renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-12 07:14:03 +08:00
Code

irqchip/genirq updates for 5.20:

Browse Source 
* Core code update:
 
   - Non-SMP IRQ affinity fixes, allowing UP kernel to behave similarly
     to SMP ones for the purpose of interrupt affinity
 
   - Let irq_set_chip_handler_name_locked() take a const struct irq_chip *
 
   - Tidy-up the NOMAP irqdomain API variant
 
   - Teach action_show() to use for_each_action_of_desc()
 
   - Make irq_chip_request_resources_parent() allow the parent callback
     to be optional
 
   - Remove dynamic allocations from populate_parent_alloc_arg()
 
 * New drivers:
 
   - Merge the long awaited IRQ support for the LoongArch architecture,
     with the provisional ACPICA update (to be reverted once the official
     support lands)
 
   - New Renesas RZ/G2L IRQC driver, equipped with its companion GPIO
     driver
 
 * Driver updates
 
   - Optimise the hot path operations for the SiFive PLIC, trading the
     locking for per-CPU priority masking masking operations which are
     apparently faster
 
   - Work around broken PLIC implementations that deal pretty badly with
     edge-triggered interrupts. Flag two implementations as affected.
 
   - Simplify the irq-stm32-exti driver, particularly the table that
     remaps the interrupts from exti to the GIC, reducing the memory usage
 
   - Convert the ocelot irq_chip to being immutable
 
   - Check ioremap() return value in the MIPS GIC driver
 
   - Move MMP driver init function declarations into the common .h
 
   - The obligatory typo fixes
 -----BEGIN PGP SIGNATURE-----
 
 iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmLhi0EPHG1hekBrZXJu
 ZWwub3JnAAoJECPQ0LrRPXpDI+wP/2BPABqCwu7JAmue8hHtpGweVkEBNulaS1K+
 1v/ElU8E1P8ppn1AVmu0lwgmAWiTtPuVWT21+AUbfOjQQ/MYKkegkH4KLmK93qSi
 Dn3MEiYv8WYsEV4yrJ7Il7fuuzr1iHIhIfhg3tMxDAJx47lzZH0o8nVoNFqXD1Ro
 WUFab/qTAOxJ/I53R9nrpx/yRf5dVRFUAZznrabYKpc/CiD/X+RLcHkbiybbRERu
 n3xwEtGMA2faCUgifKhsXoNUaW9mZLaufoF/F3J3Dyt7jNB/TTmdnxqWo6e4/rtd
 +Ut0MlH0W7bUdHGiVl1E90hDQ3yuBykUpKlTfMoYWOxeTqAx0bPYjGIuh6ajrAIy
 +fXWcK89KimOGB+aLC0cR5YrzvShHnH1G2qlrQg3pAXporigAXfZvzhnouRBsVKO
 RfnQHNsHSQHXTEu1u2HjMt7AXtmy/SoJENuPPUrtLfojg8b3aupwOvPLVx7w1Ok0
 5TKZ2yhOHdskfr3lCPisVPKK0KZ+QZhDdBkd319JkxR5/iA/tzMeMTzKslruhd2U
 Ug6hYhKNE2kKkBBBMcEVCHAuuq94DnU/q6l458UTSkkBmvq5cMMSz5Fs0kMwGFRc
 q/DncpKQnrPKGrwiilj1uGgOWO2vec8KfMJUYtKzSM/QELbKUvF7yzZeIjUQxiDO
 KqlWNczX
 =E5fZ
 -----END PGP SIGNATURE-----

Merge tag 'irqchip-5.20' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core

Pull irqchip/genirq updates from Marc Zyngier:

 * Core code update:

  - Non-SMP IRQ affinity fixes, allowing UP kernel to behave similarly
    to SMP ones for the purpose of interrupt affinity

  - Let irq_set_chip_handler_name_locked() take a const struct irq_chip *

  - Tidy-up the NOMAP irqdomain API variant

  - Teach action_show() to use for_each_action_of_desc()

  - Make irq_chip_request_resources_parent() allow the parent callback
    to be optional

  - Remove dynamic allocations from populate_parent_alloc_arg()

 * New drivers:

  - Merge the long awaited IRQ support for the LoongArch architecture,
    with the provisional ACPICA update (to be reverted once the official
    support lands)

  - New Renesas RZ/G2L IRQC driver, equipped with its companion GPIO
    driver

 * Driver updates

  - Optimise the hot path operations for the SiFive PLIC, trading the
    locking for per-CPU priority masking masking operations which are
    apparently faster

  - Work around broken PLIC implementations that deal pretty badly with
    edge-triggered interrupts. Flag two implementations as affected.

  - Simplify the irq-stm32-exti driver, particularly the table that
    remaps the interrupts from exti to the GIC, reducing the memory usage

  - Convert the ocelot irq_chip to being immutable

  - Check ioremap() return value in the MIPS GIC driver

  - Move MMP driver init function declarations into the common .h

  - The obligatory typo fixes

Link: https://lore.kernel.org/all/20220727192356.1860546-1-maz@kernel.org
This commit is contained in:
Thomas Gleixner 2022-07-28 12:36:35 +02:00
commit 779fda86bd
341 changed files with 6878 additions and 3890 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Documentation/ABI/testing/sysfs-devices-system-cpu
View File

@ -526,6 +526,7 @@ What: /sys/devices/system/cpu/vulnerabilities
/sys/devices/system/cpu/vulnerabilities/srbds
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
/sys/devices/system/cpu/vulnerabilities/itlb_multihit
/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities

1
Documentation/admin-guide/hw-vuln/index.rst
View File

@ -17,3 +17,4 @@ are configurable at compile, boot or run time.
special-register-buffer-data-sampling.rst
core-scheduling.rst
l1d_flush.rst
processor_mmio_stale_data.rst

246
Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst Normal file
View File

@ -0,0 +1,246 @@
=========================================
Processor MMIO Stale Data Vulnerabilities
=========================================
Processor MMIO Stale Data Vulnerabilities are a class of memory-mapped I/O
(MMIO) vulnerabilities that can expose data. The sequences of operations for
exposing data range from simple to very complex. Because most of the
vulnerabilities require the attacker to have access to MMIO, many environments
are not affected. System environments using virtualization where MMIO access is
provided to untrusted guests may need mitigation. These vulnerabilities are
not transient execution attacks. However, these vulnerabilities may propagate
stale data into core fill buffers where the data can subsequently be inferred
by an unmitigated transient execution attack. Mitigation for these
vulnerabilities includes a combination of microcode update and software
changes, depending on the platform and usage model. Some of these mitigations
are similar to those used to mitigate Microarchitectural Data Sampling (MDS) or
those used to mitigate Special Register Buffer Data Sampling (SRBDS).
Data Propagators
================
Propagators are operations that result in stale data being copied or moved from
one microarchitectural buffer or register to another. Processor MMIO Stale Data
Vulnerabilities are operations that may result in stale data being directly
read into an architectural, software-visible state or sampled from a buffer or
register.
Fill Buffer Stale Data Propagator (FBSDP)
-----------------------------------------
Stale data may propagate from fill buffers (FB) into the non-coherent portion
of the uncore on some non-coherent writes. Fill buffer propagation by itself
does not make stale data architecturally visible. Stale data must be propagated
to a location where it is subject to reading or sampling.
Sideband Stale Data Propagator (SSDP)
-------------------------------------
The sideband stale data propagator (SSDP) is limited to the client (including
Intel Xeon server E3) uncore implementation. The sideband response buffer is
shared by all client cores. For non-coherent reads that go to sideband
destinations, the uncore logic returns 64 bytes of data to the core, including
both requested data and unrequested stale data, from a transaction buffer and
the sideband response buffer. As a result, stale data from the sideband
response and transaction buffers may now reside in a core fill buffer.
Primary Stale Data Propagator (PSDP)
------------------------------------
The primary stale data propagator (PSDP) is limited to the client (including
Intel Xeon server E3) uncore implementation. Similar to the sideband response
buffer, the primary response buffer is shared by all client cores. For some
processors, MMIO primary reads will return 64 bytes of data to the core fill
buffer including both requested data and unrequested stale data. This is
similar to the sideband stale data propagator.
Vulnerabilities
===============
Device Register Partial Write (DRPW) (CVE-2022-21166)
-----------------------------------------------------
Some endpoint MMIO registers incorrectly handle writes that are smaller than
the register size. Instead of aborting the write or only copying the correct
subset of bytes (for example, 2 bytes for a 2-byte write), more bytes than
specified by the write transaction may be written to the register. On
processors affected by FBSDP, this may expose stale data from the fill buffers
of the core that created the write transaction.
Shared Buffers Data Sampling (SBDS) (CVE-2022-21125)
----------------------------------------------------
After propagators may have moved data around the uncore and copied stale data
into client core fill buffers, processors affected by MFBDS can leak data from
the fill buffer. It is limited to the client (including Intel Xeon server E3)
uncore implementation.
Shared Buffers Data Read (SBDR) (CVE-2022-21123)
------------------------------------------------
It is similar to Shared Buffer Data Sampling (SBDS) except that the data is
directly read into the architectural software-visible state. It is limited to
the client (including Intel Xeon server E3) uncore implementation.
Affected Processors
===================
Not all the CPUs are affected by all the variants. For instance, most
processors for the server market (excluding Intel Xeon E3 processors) are
impacted by only Device Register Partial Write (DRPW).
Below is the list of affected Intel processors [#f1]_:
=================== ============ =========
Common name Family_Model Steppings
=================== ============ =========
HASWELL_X 06_3FH 2,4
SKYLAKE_L 06_4EH 3
BROADWELL_X 06_4FH All
SKYLAKE_X 06_55H 3,4,6,7,11
BROADWELL_D 06_56H 3,4,5
SKYLAKE 06_5EH 3
ICELAKE_X 06_6AH 4,5,6
ICELAKE_D 06_6CH 1
ICELAKE_L 06_7EH 5
ATOM_TREMONT_D 06_86H All
LAKEFIELD 06_8AH 1
KABYLAKE_L 06_8EH 9 to 12
ATOM_TREMONT 06_96H 1
ATOM_TREMONT_L 06_9CH 0
KABYLAKE 06_9EH 9 to 13
COMETLAKE 06_A5H 2,3,5
COMETLAKE_L 06_A6H 0,1
ROCKETLAKE 06_A7H 1
=================== ============ =========
If a CPU is in the affected processor list, but not affected by a variant, it
is indicated by new bits in MSR IA32_ARCH_CAPABILITIES. As described in a later
section, mitigation largely remains the same for all the variants, i.e. to
clear the CPU fill buffers via VERW instruction.
New bits in MSRs
================
Newer processors and microcode update on existing affected processors added new
bits to IA32_ARCH_CAPABILITIES MSR. These bits can be used to enumerate
specific variants of Processor MMIO Stale Data vulnerabilities and mitigation
capability.
MSR IA32_ARCH_CAPABILITIES
--------------------------
Bit 13 - SBDR_SSDP_NO - When set, processor is not affected by either the
Shared Buffers Data Read (SBDR) vulnerability or the sideband stale
data propagator (SSDP).
Bit 14 - FBSDP_NO - When set, processor is not affected by the Fill Buffer
Stale Data Propagator (FBSDP).
Bit 15 - PSDP_NO - When set, processor is not affected by Primary Stale Data
Propagator (PSDP).
Bit 17 - FB_CLEAR - When set, VERW instruction will overwrite CPU fill buffer
values as part of MD_CLEAR operations. Processors that do not
enumerate MDS_NO (meaning they are affected by MDS) but that do
enumerate support for both L1D_FLUSH and MD_CLEAR implicitly enumerate
FB_CLEAR as part of their MD_CLEAR support.
Bit 18 - FB_CLEAR_CTRL - Processor supports read and write to MSR
IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]. On such processors, the FB_CLEAR_DIS
bit can be set to cause the VERW instruction to not perform the
FB_CLEAR action. Not all processors that support FB_CLEAR will support
FB_CLEAR_CTRL.
MSR IA32_MCU_OPT_CTRL
---------------------
Bit 3 - FB_CLEAR_DIS - When set, VERW instruction does not perform the FB_CLEAR
action. This may be useful to reduce the performance impact of FB_CLEAR in
cases where system software deems it warranted (for example, when performance
is more critical, or the untrusted software has no MMIO access). Note that
FB_CLEAR_DIS has no impact on enumeration (for example, it does not change
FB_CLEAR or MD_CLEAR enumeration) and it may not be supported on all processors
that enumerate FB_CLEAR.
Mitigation
==========
Like MDS, all variants of Processor MMIO Stale Data vulnerabilities have the
same mitigation strategy to force the CPU to clear the affected buffers before
an attacker can extract the secrets.
This is achieved by using the otherwise unused and obsolete VERW instruction in
combination with a microcode update. The microcode clears the affected CPU
buffers when the VERW instruction is executed.
Kernel reuses the MDS function to invoke the buffer clearing:
mds_clear_cpu_buffers()
On MDS affected CPUs, the kernel already invokes CPU buffer clear on
kernel/userspace, hypervisor/guest and C-state (idle) transitions. No
additional mitigation is needed on such CPUs.
For CPUs not affected by MDS or TAA, mitigation is needed only for the attacker
with MMIO capability. Therefore, VERW is not required for kernel/userspace. For
virtualization case, VERW is only needed at VMENTER for a guest with MMIO
capability.
Mitigation points
-----------------
Return to user space
^^^^^^^^^^^^^^^^^^^^
Same mitigation as MDS when affected by MDS/TAA, otherwise no mitigation
needed.
C-State transition
^^^^^^^^^^^^^^^^^^
Control register writes by CPU during C-state transition can propagate data
from fill buffer to uncore buffers. Execute VERW before C-state transition to
clear CPU fill buffers.
Guest entry point
^^^^^^^^^^^^^^^^^
Same mitigation as MDS when processor is also affected by MDS/TAA, otherwise
execute VERW at VMENTER only for MMIO capable guests. On CPUs not affected by
MDS/TAA, guest without MMIO access cannot extract secrets using Processor MMIO
Stale Data vulnerabilities, so there is no need to execute VERW for such guests.
Mitigation control on the kernel command line
---------------------------------------------
The kernel command line allows to control the Processor MMIO Stale Data
mitigations at boot time with the option "mmio_stale_data=". The valid
arguments for this option are:
========== =================================================================
full If the CPU is vulnerable, enable mitigation; CPU buffer clearing
on exit to userspace and when entering a VM. Idle transitions are
protected as well. It does not automatically disable SMT.
full,nosmt Same as full, with SMT disabled on vulnerable CPUs. This is the
complete mitigation.
off Disables mitigation completely.
========== =================================================================
If the CPU is affected and mmio_stale_data=off is not supplied on the kernel
command line, then the kernel selects the appropriate mitigation.
Mitigation status information
-----------------------------
The Linux kernel provides a sysfs interface to enumerate the current
vulnerability status of the system: whether the system is vulnerable, and
which mitigations are active. The relevant sysfs file is:
/sys/devices/system/cpu/vulnerabilities/mmio_stale_data
The possible values in this file are:
.. list-table::
* - 'Not affected'
- The processor is not vulnerable
* - 'Vulnerable'
- The processor is vulnerable, but no mitigation enabled
* - 'Vulnerable: Clear CPU buffers attempted, no microcode'
- The processor is vulnerable, but microcode is not updated. The
mitigation is enabled on a best effort basis.
* - 'Mitigation: Clear CPU buffers'
- The processor is vulnerable and the CPU buffer clearing mitigation is
enabled.
If the processor is vulnerable then the following information is appended to
the above information:
======================== ===========================================
'SMT vulnerable' SMT is enabled
'SMT disabled' SMT is disabled
'SMT Host state unknown' Kernel runs in a VM, Host SMT state unknown
======================== ===========================================
References
----------
.. [#f1] Affected Processors
https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html

