ctx->pos - cur; i++) {
size = offsetof(struct shfl_dirinfo, name.string) +
info->name.size;
info = (struct shfl_dirinfo *)((uintptr_t)info + size);
}
/* Info now points to the right entry, emit it. */
d_type = vboxsf_get_d_type(info->info.attr.mode);
/*
* On 32 bit systems pos is 64 signed, while ino is 32 bit
* unsigned so fake_ino may overflow, check for this.
*/
if ((ino_t)(ctx->pos + 1) != (u64)(ctx->pos + 1)) {
vbg_err("vboxsf: fake ino overflow, truncating dir\n");
return false;
}
fake_ino = ctx->pos + 1;
if (sbi->nls) {
char d_name[NAME_MAX];
err = vboxsf_nlscpy(sbi, d_name, NAME_MAX,
info->name.string.utf8,
info->name.length);
if (err) {
/* skip erroneous entry and proceed */
ctx->pos += 1;
goto try_next_entry;
}
return dir_emit(ctx, d_name, strlen(d_name),
fake_ino, d_type);
}
return dir_emit(ctx, info->name.string.utf8, info->name.length,
fake_ino, d_type);
}
return false;
}
static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx)
{
bool keep_iterating;
for (keep_iterating = true; keep_iterating; ctx->pos += 1)
keep_iterating = vboxsf_dir_emit(dir, ctx);
return 0;
}
const struct file_operations vboxsf_dir_fops = {
.open = vboxsf_dir_open,
.iterate = vboxsf_dir_iterate,
.release = vboxsf_dir_release,
.read = generic_read_dir,
.llseek = generic_file_llseek,
};
/*
* This is called during name resolution/lookup to check if the @dentry in
* the cache is still valid. the job is handled by vboxsf_inode_revalidate.
*/
static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
if (flags & LOOKUP_RCU)
return -ECHILD;
if (d_really_is_positive(dentry))
return vboxsf_inode_revalidate(dentry) == 0;
else
return vboxsf_stat_dentry(dentry, NULL) == -ENOENT;
}
const struct dentry_operations vboxsf_dentry_ops = {
.d_revalidate = vboxsf_dentry_revalidate
};
/* iops */
static struct dentry *vboxsf_dir_lookup(struct inode *parent,
struct dentry *dentry,
unsigned int flags)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
struct shfl_fsobjinfo fsinfo;
struct inode *inode;
int err;
dentry->d_time = jiffies;
err = vboxsf_stat_dentry(dentry, &fsinfo);
if (err) {
inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
} else {
inode = vboxsf_new_inode(parent->i_sb);
if (!IS_ERR(inode))
vboxsf_init_inode(sbi, inode, &fsinfo);
}
return d_splice_alias(inode, dentry);
}
static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry,
struct shfl_fsobjinfo *info)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
struct vboxsf_inode *sf_i;
struct inode *inode;
inode = vboxsf_new_inode(parent->i_sb);
if (IS_ERR(inode))
return PTR_ERR(inode);
sf_i = VBOXSF_I(inode);
/* The host may have given us different attr then requested */
sf_i->force_restat = 1;
vboxsf_init_inode(sbi, inode, info);
d_instantiate(dentry, inode);
return 0;
}
static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
umode_t mode, int is_dir)
{
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
struct shfl_createparms params = {};
int err;
params.handle = SHFL_HANDLE_NIL;
params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW |
SHFL_CF_ACT_FAIL_IF_EXISTS |
SHFL_CF_ACCESS_READWRITE |
(is_dir ? SHFL_CF_DIRECTORY : 0);
params.info.attr.mode = (mode & 0777) |
(is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE);
params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING;
err = vboxsf_create_at_dentry(dentry, &params);
if (err)
return err;
if (params.result != SHFL_FILE_CREATED)
return -EPERM;
vboxsf_close(sbi->root, params.handle);
err = vboxsf_dir_instantiate(parent, dentry, &params.info);
if (err)
return err;
/* parent directory access/change time changed */
sf_parent_i->force_restat = 1;
return 0;
}
static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry,
umode_t mode, bool excl)
{
return vboxsf_dir_create(parent, dentry, mode, 0);
}
static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry,
umode_t mode)
{
return vboxsf_dir_create(parent, dentry, mode, 1);
}
static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
struct inode *inode = d_inode(dentry);
struct shfl_string *path;
u32 flags;
int err;
if (S_ISDIR(inode->i_mode))
flags = SHFL_REMOVE_DIR;
else
flags = SHFL_REMOVE_FILE;
if (S_ISLNK(inode->i_mode))
flags |= SHFL_REMOVE_SYMLINK;
path = vboxsf_path_from_dentry(sbi, dentry);
if (IS_ERR(path))
return PTR_ERR(path);
err = vboxsf_remove(sbi->root, path, flags);
__putname(path);
if (err)
return err;
/* parent directory access/change time changed */
sf_parent_i->force_restat = 1;
return 0;
}
static int vboxsf_dir_rename(struct inode *old_parent,
struct dentry *old_dentry,
struct inode *new_parent,
struct dentry *new_dentry,
unsigned int flags)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(old_parent->i_sb);
struct vboxsf_inode *sf_old_parent_i = VBOXSF_I(old_parent);
struct vboxsf_inode *sf_new_parent_i = VBOXSF_I(new_parent);
u32 shfl_flags = SHFL_RENAME_FILE | SHFL_RENAME_REPLACE_IF_EXISTS;
struct shfl_string *old_path, *new_path;
int err;
if (flags)
return -EINVAL;
old_path = vboxsf_path_from_dentry(sbi, old_dentry);
if (IS_ERR(old_path))
return PTR_ERR(old_path);
new_path = vboxsf_path_from_dentry(sbi, new_dentry);
if (IS_ERR(new_path)) {
err = PTR_ERR(new_path);
goto err_put_old_path;
}
if (d_inode(old_dentry)->i_mode & S_IFDIR)
shfl_flags = 0;
err = vboxsf_rename(sbi->root, old_path, new_path, shfl_flags);
if (err == 0) {
/* parent directories access/change time changed */
sf_new_parent_i->force_restat = 1;
sf_old_parent_i->force_restat = 1;
}
__putname(new_path);
err_put_old_path:
__putname(old_path);
return err;
}
static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry,
const char *symname)
{
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
int symname_size = strlen(symname) + 1;
struct shfl_string *path, *ssymname;
struct shfl_fsobjinfo info;
int err;
path = vboxsf_path_from_dentry(sbi, dentry);
if (IS_ERR(path))
return PTR_ERR(path);
ssymname = kmalloc(SHFLSTRING_HEADER_SIZE + symname_size, GFP_KERNEL);
if (!ssymname) {
__putname(path);
return -ENOMEM;
}
ssymname->length = symname_size - 1;
ssymname->size = symname_size;
memcpy(ssymname->string.utf8, symname, symname_size);
err = vboxsf_symlink(sbi->root, path, ssymname, &info);
kfree(ssymname);
__putname(path);
if (err) {
/* -EROFS means symlinks are note support -> -EPERM */
return (err == -EROFS) ? -EPERM : err;
}
err = vboxsf_dir_instantiate(parent, dentry, &info);
if (err)
return err;
/* parent directory access/change time changed */
sf_parent_i->force_restat = 1;
return 0;
}
const struct inode_operations vboxsf_dir_iops = {
.lookup = vboxsf_dir_lookup,
.create = vboxsf_dir_mkfile,
.mkdir = vboxsf_dir_mkdir,
.rmdir = vboxsf_dir_unlink,
.unlink = vboxsf_dir_unlink,
.rename = vboxsf_dir_rename,
.symlink = vboxsf_dir_symlink,
.getattr = vboxsf_getattr,
.setattr = vboxsf_setattr,
};