37
Documentation/admin-guide/kernel-parameters.txt
View File

@ -2469,7 +2469,6 @@
protected: nVHE-based mode with support for guests whose
state is kept private from the host.
Not valid if the kernel is running in EL2.
Defaults to VHE/nVHE based on hardware support. Setting
mode to "protected" will disable kexec and hibernation
@ -3176,6 +3175,7 @@
srbds=off [X86,INTEL]
no_entry_flush [PPC]
no_uaccess_flush [PPC]
mmio_stale_data=off [X86]
Exceptions:
This does not have any effect on
@ -3197,6 +3197,7 @@
Equivalent to: l1tf=flush,nosmt [X86]
mds=full,nosmt [X86]
tsx_async_abort=full,nosmt [X86]
mmio_stale_data=full,nosmt [X86]
mminit_loglevel=
[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@ -3206,6 +3207,40 @@
log everything. Information is printed at KERN_DEBUG
so loglevel=8 may also need to be specified.
mmio_stale_data=
[X86,INTEL] Control mitigation for the Processor
MMIO Stale Data vulnerabilities.
Processor MMIO Stale Data is a class of
vulnerabilities that may expose data after an MMIO
operation. Exposed data could originate or end in
the same CPU buffers as affected by MDS and TAA.
Therefore, similar to MDS and TAA, the mitigation
is to clear the affected CPU buffers.
This parameter controls the mitigation. The
options are:
full - Enable mitigation on vulnerable CPUs
full,nosmt - Enable mitigation and disable SMT on
vulnerable CPUs.
off - Unconditionally disable mitigation
On MDS or TAA affected machines,
mmio_stale_data=off can be prevented by an active
MDS or TAA mitigation as these vulnerabilities are
mitigated with the same mechanism so in order to
disable this mitigation, you need to specify
mds=off and tsx_async_abort=off too.
Not specifying this option is equivalent to
mmio_stale_data=full.
For details see:
Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
module.sig_enforce
[KNL] When CONFIG_MODULE_SIG is set, this means that
modules without (valid) signatures will fail to load.

5
Documentation/devicetree/bindings/hwmon/ti,tmp401.yaml
View File

@ -40,9 +40,8 @@ properties:
value to be used for converting remote channel measurements to
temperature.
$ref: /schemas/types.yaml#/definitions/int32
items:
minimum: -128
maximum: 127
minimum: -128
maximum: 127
ti,beta-compensation:
description:

134
Documentation/devicetree/bindings/interrupt-controller/renesas,rzg2l-irqc.yaml Normal file
View File

@ -0,0 +1,134 @@
# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
%YAML 1.2
---
$id: http://devicetree.org/schemas/interrupt-controller/renesas,rzg2l-irqc.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Renesas RZ/G2L (and alike SoC's) Interrupt Controller (IA55)
maintainers:
- Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
- Geert Uytterhoeven <geert+renesas@glider.be>
description: |
IA55 performs various interrupt controls including synchronization for the external
interrupts of NMI, IRQ, and GPIOINT and the interrupts of the built-in peripheral
interrupts output by each IP. And it notifies the interrupt to the GIC
- IRQ sense select for 8 external interrupts, mapped to 8 GIC SPI interrupts
- GPIO pins used as external interrupt input pins, mapped to 32 GIC SPI interrupts
- NMI edge select (NMI is not treated as NMI exception and supports fall edge and
stand-up edge detection interrupts)
allOf:
- $ref: /schemas/interrupt-controller.yaml#
properties:
compatible:
items:
- enum:
- renesas,r9a07g044-irqc # RZ/G2{L,LC}
- renesas,r9a07g054-irqc # RZ/V2L
- const: renesas,rzg2l-irqc
'#interrupt-cells':
description: The first cell should contain external interrupt number (IRQ0-7) and the
second cell is used to specify the flag.
const: 2
'#address-cells':
const: 0
interrupt-controller: true
reg:
maxItems: 1
interrupts:
maxItems: 41
clocks:
maxItems: 2
clock-names:
items:
- const: clk
- const: pclk
power-domains:
maxItems: 1
resets:
maxItems: 1
required:
- compatible
- '#interrupt-cells'
- '#address-cells'
- interrupt-controller
- reg
- interrupts
- clocks
- clock-names
- power-domains
- resets
unevaluatedProperties: false
examples:
- |
#include <dt-bindings/interrupt-controller/arm-gic.h>
#include <dt-bindings/clock/r9a07g044-cpg.h>
irqc: interrupt-controller@110a0000 {
compatible = "renesas,r9a07g044-irqc", "renesas,rzg2l-irqc";
reg = <0x110a0000 0x10000>;
#interrupt-cells = <2>;
#address-cells = <0>;
interrupt-controller;
interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 445 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 446 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 447 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 448 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 449 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 450 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 451 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 452 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 453 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 454 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 455 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 456 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 457 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 458 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 459 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 460 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 461 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 462 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 463 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 464 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 465 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 466 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 467 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 468 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 471 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 474 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 475 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cpg CPG_MOD R9A07G044_IA55_CLK>,
<&cpg CPG_MOD R9A07G044_IA55_PCLK>;
clock-names = "clk", "pclk";
power-domains = <&cpg>;
resets = <&cpg R9A07G044_IA55_RESETN>;
};

65
Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml
View File

@ -26,9 +26,14 @@ description:
with priority below this threshold will not cause the PLIC to raise its
interrupt line leading to the context.
While the PLIC supports both edge-triggered and level-triggered interrupts,
interrupt handlers are oblivious to this distinction and therefore it is not
specified in the PLIC device-tree binding.
The PLIC supports both edge-triggered and level-triggered interrupts. For
edge-triggered interrupts, the RISC-V PLIC spec allows two responses to edges
seen while an interrupt handler is active; the PLIC may either queue them or
ignore them. In the first case, handlers are oblivious to the trigger type, so
it is not included in the interrupt specifier. In the second case, software
needs to know the trigger type, so it can reorder the interrupt flow to avoid
missing interrupts. This special handling is needed by at least the Renesas
RZ/Five SoC (AX45MP AndesCore with a NCEPLIC100) and the T-HEAD C900 PLIC.
While the RISC-V ISA doesn't specify a memory layout for the PLIC, the
"sifive,plic-1.0.0" device is a concrete implementation of the PLIC that
@ -47,6 +52,10 @@ maintainers:
properties:
compatible:
oneOf:
- items:
- enum:
- renesas,r9a07g043-plic
- const: andestech,nceplic100
- items:
- enum:
- sifive,fu540-c000-plic
@ -64,8 +73,7 @@ properties:
'#address-cells':
const: 0
'#interrupt-cells':
const: 1
'#interrupt-cells': true
interrupt-controller: true
@ -82,6 +90,12 @@ properties:
description:
Specifies how many external interrupts are supported by this controller.
clocks: true
power-domains: true
resets: true
required:
- compatible
- '#address-cells'
@ -91,6 +105,47 @@ required:
- interrupts-extended
- riscv,ndev
allOf:
- if:
properties:
compatible:
contains:
enum:
- andestech,nceplic100
- thead,c900-plic
then:
properties:
'#interrupt-cells':
const: 2
else:
properties:
'#interrupt-cells':
const: 1
- if:
properties:
compatible:
contains:
const: renesas,r9a07g043-plic
then:
properties:
clocks:
maxItems: 1
power-domains:
maxItems: 1
resets:
maxItems: 1
required:
- clocks
- power-domains
- resets
additionalProperties: false
examples:

1
Documentation/devicetree/bindings/interrupt-controller/socionext,uniphier-aidet.yaml
View File

@ -30,6 +30,7 @@ properties:
- socionext,uniphier-ld11-aidet
- socionext,uniphier-ld20-aidet
- socionext,uniphier-pxs3-aidet
- socionext,uniphier-nx1-aidet
reg:
maxItems: 1

15
Documentation/devicetree/bindings/pinctrl/renesas,rzg2l-pinctrl.yaml
View File

@ -47,6 +47,17 @@ properties:
gpio-ranges:
maxItems: 1
interrupt-controller: true
'#interrupt-cells':
const: 2
description:
The first cell contains the global GPIO port index, constructed using the
RZG2L_GPIO() helper macro in <dt-bindings/pinctrl/rzg2l-pinctrl.h> and the
second cell is used to specify the flag.
E.g. "interrupts = <RZG2L_GPIO(43, 0) IRQ_TYPE_EDGE_FALLING>;" if P43_0 is
being used as an interrupt.
clocks:
maxItems: 1
@ -110,6 +121,8 @@ required:
- gpio-controller
- '#gpio-cells'
- gpio-ranges
- interrupt-controller
- '#interrupt-cells'
- clocks
- power-domains
- resets
@ -126,6 +139,8 @@ examples:
gpio-controller;
#gpio-cells = <2>;
gpio-ranges = <&pinctrl 0 0 392>;
interrupt-controller;
#interrupt-cells = <2>;
clocks = <&cpg CPG_MOD R9A07G044_GPIO_HCLK>;
resets = <&cpg R9A07G044_GPIO_RSTN>,
<&cpg R9A07G044_GPIO_PORT_RESETN>,

68
Documentation/filesystems/ext4/attributes.rst
View File

@ -13,8 +13,8 @@ disappeared as of Linux 3.0.
There are two places where extended attributes can be found. The first
place is between the end of each inode entry and the beginning of the
next inode entry. For example, if inode.i\_extra\_isize = 28 and
sb.inode\_size = 256, then there are 256 - (128 + 28) = 100 bytes
next inode entry. For example, if inode.i_extra_isize = 28 and
sb.inode_size = 256, then there are 256 - (128 + 28) = 100 bytes
available for in-inode extended attribute storage. The second place
where extended attributes can be found is in the block pointed to by
``inode.i_file_acl``. As of Linux 3.11, it is not possible for this
@ -38,8 +38,8 @@ Extended attributes, when stored after the inode, have a header
- Name
- Description
* - 0x0
- \_\_le32
- h\_magic
- __le32
- h_magic
- Magic number for identification, 0xEA020000. This value is set by the
Linux driver, though e2fsprogs doesn't seem to check it(?)
@ -55,28 +55,28 @@ The beginning of an extended attribute block is in
- Name
- Description
* - 0x0
- \_\_le32
- h\_magic
- __le32
- h_magic
- Magic number for identification, 0xEA020000.
* - 0x4
- \_\_le32
- h\_refcount
- __le32
- h_refcount
- Reference count.
* - 0x8
- \_\_le32
- h\_blocks
- __le32
- h_blocks
- Number of disk blocks used.
* - 0xC
- \_\_le32
- h\_hash
- __le32
- h_hash
- Hash value of all attributes.
* - 0x10
- \_\_le32
- h\_checksum
- __le32
- h_checksum
- Checksum of the extended attribute block.
* - 0x14
- \_\_u32
- h\_reserved[3]
- __u32
- h_reserved[3]
- Zero.
The checksum is calculated against the FS UUID, the 64-bit block number
@ -100,46 +100,46 @@ Attributes stored inside an inode do not need be stored in sorted order.
- Name
- Description
* - 0x0
- \_\_u8
- e\_name\_len
- __u8
- e_name_len
- Length of name.
* - 0x1
- \_\_u8
- e\_name\_index
- __u8
- e_name_index
- Attribute name index. There is a discussion of this below.
* - 0x2
- \_\_le16
- e\_value\_offs
- __le16
- e_value_offs
- Location of this attribute's value on the disk block where it is stored.
Multiple attributes can share the same value. For an inode attribute
this value is relative to the start of the first entry; for a block this
value is relative to the start of the block (i.e. the header).
* - 0x4
- \_\_le32
- e\_value\_inum
- __le32
- e_value_inum
- The inode where the value is stored. Zero indicates the value is in the
same block as this entry. This field is only used if the
INCOMPAT\_EA\_INODE feature is enabled.
INCOMPAT_EA_INODE feature is enabled.
* - 0x8
- \_\_le32
- e\_value\_size
- __le32
- e_value_size
- Length of attribute value.
* - 0xC
- \_\_le32
- e\_hash
- __le32
- e_hash
- Hash value of attribute name and attribute value. The kernel doesn't
update the hash for in-inode attributes, so for that case this value
must be zero, because e2fsck validates any non-zero hash regardless of
where the xattr lives.
* - 0x10
- char
- e\_name[e\_name\_len]
- e_name[e_name_len]
- Attribute name. Does not include trailing NULL.
Attribute values can follow the end of the entry table. There appears to
be a requirement that they be aligned to 4-byte boundaries. The values
are stored starting at the end of the block and grow towards the
xattr\_header/xattr\_entry table. When the two collide, the overflow is
xattr_header/xattr_entry table. When the two collide, the overflow is
put into a separate disk block. If the disk block fills up, the
filesystem returns -ENOSPC.
@ -167,15 +167,15 @@ the key name. Here is a map of name index values to key prefixes:
* - 1
- “user.”
* - 2
- “system.posix\_acl\_access”
- “system.posix_acl_access”
* - 3
- “system.posix\_acl\_default”
- “system.posix_acl_default”
* - 4
- “trusted.”
* - 6
- “security.”
* - 7
- “system.” (inline\_data only?)
- “system.” (inline_data only?)
* - 8
- “system.richacl” (SuSE kernels only?)

2
Documentation/filesystems/ext4/bigalloc.rst
View File

@ -23,7 +23,7 @@ means that a block group addresses 32 gigabytes instead of 128 megabytes,
also shrinking the amount of file system overhead for metadata.
The administrator can set a block cluster size at mkfs time (which is
stored in the s\_log\_cluster\_size field in the superblock); from then
stored in the s_log_cluster_size field in the superblock); from then
on, the block bitmaps track clusters, not individual blocks. This means
that block groups can be several gigabytes in size (instead of just
128MiB); however, the minimum allocation unit becomes a cluster, not a

6
Documentation/filesystems/ext4/bitmaps.rst
View File

@ -9,15 +9,15 @@ group.
The inode bitmap records which entries in the inode table are in use.
As with most bitmaps, one bit represents the usage status of one data
block or inode table entry. This implies a block group size of 8 \*
number\_of\_bytes\_in\_a\_logical\_block.
block or inode table entry. This implies a block group size of 8 *
number_of_bytes_in_a_logical_block.
NOTE: If ``BLOCK_UNINIT`` is set for a given block group, various parts
of the kernel and e2fsprogs code pretends that the block bitmap contains
zeros (i.e. all blocks in the group are free). However, it is not
necessarily the case that no blocks are in use -- if ``meta_bg`` is set,
the bitmaps and group descriptor live inside the group. Unfortunately,
ext2fs\_test\_block\_bitmap2() will return '0' for those locations,
ext2fs_test_block_bitmap2() will return '0' for those locations,
which produces confusing debugfs output.
Inode Table

30
Documentation/filesystems/ext4/blockgroup.rst
View File

@ -56,39 +56,39 @@ established that the super block and the group descriptor table, if
present, will be at the beginning of the block group. The bitmaps and
the inode table can be anywhere, and it is quite possible for the
bitmaps to come after the inode table, or for both to be in different
groups (flex\_bg). Leftover space is used for file data blocks, indirect
groups (flex_bg). Leftover space is used for file data blocks, indirect
block maps, extent tree blocks, and extended attributes.
Flexible Block Groups
---------------------
Starting in ext4, there is a new feature called flexible block groups
(flex\_bg). In a flex\_bg, several block groups are tied together as one
(flex_bg). In a flex_bg, several block groups are tied together as one
logical block group; the bitmap spaces and the inode table space in the
first block group of the flex\_bg are expanded to include the bitmaps
and inode tables of all other block groups in the flex\_bg. For example,
if the flex\_bg size is 4, then group 0 will contain (in order) the
first block group of the flex_bg are expanded to include the bitmaps
and inode tables of all other block groups in the flex_bg. For example,
if the flex_bg size is 4, then group 0 will contain (in order) the
superblock, group descriptors, data block bitmaps for groups 0-3, inode
bitmaps for groups 0-3, inode tables for groups 0-3, and the remaining
space in group 0 is for file data. The effect of this is to group the
block group metadata close together for faster loading, and to enable
large files to be continuous on disk. Backup copies of the superblock
and group descriptors are always at the beginning of block groups, even
if flex\_bg is enabled. The number of block groups that make up a
flex\_bg is given by 2 ^ ``sb.s_log_groups_per_flex``.
if flex_bg is enabled. The number of block groups that make up a
flex_bg is given by 2 ^ ``sb.s_log_groups_per_flex``.
Meta Block Groups
-----------------
Without the option META\_BG, for safety concerns, all block group
Without the option META_BG, for safety concerns, all block group
descriptors copies are kept in the first block group. Given the default
128MiB(2^27 bytes) block group size and 64-byte group descriptors, ext4
can have at most 2^27/64 = 2^21 block groups. This limits the entire
filesystem size to 2^21 * 2^27 = 2^48bytes or 256TiB.
The solution to this problem is to use the metablock group feature
(META\_BG), which is already in ext3 for all 2.6 releases. With the
META\_BG feature, ext4 filesystems are partitioned into many metablock
(META_BG), which is already in ext3 for all 2.6 releases. With the
META_BG feature, ext4 filesystems are partitioned into many metablock
groups. Each metablock group is a cluster of block groups whose group
descriptor structures can be stored in a single disk block. For ext4
filesystems with 4 KB block size, a single metablock group partition
@ -110,7 +110,7 @@ bytes, a meta-block group contains 32 block groups for filesystems with
a 1KB block size, and 128 block groups for filesystems with a 4KB
blocksize. Filesystems can either be created using this new block group
descriptor layout, or existing filesystems can be resized on-line, and
the field s\_first\_meta\_bg in the superblock will indicate the first
the field s_first_meta_bg in the superblock will indicate the first
block group using this new layout.
Please see an important note about ``BLOCK_UNINIT`` in the section about
@ -121,15 +121,15 @@ Lazy Block Group Initialization
A new feature for ext4 are three block group descriptor flags that
enable mkfs to skip initializing other parts of the block group
metadata. Specifically, the INODE\_UNINIT and BLOCK\_UNINIT flags mean
metadata. Specifically, the INODE_UNINIT and BLOCK_UNINIT flags mean
that the inode and block bitmaps for that group can be calculated and
therefore the on-disk bitmap blocks are not initialized. This is
generally the case for an empty block group or a block group containing
only fixed-location block group metadata. The INODE\_ZEROED flag means
only fixed-location block group metadata. The INODE_ZEROED flag means
that the inode table has been initialized; mkfs will unset this flag and
rely on the kernel to initialize the inode tables in the background.
By not writing zeroes to the bitmaps and inode table, mkfs time is
reduced considerably. Note the feature flag is RO\_COMPAT\_GDT\_CSUM,
but the dumpe2fs output prints this as “uninit\_bg”. They are the same
reduced considerably. Note the feature flag is RO_COMPAT_GDT_CSUM,
but the dumpe2fs output prints this as “uninit_bg”. They are the same
thing.

2
Documentation/filesystems/ext4/blockmap.rst
View File

@ -1,7 +1,7 @@
.. SPDX-License-Identifier: GPL-2.0
+---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| i.i\_block Offset | Where It Points |
| i.i_block Offset | Where It Points |
+=====================+==============================================================================================================================================================================================================================+
| 0 to 11 | Direct map to file blocks 0 to 11. |
+---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

26
Documentation/filesystems/ext4/checksums.rst
View File

@ -4,7 +4,7 @@ Checksums
---------
Starting in early 2012, metadata checksums were added to all major ext4
and jbd2 data structures. The associated feature flag is metadata\_csum.
and jbd2 data structures. The associated feature flag is metadata_csum.
The desired checksum algorithm is indicated in the superblock, though as
of October 2012 the only supported algorithm is crc32c. Some data
structures did not have space to fit a full 32-bit checksum, so only the
@ -20,7 +20,7 @@ encounters directory blocks that lack sufficient empty space to add a
checksum, it will request that you run ``e2fsck -D`` to have the
directories rebuilt with checksums. This has the added benefit of
removing slack space from the directory files and rebalancing the htree
indexes. If you \_ignore\_ this step, your directories will not be
indexes. If you _ignore_ this step, your directories will not be
protected by a checksum!
The following table describes the data elements that go into each type
@ -35,39 +35,39 @@ of checksum. The checksum function is whatever the superblock describes
- Length
- Ingredients
* - Superblock
- \_\_le32
- __le32
- The entire superblock up to the checksum field. The UUID lives inside
the superblock.
* - MMP
- \_\_le32
- __le32
- UUID + the entire MMP block up to the checksum field.
* - Extended Attributes
- \_\_le32
- __le32
- UUID + the entire extended attribute block. The checksum field is set to
zero.
* - Directory Entries
- \_\_le32
- __le32
- UUID + inode number + inode generation + the directory block up to the
fake entry enclosing the checksum field.
* - HTREE Nodes
- \_\_le32
- __le32
- UUID + inode number + inode generation + all valid extents + HTREE tail.
The checksum field is set to zero.
* - Extents
- \_\_le32
- __le32
- UUID + inode number + inode generation + the entire extent block up to
the checksum field.
* - Bitmaps
- \_\_le32 or \_\_le16
- __le32 or __le16
- UUID + the entire bitmap. Checksums are stored in the group descriptor,
and truncated if the group descriptor size is 32 bytes (i.e. ^64bit)
* - Inodes
- \_\_le32
- __le32
- UUID + inode number + inode generation + the entire inode. The checksum
field is set to zero. Each inode has its own checksum.
* - Group Descriptors
- \_\_le16
- If metadata\_csum, then UUID + group number + the entire descriptor;
else if gdt\_csum, then crc16(UUID + group number + the entire
- __le16
- If metadata_csum, then UUID + group number + the entire descriptor;
else if gdt_csum, then crc16(UUID + group number + the entire
descriptor). In all cases, only the lower 16 bits are stored.