370
drivers/staging/vboxsf/file.c
View File

@ -1,370 +0,0 @@
// SPDX-License-Identifier: MIT
/*
* VirtualBox Guest Shared Folders support: Regular file inode and file ops.
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/sizes.h>
#include "vfsmod.h"
struct vboxsf_handle {
u64 handle;
u32 root;
u32 access_flags;
struct kref refcount;
struct list_head head;
};
static int vboxsf_file_open(struct inode *inode, struct file *file)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
struct shfl_createparms params = {};
struct vboxsf_handle *sf_handle;
u32 access_flags = 0;
int err;
sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL);
if (!sf_handle)
return -ENOMEM;
/*
* We check the value of params.handle afterwards to find out if
* the call succeeded or failed, as the API does not seem to cleanly
* distinguish error and informational messages.
*
* Furthermore, we must set params.handle to SHFL_HANDLE_NIL to
* make the shared folders host service use our mode parameter.
*/
params.handle = SHFL_HANDLE_NIL;
if (file->f_flags & O_CREAT) {
params.create_flags |= SHFL_CF_ACT_CREATE_IF_NEW;
/*
* We ignore O_EXCL, as the Linux kernel seems to call create
* beforehand itself, so O_EXCL should always fail.
*/
if (file->f_flags & O_TRUNC)
params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
else
params.create_flags |= SHFL_CF_ACT_OPEN_IF_EXISTS;
} else {
params.create_flags |= SHFL_CF_ACT_FAIL_IF_NEW;
if (file->f_flags & O_TRUNC)
params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
}
switch (file->f_flags & O_ACCMODE) {
case O_RDONLY:
access_flags |= SHFL_CF_ACCESS_READ;
break;
case O_WRONLY:
access_flags |= SHFL_CF_ACCESS_WRITE;
break;
case O_RDWR:
access_flags |= SHFL_CF_ACCESS_READWRITE;
break;
default:
WARN_ON(1);
}
if (file->f_flags & O_APPEND)
access_flags |= SHFL_CF_ACCESS_APPEND;
params.create_flags |= access_flags;
params.info.attr.mode = inode->i_mode;
err = vboxsf_create_at_dentry(file_dentry(file), &params);
if (err == 0 && params.handle == SHFL_HANDLE_NIL)
err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT;
if (err) {
kfree(sf_handle);
return err;
}
/* the host may have given us different attr then requested */
sf_i->force_restat = 1;
/* init our handle struct and add it to the inode's handles list */
sf_handle->handle = params.handle;
sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
sf_handle->access_flags = access_flags;
kref_init(&sf_handle->refcount);
mutex_lock(&sf_i->handle_list_mutex);
list_add(&sf_handle->head, &sf_i->handle_list);
mutex_unlock(&sf_i->handle_list_mutex);
file->private_data = sf_handle;
return 0;
}
static void vboxsf_handle_release(struct kref *refcount)
{
struct vboxsf_handle *sf_handle =
container_of(refcount, struct vboxsf_handle, refcount);
vboxsf_close(sf_handle->root, sf_handle->handle);
kfree(sf_handle);
}
static int vboxsf_file_release(struct inode *inode, struct file *file)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
struct vboxsf_handle *sf_handle = file->private_data;
/*
* When a file is closed on our (the guest) side, we want any subsequent
* accesses done on the host side to see all changes done from our side.
*/
filemap_write_and_wait(inode->i_mapping);
mutex_lock(&sf_i->handle_list_mutex);
list_del(&sf_handle->head);
mutex_unlock(&sf_i->handle_list_mutex);
kref_put(&sf_handle->refcount, vboxsf_handle_release);
return 0;
}
/*
* Write back dirty pages now, because there may not be any suitable
* open files later
*/
static void vboxsf_vma_close(struct vm_area_struct *vma)
{
filemap_write_and_wait(vma->vm_file->f_mapping);
}
static const struct vm_operations_struct vboxsf_file_vm_ops = {
.close = vboxsf_vma_close,
.fault = filemap_fault,
.map_pages = filemap_map_pages,
};
static int vboxsf_file_mmap(struct file *file, struct vm_area_struct *vma)
{
int err;
err = generic_file_mmap(file, vma);
if (!err)
vma->vm_ops = &vboxsf_file_vm_ops;
return err;
}
/*
* Note that since we are accessing files on the host's filesystem, files
* may always be changed underneath us by the host!
*
* The vboxsf API between the guest and the host does not offer any functions
* to deal with this. There is no inode-generation to check for changes, no
* events / callback on changes and no way to lock files.
*
* To avoid returning stale data when a file gets *opened* on our (the guest)
* side, we do a "stat" on the host side, then compare the mtime with the
* last known mtime and invalidate the page-cache if they differ.
* This is done from vboxsf_inode_revalidate().
*
* When reads are done through the read_iter fop, it is possible to do
* further cache revalidation then, there are 3 options to deal with this:
*
* 1) Rely solely on the revalidation done at open time
* 2) Do another "stat" and compare mtime again. Unfortunately the vboxsf
* host API does not allow stat on handles, so we would need to use
* file->f_path.dentry and the stat will then fail if the file was unlinked
* or renamed (and there is no thing like NFS' silly-rename). So we get:
* 2a) "stat" and compare mtime, on stat failure invalidate the cache
* 2b) "stat" and compare mtime, on stat failure do nothing
* 3) Simply always call invalidate_inode_pages2_range on the range of the read
*
* Currently we are keeping things KISS and using option 1. this allows
* directly using generic_file_read_iter without wrapping it.
*
* This means that only data written on the host side before open() on
* the guest side is guaranteed to be seen by the guest. If necessary
* we may provide other read-cache strategies in the future and make this
* configurable through a mount option.
*/
const struct file_operations vboxsf_reg_fops = {
.llseek = generic_file_llseek,
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.mmap = vboxsf_file_mmap,
.open = vboxsf_file_open,
.release = vboxsf_file_release,
.fsync = noop_fsync,
.splice_read = generic_file_splice_read,
};
const struct inode_operations vboxsf_reg_iops = {
.getattr = vboxsf_getattr,
.setattr = vboxsf_setattr
};
static int vboxsf_readpage(struct file *file, struct page *page)
{
struct vboxsf_handle *sf_handle = file->private_data;
loff_t off = page_offset(page);
u32 nread = PAGE_SIZE;
u8 *buf;
int err;
buf = kmap(page);
err = vboxsf_read(sf_handle->root, sf_handle->handle, off, &nread, buf);
if (err == 0) {
memset(&buf[nread], 0, PAGE_SIZE - nread);
flush_dcache_page(page);
SetPageUptodate(page);
} else {
SetPageError(page);
}
kunmap(page);
unlock_page(page);
return err;
}
static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i)
{
struct vboxsf_handle *h, *sf_handle = NULL;
mutex_lock(&sf_i->handle_list_mutex);
list_for_each_entry(h, &sf_i->handle_list, head) {
if (h->access_flags == SHFL_CF_ACCESS_WRITE ||
h->access_flags == SHFL_CF_ACCESS_READWRITE) {
kref_get(&h->refcount);
sf_handle = h;
break;
}
}
mutex_unlock(&sf_i->handle_list_mutex);
return sf_handle;
}
static int vboxsf_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
struct vboxsf_handle *sf_handle;
loff_t off = page_offset(page);
loff_t size = i_size_read(inode);
u32 nwrite = PAGE_SIZE;
u8 *buf;
int err;
if (off + PAGE_SIZE > size)
nwrite = size & ~PAGE_MASK;
sf_handle = vboxsf_get_write_handle(sf_i);
if (!sf_handle)
return -EBADF;
buf = kmap(page);
err = vboxsf_write(sf_handle->root, sf_handle->handle,
off, &nwrite, buf);
kunmap(page);
kref_put(&sf_handle->refcount, vboxsf_handle_release);
if (err == 0) {
ClearPageError(page);
/* mtime changed */
sf_i->force_restat = 1;
} else {
ClearPageUptodate(page);
}
unlock_page(page);
return err;
}
static int vboxsf_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned int len, unsigned int copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
struct vboxsf_handle *sf_handle = file->private_data;
unsigned int from = pos & ~PAGE_MASK;
u32 nwritten = len;
u8 *buf;
int err;
buf = kmap(page);
err = vboxsf_write(sf_handle->root, sf_handle->handle,
pos, &nwritten, buf + from);
kunmap(page);
if (err) {
nwritten = 0;
goto out;
}
/* mtime changed */
VBOXSF_I(inode)->force_restat = 1;
if (!PageUptodate(page) && nwritten == PAGE_SIZE)
SetPageUptodate(page);
pos += nwritten;
if (pos > inode->i_size)
i_size_write(inode, pos);
out:
unlock_page(page);
put_page(page);
return nwritten;
}
const struct address_space_operations vboxsf_reg_aops = {
.readpage = vboxsf_readpage,
.writepage = vboxsf_writepage,
.set_page_dirty = __set_page_dirty_nobuffers,
.write_begin = simple_write_begin,
.write_end = vboxsf_write_end,
};
static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode,
struct delayed_call *done)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
struct shfl_string *path;
char *link;
int err;
if (!dentry)
return ERR_PTR(-ECHILD);
path = vboxsf_path_from_dentry(sbi, dentry);
if (IS_ERR(path))
return (char *)path;
link = kzalloc(PATH_MAX, GFP_KERNEL);
if (!link) {
__putname(path);
return ERR_PTR(-ENOMEM);
}
err = vboxsf_readlink(sbi->root, path, PATH_MAX, link);
__putname(path);
if (err) {
kfree(link);
return ERR_PTR(err);
}
set_delayed_call(done, kfree_link, link);
return link;
}
const struct inode_operations vboxsf_lnk_iops = {
.get_link = vboxsf_get_link
};