166
Documentation/filesystems/ext4/directory.rst
View File

@ -42,24 +42,24 @@ is at most 263 bytes long, though on disk you'll need to reference
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- inode
- Number of the inode that this directory entry points to.
* - 0x4
- \_\_le16
- rec\_len
- __le16
- rec_len
- Length of this directory entry. Must be a multiple of 4.
* - 0x6
- \_\_le16
- name\_len
- __le16
- name_len
- Length of the file name.
* - 0x8
- char
- name[EXT4\_NAME\_LEN]
- name[EXT4_NAME_LEN]
- File name.
Since file names cannot be longer than 255 bytes, the new directory
entry format shortens the name\_len field and uses the space for a file
entry format shortens the name_len field and uses the space for a file
type flag, probably to avoid having to load every inode during directory
tree traversal. This format is ``ext4_dir_entry_2``, which is at most
263 bytes long, though on disk you'll need to reference
@ -74,24 +74,24 @@ tree traversal. This format is ``ext4_dir_entry_2``, which is at most
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- inode
- Number of the inode that this directory entry points to.
* - 0x4
- \_\_le16
- rec\_len
- __le16
- rec_len
- Length of this directory entry.
* - 0x6
- \_\_u8
- name\_len
- __u8
- name_len
- Length of the file name.
* - 0x7
- \_\_u8
- file\_type
- __u8
- file_type
- File type code, see ftype_ table below.
* - 0x8
- char
- name[EXT4\_NAME\_LEN]
- name[EXT4_NAME_LEN]
- File name.
.. _ftype:
@ -137,19 +137,19 @@ entry uses this extension, it may be up to 271 bytes.
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- hash
- The hash of the directory name
* - 0x4
- \_\_le32
- minor\_hash
- __le32
- minor_hash
- The minor hash of the directory name
In order to add checksums to these classic directory blocks, a phony
``struct ext4_dir_entry`` is placed at the end of each leaf block to
hold the checksum. The directory entry is 12 bytes long. The inode
number and name\_len fields are set to zero to fool old software into
number and name_len fields are set to zero to fool old software into
ignoring an apparently empty directory entry, and the checksum is stored
in the place where the name normally goes. The structure is
``struct ext4_dir_entry_tail``:
@ -163,24 +163,24 @@ in the place where the name normally goes. The structure is
- Name
- Description
* - 0x0
- \_\_le32
- det\_reserved\_zero1
- __le32
- det_reserved_zero1
- Inode number, which must be zero.
* - 0x4
- \_\_le16
- det\_rec\_len
- __le16
- det_rec_len
- Length of this directory entry, which must be 12.
* - 0x6
- \_\_u8
- det\_reserved\_zero2
- __u8
- det_reserved_zero2
- Length of the file name, which must be zero.
* - 0x7
- \_\_u8
- det\_reserved\_ft
- __u8
- det_reserved_ft
- File type, which must be 0xDE.
* - 0x8
- \_\_le32
- det\_checksum
- __le32
- det_checksum
- Directory leaf block checksum.
The leaf directory block checksum is calculated against the FS UUID, the
@ -194,7 +194,7 @@ Hash Tree Directories
A linear array of directory entries isn't great for performance, so a
new feature was added to ext3 to provide a faster (but peculiar)
balanced tree keyed off a hash of the directory entry name. If the
EXT4\_INDEX\_FL (0x1000) flag is set in the inode, this directory uses a
EXT4_INDEX_FL (0x1000) flag is set in the inode, this directory uses a
hashed btree (htree) to organize and find directory entries. For
backwards read-only compatibility with ext2, this tree is actually
hidden inside the directory file, masquerading as “empty” directory data
@ -206,14 +206,14 @@ rest of the directory block is empty so that it moves on.
The root of the tree always lives in the first data block of the
directory. By ext2 custom, the '.' and '..' entries must appear at the
beginning of this first block, so they are put here as two
``struct ext4_dir_entry_2``\ s and not stored in the tree. The rest of
``struct ext4_dir_entry_2`` s and not stored in the tree. The rest of
the root node contains metadata about the tree and finally a hash->block
map to find nodes that are lower in the htree. If
``dx_root.info.indirect_levels`` is non-zero then the htree has two
levels; the data block pointed to by the root node's map is an interior
node, which is indexed by a minor hash. Interior nodes in this tree
contains a zeroed out ``struct ext4_dir_entry_2`` followed by a
minor\_hash->block map to find leafe nodes. Leaf nodes contain a linear
minor_hash->block map to find leafe nodes. Leaf nodes contain a linear
array of all ``struct ext4_dir_entry_2``; all of these entries
(presumably) hash to the same value. If there is an overflow, the
entries simply overflow into the next leaf node, and the
@ -245,83 +245,83 @@ of a data block:
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- dot.inode
- inode number of this directory.
* - 0x4
- \_\_le16
- dot.rec\_len
- __le16
- dot.rec_len
- Length of this record, 12.
* - 0x6
- u8
- dot.name\_len
- dot.name_len
- Length of the name, 1.
* - 0x7
- u8
- dot.file\_type
- dot.file_type
- File type of this entry, 0x2 (directory) (if the feature flag is set).
* - 0x8
- char
- dot.name[4]
- “.\\0\\0\\0”
- “.\0\0\0”
* - 0xC
- \_\_le32
- __le32
- dotdot.inode
- inode number of parent directory.
* - 0x10
- \_\_le16
- dotdot.rec\_len
- block\_size - 12. The record length is long enough to cover all htree
- __le16
- dotdot.rec_len
- block_size - 12. The record length is long enough to cover all htree
data.
* - 0x12
- u8
- dotdot.name\_len
- dotdot.name_len
- Length of the name, 2.
* - 0x13
- u8
- dotdot.file\_type
- dotdot.file_type
- File type of this entry, 0x2 (directory) (if the feature flag is set).
* - 0x14
- char
- dotdot\_name[4]
- “..\\0\\0”
- dotdot_name[4]
- “..\0\0”
* - 0x18
- \_\_le32
- struct dx\_root\_info.reserved\_zero
- __le32
- struct dx_root_info.reserved_zero
- Zero.
* - 0x1C
- u8
- struct dx\_root\_info.hash\_version
- struct dx_root_info.hash_version
- Hash type, see dirhash_ table below.
* - 0x1D
- u8
- struct dx\_root\_info.info\_length
- struct dx_root_info.info_length
- Length of the tree information, 0x8.
* - 0x1E
- u8
- struct dx\_root\_info.indirect\_levels
- Depth of the htree. Cannot be larger than 3 if the INCOMPAT\_LARGEDIR
- struct dx_root_info.indirect_levels
- Depth of the htree. Cannot be larger than 3 if the INCOMPAT_LARGEDIR
feature is set; cannot be larger than 2 otherwise.
* - 0x1F
- u8
- struct dx\_root\_info.unused\_flags
- struct dx_root_info.unused_flags
-
* - 0x20
- \_\_le16
- __le16
- limit
- Maximum number of dx\_entries that can follow this header, plus 1 for
- Maximum number of dx_entries that can follow this header, plus 1 for
the header itself.
* - 0x22
- \_\_le16
- __le16
- count
- Actual number of dx\_entries that follow this header, plus 1 for the
- Actual number of dx_entries that follow this header, plus 1 for the
header itself.
* - 0x24
- \_\_le32
- __le32
- block
- The block number (within the directory file) that goes with hash=0.
* - 0x28
- struct dx\_entry
- struct dx_entry
- entries[0]
- As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
@ -362,38 +362,38 @@ also the full length of a data block:
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- fake.inode
- Zero, to make it look like this entry is not in use.
* - 0x4
- \_\_le16
- fake.rec\_len
- The size of the block, in order to hide all of the dx\_node data.
- __le16
- fake.rec_len
- The size of the block, in order to hide all of the dx_node data.
* - 0x6
- u8
- name\_len
- name_len
- Zero. There is no name for this “unused” directory entry.
* - 0x7
- u8
- file\_type
- file_type
- Zero. There is no file type for this “unused” directory entry.
* - 0x8
- \_\_le16
- __le16
- limit
- Maximum number of dx\_entries that can follow this header, plus 1 for
- Maximum number of dx_entries that can follow this header, plus 1 for
the header itself.
* - 0xA
- \_\_le16
- __le16
- count
- Actual number of dx\_entries that follow this header, plus 1 for the
- Actual number of dx_entries that follow this header, plus 1 for the
header itself.
* - 0xE
- \_\_le32
- __le32
- block
- The block number (within the directory file) that goes with the lowest
hash value of this block. This value is stored in the parent block.
* - 0x12
- struct dx\_entry
- struct dx_entry
- entries[0]
- As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
@ -410,11 +410,11 @@ long:
- Name
- Description
* - 0x0
- \_\_le32
- __le32
- hash
- Hash code.
* - 0x4
- \_\_le32
- __le32
- block
- Block number (within the directory file, not filesystem blocks) of the
next node in the htree.
@ -423,13 +423,13 @@ long:
author.)
If metadata checksums are enabled, the last 8 bytes of the directory
block (precisely the length of one dx\_entry) are used to store a
block (precisely the length of one dx_entry) are used to store a
``struct dx_tail``, which contains the checksum. The ``limit`` and
``count`` entries in the dx\_root/dx\_node structures are adjusted as
necessary to fit the dx\_tail into the block. If there is no space for
the dx\_tail, the user is notified to run e2fsck -D to rebuild the
``count`` entries in the dx_root/dx_node structures are adjusted as
necessary to fit the dx_tail into the block. If there is no space for
the dx_tail, the user is notified to run e2fsck -D to rebuild the
directory index (which will ensure that there's space for the checksum.
The dx\_tail structure is 8 bytes long and looks like this:
The dx_tail structure is 8 bytes long and looks like this:
.. list-table::
:widths: 8 8 24 40
@ -441,13 +441,13 @@ The dx\_tail structure is 8 bytes long and looks like this:
- Description
* - 0x0
- u32
- dt\_reserved
- dt_reserved
- Zero.
* - 0x4
- \_\_le32
- dt\_checksum
- __le32
- dt_checksum
- Checksum of the htree directory block.
The checksum is calculated against the FS UUID, the htree index header
(dx\_root or dx\_node), all of the htree indices (dx\_entry) that are in
use, and the tail block (dx\_tail).
(dx_root or dx_node), all of the htree indices (dx_entry) that are in
use, and the tail block (dx_tail).

10
Documentation/filesystems/ext4/eainode.rst
View File

@ -5,14 +5,14 @@ Large Extended Attribute Values
To enable ext4 to store extended attribute values that do not fit in the
inode or in the single extended attribute block attached to an inode,
the EA\_INODE feature allows us to store the value in the data blocks of
the EA_INODE feature allows us to store the value in the data blocks of
a regular file inode. This “EA inode” is linked only from the extended
attribute name index and must not appear in a directory entry. The
inode's i\_atime field is used to store a checksum of the xattr value;
and i\_ctime/i\_version store a 64-bit reference count, which enables
inode's i_atime field is used to store a checksum of the xattr value;
and i_ctime/i_version store a 64-bit reference count, which enables
sharing of large xattr values between multiple owning inodes. For
backward compatibility with older versions of this feature, the
i\_mtime/i\_generation *may* store a back-reference to the inode number
and i\_generation of the **one** owning inode (in cases where the EA
i_mtime/i_generation *may* store a back-reference to the inode number
and i_generation of the **one** owning inode (in cases where the EA
inode is not referenced by multiple inodes) to verify that the EA inode
is the correct one being accessed.