901
drivers/staging/vboxsf/shfl_hostintf.h
View File

@ -1,901 +0,0 @@
/* SPDX-License-Identifier: MIT */
/*
* VirtualBox Shared Folders: host interface definition.
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#ifndef SHFL_HOSTINTF_H
#define SHFL_HOSTINTF_H
#include <linux/vbox_vmmdev_types.h>
/* The max in/out buffer size for a FN_READ or FN_WRITE call */
#define SHFL_MAX_RW_COUNT (16 * SZ_1M)
/*
* Structures shared between guest and the service
* can be relocated and use offsets to point to variable
* length parts.
*
* Shared folders protocol works with handles.
* Before doing any action on a file system object,
* one have to obtain the object handle via a SHFL_FN_CREATE
* request. A handle must be closed with SHFL_FN_CLOSE.
*/
enum {
SHFL_FN_QUERY_MAPPINGS = 1, /* Query mappings changes. */
SHFL_FN_QUERY_MAP_NAME = 2, /* Query map name. */
SHFL_FN_CREATE = 3, /* Open/create object. */
SHFL_FN_CLOSE = 4, /* Close object handle. */
SHFL_FN_READ = 5, /* Read object content. */
SHFL_FN_WRITE = 6, /* Write new object content. */
SHFL_FN_LOCK = 7, /* Lock/unlock a range in the object. */
SHFL_FN_LIST = 8, /* List object content. */
SHFL_FN_INFORMATION = 9, /* Query/set object information. */
/* Note function number 10 is not used! */
SHFL_FN_REMOVE = 11, /* Remove object */
SHFL_FN_MAP_FOLDER_OLD = 12, /* Map folder (legacy) */
SHFL_FN_UNMAP_FOLDER = 13, /* Unmap folder */
SHFL_FN_RENAME = 14, /* Rename object */
SHFL_FN_FLUSH = 15, /* Flush file */
SHFL_FN_SET_UTF8 = 16, /* Select UTF8 filename encoding */
SHFL_FN_MAP_FOLDER = 17, /* Map folder */
SHFL_FN_READLINK = 18, /* Read symlink dest (as of VBox 4.0) */
SHFL_FN_SYMLINK = 19, /* Create symlink (as of VBox 4.0) */
SHFL_FN_SET_SYMLINKS = 20, /* Ask host to show symlinks (4.0+) */
};
/* Root handles for a mapping are of type u32, Root handles are unique. */
#define SHFL_ROOT_NIL UINT_MAX
/* Shared folders handle for an opened object are of type u64. */
#define SHFL_HANDLE_NIL ULLONG_MAX
/* Hardcoded maximum length (in chars) of a shared folder name. */
#define SHFL_MAX_LEN (256)
/* Hardcoded maximum number of shared folder mapping available to the guest. */
#define SHFL_MAX_MAPPINGS (64)
/** Shared folder string buffer structure. */
struct shfl_string {
/** Allocated size of the string member in bytes. */
u16 size;
/** Length of string without trailing nul in bytes. */
u16 length;
/** UTF-8 or UTF-16 string. Nul terminated. */
union {
u8 utf8[2];
u16 utf16[1];
u16 ucs2[1]; /* misnomer, use utf16. */
} string;
};
VMMDEV_ASSERT_SIZE(shfl_string, 6);
/* The size of shfl_string w/o the string part. */
#define SHFLSTRING_HEADER_SIZE 4
/* Calculate size of the string. */
static inline u32 shfl_string_buf_size(const struct shfl_string *string)
{
return string ? SHFLSTRING_HEADER_SIZE + string->size : 0;
}
/* Set user id on execution (S_ISUID). */
#define SHFL_UNIX_ISUID 0004000U
/* Set group id on execution (S_ISGID). */
#define SHFL_UNIX_ISGID 0002000U
/* Sticky bit (S_ISVTX / S_ISTXT). */
#define SHFL_UNIX_ISTXT 0001000U
/* Owner readable (S_IRUSR). */
#define SHFL_UNIX_IRUSR 0000400U
/* Owner writable (S_IWUSR). */
#define SHFL_UNIX_IWUSR 0000200U
/* Owner executable (S_IXUSR). */
#define SHFL_UNIX_IXUSR 0000100U
/* Group readable (S_IRGRP). */
#define SHFL_UNIX_IRGRP 0000040U
/* Group writable (S_IWGRP). */
#define SHFL_UNIX_IWGRP 0000020U
/* Group executable (S_IXGRP). */
#define SHFL_UNIX_IXGRP 0000010U
/* Other readable (S_IROTH). */
#define SHFL_UNIX_IROTH 0000004U
/* Other writable (S_IWOTH). */
#define SHFL_UNIX_IWOTH 0000002U
/* Other executable (S_IXOTH). */
#define SHFL_UNIX_IXOTH 0000001U
/* Named pipe (fifo) (S_IFIFO). */
#define SHFL_TYPE_FIFO 0010000U
/* Character device (S_IFCHR). */
#define SHFL_TYPE_DEV_CHAR 0020000U
/* Directory (S_IFDIR). */
#define SHFL_TYPE_DIRECTORY 0040000U
/* Block device (S_IFBLK). */
#define SHFL_TYPE_DEV_BLOCK 0060000U
/* Regular file (S_IFREG). */
#define SHFL_TYPE_FILE 0100000U
/* Symbolic link (S_IFLNK). */
#define SHFL_TYPE_SYMLINK 0120000U
/* Socket (S_IFSOCK). */
#define SHFL_TYPE_SOCKET 0140000U
/* Whiteout (S_IFWHT). */
#define SHFL_TYPE_WHITEOUT 0160000U
/* Type mask (S_IFMT). */
#define SHFL_TYPE_MASK 0170000U
/* Checks the mode flags indicate a directory (S_ISDIR). */
#define SHFL_IS_DIRECTORY(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_DIRECTORY)
/* Checks the mode flags indicate a symbolic link (S_ISLNK). */
#define SHFL_IS_SYMLINK(m) (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_SYMLINK)
/** The available additional information in a shfl_fsobjattr object. */
enum shfl_fsobjattr_add {
/** No additional information is available / requested. */
SHFLFSOBJATTRADD_NOTHING = 1,
/**
* The additional unix attributes (shfl_fsobjattr::u::unix_attr) are
* available / requested.
*/
SHFLFSOBJATTRADD_UNIX,
/**
* The additional extended attribute size (shfl_fsobjattr::u::size) is
* available / requested.
*/
SHFLFSOBJATTRADD_EASIZE,
/**
* The last valid item (inclusive).
* The valid range is SHFLFSOBJATTRADD_NOTHING thru
* SHFLFSOBJATTRADD_LAST.
*/
SHFLFSOBJATTRADD_LAST = SHFLFSOBJATTRADD_EASIZE,
/** The usual 32-bit hack. */
SHFLFSOBJATTRADD_32BIT_SIZE_HACK = 0x7fffffff
};
/**
* Additional unix Attributes, these are available when
* shfl_fsobjattr.additional == SHFLFSOBJATTRADD_UNIX.
*/
struct shfl_fsobjattr_unix {
/**
* The user owning the filesystem object (st_uid).
* This field is ~0U if not supported.
*/
u32 uid;
/**
* The group the filesystem object is assigned (st_gid).
* This field is ~0U if not supported.
*/
u32 gid;
/**
* Number of hard links to this filesystem object (st_nlink).
* This field is 1 if the filesystem doesn't support hardlinking or
* the information isn't available.
*/
u32 hardlinks;
/**
* The device number of the device which this filesystem object resides
* on (st_dev). This field is 0 if this information is not available.
*/
u32 inode_id_device;
/**
* The unique identifier (within the filesystem) of this filesystem
* object (st_ino). Together with inode_id_device, this field can be
* used as a OS wide unique id, when both their values are not 0.
* This field is 0 if the information is not available.
*/
u64 inode_id;
/**
* User flags (st_flags).
* This field is 0 if this information is not available.
*/
u32 flags;
/**
* The current generation number (st_gen).
* This field is 0 if this information is not available.
*/
u32 generation_id;
/**
* The device number of a char. or block device type object (st_rdev).
* This field is 0 if the file isn't a char. or block device or when
* the OS doesn't use the major+minor device idenfication scheme.
*/
u32 device;
} __packed;
/** Extended attribute size. */
struct shfl_fsobjattr_easize {
/** Size of EAs. */
s64 cb;
} __packed;
/** Shared folder filesystem object attributes. */
struct shfl_fsobjattr {
/** Mode flags (st_mode). SHFL_UNIX_*, SHFL_TYPE_*, and SHFL_DOS_*. */
u32 mode;
/** The additional attributes available. */
enum shfl_fsobjattr_add additional;
/**
* Additional attributes.
*
* Unless explicitly specified to an API, the API can provide additional
* data as it is provided by the underlying OS.
*/
union {
struct shfl_fsobjattr_unix unix_attr;
struct shfl_fsobjattr_easize size;
} __packed u;
} __packed;
VMMDEV_ASSERT_SIZE(shfl_fsobjattr, 44);
struct shfl_timespec {
s64 ns_relative_to_unix_epoch;
};
/** Filesystem object information structure. */
struct shfl_fsobjinfo {
/**
* Logical size (st_size).
* For normal files this is the size of the file.
* For symbolic links, this is the length of the path name contained
* in the symbolic link.
* For other objects this fields needs to be specified.
*/
s64 size;
/** Disk allocation size (st_blocks * DEV_BSIZE). */
s64 allocated;
/** Time of last access (st_atime). */
struct shfl_timespec access_time;
/** Time of last data modification (st_mtime). */
struct shfl_timespec modification_time;
/**
* Time of last status change (st_ctime).
* If not available this is set to modification_time.
*/
struct shfl_timespec change_time;
/**
* Time of file birth (st_birthtime).
* If not available this is set to change_time.
*/
struct shfl_timespec birth_time;
/** Attributes. */
struct shfl_fsobjattr attr;
} __packed;
VMMDEV_ASSERT_SIZE(shfl_fsobjinfo, 92);
/**
* result of an open/create request.
* Along with handle value the result code
* identifies what has happened while
* trying to open the object.
*/
enum shfl_create_result {
SHFL_NO_RESULT,
/** Specified path does not exist. */
SHFL_PATH_NOT_FOUND,
/** Path to file exists, but the last component does not. */
SHFL_FILE_NOT_FOUND,
/** File already exists and either has been opened or not. */
SHFL_FILE_EXISTS,
/** New file was created. */
SHFL_FILE_CREATED,
/** Existing file was replaced or overwritten. */
SHFL_FILE_REPLACED
};
/* No flags. Initialization value. */
#define SHFL_CF_NONE (0x00000000)
/*
* Only lookup the object, do not return a handle. When this is set all other
* flags are ignored.
*/
#define SHFL_CF_LOOKUP (0x00000001)
/*
* Open parent directory of specified object.
* Useful for the corresponding Windows FSD flag
* and for opening paths like \\dir\\*.* to search the 'dir'.
*/
#define SHFL_CF_OPEN_TARGET_DIRECTORY (0x00000002)
/* Create/open a directory. */
#define SHFL_CF_DIRECTORY (0x00000004)
/*
* Open/create action to do if object exists
* and if the object does not exists.
* REPLACE file means atomically DELETE and CREATE.
* OVERWRITE file means truncating the file to 0 and
* setting new size.
* When opening an existing directory REPLACE and OVERWRITE
* actions are considered invalid, and cause returning
* FILE_EXISTS with NIL handle.
*/
#define SHFL_CF_ACT_MASK_IF_EXISTS (0x000000f0)
#define SHFL_CF_ACT_MASK_IF_NEW (0x00000f00)
/* What to do if object exists. */
#define SHFL_CF_ACT_OPEN_IF_EXISTS (0x00000000)
#define SHFL_CF_ACT_FAIL_IF_EXISTS (0x00000010)
#define SHFL_CF_ACT_REPLACE_IF_EXISTS (0x00000020)
#define SHFL_CF_ACT_OVERWRITE_IF_EXISTS (0x00000030)
/* What to do if object does not exist. */
#define SHFL_CF_ACT_CREATE_IF_NEW (0x00000000)
#define SHFL_CF_ACT_FAIL_IF_NEW (0x00000100)