126
Documentation/filesystems/ext4/group_descr.rst
View File

@ -7,34 +7,34 @@ Each block group on the filesystem has one of these descriptors
associated with it. As noted in the Layout section above, the group
descriptors (if present) are the second item in the block group. The
standard configuration is for each block group to contain a full copy of
the block group descriptor table unless the sparse\_super feature flag
the block group descriptor table unless the sparse_super feature flag
is set.
Notice how the group descriptor records the location of both bitmaps and
the inode table (i.e. they can float). This means that within a block
group, the only data structures with fixed locations are the superblock
and the group descriptor table. The flex\_bg mechanism uses this
and the group descriptor table. The flex_bg mechanism uses this
property to group several block groups into a flex group and lay out all
of the groups' bitmaps and inode tables into one long run in the first
group of the flex group.
If the meta\_bg feature flag is set, then several block groups are
grouped together into a meta group. Note that in the meta\_bg case,
If the meta_bg feature flag is set, then several block groups are
grouped together into a meta group. Note that in the meta_bg case,
however, the first and last two block groups within the larger meta
group contain only group descriptors for the groups inside the meta
group.
flex\_bg and meta\_bg do not appear to be mutually exclusive features.
flex_bg and meta_bg do not appear to be mutually exclusive features.
In ext2, ext3, and ext4 (when the 64bit feature is not enabled), the
block group descriptor was only 32 bytes long and therefore ends at
bg\_checksum. On an ext4 filesystem with the 64bit feature enabled, the
bg_checksum. On an ext4 filesystem with the 64bit feature enabled, the
block group descriptor expands to at least the 64 bytes described below;
the size is stored in the superblock.
If gdt\_csum is set and metadata\_csum is not set, the block group
If gdt_csum is set and metadata_csum is not set, the block group
checksum is the crc16 of the FS UUID, the group number, and the group
descriptor structure. If metadata\_csum is set, then the block group
descriptor structure. If metadata_csum is set, then the block group
checksum is the lower 16 bits of the checksum of the FS UUID, the group
number, and the group descriptor structure. Both block and inode bitmap
checksums are calculated against the FS UUID, the group number, and the
@ -51,59 +51,59 @@ The block group descriptor is laid out in ``struct ext4_group_desc``.
- Name
- Description
* - 0x0
- \_\_le32
- bg\_block\_bitmap\_lo
- __le32
- bg_block_bitmap_lo
- Lower 32-bits of location of block bitmap.
* - 0x4
- \_\_le32
- bg\_inode\_bitmap\_lo
- __le32
- bg_inode_bitmap_lo
- Lower 32-bits of location of inode bitmap.
* - 0x8
- \_\_le32
- bg\_inode\_table\_lo
- __le32
- bg_inode_table_lo
- Lower 32-bits of location of inode table.
* - 0xC
- \_\_le16
- bg\_free\_blocks\_count\_lo
- __le16
- bg_free_blocks_count_lo
- Lower 16-bits of free block count.
* - 0xE
- \_\_le16
- bg\_free\_inodes\_count\_lo
- __le16
- bg_free_inodes_count_lo
- Lower 16-bits of free inode count.
* - 0x10
- \_\_le16
- bg\_used\_dirs\_count\_lo
- __le16
- bg_used_dirs_count_lo
- Lower 16-bits of directory count.
* - 0x12
- \_\_le16
- bg\_flags
- __le16
- bg_flags
- Block group flags. See the bgflags_ table below.
* - 0x14
- \_\_le32
- bg\_exclude\_bitmap\_lo
- __le32
- bg_exclude_bitmap_lo
- Lower 32-bits of location of snapshot exclusion bitmap.
* - 0x18
- \_\_le16
- bg\_block\_bitmap\_csum\_lo
- __le16
- bg_block_bitmap_csum_lo
- Lower 16-bits of the block bitmap checksum.
* - 0x1A
- \_\_le16
- bg\_inode\_bitmap\_csum\_lo
- __le16
- bg_inode_bitmap_csum_lo
- Lower 16-bits of the inode bitmap checksum.
* - 0x1C
- \_\_le16
- bg\_itable\_unused\_lo
- __le16
- bg_itable_unused_lo
- Lower 16-bits of unused inode count. If set, we needn't scan past the
``(sb.s_inodes_per_group - gdt.bg_itable_unused)``\ th entry in the
``(sb.s_inodes_per_group - gdt.bg_itable_unused)`` th entry in the
inode table for this group.
* - 0x1E
- \_\_le16
- bg\_checksum
- Group descriptor checksum; crc16(sb\_uuid+group\_num+bg\_desc) if the
RO\_COMPAT\_GDT\_CSUM feature is set, or
crc32c(sb\_uuid+group\_num+bg\_desc) & 0xFFFF if the
RO\_COMPAT\_METADATA\_CSUM feature is set. The bg\_checksum
field in bg\_desc is skipped when calculating crc16 checksum,
- __le16
- bg_checksum
- Group descriptor checksum; crc16(sb_uuid+group_num+bg_desc) if the
RO_COMPAT_GDT_CSUM feature is set, or
crc32c(sb_uuid+group_num+bg_desc) & 0xFFFF if the
RO_COMPAT_METADATA_CSUM feature is set. The bg_checksum
field in bg_desc is skipped when calculating crc16 checksum,
and set to zero if crc32c checksum is used.
* -
-
@ -111,48 +111,48 @@ The block group descriptor is laid out in ``struct ext4_group_desc``.
- These fields only exist if the 64bit feature is enabled and s_desc_size
> 32.
* - 0x20
- \_\_le32
- bg\_block\_bitmap\_hi
- __le32
- bg_block_bitmap_hi
- Upper 32-bits of location of block bitmap.
* - 0x24
- \_\_le32
- bg\_inode\_bitmap\_hi
- __le32
- bg_inode_bitmap_hi
- Upper 32-bits of location of inodes bitmap.
* - 0x28
- \_\_le32
- bg\_inode\_table\_hi
- __le32
- bg_inode_table_hi
- Upper 32-bits of location of inodes table.
* - 0x2C
- \_\_le16
- bg\_free\_blocks\_count\_hi
- __le16
- bg_free_blocks_count_hi
- Upper 16-bits of free block count.
* - 0x2E
- \_\_le16
- bg\_free\_inodes\_count\_hi
- __le16
- bg_free_inodes_count_hi
- Upper 16-bits of free inode count.
* - 0x30
- \_\_le16
- bg\_used\_dirs\_count\_hi
- __le16
- bg_used_dirs_count_hi
- Upper 16-bits of directory count.
* - 0x32
- \_\_le16
- bg\_itable\_unused\_hi
- __le16
- bg_itable_unused_hi
- Upper 16-bits of unused inode count.
* - 0x34
- \_\_le32
- bg\_exclude\_bitmap\_hi
- __le32
- bg_exclude_bitmap_hi
- Upper 32-bits of location of snapshot exclusion bitmap.
* - 0x38
- \_\_le16
- bg\_block\_bitmap\_csum\_hi
- __le16
- bg_block_bitmap_csum_hi
- Upper 16-bits of the block bitmap checksum.
* - 0x3A
- \_\_le16
- bg\_inode\_bitmap\_csum\_hi
- __le16
- bg_inode_bitmap_csum_hi
- Upper 16-bits of the inode bitmap checksum.
* - 0x3C
- \_\_u32
- bg\_reserved
- __u32
- bg_reserved
- Padding to 64 bytes.
.. _bgflags:
@ -166,8 +166,8 @@ Block group flags can be any combination of the following:
* - Value
- Description
* - 0x1
- inode table and bitmap are not initialized (EXT4\_BG\_INODE\_UNINIT).
- inode table and bitmap are not initialized (EXT4_BG_INODE_UNINIT).
* - 0x2
- block bitmap is not initialized (EXT4\_BG\_BLOCK\_UNINIT).
- block bitmap is not initialized (EXT4_BG_BLOCK_UNINIT).
* - 0x4
- inode table is zeroed (EXT4\_BG\_INODE\_ZEROED).
- inode table is zeroed (EXT4_BG_INODE_ZEROED).

60
Documentation/filesystems/ext4/ifork.rst
View File

@ -1,6 +1,6 @@
.. SPDX-License-Identifier: GPL-2.0
The Contents of inode.i\_block
The Contents of inode.i_block
------------------------------
Depending on the type of file an inode describes, the 60 bytes of
@ -47,7 +47,7 @@ In ext4, the file to logical block map has been replaced with an extent
tree. Under the old scheme, allocating a contiguous run of 1,000 blocks
requires an indirect block to map all 1,000 entries; with extents, the
mapping is reduced to a single ``struct ext4_extent`` with
``ee_len = 1000``. If flex\_bg is enabled, it is possible to allocate
``ee_len = 1000``. If flex_bg is enabled, it is possible to allocate
very large files with a single extent, at a considerable reduction in
metadata block use, and some improvement in disk efficiency. The inode
must have the extents flag (0x80000) flag set for this feature to be in
@ -76,28 +76,28 @@ which is 12 bytes long:
- Name
- Description
* - 0x0
- \_\_le16
- eh\_magic
- __le16
- eh_magic
- Magic number, 0xF30A.
* - 0x2
- \_\_le16
- eh\_entries
- __le16
- eh_entries
- Number of valid entries following the header.
* - 0x4
- \_\_le16
- eh\_max
- __le16
- eh_max
- Maximum number of entries that could follow the header.
* - 0x6
- \_\_le16
- eh\_depth
- __le16
- eh_depth
- Depth of this extent node in the extent tree. 0 = this extent node
points to data blocks; otherwise, this extent node points to other
extent nodes. The extent tree can be at most 5 levels deep: a logical
block number can be at most ``2^32``, and the smallest ``n`` that
satisfies ``4*(((blocksize - 12)/12)^n) >= 2^32`` is 5.
* - 0x8
- \_\_le32
- eh\_generation
- __le32
- eh_generation
- Generation of the tree. (Used by Lustre, but not standard ext4).
Internal nodes of the extent tree, also known as index nodes, are
@ -112,22 +112,22 @@ recorded as ``struct ext4_extent_idx``, and are 12 bytes long:
- Name
- Description
* - 0x0
- \_\_le32
- ei\_block
- __le32
- ei_block
- This index node covers file blocks from 'block' onward.
* - 0x4
- \_\_le32
- ei\_leaf\_lo
- __le32
- ei_leaf_lo
- Lower 32-bits of the block number of the extent node that is the next
level lower in the tree. The tree node pointed to can be either another
internal node or a leaf node, described below.
* - 0x8
- \_\_le16
- ei\_leaf\_hi
- __le16
- ei_leaf_hi
- Upper 16-bits of the previous field.
* - 0xA
- \_\_u16
- ei\_unused
- __u16
- ei_unused
-
Leaf nodes of the extent tree are recorded as ``struct ext4_extent``,
@ -142,24 +142,24 @@ and are also 12 bytes long:
- Name
- Description
* - 0x0
- \_\_le32
- ee\_block
- __le32
- ee_block
- First file block number that this extent covers.
* - 0x4
- \_\_le16
- ee\_len
- __le16
- ee_len
- Number of blocks covered by extent. If the value of this field is <=
32768, the extent is initialized. If the value of the field is > 32768,
the extent is uninitialized and the actual extent length is ``ee_len`` -
32768. Therefore, the maximum length of a initialized extent is 32768
blocks, and the maximum length of an uninitialized extent is 32767.
* - 0x6
- \_\_le16
- ee\_start\_hi
- __le16
- ee_start_hi
- Upper 16-bits of the block number to which this extent points.
* - 0x8
- \_\_le32
- ee\_start\_lo
- __le32
- ee_start_lo
- Lower 32-bits of the block number to which this extent points.
Prior to the introduction of metadata checksums, the extent header +
@ -182,8 +182,8 @@ including) the checksum itself.
- Name
- Description
* - 0x0
- \_\_le32
- eb\_checksum
- __le32
- eb_checksum
- Checksum of the extent block, crc32c(uuid+inum+igeneration+extentblock)
Inline Data