/* Read/write requested access for the object. */
#define SHFL_CF_ACCESS_MASK_RW (0x00003000)
/* No access requested. */
#define SHFL_CF_ACCESS_NONE (0x00000000)
/* Read access requested. */
#define SHFL_CF_ACCESS_READ (0x00001000)
/* Write access requested. */
#define SHFL_CF_ACCESS_WRITE (0x00002000)
/* Read/Write access requested. */
#define SHFL_CF_ACCESS_READWRITE (0x00003000)
/* Requested share access for the object. */
#define SHFL_CF_ACCESS_MASK_DENY (0x0000c000)
/* Allow any access. */
#define SHFL_CF_ACCESS_DENYNONE (0x00000000)
/* Do not allow read. */
#define SHFL_CF_ACCESS_DENYREAD (0x00004000)
/* Do not allow write. */
#define SHFL_CF_ACCESS_DENYWRITE (0x00008000)
/* Do not allow access. */
#define SHFL_CF_ACCESS_DENYALL (0x0000c000)
/* Requested access to attributes of the object. */
#define SHFL_CF_ACCESS_MASK_ATTR (0x00030000)
/* No access requested. */
#define SHFL_CF_ACCESS_ATTR_NONE (0x00000000)
/* Read access requested. */
#define SHFL_CF_ACCESS_ATTR_READ (0x00010000)
/* Write access requested. */
#define SHFL_CF_ACCESS_ATTR_WRITE (0x00020000)
/* Read/Write access requested. */
#define SHFL_CF_ACCESS_ATTR_READWRITE (0x00030000)
/*
* The file is opened in append mode.
* Ignored if SHFL_CF_ACCESS_WRITE is not set.
*/
#define SHFL_CF_ACCESS_APPEND (0x00040000)
/** Create parameters buffer struct for SHFL_FN_CREATE call */
struct shfl_createparms {
/** Returned handle of opened object. */
u64 handle;
/** Returned result of the operation */
enum shfl_create_result result;
/** SHFL_CF_* */
u32 create_flags;
/**
* Attributes of object to create and
* returned actual attributes of opened/created object.
*/
struct shfl_fsobjinfo info;
} __packed;
/** Shared Folder directory information */
struct shfl_dirinfo {
/** Full information about the object. */
struct shfl_fsobjinfo info;
/**
* The length of the short field (number of UTF16 chars).
* It is 16-bit for reasons of alignment.
*/
u16 short_name_len;
/**
* The short name for 8.3 compatibility.
* Empty string if not available.
*/
u16 short_name[14];
struct shfl_string name;
};
/** Shared folder filesystem properties. */
struct shfl_fsproperties {
/**
* The maximum size of a filesystem object name.
* This does not include the '\\0'.
*/
u32 max_component_len;
/**
* True if the filesystem is remote.
* False if the filesystem is local.
*/
bool remote;
/**
* True if the filesystem is case sensitive.
* False if the filesystem is case insensitive.
*/
bool case_sensitive;
/**
* True if the filesystem is mounted read only.
* False if the filesystem is mounted read write.
*/
bool read_only;
/**
* True if the filesystem can encode unicode object names.
* False if it can't.
*/
bool supports_unicode;
/**
* True if the filesystem is compresses.
* False if it isn't or we don't know.
*/
bool compressed;
/**
* True if the filesystem compresses of individual files.
* False if it doesn't or we don't know.
*/
bool file_compression;
};
VMMDEV_ASSERT_SIZE(shfl_fsproperties, 12);
struct shfl_volinfo {
s64 total_allocation_bytes;
s64 available_allocation_bytes;
u32 bytes_per_allocation_unit;
u32 bytes_per_sector;
u32 serial;
struct shfl_fsproperties properties;
};
/** SHFL_FN_MAP_FOLDER Parameters structure. */
struct shfl_map_folder {
/**
* pointer, in:
* Points to struct shfl_string buffer.
*/
struct vmmdev_hgcm_function_parameter path;
/**
* pointer, out: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in: UTF16
* Path delimiter
*/
struct vmmdev_hgcm_function_parameter delimiter;
/**
* pointer, in: SHFLROOT (u32)
* Case senstive flag
*/
struct vmmdev_hgcm_function_parameter case_sensitive;
};
/* Number of parameters */
#define SHFL_CPARMS_MAP_FOLDER (4)
/** SHFL_FN_UNMAP_FOLDER Parameters structure. */
struct shfl_unmap_folder {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
};
/* Number of parameters */
#define SHFL_CPARMS_UNMAP_FOLDER (1)
/** SHFL_FN_CREATE Parameters structure. */
struct shfl_create {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in:
* Points to struct shfl_string buffer.
*/
struct vmmdev_hgcm_function_parameter path;
/**
* pointer, in/out:
* Points to struct shfl_createparms buffer.
*/
struct vmmdev_hgcm_function_parameter parms;
};
/* Number of parameters */
#define SHFL_CPARMS_CREATE (3)
/** SHFL_FN_CLOSE Parameters structure. */
struct shfl_close {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* value64, in:
* SHFLHANDLE (u64) of object to close.
*/
struct vmmdev_hgcm_function_parameter handle;
};
/* Number of parameters */
#define SHFL_CPARMS_CLOSE (2)
/** SHFL_FN_READ Parameters structure. */
struct shfl_read {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* value64, in:
* SHFLHANDLE (u64) of object to read from.
*/
struct vmmdev_hgcm_function_parameter handle;
/**
* value64, in:
* Offset to read from.
*/
struct vmmdev_hgcm_function_parameter offset;
/**
* value64, in/out:
* Bytes to read/How many were read.
*/
struct vmmdev_hgcm_function_parameter cb;
/**
* pointer, out:
* Buffer to place data to.
*/
struct vmmdev_hgcm_function_parameter buffer;
};
/* Number of parameters */
#define SHFL_CPARMS_READ (5)
/** SHFL_FN_WRITE Parameters structure. */
struct shfl_write {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* value64, in:
* SHFLHANDLE (u64) of object to write to.
*/
struct vmmdev_hgcm_function_parameter handle;
/**
* value64, in:
* Offset to write to.
*/
struct vmmdev_hgcm_function_parameter offset;
/**
* value64, in/out:
* Bytes to write/How many were written.
*/
struct vmmdev_hgcm_function_parameter cb;
/**
* pointer, in:
* Data to write.
*/
struct vmmdev_hgcm_function_parameter buffer;
};
/* Number of parameters */
#define SHFL_CPARMS_WRITE (5)
/*
* SHFL_FN_LIST
* Listing information includes variable length RTDIRENTRY[EX] structures.
*/
#define SHFL_LIST_NONE 0
#define SHFL_LIST_RETURN_ONE 1
/** SHFL_FN_LIST Parameters structure. */
struct shfl_list {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* value64, in:
* SHFLHANDLE (u64) of object to be listed.
*/
struct vmmdev_hgcm_function_parameter handle;
/**
* value32, in:
* List flags SHFL_LIST_*.
*/
struct vmmdev_hgcm_function_parameter flags;
/**
* value32, in/out:
* Bytes to be used for listing information/How many bytes were used.
*/
struct vmmdev_hgcm_function_parameter cb;
/**
* pointer, in/optional
* Points to struct shfl_string buffer that specifies a search path.
*/
struct vmmdev_hgcm_function_parameter path;
/**
* pointer, out:
* Buffer to place listing information to. (struct shfl_dirinfo)
*/
struct vmmdev_hgcm_function_parameter buffer;
/**
* value32, in/out:
* Indicates a key where the listing must be resumed.
* in: 0 means start from begin of object.
* out: 0 means listing completed.
*/
struct vmmdev_hgcm_function_parameter resume_point;
/**
* pointer, out:
* Number of files returned
*/
struct vmmdev_hgcm_function_parameter file_count;
};
/* Number of parameters */
#define SHFL_CPARMS_LIST (8)
/** SHFL_FN_READLINK Parameters structure. */
struct shfl_readLink {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in:
* Points to struct shfl_string buffer.
*/
struct vmmdev_hgcm_function_parameter path;
/**
* pointer, out:
* Buffer to place data to.
*/
struct vmmdev_hgcm_function_parameter buffer;
};
/* Number of parameters */
#define SHFL_CPARMS_READLINK (3)
/* SHFL_FN_INFORMATION */
/* Mask of Set/Get bit. */
#define SHFL_INFO_MODE_MASK (0x1)
/* Get information */
#define SHFL_INFO_GET (0x0)
/* Set information */
#define SHFL_INFO_SET (0x1)
/* Get name of the object. */
#define SHFL_INFO_NAME (0x2)
/* Set size of object (extend/trucate); only applies to file objects */
#define SHFL_INFO_SIZE (0x4)
/* Get/Set file object info. */
#define SHFL_INFO_FILE (0x8)
/* Get volume information. */
#define SHFL_INFO_VOLUME (0x10)
/** SHFL_FN_INFORMATION Parameters structure. */
struct shfl_information {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* value64, in:
* SHFLHANDLE (u64) of object to be listed.
*/
struct vmmdev_hgcm_function_parameter handle;
/**
* value32, in:
* SHFL_INFO_*
*/
struct vmmdev_hgcm_function_parameter flags;
/**
* value32, in/out:
* Bytes to be used for information/How many bytes were used.
*/
struct vmmdev_hgcm_function_parameter cb;
/**
* pointer, in/out:
* Information to be set/get (shfl_fsobjinfo or shfl_string). Do not
* forget to set the shfl_fsobjinfo::attr::additional for a get
* operation as well.
*/
struct vmmdev_hgcm_function_parameter info;
};
/* Number of parameters */
#define SHFL_CPARMS_INFORMATION (5)
/* SHFL_FN_REMOVE */
#define SHFL_REMOVE_FILE (0x1)
#define SHFL_REMOVE_DIR (0x2)
#define SHFL_REMOVE_SYMLINK (0x4)
/** SHFL_FN_REMOVE Parameters structure. */
struct shfl_remove {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in:
* Points to struct shfl_string buffer.
*/
struct vmmdev_hgcm_function_parameter path;
/**
* value32, in:
* remove flags (file/directory)
*/
struct vmmdev_hgcm_function_parameter flags;
};
#define SHFL_CPARMS_REMOVE (3)
/* SHFL_FN_RENAME */
#define SHFL_RENAME_FILE (0x1)
#define SHFL_RENAME_DIR (0x2)
#define SHFL_RENAME_REPLACE_IF_EXISTS (0x4)
/** SHFL_FN_RENAME Parameters structure. */
struct shfl_rename {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in:
* Points to struct shfl_string src.
*/
struct vmmdev_hgcm_function_parameter src;
/**
* pointer, in:
* Points to struct shfl_string dest.
*/
struct vmmdev_hgcm_function_parameter dest;
/**
* value32, in:
* rename flags (file/directory)
*/
struct vmmdev_hgcm_function_parameter flags;
};
#define SHFL_CPARMS_RENAME (4)
/** SHFL_FN_SYMLINK Parameters structure. */
struct shfl_symlink {
/**
* pointer, in: SHFLROOT (u32)
* Root handle of the mapping which name is queried.
*/
struct vmmdev_hgcm_function_parameter root;
/**
* pointer, in:
* Points to struct shfl_string of path for the new symlink.
*/
struct vmmdev_hgcm_function_parameter new_path;
/**
* pointer, in:
* Points to struct shfl_string of destination for symlink.
*/
struct vmmdev_hgcm_function_parameter old_path;
/**
* pointer, out:
* Information about created symlink.
*/
struct vmmdev_hgcm_function_parameter info;
};
#define SHFL_CPARMS_SYMLINK (4)
#endif