8
Documentation/filesystems/ext4/inlinedata.rst
View File

@ -11,12 +11,12 @@ file is smaller than 60 bytes, then the data are stored inline in
attribute space, then it might be found as an extended attribute
“system.data” within the inode body (“ibody EA”). This of course
constrains the amount of extended attributes one can attach to an inode.
If the data size increases beyond i\_block + ibody EA, a regular block
If the data size increases beyond i_block + ibody EA, a regular block
is allocated and the contents moved to that block.
Pending a change to compact the extended attribute key used to store
inline data, one ought to be able to store 160 bytes of data in a
256-byte inode (as of June 2015, when i\_extra\_isize is 28). Prior to
256-byte inode (as of June 2015, when i_extra_isize is 28). Prior to
that, the limit was 156 bytes due to inefficient use of inode space.
The inline data feature requires the presence of an extended attribute
@ -25,12 +25,12 @@ for “system.data”, even if the attribute value is zero length.
Inline Directories
~~~~~~~~~~~~~~~~~~
The first four bytes of i\_block are the inode number of the parent
The first four bytes of i_block are the inode number of the parent
directory. Following that is a 56-byte space for an array of directory
entries; see ``struct ext4_dir_entry``. If there is a “system.data”
attribute in the inode body, the EA value is an array of
``struct ext4_dir_entry`` as well. Note that for inline directories, the
i\_block and EA space are treated as separate dirent blocks; directory
i_block and EA space are treated as separate dirent blocks; directory
entries cannot span the two.
Inline directory entries are not checksummed, as the inode checksum

306
Documentation/filesystems/ext4/inodes.rst
View File

@ -38,138 +38,138 @@ The inode table entry is laid out in ``struct ext4_inode``.
- Name
- Description
* - 0x0
- \_\_le16
- i\_mode
- __le16
- i_mode
- File mode. See the table i_mode_ below.
* - 0x2
- \_\_le16
- i\_uid
- __le16
- i_uid
- Lower 16-bits of Owner UID.
* - 0x4
- \_\_le32
- i\_size\_lo
- __le32
- i_size_lo
- Lower 32-bits of size in bytes.
* - 0x8
- \_\_le32
- i\_atime
- Last access time, in seconds since the epoch. However, if the EA\_INODE
- __le32
- i_atime
- Last access time, in seconds since the epoch. However, if the EA_INODE
inode flag is set, this inode stores an extended attribute value and
this field contains the checksum of the value.
* - 0xC
- \_\_le32
- i\_ctime
- __le32
- i_ctime
- Last inode change time, in seconds since the epoch. However, if the
EA\_INODE inode flag is set, this inode stores an extended attribute
EA_INODE inode flag is set, this inode stores an extended attribute
value and this field contains the lower 32 bits of the attribute value's
reference count.
* - 0x10
- \_\_le32
- i\_mtime
- __le32
- i_mtime
- Last data modification time, in seconds since the epoch. However, if the
EA\_INODE inode flag is set, this inode stores an extended attribute
EA_INODE inode flag is set, this inode stores an extended attribute
value and this field contains the number of the inode that owns the
extended attribute.
* - 0x14
- \_\_le32
- i\_dtime
- __le32
- i_dtime
- Deletion Time, in seconds since the epoch.
* - 0x18
- \_\_le16
- i\_gid
- __le16
- i_gid
- Lower 16-bits of GID.
* - 0x1A
- \_\_le16
- i\_links\_count
- __le16
- i_links_count
- Hard link count. Normally, ext4 does not permit an inode to have more
than 65,000 hard links. This applies to files as well as directories,
which means that there cannot be more than 64,998 subdirectories in a
directory (each subdirectory's '..' entry counts as a hard link, as does
the '.' entry in the directory itself). With the DIR\_NLINK feature
the '.' entry in the directory itself). With the DIR_NLINK feature
enabled, ext4 supports more than 64,998 subdirectories by setting this
field to 1 to indicate that the number of hard links is not known.
* - 0x1C
- \_\_le32
- i\_blocks\_lo
- Lower 32-bits of “block” count. If the huge\_file feature flag is not
- __le32
- i_blocks_lo
- Lower 32-bits of “block” count. If the huge_file feature flag is not
set on the filesystem, the file consumes ``i_blocks_lo`` 512-byte blocks
on disk. If huge\_file is set and EXT4\_HUGE\_FILE\_FL is NOT set in
on disk. If huge_file is set and EXT4_HUGE_FILE_FL is NOT set in
``inode.i_flags``, then the file consumes ``i_blocks_lo + (i_blocks_hi
<< 32)`` 512-byte blocks on disk. If huge\_file is set and
EXT4\_HUGE\_FILE\_FL IS set in ``inode.i_flags``, then this file
<< 32)`` 512-byte blocks on disk. If huge_file is set and
EXT4_HUGE_FILE_FL IS set in ``inode.i_flags``, then this file
consumes (``i_blocks_lo + i_blocks_hi`` << 32) filesystem blocks on
disk.
* - 0x20
- \_\_le32
- i\_flags
- __le32
- i_flags
- Inode flags. See the table i_flags_ below.
* - 0x24
- 4 bytes
- i\_osd1
- i_osd1
- See the table i_osd1_ for more details.
* - 0x28
- 60 bytes
- i\_block[EXT4\_N\_BLOCKS=15]
- Block map or extent tree. See the section “The Contents of inode.i\_block”.
- i_block[EXT4_N_BLOCKS=15]
- Block map or extent tree. See the section “The Contents of inode.i_block”.
* - 0x64
- \_\_le32
- i\_generation
- __le32
- i_generation
- File version (for NFS).
* - 0x68
- \_\_le32
- i\_file\_acl\_lo
- __le32
- i_file_acl_lo
- Lower 32-bits of extended attribute block. ACLs are of course one of
many possible extended attributes; I think the name of this field is a
result of the first use of extended attributes being for ACLs.
* - 0x6C
- \_\_le32
- i\_size\_high / i\_dir\_acl
- __le32
- i_size_high / i_dir_acl
- Upper 32-bits of file/directory size. In ext2/3 this field was named
i\_dir\_acl, though it was usually set to zero and never used.
i_dir_acl, though it was usually set to zero and never used.
* - 0x70
- \_\_le32
- i\_obso\_faddr
- __le32
- i_obso_faddr
- (Obsolete) fragment address.
* - 0x74
- 12 bytes
- i\_osd2
- i_osd2
- See the table i_osd2_ for more details.
* - 0x80
- \_\_le16
- i\_extra\_isize
- __le16
- i_extra_isize
- Size of this inode - 128. Alternately, the size of the extended inode
fields beyond the original ext2 inode, including this field.
* - 0x82
- \_\_le16
- i\_checksum\_hi
- __le16
- i_checksum_hi
- Upper 16-bits of the inode checksum.
* - 0x84
- \_\_le32
- i\_ctime\_extra
- __le32
- i_ctime_extra
- Extra change time bits. This provides sub-second precision. See Inode
Timestamps section.
* - 0x88
- \_\_le32
- i\_mtime\_extra
- __le32
- i_mtime_extra
- Extra modification time bits. This provides sub-second precision.
* - 0x8C
- \_\_le32
- i\_atime\_extra
- __le32
- i_atime_extra
- Extra access time bits. This provides sub-second precision.
* - 0x90
- \_\_le32
- i\_crtime
- __le32
- i_crtime
- File creation time, in seconds since the epoch.
* - 0x94
- \_\_le32
- i\_crtime\_extra
- __le32
- i_crtime_extra
- Extra file creation time bits. This provides sub-second precision.
* - 0x98
- \_\_le32
- i\_version\_hi
- __le32
- i_version_hi
- Upper 32-bits for version number.
* - 0x9C
- \_\_le32
- i\_projid
- __le32
- i_projid
- Project ID.
.. _i_mode:
@ -183,45 +183,45 @@ The ``i_mode`` value is a combination of the following flags:
* - Value
- Description
* - 0x1
- S\_IXOTH (Others may execute)
- S_IXOTH (Others may execute)
* - 0x2
- S\_IWOTH (Others may write)
- S_IWOTH (Others may write)
* - 0x4
- S\_IROTH (Others may read)
- S_IROTH (Others may read)
* - 0x8
- S\_IXGRP (Group members may execute)
- S_IXGRP (Group members may execute)
* - 0x10
- S\_IWGRP (Group members may write)
- S_IWGRP (Group members may write)
* - 0x20
- S\_IRGRP (Group members may read)
- S_IRGRP (Group members may read)
* - 0x40
- S\_IXUSR (Owner may execute)
- S_IXUSR (Owner may execute)
* - 0x80
- S\_IWUSR (Owner may write)
- S_IWUSR (Owner may write)
* - 0x100
- S\_IRUSR (Owner may read)
- S_IRUSR (Owner may read)
* - 0x200
- S\_ISVTX (Sticky bit)
- S_ISVTX (Sticky bit)
* - 0x400
- S\_ISGID (Set GID)
- S_ISGID (Set GID)
* - 0x800
- S\_ISUID (Set UID)
- S_ISUID (Set UID)
* -
- These are mutually-exclusive file types:
* - 0x1000
- S\_IFIFO (FIFO)
- S_IFIFO (FIFO)
* - 0x2000
- S\_IFCHR (Character device)
- S_IFCHR (Character device)
* - 0x4000
- S\_IFDIR (Directory)
- S_IFDIR (Directory)
* - 0x6000
- S\_IFBLK (Block device)
- S_IFBLK (Block device)
* - 0x8000
- S\_IFREG (Regular file)
- S_IFREG (Regular file)
* - 0xA000
- S\_IFLNK (Symbolic link)
- S_IFLNK (Symbolic link)
* - 0xC000
- S\_IFSOCK (Socket)
- S_IFSOCK (Socket)
.. _i_flags:
@ -234,56 +234,56 @@ The ``i_flags`` field is a combination of these values:
* - Value
- Description
* - 0x1
- This file requires secure deletion (EXT4\_SECRM\_FL). (not implemented)
- This file requires secure deletion (EXT4_SECRM_FL). (not implemented)
* - 0x2
- This file should be preserved, should undeletion be desired
(EXT4\_UNRM\_FL). (not implemented)
(EXT4_UNRM_FL). (not implemented)
* - 0x4
- File is compressed (EXT4\_COMPR\_FL). (not really implemented)
- File is compressed (EXT4_COMPR_FL). (not really implemented)
* - 0x8
- All writes to the file must be synchronous (EXT4\_SYNC\_FL).
- All writes to the file must be synchronous (EXT4_SYNC_FL).
* - 0x10
- File is immutable (EXT4\_IMMUTABLE\_FL).
- File is immutable (EXT4_IMMUTABLE_FL).
* - 0x20
- File can only be appended (EXT4\_APPEND\_FL).
- File can only be appended (EXT4_APPEND_FL).
* - 0x40
- The dump(1) utility should not dump this file (EXT4\_NODUMP\_FL).
- The dump(1) utility should not dump this file (EXT4_NODUMP_FL).
* - 0x80
- Do not update access time (EXT4\_NOATIME\_FL).
- Do not update access time (EXT4_NOATIME_FL).
* - 0x100
- Dirty compressed file (EXT4\_DIRTY\_FL). (not used)
- Dirty compressed file (EXT4_DIRTY_FL). (not used)
* - 0x200
- File has one or more compressed clusters (EXT4\_COMPRBLK\_FL). (not used)
- File has one or more compressed clusters (EXT4_COMPRBLK_FL). (not used)
* - 0x400
- Do not compress file (EXT4\_NOCOMPR\_FL). (not used)
- Do not compress file (EXT4_NOCOMPR_FL). (not used)
* - 0x800
- Encrypted inode (EXT4\_ENCRYPT\_FL). This bit value previously was
EXT4\_ECOMPR\_FL (compression error), which was never used.
- Encrypted inode (EXT4_ENCRYPT_FL). This bit value previously was
EXT4_ECOMPR_FL (compression error), which was never used.
* - 0x1000
- Directory has hashed indexes (EXT4\_INDEX\_FL).
- Directory has hashed indexes (EXT4_INDEX_FL).
* - 0x2000
- AFS magic directory (EXT4\_IMAGIC\_FL).
- AFS magic directory (EXT4_IMAGIC_FL).
* - 0x4000
- File data must always be written through the journal
(EXT4\_JOURNAL\_DATA\_FL).
(EXT4_JOURNAL_DATA_FL).
* - 0x8000
- File tail should not be merged (EXT4\_NOTAIL\_FL). (not used by ext4)
- File tail should not be merged (EXT4_NOTAIL_FL). (not used by ext4)
* - 0x10000