501
drivers/staging/vboxsf/super.c
View File

@ -1,501 +0,0 @@
// SPDX-License-Identifier: MIT
/*
* VirtualBox Guest Shared Folders support: Virtual File System.
*
* Module initialization/finalization
* File system registration/deregistration
* Superblock reading
* Few utility functions
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#include <linux/idr.h>
#include <linux/fs_parser.h>
#include <linux/magic.h>
#include <linux/module.h>
#include <linux/nls.h>
#include <linux/statfs.h>
#include <linux/vbox_utils.h>
#include "vfsmod.h"
#define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */
#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000')
#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377')
#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376')
#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375')
static int follow_symlinks;
module_param(follow_symlinks, int, 0444);
MODULE_PARM_DESC(follow_symlinks,
"Let host resolve symlinks rather than showing them");
static DEFINE_IDA(vboxsf_bdi_ida);
static DEFINE_MUTEX(vboxsf_setup_mutex);
static bool vboxsf_setup_done;
static struct super_operations vboxsf_super_ops; /* forward declaration */
static struct kmem_cache *vboxsf_inode_cachep;
static char * const vboxsf_default_nls = CONFIG_NLS_DEFAULT;
enum { opt_nls, opt_uid, opt_gid, opt_ttl, opt_dmode, opt_fmode,
opt_dmask, opt_fmask };
static const struct fs_parameter_spec vboxsf_param_specs[] = {
fsparam_string ("nls", opt_nls),
fsparam_u32 ("uid", opt_uid),
fsparam_u32 ("gid", opt_gid),
fsparam_u32 ("ttl", opt_ttl),
fsparam_u32oct ("dmode", opt_dmode),
fsparam_u32oct ("fmode", opt_fmode),
fsparam_u32oct ("dmask", opt_dmask),
fsparam_u32oct ("fmask", opt_fmask),
{}
};
static const struct fs_parameter_description vboxsf_fs_parameters = {
.name = "vboxsf",
.specs = vboxsf_param_specs,
};
static int vboxsf_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
struct vboxsf_fs_context *ctx = fc->fs_private;
struct fs_parse_result result;
kuid_t uid;
kgid_t gid;
int opt;
opt = fs_parse(fc, &vboxsf_fs_parameters, param, &result);
if (opt < 0)
return opt;
switch (opt) {
case opt_nls:
if (fc->purpose != FS_CONTEXT_FOR_MOUNT) {
vbg_err("vboxsf: Cannot reconfigure nls option\n");
return -EINVAL;
}
ctx->nls_name = param->string;
param->string = NULL;
break;
case opt_uid:
uid = make_kuid(current_user_ns(), result.uint_32);
if (!uid_valid(uid))
return -EINVAL;
ctx->o.uid = uid;
break;
case opt_gid:
gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(gid))
return -EINVAL;
ctx->o.gid = gid;
break;
case opt_ttl:
ctx->o.ttl = msecs_to_jiffies(result.uint_32);
break;
case opt_dmode:
if (result.uint_32 & ~0777)
return -EINVAL;
ctx->o.dmode = result.uint_32;
ctx->o.dmode_set = true;
break;
case opt_fmode:
if (result.uint_32 & ~0777)
return -EINVAL;
ctx->o.fmode = result.uint_32;
ctx->o.fmode_set = true;
break;
case opt_dmask:
if (result.uint_32 & ~07777)
return -EINVAL;
ctx->o.dmask = result.uint_32;
break;
case opt_fmask:
if (result.uint_32 & ~07777)
return -EINVAL;
ctx->o.fmask = result.uint_32;
break;
default:
return -EINVAL;
}
return 0;
}
static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct vboxsf_fs_context *ctx = fc->fs_private;
struct shfl_string *folder_name, root_path;
struct vboxsf_sbi *sbi;
struct dentry *droot;
struct inode *iroot;
char *nls_name;
size_t size;
int err;
if (!fc->source)
return -EINVAL;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
sbi->o = ctx->o;
idr_init(&sbi->ino_idr);
spin_lock_init(&sbi->ino_idr_lock);
sbi->next_generation = 1;
sbi->bdi_id = -1;
/* Load nls if not utf8 */
nls_name = ctx->nls_name ? ctx->nls_name : vboxsf_default_nls;
if (strcmp(nls_name, "utf8") != 0) {
if (nls_name == vboxsf_default_nls)
sbi->nls = load_nls_default();
else
sbi->nls = load_nls(nls_name);
if (!sbi->nls) {
vbg_err("vboxsf: Count not load '%s' nls\n", nls_name);
err = -EINVAL;
goto fail_free;
}
}
sbi->bdi_id = ida_simple_get(&vboxsf_bdi_ida, 0, 0, GFP_KERNEL);
if (sbi->bdi_id < 0) {
err = sbi->bdi_id;
goto fail_free;
}
err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id);
if (err)
goto fail_free;
/* Turn source into a shfl_string and map the folder */
size = strlen(fc->source) + 1;
folder_name = kmalloc(SHFLSTRING_HEADER_SIZE + size, GFP_KERNEL);
if (!folder_name) {
err = -ENOMEM;
goto fail_free;
}
folder_name->size = size;
folder_name->length = size - 1;
strlcpy(folder_name->string.utf8, fc->source, size);
err = vboxsf_map_folder(folder_name, &sbi->root);
kfree(folder_name);
if (err) {
vbg_err("vboxsf: Host rejected mount of '%s' with error %d\n",
fc->source, err);
goto fail_free;
}
root_path.length = 1;
root_path.size = 2;
root_path.string.utf8[0] = '/';
root_path.string.utf8[1] = 0;
err = vboxsf_stat(sbi, &root_path, &sbi->root_info);
if (err)
goto fail_unmap;
sb->s_magic = VBOXSF_SUPER_MAGIC;
sb->s_blocksize = 1024;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_op = &vboxsf_super_ops;
sb->s_d_op = &vboxsf_dentry_ops;
iroot = iget_locked(sb, 0);
if (!iroot) {
err = -ENOMEM;
goto fail_unmap;
}
vboxsf_init_inode(sbi, iroot, &sbi->root_info);
unlock_new_inode(iroot);
droot = d_make_root(iroot);
if (!droot) {
err = -ENOMEM;
goto fail_unmap;
}
sb->s_root = droot;
sb->s_fs_info = sbi;
return 0;
fail_unmap:
vboxsf_unmap_folder(sbi->root);
fail_free:
if (sbi->bdi_id >= 0)
ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
if (sbi->nls)
unload_nls(sbi->nls);
idr_destroy(&sbi->ino_idr);
kfree(sbi);
return err;
}
static void vboxsf_inode_init_once(void *data)
{
struct vboxsf_inode *sf_i = data;
mutex_init(&sf_i->handle_list_mutex);
inode_init_once(&sf_i->vfs_inode);
}
static struct inode *vboxsf_alloc_inode(struct super_block *sb)
{
struct vboxsf_inode *sf_i;
sf_i = kmem_cache_alloc(vboxsf_inode_cachep, GFP_NOFS);
if (!sf_i)
return NULL;
sf_i->force_restat = 0;
INIT_LIST_HEAD(&sf_i->handle_list);
return &sf_i->vfs_inode;
}
static void vboxsf_free_inode(struct inode *inode)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
unsigned long flags;
spin_lock_irqsave(&sbi->ino_idr_lock, flags);
idr_remove(&sbi->ino_idr, inode->i_ino);
spin_unlock_irqrestore(&sbi->ino_idr_lock, flags);
kmem_cache_free(vboxsf_inode_cachep, VBOXSF_I(inode));
}
static void vboxsf_put_super(struct super_block *sb)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(sb);
vboxsf_unmap_folder(sbi->root);
if (sbi->bdi_id >= 0)
ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
if (sbi->nls)
unload_nls(sbi->nls);
/*
* vboxsf_free_inode uses the idr, make sure all delayed rcu free
* inodes are flushed.
*/
rcu_barrier();
idr_destroy(&sbi->ino_idr);
kfree(sbi);
}
static int vboxsf_statfs(struct dentry *dentry, struct kstatfs *stat)
{
struct super_block *sb = dentry->d_sb;
struct shfl_volinfo shfl_volinfo;
struct vboxsf_sbi *sbi;
u32 buf_len;
int err;
sbi = VBOXSF_SBI(sb);
buf_len = sizeof(shfl_volinfo);
err = vboxsf_fsinfo(sbi->root, 0, SHFL_INFO_GET | SHFL_INFO_VOLUME,
&buf_len, &shfl_volinfo);
if (err)
return err;
stat->f_type = VBOXSF_SUPER_MAGIC;
stat->f_bsize = shfl_volinfo.bytes_per_allocation_unit;
do_div(shfl_volinfo.total_allocation_bytes,
shfl_volinfo.bytes_per_allocation_unit);
stat->f_blocks = shfl_volinfo.total_allocation_bytes;
do_div(shfl_volinfo.available_allocation_bytes,
shfl_volinfo.bytes_per_allocation_unit);
stat->f_bfree = shfl_volinfo.available_allocation_bytes;
stat->f_bavail = shfl_volinfo.available_allocation_bytes;
stat->f_files = 1000;
/*
* Don't return 0 here since the guest may then think that it is not
* possible to create any more files.
*/
stat->f_ffree = 1000000;
stat->f_fsid.val[0] = 0;
stat->f_fsid.val[1] = 0;
stat->f_namelen = 255;
return 0;
}
static struct super_operations vboxsf_super_ops = {
.alloc_inode = vboxsf_alloc_inode,
.free_inode = vboxsf_free_inode,
.put_super = vboxsf_put_super,
.statfs = vboxsf_statfs,
};
static int vboxsf_setup(void)
{
int err;
mutex_lock(&vboxsf_setup_mutex);
if (vboxsf_setup_done)
goto success;
vboxsf_inode_cachep =
kmem_cache_create("vboxsf_inode_cache",
sizeof(struct vboxsf_inode), 0,
(SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
SLAB_ACCOUNT),
vboxsf_inode_init_once);
if (!vboxsf_inode_cachep) {
err = -ENOMEM;
goto fail_nomem;
}
err = vboxsf_connect();
if (err) {
vbg_err("vboxsf: err %d connecting to guest PCI-device\n", err);
vbg_err("vboxsf: make sure you are inside a VirtualBox VM\n");
vbg_err("vboxsf: and check dmesg for vboxguest errors\n");
goto fail_free_cache;
}
err = vboxsf_set_utf8();
if (err) {
vbg_err("vboxsf_setutf8 error %d\n", err);
goto fail_disconnect;
}
if (!follow_symlinks) {
err = vboxsf_set_symlinks();
if (err)
vbg_warn("vboxsf: Unable to show symlinks: %d\n", err);
}
vboxsf_setup_done = true;
success:
mutex_unlock(&vboxsf_setup_mutex);
return 0;
fail_disconnect:
vboxsf_disconnect();
fail_free_cache:
kmem_cache_destroy(vboxsf_inode_cachep);
fail_nomem:
mutex_unlock(&vboxsf_setup_mutex);
return err;
}
static int vboxsf_parse_monolithic(struct fs_context *fc, void *data)
{
char *options = data;
if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 &&
options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 &&
options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 &&
options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) {
vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n");
return -EINVAL;
}
return generic_parse_monolithic(fc, data);
}
static int vboxsf_get_tree(struct fs_context *fc)
{
int err;
err = vboxsf_setup();
if (err)
return err;
return vfs_get_super(fc, vfs_get_independent_super, vboxsf_fill_super);
}
static int vboxsf_reconfigure(struct fs_context *fc)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(fc->root->d_sb);
struct vboxsf_fs_context *ctx = fc->fs_private;
struct inode *iroot;
iroot = ilookup(fc->root->d_sb, 0);
if (!iroot)
return -ENOENT;
/* Apply changed options to the root inode */
sbi->o = ctx->o;
vboxsf_init_inode(sbi, iroot, &sbi->root_info);
return 0;
}
static void vboxsf_free_fc(struct fs_context *fc)
{
struct vboxsf_fs_context *ctx = fc->fs_private;
kfree(ctx->nls_name);
kfree(ctx);
}
static const struct fs_context_operations vboxsf_context_ops = {
.free = vboxsf_free_fc,
.parse_param = vboxsf_parse_param,
.parse_monolithic = vboxsf_parse_monolithic,
.get_tree = vboxsf_get_tree,
.reconfigure = vboxsf_reconfigure,
};
static int vboxsf_init_fs_context(struct fs_context *fc)
{
struct vboxsf_fs_context *ctx;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
current_uid_gid(&ctx->o.uid, &ctx->o.gid);
fc->fs_private = ctx;
fc->ops = &vboxsf_context_ops;
return 0;
}
static struct file_system_type vboxsf_fs_type = {
.owner = THIS_MODULE,
.name = "vboxsf",
.init_fs_context = vboxsf_init_fs_context,
.parameters = &vboxsf_fs_parameters,
.kill_sb = kill_anon_super
};
/* Module initialization/finalization handlers */
static int __init vboxsf_init(void)
{
return register_filesystem(&vboxsf_fs_type);
}
static void __exit vboxsf_fini(void)
{
unregister_filesystem(&vboxsf_fs_type);
mutex_lock(&vboxsf_setup_mutex);
if (vboxsf_setup_done) {
vboxsf_disconnect();
/*
* Make sure all delayed rcu free inodes are flushed
* before we destroy the cache.
*/
rcu_barrier();
kmem_cache_destroy(vboxsf_inode_cachep);
}
mutex_unlock(&vboxsf_setup_mutex);
}
module_init(vboxsf_init);
module_exit(vboxsf_fini);
MODULE_DESCRIPTION("Oracle VM VirtualBox Module for Host File System Access");
MODULE_AUTHOR("Oracle Corporation");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_FS("vboxsf");