- All directory entry data should be written synchronously (see
``dirsync``) (EXT4\_DIRSYNC\_FL).
``dirsync``) (EXT4_DIRSYNC_FL).
* - 0x20000
- Top of directory hierarchy (EXT4\_TOPDIR\_FL).
- Top of directory hierarchy (EXT4_TOPDIR_FL).
* - 0x40000
- This is a huge file (EXT4\_HUGE\_FILE\_FL).
- This is a huge file (EXT4_HUGE_FILE_FL).
* - 0x80000
- Inode uses extents (EXT4\_EXTENTS\_FL).
- Inode uses extents (EXT4_EXTENTS_FL).
* - 0x100000
- Verity protected file (EXT4\_VERITY\_FL).
- Verity protected file (EXT4_VERITY_FL).
* - 0x200000
- Inode stores a large extended attribute value in its data blocks
(EXT4\_EA\_INODE\_FL).
(EXT4_EA_INODE_FL).
* - 0x400000
- This file has blocks allocated past EOF (EXT4\_EOFBLOCKS\_FL).
- This file has blocks allocated past EOF (EXT4_EOFBLOCKS_FL).
(deprecated)
* - 0x01000000
- Inode is a snapshot (``EXT4_SNAPFILE_FL``). (not in mainline)
@ -294,21 +294,21 @@ The ``i_flags`` field is a combination of these values:
- Snapshot shrink has completed (``EXT4_SNAPFILE_SHRUNK_FL``). (not in
mainline)
* - 0x10000000
- Inode has inline data (EXT4\_INLINE\_DATA\_FL).
- Inode has inline data (EXT4_INLINE_DATA_FL).
* - 0x20000000
- Create children with the same project ID (EXT4\_PROJINHERIT\_FL).
- Create children with the same project ID (EXT4_PROJINHERIT_FL).
* - 0x80000000
- Reserved for ext4 library (EXT4\_RESERVED\_FL).
- Reserved for ext4 library (EXT4_RESERVED_FL).
* -
- Aggregate flags:
* - 0x705BDFFF
- User-visible flags.
* - 0x604BC0FF
- User-modifiable flags. Note that while EXT4\_JOURNAL\_DATA\_FL and
EXT4\_EXTENTS\_FL can be set with setattr, they are not in the kernel's
EXT4\_FL\_USER\_MODIFIABLE mask, since it needs to handle the setting of
- User-modifiable flags. Note that while EXT4_JOURNAL_DATA_FL and
EXT4_EXTENTS_FL can be set with setattr, they are not in the kernel's
EXT4_FL_USER_MODIFIABLE mask, since it needs to handle the setting of
these flags in a special manner and they are masked out of the set of
flags that are saved directly to i\_flags.
flags that are saved directly to i_flags.
.. _i_osd1:
@ -325,9 +325,9 @@ Linux:
- Name
- Description
* - 0x0
- \_\_le32
- l\_i\_version
- Inode version. However, if the EA\_INODE inode flag is set, this inode
- __le32
- l_i_version
- Inode version. However, if the EA_INODE inode flag is set, this inode
stores an extended attribute value and this field contains the upper 32
bits of the attribute value's reference count.
@ -342,8 +342,8 @@ Hurd:
- Name
- Description
* - 0x0
- \_\_le32
- h\_i\_translator
- __le32
- h_i_translator
- ??
Masix:
@ -357,8 +357,8 @@ Masix:
- Name
- Description
* - 0x0
- \_\_le32
- m\_i\_reserved
- __le32
- m_i_reserved
- ??
.. _i_osd2:
@ -376,30 +376,30 @@ Linux:
- Name
- Description
* - 0x0
- \_\_le16
- l\_i\_blocks\_high
- __le16
- l_i_blocks_high
- Upper 16-bits of the block count. Please see the note attached to
i\_blocks\_lo.
i_blocks_lo.
* - 0x2
- \_\_le16
- l\_i\_file\_acl\_high
- __le16
- l_i_file_acl_high
- Upper 16-bits of the extended attribute block (historically, the file
ACL location). See the Extended Attributes section below.
* - 0x4
- \_\_le16
- l\_i\_uid\_high
- __le16
- l_i_uid_high
- Upper 16-bits of the Owner UID.
* - 0x6
- \_\_le16
- l\_i\_gid\_high
- __le16
- l_i_gid_high
- Upper 16-bits of the GID.
* - 0x8
- \_\_le16
- l\_i\_checksum\_lo
- __le16
- l_i_checksum_lo
- Lower 16-bits of the inode checksum.
* - 0xA
- \_\_le16
- l\_i\_reserved
- __le16
- l_i_reserved
- Unused.
Hurd:
@ -413,24 +413,24 @@ Hurd:
- Name
- Description
* - 0x0
- \_\_le16
- h\_i\_reserved1
- __le16
- h_i_reserved1
- ??
* - 0x2
- \_\_u16
- h\_i\_mode\_high
- __u16
- h_i_mode_high
- Upper 16-bits of the file mode.
* - 0x4
- \_\_le16
- h\_i\_uid\_high
- __le16
- h_i_uid_high
- Upper 16-bits of the Owner UID.
* - 0x6
- \_\_le16
- h\_i\_gid\_high
- __le16
- h_i_gid_high
- Upper 16-bits of the GID.
* - 0x8
- \_\_u32
- h\_i\_author
- __u32
- h_i_author
- Author code?
Masix:
@ -444,17 +444,17 @@ Masix:
- Name
- Description
* - 0x0
- \_\_le16
- h\_i\_reserved1
- __le16
- h_i_reserved1
- ??
* - 0x2
- \_\_u16
- m\_i\_file\_acl\_high
- __u16
- m_i_file_acl_high
- Upper 16-bits of the extended attribute block (historically, the file
ACL location).
* - 0x4
- \_\_u32
- m\_i\_reserved2[2]
- __u32
- m_i_reserved2[2]
- ??
Inode Size
@ -466,11 +466,11 @@ In ext2 and ext3, the inode structure size was fixed at 128 bytes
on-disk inode at format time for all inodes in the filesystem to provide
space beyond the end of the original ext2 inode. The on-disk inode
record size is recorded in the superblock as ``s_inode_size``. The
number of bytes actually used by struct ext4\_inode beyond the original
number of bytes actually used by struct ext4_inode beyond the original
128-byte ext2 inode is recorded in the ``i_extra_isize`` field for each
inode, which allows struct ext4\_inode to grow for a new kernel without
inode, which allows struct ext4_inode to grow for a new kernel without
having to upgrade all of the on-disk inodes. Access to fields beyond
EXT2\_GOOD\_OLD\_INODE\_SIZE should be verified to be within
EXT2_GOOD_OLD_INODE_SIZE should be verified to be within
``i_extra_isize``. By default, ext4 inode records are 256 bytes, and (as
of August 2019) the inode structure is 160 bytes
(``i_extra_isize = 32``). The extra space between the end of the inode
@ -516,7 +516,7 @@ creation time (crtime); this field is 64-bits wide and decoded in the
same manner as 64-bit [cma]time. Neither crtime nor dtime are accessible
through the regular stat() interface, though debugfs will report them.
We use the 32-bit signed time value plus (2^32 \* (extra epoch bits)).
We use the 32-bit signed time value plus (2^32 * (extra epoch bits)).
In other words:
.. list-table::
@ -525,8 +525,8 @@ In other words:
* - Extra epoch bits
- MSB of 32-bit time
- Adjustment for signed 32-bit to 64-bit tv\_sec
- Decoded 64-bit tv\_sec
- Adjustment for signed 32-bit to 64-bit tv_sec
- Decoded 64-bit tv_sec
- valid time range
* - 0 0
- 1

214
Documentation/filesystems/ext4/journal.rst
View File

@ -63,8 +63,8 @@ Generally speaking, the journal has this format:
:header-rows: 1
* - Superblock
- descriptor\_block (data\_blocks or revocation\_block) [more data or
revocations] commmit\_block
- descriptor_block (data_blocks or revocation_block) [more data or
revocations] commmit_block
- [more transactions...]
* -
- One transaction
@ -93,8 +93,8 @@ superblock.
* - 1024 bytes of padding
- ext4 Superblock
- Journal Superblock
- descriptor\_block (data\_blocks or revocation\_block) [more data or
revocations] commmit\_block
- descriptor_block (data_blocks or revocation_block) [more data or
revocations] commmit_block
- [more transactions...]
* -
-
@ -117,17 +117,17 @@ Every block in the journal starts with a common 12-byte header
- Name
- Description
* - 0x0
- \_\_be32
- h\_magic
- __be32
- h_magic
- jbd2 magic number, 0xC03B3998.
* - 0x4
- \_\_be32
- h\_blocktype
- __be32
- h_blocktype
- Description of what this block contains. See the jbd2_blocktype_ table
below.
* - 0x8
- \_\_be32
- h\_sequence
- __be32
- h_sequence
- The transaction ID that goes with this block.
.. _jbd2_blocktype:
@ -177,99 +177,99 @@ which is 1024 bytes long:
-
- Static information describing the journal.
* - 0x0
- journal\_header\_t (12 bytes)
- s\_header
- journal_header_t (12 bytes)
- s_header
- Common header identifying this as a superblock.
* - 0xC
- \_\_be32
- s\_blocksize
- __be32
- s_blocksize
- Journal device block size.
* - 0x10
- \_\_be32
- s\_maxlen
- __be32
- s_maxlen
- Total number of blocks in this journal.
* - 0x14
- \_\_be32
- s\_first
- __be32
- s_first
- First block of log information.
* -
-
-
- Dynamic information describing the current state of the log.
* - 0x18
- \_\_be32
- s\_sequence
- __be32
- s_sequence
- First commit ID expected in log.
* - 0x1C
- \_\_be32
- s\_start
- __be32
- s_start
- Block number of the start of log. Contrary to the comments, this field
being zero does not imply that the journal is clean!
* - 0x20
- \_\_be32
- s\_errno
- Error value, as set by jbd2\_journal\_abort().
- __be32
- s_errno
- Error value, as set by jbd2_journal_abort().
* -
-
-
- The remaining fields are only valid in a v2 superblock.
* - 0x24
- \_\_be32
- s\_feature\_compat;
- __be32
- s_feature_compat;
- Compatible feature set. See the table jbd2_compat_ below.
* - 0x28
- \_\_be32
- s\_feature\_incompat
- __be32
- s_feature_incompat
- Incompatible feature set. See the table jbd2_incompat_ below.
* - 0x2C
- \_\_be32
- s\_feature\_ro\_compat
- __be32
- s_feature_ro_compat
- Read-only compatible feature set. There aren't any of these currently.
* - 0x30
- \_\_u8
- s\_uuid[16]
- __u8
- s_uuid[16]
- 128-bit uuid for journal. This is compared against the copy in the ext4
super block at mount time.
* - 0x40
- \_\_be32
- s\_nr\_users
- __be32
- s_nr_users
- Number of file systems sharing this journal.
* - 0x44
- \_\_be32
- s\_dynsuper
- __be32
- s_dynsuper
- Location of dynamic super block copy. (Not used?)
* - 0x48
- \_\_be32
- s\_max\_transaction
- __be32
- s_max_transaction
- Limit of journal blocks per transaction. (Not used?)
* - 0x4C
- \_\_be32
- s\_max\_trans\_data
- __be32
- s_max_trans_data
- Limit of data blocks per transaction. (Not used?)
* - 0x50
- \_\_u8
- s\_checksum\_type
- __u8
- s_checksum_type
- Checksum algorithm used for the journal. See jbd2_checksum_type_ for
more info.
* - 0x51
- \_\_u8[3]
- s\_padding2
- __u8[3]
- s_padding2
-
* - 0x54
- \_\_be32
- s\_num\_fc\_blocks
- __be32
- s_num_fc_blocks
- Number of fast commit blocks in the journal.
* - 0x58
- \_\_u32
- s\_padding[42]
- __u32
- s_padding[42]
-
* - 0xFC
- \_\_be32
- s\_checksum
- __be32
- s_checksum
- Checksum of the entire superblock, with this field set to zero.
* - 0x100
- \_\_u8
- s\_users[16\*48]
- __u8
- s_users[16*48]
- ids of all file systems sharing the log. e2fsprogs/Linux don't allow
shared external journals, but I imagine Lustre (or ocfs2?), which use
the jbd2 code, might.
@ -286,7 +286,7 @@ The journal compat features are any combination of the following:
- Description
* - 0x1
- Journal maintains checksums on the data blocks.
(JBD2\_FEATURE\_COMPAT\_CHECKSUM)
(JBD2_FEATURE_COMPAT_CHECKSUM)
.. _jbd2_incompat:
@ -299,23 +299,23 @@ The journal incompat features are any combination of the following:
* - Value
- Description
* - 0x1
- Journal has block revocation records. (JBD2\_FEATURE\_INCOMPAT\_REVOKE)
- Journal has block revocation records. (JBD2_FEATURE_INCOMPAT_REVOKE)
* - 0x2
- Journal can deal with 64-bit block numbers.
(JBD2\_FEATURE\_INCOMPAT\_64BIT)
(JBD2_FEATURE_INCOMPAT_64BIT)
* - 0x4
- Journal commits asynchronously. (JBD2\_FEATURE\_INCOMPAT\_ASYNC\_COMMIT)
- Journal commits asynchronously. (JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)