551
drivers/staging/vboxsf/utils.c
View File

@ -1,551 +0,0 @@
// SPDX-License-Identifier: MIT
/*
* VirtualBox Guest Shared Folders support: Utility functions.
* Mainly conversion from/to VirtualBox/Linux data structures.
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#include <linux/namei.h>
#include <linux/nls.h>
#include <linux/sizes.h>
#include <linux/vfs.h>
#include "vfsmod.h"
struct inode *vboxsf_new_inode(struct super_block *sb)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(sb);
struct inode *inode;
unsigned long flags;
int cursor, ret;
u32 gen;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
idr_preload(GFP_KERNEL);
spin_lock_irqsave(&sbi->ino_idr_lock, flags);
cursor = idr_get_cursor(&sbi->ino_idr);
ret = idr_alloc_cyclic(&sbi->ino_idr, inode, 1, 0, GFP_ATOMIC);
if (ret >= 0 && ret < cursor)
sbi->next_generation++;
gen = sbi->next_generation;
spin_unlock_irqrestore(&sbi->ino_idr_lock, flags);
idr_preload_end();
if (ret < 0) {
iput(inode);
return ERR_PTR(ret);
}
inode->i_ino = ret;
inode->i_generation = gen;
return inode;
}
/* set [inode] attributes based on [info], uid/gid based on [sbi] */
void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
const struct shfl_fsobjinfo *info)
{
const struct shfl_fsobjattr *attr;
s64 allocated;
int mode;
attr = &info->attr;
#define mode_set(r) ((attr->mode & (SHFL_UNIX_##r)) ? (S_##r) : 0)
mode = mode_set(IRUSR);
mode |= mode_set(IWUSR);
mode |= mode_set(IXUSR);
mode |= mode_set(IRGRP);
mode |= mode_set(IWGRP);
mode |= mode_set(IXGRP);
mode |= mode_set(IROTH);
mode |= mode_set(IWOTH);
mode |= mode_set(IXOTH);
#undef mode_set
/* We use the host-side values for these */
inode->i_flags |= S_NOATIME | S_NOCMTIME;
inode->i_mapping->a_ops = &vboxsf_reg_aops;
if (SHFL_IS_DIRECTORY(attr->mode)) {
inode->i_mode = sbi->o.dmode_set ? sbi->o.dmode : mode;
inode->i_mode &= ~sbi->o.dmask;
inode->i_mode |= S_IFDIR;
inode->i_op = &vboxsf_dir_iops;
inode->i_fop = &vboxsf_dir_fops;
/*
* XXX: this probably should be set to the number of entries
* in the directory plus two (. ..)
*/
set_nlink(inode, 1);
} else if (SHFL_IS_SYMLINK(attr->mode)) {
inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
inode->i_mode &= ~sbi->o.fmask;
inode->i_mode |= S_IFLNK;
inode->i_op = &vboxsf_lnk_iops;
set_nlink(inode, 1);
} else {
inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
inode->i_mode &= ~sbi->o.fmask;
inode->i_mode |= S_IFREG;
inode->i_op = &vboxsf_reg_iops;
inode->i_fop = &vboxsf_reg_fops;
set_nlink(inode, 1);
}
inode->i_uid = sbi->o.uid;
inode->i_gid = sbi->o.gid;
inode->i_size = info->size;
inode->i_blkbits = 12;
/* i_blocks always in units of 512 bytes! */
allocated = info->allocated + 511;
do_div(allocated, 512);
inode->i_blocks = allocated;
inode->i_atime = ns_to_timespec64(
info->access_time.ns_relative_to_unix_epoch);
inode->i_ctime = ns_to_timespec64(
info->change_time.ns_relative_to_unix_epoch);
inode->i_mtime = ns_to_timespec64(
info->modification_time.ns_relative_to_unix_epoch);
}
int vboxsf_create_at_dentry(struct dentry *dentry,
struct shfl_createparms *params)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
struct shfl_string *path;
int err;
path = vboxsf_path_from_dentry(sbi, dentry);
if (IS_ERR(path))
return PTR_ERR(path);
err = vboxsf_create(sbi->root, path, params);
__putname(path);
return err;
}
int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
struct shfl_fsobjinfo *info)
{
struct shfl_createparms params = {};
int err;
params.handle = SHFL_HANDLE_NIL;
params.create_flags = SHFL_CF_LOOKUP | SHFL_CF_ACT_FAIL_IF_NEW;
err = vboxsf_create(sbi->root, path, &params);
if (err)
return err;
if (params.result != SHFL_FILE_EXISTS)
return -ENOENT;
if (info)
*info = params.info;
return 0;
}
int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info)
{
struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
struct shfl_string *path;
int err;
path = vboxsf_path_from_dentry(sbi, dentry);
if (IS_ERR(path))
return PTR_ERR(path);
err = vboxsf_stat(sbi, path, info);
__putname(path);
return err;
}
int vboxsf_inode_revalidate(struct dentry *dentry)
{
struct vboxsf_sbi *sbi;
struct vboxsf_inode *sf_i;
struct shfl_fsobjinfo info;
struct timespec64 prev_mtime;
struct inode *inode;
int err;
if (!dentry || !d_really_is_positive(dentry))
return -EINVAL;
inode = d_inode(dentry);
prev_mtime = inode->i_mtime;
sf_i = VBOXSF_I(inode);
sbi = VBOXSF_SBI(dentry->d_sb);
if (!sf_i->force_restat) {
if (time_before(jiffies, dentry->d_time + sbi->o.ttl))
return 0;
}
err = vboxsf_stat_dentry(dentry, &info);
if (err)
return err;
dentry->d_time = jiffies;
sf_i->force_restat = 0;
vboxsf_init_inode(sbi, inode, &info);
/*
* If the file was changed on the host side we need to invalidate the
* page-cache for it. Note this also gets triggered by our own writes,
* this is unavoidable.
*/
if (timespec64_compare(&inode->i_mtime, &prev_mtime) > 0)
invalidate_inode_pages2(inode->i_mapping);
return 0;
}
int vboxsf_getattr(const struct path *path, struct kstat *kstat,
u32 request_mask, unsigned int flags)
{
int err;
struct dentry *dentry = path->dentry;
struct inode *inode = d_inode(dentry);
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
switch (flags & AT_STATX_SYNC_TYPE) {
case AT_STATX_DONT_SYNC:
err = 0;
break;
case AT_STATX_FORCE_SYNC:
sf_i->force_restat = 1;
/* fall-through */
default:
err = vboxsf_inode_revalidate(dentry);
}
if (err)
return err;
generic_fillattr(d_inode(dentry), kstat);
return 0;
}
int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry));
struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
struct shfl_createparms params = {};
struct shfl_fsobjinfo info = {};
u32 buf_len;
int err;
params.handle = SHFL_HANDLE_NIL;
params.create_flags = SHFL_CF_ACT_OPEN_IF_EXISTS |
SHFL_CF_ACT_FAIL_IF_NEW |
SHFL_CF_ACCESS_ATTR_WRITE;
/* this is at least required for Posix hosts */
if (iattr->ia_valid & ATTR_SIZE)
params.create_flags |= SHFL_CF_ACCESS_WRITE;
err = vboxsf_create_at_dentry(dentry, &params);
if (err || params.result != SHFL_FILE_EXISTS)
return err ? err : -ENOENT;
#define mode_set(r) ((iattr->ia_mode & (S_##r)) ? SHFL_UNIX_##r : 0)
/*
* Setting the file size and setting the other attributes has to
* be handled separately.
*/
if (iattr->ia_valid & (ATTR_MODE | ATTR_ATIME | ATTR_MTIME)) {
if (iattr->ia_valid & ATTR_MODE) {
info.attr.mode = mode_set(IRUSR);
info.attr.mode |= mode_set(IWUSR);
info.attr.mode |= mode_set(IXUSR);
info.attr.mode |= mode_set(IRGRP);
info.attr.mode |= mode_set(IWGRP);
info.attr.mode |= mode_set(IXGRP);
info.attr.mode |= mode_set(IROTH);
info.attr.mode |= mode_set(IWOTH);
info.attr.mode |= mode_set(IXOTH);
if (iattr->ia_mode & S_IFDIR)
info.attr.mode |= SHFL_TYPE_DIRECTORY;
else
info.attr.mode |= SHFL_TYPE_FILE;
}
if (iattr->ia_valid & ATTR_ATIME)
info.access_time.ns_relative_to_unix_epoch =
timespec64_to_ns(&iattr->ia_atime);
if (iattr->ia_valid & ATTR_MTIME)
info.modification_time.ns_relative_to_unix_epoch =
timespec64_to_ns(&iattr->ia_mtime);
/*
* Ignore ctime (inode change time) as it can't be set
* from userland anyway.
*/
buf_len = sizeof(info);
err = vboxsf_fsinfo(sbi->root, params.handle,
SHFL_INFO_SET | SHFL_INFO_FILE, &buf_len,
&info);
if (err) {
vboxsf_close(sbi->root, params.handle);
return err;
}
/* the host may have given us different attr then requested */
sf_i->force_restat = 1;
}
#undef mode_set
if (iattr->ia_valid & ATTR_SIZE) {
memset(&info, 0, sizeof(info));
info.size = iattr->ia_size;
buf_len = sizeof(info);
err = vboxsf_fsinfo(sbi->root, params.handle,
SHFL_INFO_SET | SHFL_INFO_SIZE, &buf_len,
&info);
if (err) {
vboxsf_close(sbi->root, params.handle);
return err;
}
/* the host may have given us different attr then requested */
sf_i->force_restat = 1;
}
vboxsf_close(sbi->root, params.handle);
/* Update the inode with what the host has actually given us. */
if (sf_i->force_restat)
vboxsf_inode_revalidate(dentry);
return 0;
}
/*
* [dentry] contains string encoded in coding system that corresponds
* to [sbi]->nls, we must convert it to UTF8 here.
* Returns a shfl_string allocated through __getname (must be freed using
* __putname), or an ERR_PTR on error.
*/
struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
struct dentry *dentry)
{
struct shfl_string *shfl_path;
int path_len, out_len, nb;
char *buf, *path;
wchar_t uni;
u8 *out;
buf = __getname();
if (!buf)
return ERR_PTR(-ENOMEM);
path = dentry_path_raw(dentry, buf, PATH_MAX);
if (IS_ERR(path)) {
__putname(buf);
return (struct shfl_string *)path;
}
path_len = strlen(path);
if (sbi->nls) {
shfl_path = __getname();
if (!shfl_path) {
__putname(buf);
return ERR_PTR(-ENOMEM);
}
out = shfl_path->string.utf8;
out_len = PATH_MAX - SHFLSTRING_HEADER_SIZE - 1;
while (path_len) {
nb = sbi->nls->char2uni(path, path_len, &uni);
if (nb < 0) {
__putname(shfl_path);
__putname(buf);
return ERR_PTR(-EINVAL);
}
path += nb;
path_len -= nb;
nb = utf32_to_utf8(uni, out, out_len);
if (nb < 0) {
__putname(shfl_path);
__putname(buf);
return ERR_PTR(-ENAMETOOLONG);
}
out += nb;
out_len -= nb;
}
*out = 0;
shfl_path->length = out - shfl_path->string.utf8;
shfl_path->size = shfl_path->length + 1;
__putname(buf);
} else {
if ((SHFLSTRING_HEADER_SIZE + path_len + 1) > PATH_MAX) {
__putname(buf);
return ERR_PTR(-ENAMETOOLONG);
}
/*
* dentry_path stores the name at the end of buf, but the
* shfl_string string we return must be properly aligned.
*/
shfl_path = (struct shfl_string *)buf;
memmove(shfl_path->string.utf8, path, path_len);
shfl_path->string.utf8[path_len] = 0;
shfl_path->length = path_len;
shfl_path->size = path_len + 1;
}
return shfl_path;
}
int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
const unsigned char *utf8_name, size_t utf8_len)
{
const char *in;
char *out;
size_t out_len;
size_t out_bound_len;
size_t in_bound_len;
in = utf8_name;
in_bound_len = utf8_len;
out = name;
out_len = 0;
/* Reserve space for terminating 0 */
out_bound_len = name_bound_len - 1;
while (in_bound_len) {
int nb;
unicode_t uni;
nb = utf8_to_utf32(in, in_bound_len, &uni);
if (nb < 0)
return -EINVAL;
in += nb;
in_bound_len -= nb;
nb = sbi->nls->uni2char(uni, out, out_bound_len);
if (nb < 0)
return nb;
out += nb;
out_bound_len -= nb;
out_len += nb;
}
*out = 0;
return 0;
}
static struct vboxsf_dir_buf *vboxsf_dir_buf_alloc(struct list_head *list)
{
struct vboxsf_dir_buf *b;
b = kmalloc(sizeof(*b), GFP_KERNEL);
if (!b)
return NULL;
b->buf = kmalloc(DIR_BUFFER_SIZE, GFP_KERNEL);
if (!b->buf) {
kfree(b);
return NULL;
}
b->entries = 0;
b->used = 0;
b->free = DIR_BUFFER_SIZE;
list_add(&b->head, list);
return b;
}
static void vboxsf_dir_buf_free(struct vboxsf_dir_buf *b)
{
list_del(&b->head);
kfree(b->buf);
kfree(b);
}
struct vboxsf_dir_info *vboxsf_dir_info_alloc(void)
{
struct vboxsf_dir_info *p;
p = kmalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return NULL;
INIT_LIST_HEAD(&p->info_list);
return p;
}
void vboxsf_dir_info_free(struct vboxsf_dir_info *p)
{
struct list_head *list, *pos, *tmp;
list = &p->info_list;
list_for_each_safe(pos, tmp, list) {
struct vboxsf_dir_buf *b;
b = list_entry(pos, struct vboxsf_dir_buf, head);
vboxsf_dir_buf_free(b);
}
kfree(p);
}
int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d,
u64 handle)
{
struct vboxsf_dir_buf *b;
u32 entries, size;
int err = 0;
void *buf;
/* vboxsf_dirinfo returns 1 on end of dir */
while (err == 0) {
b = vboxsf_dir_buf_alloc(&sf_d->info_list);
if (!b) {
err = -ENOMEM;
break;
}
buf = b->buf;
size = b->free;
err = vboxsf_dirinfo(sbi->root, handle, NULL, 0, 0,
&size, buf, &entries);
if (err < 0)
break;
b->entries += entries;
b->free -= size;
b->used += size;
}
if (b && b->used == 0)
vboxsf_dir_buf_free(b);
/* -EILSEQ means the host could not translate a filename, ignore */
if (err > 0 || err == -EILSEQ)
err = 0;
return err;
}

371
drivers/staging/vboxsf/vboxsf_wrappers.c
View File

@ -1,371 +0,0 @@
// SPDX-License-Identifier: MIT
/*
* Wrapper functions for the shfl host calls.
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/vbox_err.h>
#include <linux/vbox_utils.h>
#include "vfsmod.h"
#define SHFL_REQUEST \
(VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV_OTHER | \
VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
static u32 vboxsf_client_id;
int vboxsf_connect(void)
{
struct vbg_dev *gdev;
struct vmmdev_hgcm_service_location loc;
int err, vbox_status;
loc.type = VMMDEV_HGCM_LOC_LOCALHOST_EXISTING;
strcpy(loc.u.localhost.service_name, "VBoxSharedFolders");
gdev = vbg_get_gdev();
if (IS_ERR(gdev))
return -ENODEV; /* No guest-device */
err = vbg_hgcm_connect(gdev, SHFL_REQUEST, &loc,
&vboxsf_client_id, &vbox_status);
vbg_put_gdev(gdev);
return err ? err : vbg_status_code_to_errno(vbox_status);
}
void vboxsf_disconnect(void)
{
struct vbg_dev *gdev;
int vbox_status;
gdev = vbg_get_gdev();
if (IS_ERR(gdev))
return; /* guest-device is gone, already disconnected */
vbg_hgcm_disconnect(gdev, SHFL_REQUEST, vboxsf_client_id, &vbox_status);
vbg_put_gdev(gdev);
}
static int vboxsf_call(u32 function, void *parms, u32 parm_count, int *status)
{
struct vbg_dev *gdev;
int err, vbox_status;
gdev = vbg_get_gdev();
if (IS_ERR(gdev))
return -ESHUTDOWN; /* guest-dev removed underneath us */
err = vbg_hgcm_call(gdev, SHFL_REQUEST, vboxsf_client_id, function,
U32_MAX, parms, parm_count, &vbox_status);
vbg_put_gdev(gdev);
if (err < 0)
return err;
if (status)
*status = vbox_status;
return vbg_status_code_to_errno(vbox_status);
}
int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root)
{
struct shfl_map_folder parms;
int err, status;
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
parms.path.u.pointer.size = shfl_string_buf_size(folder_name);
parms.path.u.pointer.u.linear_addr = (uintptr_t)folder_name;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = 0;
parms.delimiter.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.delimiter.u.value32 = '/';
parms.case_sensitive.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.case_sensitive.u.value32 = 1;
err = vboxsf_call(SHFL_FN_MAP_FOLDER, &parms, SHFL_CPARMS_MAP_FOLDER,
&status);
if (err == -ENOSYS && status == VERR_NOT_IMPLEMENTED)
vbg_err("%s: Error host is too old\n", __func__);
*root = parms.root.u.value32;
return err;
}
int vboxsf_unmap_folder(u32 root)
{
struct shfl_unmap_folder parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
return vboxsf_call(SHFL_FN_UNMAP_FOLDER, &parms,
SHFL_CPARMS_UNMAP_FOLDER, NULL);
}
/**
* vboxsf_create - Create a new file or folder
* @root: Root of the shared folder in which to create the file
* @parsed_path: The path of the file or folder relative to the shared folder
* @param: create_parms Parameters for file/folder creation.
*
* Create a new file or folder or open an existing one in a shared folder.
* Note this function always returns 0 / success unless an exceptional condition
* occurs - out of memory, invalid arguments, etc. If the file or folder could
* not be opened or created, create_parms->handle will be set to
* SHFL_HANDLE_NIL on return. In this case the value in create_parms->result
* provides information as to why (e.g. SHFL_FILE_EXISTS), create_parms->result
* is also set on success as additional information.
*
* Returns:
* 0 or negative errno value.
*/
int vboxsf_create(u32 root, struct shfl_string *parsed_path,
struct shfl_createparms *create_parms)
{
struct shfl_create parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
parms.parms.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
parms.parms.u.pointer.size = sizeof(struct shfl_createparms);
parms.parms.u.pointer.u.linear_addr = (uintptr_t)create_parms;
return vboxsf_call(SHFL_FN_CREATE, &parms, SHFL_CPARMS_CREATE, NULL);
}
int vboxsf_close(u32 root, u64 handle)
{
struct shfl_close parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.handle.u.value64 = handle;
return vboxsf_call(SHFL_FN_CLOSE, &parms, SHFL_CPARMS_CLOSE, NULL);
}
int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags)
{
struct shfl_remove parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.flags.u.value32 = flags;
return vboxsf_call(SHFL_FN_REMOVE, &parms, SHFL_CPARMS_REMOVE, NULL);
}
int vboxsf_rename(u32 root, struct shfl_string *src_path,
struct shfl_string *dest_path, u32 flags)
{
struct shfl_rename parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.src.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.src.u.pointer.size = shfl_string_buf_size(src_path);
parms.src.u.pointer.u.linear_addr = (uintptr_t)src_path;
parms.dest.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.dest.u.pointer.size = shfl_string_buf_size(dest_path);
parms.dest.u.pointer.u.linear_addr = (uintptr_t)dest_path;
parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.flags.u.value32 = flags;
return vboxsf_call(SHFL_FN_RENAME, &parms, SHFL_CPARMS_RENAME, NULL);
}
int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf)
{
struct shfl_read parms;
int err;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.handle.u.value64 = handle;
parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.offset.u.value64 = offset;
parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.cb.u.value32 = *buf_len;
parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
parms.buffer.u.pointer.size = *buf_len;
parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
err = vboxsf_call(SHFL_FN_READ, &parms, SHFL_CPARMS_READ, NULL);
*buf_len = parms.cb.u.value32;
return err;
}
int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf)
{
struct shfl_write parms;
int err;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.handle.u.value64 = handle;
parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.offset.u.value64 = offset;
parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.cb.u.value32 = *buf_len;
parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.buffer.u.pointer.size = *buf_len;
parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
err = vboxsf_call(SHFL_FN_WRITE, &parms, SHFL_CPARMS_WRITE, NULL);
*buf_len = parms.cb.u.value32;
return err;
}
/* Returns 0 on success, 1 on end-of-dir, negative errno otherwise */
int vboxsf_dirinfo(u32 root, u64 handle,
struct shfl_string *parsed_path, u32 flags, u32 index,
u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count)
{
struct shfl_list parms;
int err, status;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.handle.u.value64 = handle;
parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.flags.u.value32 = flags;
parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.cb.u.value32 = *buf_len;
if (parsed_path) {
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
} else {
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_IN;
parms.path.u.pointer.size = 0;
parms.path.u.pointer.u.linear_addr = 0;
}
parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
parms.buffer.u.pointer.size = *buf_len;
parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
parms.resume_point.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.resume_point.u.value32 = index;
parms.file_count.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.file_count.u.value32 = 0; /* out parameter only */
err = vboxsf_call(SHFL_FN_LIST, &parms, SHFL_CPARMS_LIST, &status);
if (err == -ENODATA && status == VERR_NO_MORE_FILES)
err = 1;
*buf_len = parms.cb.u.value32;
*file_count = parms.file_count.u.value32;
return err;
}
int vboxsf_fsinfo(u32 root, u64 handle, u32 flags,
u32 *buf_len, void *buf)
{
struct shfl_information parms;
int err;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
parms.handle.u.value64 = handle;
parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.flags.u.value32 = flags;
parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.cb.u.value32 = *buf_len;
parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
parms.info.u.pointer.size = *buf_len;
parms.info.u.pointer.u.linear_addr = (uintptr_t)buf;
err = vboxsf_call(SHFL_FN_INFORMATION, &parms, SHFL_CPARMS_INFORMATION,
NULL);
*buf_len = parms.cb.u.value32;
return err;
}
int vboxsf_readlink(u32 root, struct shfl_string *parsed_path,
u32 buf_len, u8 *buf)
{
struct shfl_readLink parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
parms.buffer.u.pointer.size = buf_len;
parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
return vboxsf_call(SHFL_FN_READLINK, &parms, SHFL_CPARMS_READLINK,
NULL);
}
int vboxsf_symlink(u32 root, struct shfl_string *new_path,
struct shfl_string *old_path, struct shfl_fsobjinfo *buf)
{
struct shfl_symlink parms;
parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
parms.root.u.value32 = root;
parms.new_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.new_path.u.pointer.size = shfl_string_buf_size(new_path);
parms.new_path.u.pointer.u.linear_addr = (uintptr_t)new_path;
parms.old_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
parms.old_path.u.pointer.size = shfl_string_buf_size(old_path);
parms.old_path.u.pointer.u.linear_addr = (uintptr_t)old_path;
parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
parms.info.u.pointer.size = sizeof(struct shfl_fsobjinfo);
parms.info.u.pointer.u.linear_addr = (uintptr_t)buf;
return vboxsf_call(SHFL_FN_SYMLINK, &parms, SHFL_CPARMS_SYMLINK, NULL);
}
int vboxsf_set_utf8(void)
{
return vboxsf_call(SHFL_FN_SET_UTF8, NULL, 0, NULL);
}
int vboxsf_set_symlinks(void)
{
return vboxsf_call(SHFL_FN_SET_SYMLINKS, NULL, 0, NULL);
}

137
drivers/staging/vboxsf/vfsmod.h
View File

@ -1,137 +0,0 @@
/* SPDX-License-Identifier: MIT */
/*
* VirtualBox Guest Shared Folders support: module header.
*
* Copyright (C) 2006-2018 Oracle Corporation
*/
#ifndef VFSMOD_H
#define VFSMOD_H
#include <linux/backing-dev.h>
#include <linux/idr.h>
#include "shfl_hostintf.h"
#define DIR_BUFFER_SIZE SZ_16K
/* The cast is to prevent assignment of void * to pointers of arbitrary type */
#define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info)
#define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode)
struct vboxsf_options {
unsigned long ttl;
kuid_t uid;
kgid_t gid;
bool dmode_set;
bool fmode_set;
umode_t dmode;
umode_t fmode;
umode_t dmask;
umode_t fmask;
};
struct vboxsf_fs_context {
struct vboxsf_options o;
char *nls_name;
};
/* per-shared folder information */
struct vboxsf_sbi {
struct vboxsf_options o;
struct shfl_fsobjinfo root_info;
struct idr ino_idr;
spinlock_t ino_idr_lock; /* This protects ino_idr */
struct nls_table *nls;
u32 next_generation;
u32 root;
int bdi_id;
};
/* per-inode information */
struct vboxsf_inode {
/* some information was changed, update data on next revalidate */
int force_restat;
/* list of open handles for this inode + lock protecting it */
struct list_head handle_list;
/* This mutex protects handle_list accesses */
struct mutex handle_list_mutex;
/* The VFS inode struct */
struct inode vfs_inode;
};
struct vboxsf_dir_info {
struct list_head info_list;
};
struct vboxsf_dir_buf {
size_t entries;
size_t free;
size_t used;
void *buf;
struct list_head head;
};
/* globals */
extern const struct inode_operations vboxsf_dir_iops;
extern const struct inode_operations vboxsf_lnk_iops;
extern const struct inode_operations vboxsf_reg_iops;
extern const struct file_operations vboxsf_dir_fops;
extern const struct file_operations vboxsf_reg_fops;
extern const struct address_space_operations vboxsf_reg_aops;
extern const struct dentry_operations vboxsf_dentry_ops;
/* from utils.c */
struct inode *vboxsf_new_inode(struct super_block *sb);
void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
const struct shfl_fsobjinfo *info);
int vboxsf_create_at_dentry(struct dentry *dentry,
struct shfl_createparms *params);
int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
struct shfl_fsobjinfo *info);
int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info);
int vboxsf_inode_revalidate(struct dentry *dentry);
int vboxsf_getattr(const struct path *path, struct kstat *kstat,
u32 request_mask, unsigned int query_flags);
int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr);
struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
struct dentry *dentry);
int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
const unsigned char *utf8_name, size_t utf8_len);
struct vboxsf_dir_info *vboxsf_dir_info_alloc(void);
void vboxsf_dir_info_free(struct vboxsf_dir_info *p);
int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d,
u64 handle);
/* from vboxsf_wrappers.c */
int vboxsf_connect(void);
void vboxsf_disconnect(void);
int vboxsf_create(u32 root, struct shfl_string *parsed_path,
struct shfl_createparms *create_parms);
int vboxsf_close(u32 root, u64 handle);
int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags);
int vboxsf_rename(u32 root, struct shfl_string *src_path,
struct shfl_string *dest_path, u32 flags);
int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf);
int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf);
int vboxsf_dirinfo(u32 root, u64 handle,
struct shfl_string *parsed_path, u32 flags, u32 index,
u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count);
int vboxsf_fsinfo(u32 root, u64 handle, u32 flags,
u32 *buf_len, void *buf);
int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root);
int vboxsf_unmap_folder(u32 root);
int vboxsf_readlink(u32 root, struct shfl_string *parsed_path,
u32 buf_len, u8 *buf);
int vboxsf_symlink(u32 root, struct shfl_string *new_path,
struct shfl_string *old_path, struct shfl_fsobjinfo *buf);
int vboxsf_set_utf8(void);
int vboxsf_set_symlinks(void);
#endif

30
include/linux/cpu.h
View File

@ -59,6 +59,11 @@ extern ssize_t cpu_show_l1tf(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_mds(struct device *dev,
struct device_attribute *attr, char *buf);
extern ssize_t cpu_show_tsx_async_abort(struct device *dev,
struct device_attribute *attr,
char *buf);
extern ssize_t cpu_show_itlb_multihit(struct device *dev,
struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
@ -213,28 +218,7 @@ static inline int cpuhp_smt_enable(void) { return 0; }
static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
#endif
/*
* These are used for a global "mitigations=" cmdline option for toggling
* optional CPU mitigations.
*/
enum cpu_mitigations {
CPU_MITIGATIONS_OFF,
CPU_MITIGATIONS_AUTO,
CPU_MITIGATIONS_AUTO_NOSMT,
};
extern enum cpu_mitigations cpu_mitigations;
/* mitigations=off */
static inline bool cpu_mitigations_off(void)
{
return cpu_mitigations == CPU_MITIGATIONS_OFF;
}
/* mitigations=auto,nosmt */
static inline bool cpu_mitigations_auto_nosmt(void)
{
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
extern bool cpu_mitigations_off(void);
extern bool cpu_mitigations_auto_nosmt(void);
#endif /* _LINUX_CPU_H_ */

7
include/linux/kvm_host.h
View File

@ -966,6 +966,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
bool kvm_is_reserved_pfn(kvm_pfn_t pfn);
bool kvm_is_zone_device_pfn(kvm_pfn_t pfn);
struct kvm_irq_ack_notifier {
struct hlist_node link;
@ -1382,4 +1383,10 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
}
#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */
typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data);
int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
uintptr_t data, const char *name,
struct task_struct **thread_ptr);
#endif

27
kernel/cpu.c
View File

@ -2380,7 +2380,18 @@ void __init boot_cpu_hotplug_init(void)
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
/*
* These are used for a global "mitigations=" cmdline option for toggling
* optional CPU mitigations.
*/
enum cpu_mitigations {
CPU_MITIGATIONS_OFF,
CPU_MITIGATIONS_AUTO,
CPU_MITIGATIONS_AUTO_NOSMT,
};
static enum cpu_mitigations cpu_mitigations __ro_after_init =
CPU_MITIGATIONS_AUTO;
static int __init mitigations_parse_cmdline(char *arg)
{
@ -2397,3 +2408,17 @@ static int __init mitigations_parse_cmdline(char *arg)
return 0;
}
early_param("mitigations", mitigations_parse_cmdline);
/* mitigations=off */
bool cpu_mitigations_off(void)
{
return cpu_mitigations == CPU_MITIGATIONS_OFF;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_off);
/* mitigations=auto,nosmt */
bool cpu_mitigations_auto_nosmt(void)
{
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
}
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);

2
kernel/signal.c
View File

@ -2205,8 +2205,8 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t
*/
preempt_disable();
read_unlock(&tasklist_lock);
preempt_enable_no_resched();
cgroup_enter_frozen();
preempt_enable_no_resched();
freezable_schedule();
cgroup_leave_frozen(true);
} else {

160
virt/kvm/kvm_main.c
View File

@ -50,6 +50,7 @@
#include <linux/bsearch.h>
#include <linux/io.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
#include <asm/processor.h>
#include <asm/ioctl.h>
@ -149,10 +150,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
return 0;
}
bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
{
/*
* The metadata used by is_zone_device_page() to determine whether or
* not a page is ZONE_DEVICE is guaranteed to be valid if and only if
* the device has been pinned, e.g. by get_user_pages(). WARN if the
* page_count() is zero to help detect bad usage of this helper.
*/
if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
return false;
return is_zone_device_page(pfn_to_page(pfn));
}
bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
{
/*
* ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
* perspective they are "normal" pages, albeit with slightly different
* usage rules.
*/
if (pfn_valid(pfn))
return PageReserved(pfn_to_page(pfn));
return PageReserved(pfn_to_page(pfn)) &&
!kvm_is_zone_device_pfn(pfn);
return true;
}
@ -625,6 +646,23 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
return 0;
}
/*
* Called after the VM is otherwise initialized, but just before adding it to
* the vm_list.
*/
int __weak kvm_arch_post_init_vm(struct kvm *kvm)
{
return 0;
}
/*
* Called just after removing the VM from the vm_list, but before doing any
* other destruction.
*/
void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
{
}
static struct kvm *kvm_create_vm(unsigned long type)
{
struct kvm *kvm = kvm_arch_alloc_vm();
@ -645,6 +683,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
if (init_srcu_struct(&kvm->srcu))
goto out_err_no_srcu;
if (init_srcu_struct(&kvm->irq_srcu))
goto out_err_no_irq_srcu;
refcount_set(&kvm->users_count, 1);
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
struct kvm_memslots *slots = kvm_alloc_memslots();
@ -662,7 +706,6 @@ static struct kvm *kvm_create_vm(unsigned long type)
goto out_err_no_arch_destroy_vm;
}
refcount_set(&kvm->users_count, 1);
r = kvm_arch_init_vm(kvm, type);
if (r)
goto out_err_no_arch_destroy_vm;
@ -675,12 +718,11 @@ static struct kvm *kvm_create_vm(unsigned long type)
INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif
if (init_srcu_struct(&kvm->srcu))
goto out_err_no_srcu;
if (init_srcu_struct(&kvm->irq_srcu))
goto out_err_no_irq_srcu;
r = kvm_init_mmu_notifier(kvm);
if (r)
goto out_err_no_mmu_notifier;
r = kvm_arch_post_init_vm(kvm);
if (r)
goto out_err;
@ -693,19 +735,24 @@ static struct kvm *kvm_create_vm(unsigned long type)
return kvm;
out_err:
cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
out_err_no_srcu:
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
if (kvm->mmu_notifier.ops)
mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
#endif
out_err_no_mmu_notifier:
hardware_disable_all();
out_err_no_disable:
kvm_arch_destroy_vm(kvm);
WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
out_err_no_arch_destroy_vm:
WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm_get_bus(kvm, i));
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
out_err_no_srcu:
kvm_arch_free_vm(kvm);
mmdrop(current->mm);
return ERR_PTR(r);
@ -737,6 +784,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
mutex_lock(&kvm_lock);
list_del(&kvm->vm_list);
mutex_unlock(&kvm_lock);
kvm_arch_pre_destroy_vm(kvm);
kvm_free_irq_routing(kvm);
for (i = 0; i < KVM_NR_BUSES; i++) {
struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
@ -1857,7 +1906,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
void kvm_set_pfn_dirty(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn)) {
if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
SetPageDirty(page);
@ -1867,7 +1916,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
void kvm_set_pfn_accessed(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn))
if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
@ -4371,3 +4420,86 @@ void kvm_exit(void)
kvm_vfio_ops_exit();
}
EXPORT_SYMBOL_GPL(kvm_exit);
struct kvm_vm_worker_thread_context {
struct kvm *kvm;
struct task_struct *parent;
struct completion init_done;
kvm_vm_thread_fn_t thread_fn;
uintptr_t data;
int err;
};
static int kvm_vm_worker_thread(void *context)
{
/*
* The init_context is allocated on the stack of the parent thread, so
* we have to locally copy anything that is needed beyond initialization
*/
struct kvm_vm_worker_thread_context *init_context = context;
struct kvm *kvm = init_context->kvm;
kvm_vm_thread_fn_t thread_fn = init_context->thread_fn;
uintptr_t data = init_context->data;
int err;
err = kthread_park(current);
/* kthread_park(current) is never supposed to return an error */
WARN_ON(err != 0);
if (err)
goto init_complete;
err = cgroup_attach_task_all(init_context->parent, current);
if (err) {
kvm_err("%s: cgroup_attach_task_all failed with err %d\n",
__func__, err);
goto init_complete;
}
set_user_nice(current, task_nice(init_context->parent));
init_complete:
init_context->err = err;
complete(&init_context->init_done);
init_context = NULL;
if (err)
return err;
/* Wait to be woken up by the spawner before proceeding. */
kthread_parkme();
if (!kthread_should_stop())
err = thread_fn(kvm, data);
return err;
}
int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
uintptr_t data, const char *name,
struct task_struct **thread_ptr)
{
struct kvm_vm_worker_thread_context init_context = {};
struct task_struct *thread;
*thread_ptr = NULL;
init_context.kvm = kvm;
init_context.parent = current;
init_context.thread_fn = thread_fn;
init_context.data = data;
init_completion(&init_context.init_done);
thread = kthread_run(kvm_vm_worker_thread, &init_context,
"%s-%d", name, task_pid_nr(current));
if (IS_ERR(thread))
return PTR_ERR(thread);
/* kthread_run is never supposed to return NULL */
WARN_ON(thread == NULL);
wait_for_completion(&init_context.init_done);
if (!init_context.err)
*thread_ptr = thread;
return init_context.err;
}