* - 0x8
- This journal uses v2 of the checksum on-disk format. Each journal
metadata block gets its own checksum, and the block tags in the
descriptor table contain checksums for each of the data blocks in the
journal. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2)
journal. (JBD2_FEATURE_INCOMPAT_CSUM_V2)
* - 0x10
- This journal uses v3 of the checksum on-disk format. This is the same as
v2, but the journal block tag size is fixed regardless of the size of
block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
block numbers. (JBD2_FEATURE_INCOMPAT_CSUM_V3)
* - 0x20
- Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)
- Journal has fast commit blocks. (JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
.. _jbd2_checksum_type:
@ -355,11 +355,11 @@ Descriptor blocks consume at least 36 bytes, but use a full block:
- Name
- Descriptor
* - 0x0
- journal\_header\_t
- journal_header_t
- (open coded)
- Common block header.
* - 0xC
- struct journal\_block\_tag\_s
- struct journal_block_tag_s
- open coded array[]
- Enough tags either to fill up the block or to describe all the data
blocks that follow this descriptor block.
@ -367,7 +367,7 @@ Descriptor blocks consume at least 36 bytes, but use a full block:
Journal block tags have any of the following formats, depending on which
journal feature and block tag flags are set.
If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is set, the journal block tag is
If JBD2_FEATURE_INCOMPAT_CSUM_V3 is set, the journal block tag is
defined as ``struct journal_block_tag3_s``, which looks like the
following. The size is 16 or 32 bytes.
@ -380,24 +380,24 @@ following. The size is 16 or 32 bytes.
- Name
- Descriptor
* - 0x0
- \_\_be32
- t\_blocknr
- __be32
- t_blocknr
- Lower 32-bits of the location of where the corresponding data block
should end up on disk.
* - 0x4
- \_\_be32
- t\_flags
- __be32
- t_flags
- Flags that go with the descriptor. See the table jbd2_tag_flags_ for
more info.
* - 0x8
- \_\_be32
- t\_blocknr\_high
- __be32
- t_blocknr_high
- Upper 32-bits of the location of where the corresponding data block
should end up on disk. This is zero if JBD2\_FEATURE\_INCOMPAT\_64BIT is
should end up on disk. This is zero if JBD2_FEATURE_INCOMPAT_64BIT is
not enabled.
* - 0xC
- \_\_be32
- t\_checksum
- __be32
- t_checksum
- Checksum of the journal UUID, the sequence number, and the data block.
* -
-
@ -433,7 +433,7 @@ The journal tag flags are any combination of the following:
* - 0x8
- This is the last tag in this descriptor block.
If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is NOT set, the journal block tag
If JBD2_FEATURE_INCOMPAT_CSUM_V3 is NOT set, the journal block tag
is defined as ``struct journal_block_tag_s``, which looks like the
following. The size is 8, 12, 24, or 28 bytes:
@ -446,18 +446,18 @@ following. The size is 8, 12, 24, or 28 bytes:
- Name
- Descriptor
* - 0x0
- \_\_be32
- t\_blocknr
- __be32
- t_blocknr
- Lower 32-bits of the location of where the corresponding data block
should end up on disk.
* - 0x4
- \_\_be16
- t\_checksum
- __be16
- t_checksum
- Checksum of the journal UUID, the sequence number, and the data block.
Note that only the lower 16 bits are stored.
* - 0x6
- \_\_be16
- t\_flags
- __be16
- t_flags
- Flags that go with the descriptor. See the table jbd2_tag_flags_ for
more info.
* -
@ -466,8 +466,8 @@ following. The size is 8, 12, 24, or 28 bytes:
- This next field is only present if the super block indicates support for
64-bit block numbers.
* - 0x8
- \_\_be32
- t\_blocknr\_high
- __be32
- t_blocknr_high
- Upper 32-bits of the location of where the corresponding data block
should end up on disk.
* -
@ -483,8 +483,8 @@ following. The size is 8, 12, 24, or 28 bytes:
``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
field.
If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a
If JBD2_FEATURE_INCOMPAT_CSUM_V2 or
JBD2_FEATURE_INCOMPAT_CSUM_V3 are set, the end of the block is a
``struct jbd2_journal_block_tail``, which looks like this:
.. list-table::
@ -496,8 +496,8 @@ JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a
- Name
- Descriptor
* - 0x0
- \_\_be32
- t\_checksum
- __be32
- t_checksum
- Checksum of the journal UUID + the descriptor block, with this field set
to zero.
@ -538,25 +538,25 @@ length, but use a full block:
- Name
- Description
* - 0x0
- journal\_header\_t
- r\_header
- journal_header_t
- r_header
- Common block header.
* - 0xC
- \_\_be32
- r\_count
- __be32
- r_count
- Number of bytes used in this block.
* - 0x10
- \_\_be32 or \_\_be64
- __be32 or __be64
- blocks[0]
- Blocks to revoke.
After r\_count is a linear array of block numbers that are effectively
After r_count is a linear array of block numbers that are effectively
revoked by this transaction. The size of each block number is 8 bytes if
the superblock advertises 64-bit block number support, or 4 bytes
otherwise.
If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation
If JBD2_FEATURE_INCOMPAT_CSUM_V2 or
JBD2_FEATURE_INCOMPAT_CSUM_V3 are set, the end of the revocation
block is a ``struct jbd2_journal_revoke_tail``, which has this format:
.. list-table::
@ -568,8 +568,8 @@ block is a ``struct jbd2_journal_revoke_tail``, which has this format:
- Name
- Description
* - 0x0
- \_\_be32
- r\_checksum
- __be32
- r_checksum
- Checksum of the journal UUID + revocation block
Commit Block
@ -592,38 +592,38 @@ bytes long (but uses a full block):
- Name
- Descriptor
* - 0x0
- journal\_header\_s
- journal_header_s
- (open coded)
- Common block header.
* - 0xC
- unsigned char
- h\_chksum\_type
- h_chksum_type
- The type of checksum to use to verify the integrity of the data blocks
in the transaction. See jbd2_checksum_type_ for more info.
* - 0xD
- unsigned char
- h\_chksum\_size
- h_chksum_size
- The number of bytes used by the checksum. Most likely 4.
* - 0xE
- unsigned char
- h\_padding[2]
- h_padding[2]
-
* - 0x10
- \_\_be32
- h\_chksum[JBD2\_CHECKSUM\_BYTES]
- __be32
- h_chksum[JBD2_CHECKSUM_BYTES]
- 32 bytes of space to store checksums. If
JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3
JBD2_FEATURE_INCOMPAT_CSUM_V2 or JBD2_FEATURE_INCOMPAT_CSUM_V3
are set, the first ``__be32`` is the checksum of the journal UUID and
the entire commit block, with this field zeroed. If
JBD2\_FEATURE\_COMPAT\_CHECKSUM is set, the first ``__be32`` is the
JBD2_FEATURE_COMPAT_CHECKSUM is set, the first ``__be32`` is the
crc32 of all the blocks already written to the transaction.
* - 0x30
- \_\_be64
- h\_commit\_sec
- __be64
- h_commit_sec
- The time that the transaction was committed, in seconds since the epoch.
* - 0x38
- \_\_be32
- h\_commit\_nsec
- __be32
- h_commit_nsec
- Nanoseconds component of the above timestamp.
Fast commits

36
Documentation/filesystems/ext4/mmp.rst
View File

@ -7,8 +7,8 @@ Multiple mount protection (MMP) is a feature that protects the
filesystem against multiple hosts trying to use the filesystem
simultaneously. When a filesystem is opened (for mounting, or fsck,
etc.), the MMP code running on the node (call it node A) checks a
sequence number. If the sequence number is EXT4\_MMP\_SEQ\_CLEAN, the
open continues. If the sequence number is EXT4\_MMP\_SEQ\_FSCK, then
sequence number. If the sequence number is EXT4_MMP_SEQ_CLEAN, the
open continues. If the sequence number is EXT4_MMP_SEQ_FSCK, then
fsck is (hopefully) running, and open fails immediately. Otherwise, the
open code will wait for twice the specified MMP check interval and check
the sequence number again. If the sequence number has changed, then the
@ -40,38 +40,38 @@ The MMP structure (``struct mmp_struct``) is as follows:
- Name
- Description
* - 0x0
- \_\_le32
- mmp\_magic
- __le32
- mmp_magic
- Magic number for MMP, 0x004D4D50 (“MMP”).
* - 0x4
- \_\_le32
- mmp\_seq
- __le32
- mmp_seq
- Sequence number, updated periodically.
* - 0x8
- \_\_le64
- mmp\_time
- __le64
- mmp_time
- Time that the MMP block was last updated.
* - 0x10
- char[64]
- mmp\_nodename
- mmp_nodename
- Hostname of the node that opened the filesystem.
* - 0x50
- char[32]
- mmp\_bdevname
- mmp_bdevname
- Block device name of the filesystem.
* - 0x70
- \_\_le16
- mmp\_check\_interval
- __le16
- mmp_check_interval
- The MMP re-check interval, in seconds.
* - 0x72
- \_\_le16
- mmp\_pad1
- __le16
- mmp_pad1
- Zero.
* - 0x74
- \_\_le32[226]
- mmp\_pad2
- __le32[226]
- mmp_pad2
- Zero.
* - 0x3FC
- \_\_le32
- mmp\_checksum
- __le32
- mmp_checksum
- Checksum of the MMP block.

2
Documentation/filesystems/ext4/overview.rst
View File

@ -7,7 +7,7 @@ An ext4 file system is split into a series of block groups. To reduce
performance difficulties due to fragmentation, the block allocator tries
very hard to keep each file's blocks within the same group, thereby
reducing seek times. The size of a block group is specified in
``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 \*
``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 *
``block_size_in_bytes``. With the default block size of 4KiB, each group
will contain 32,768 blocks, for a length of 128MiB. The number of block
groups is the size of the device divided by the size of a block group.

8
Documentation/filesystems/ext4/special_inodes.rst
View File

@ -34,7 +34,7 @@ ext4 reserves some inode for special features, as follows:
* - 10
- Replica inode, used for some non-upstream feature?
* - 11
- Traditional first non-reserved inode. Usually this is the lost+found directory. See s\_first\_ino in the superblock.
- Traditional first non-reserved inode. Usually this is the lost+found directory. See s_first_ino in the superblock.
Note that there are also some inodes allocated from non-reserved inode numbers
for other filesystem features which are not referenced from standard directory
@ -47,9 +47,9 @@ hierarchy. These are generally reference from the superblock. They are:
* - Superblock field
- Description
* - s\_lpf\_ino
* - s_lpf_ino
- Inode number of lost+found directory.
* - s\_prj\_quota\_inum
* - s_prj_quota_inum
- Inode number of quota file tracking project quotas
* - s\_orphan\_file\_inum
* - s_orphan_file_inum
- Inode number of file tracking orphan inodes.

550
Documentation/filesystems/ext4/super.rst
View File

@ -7,7 +7,7 @@ The superblock records various information about the enclosing
filesystem, such as block counts, inode counts, supported features,
maintenance information, and more.
If the sparse\_super feature flag is set, redundant copies of the
If the sparse_super feature flag is set, redundant copies of the
superblock and group descriptors are kept only in the groups whose group
number is either 0 or a power of 3, 5, or 7. If the flag is not set,
redundant copies are kept in all groups.
@ -27,107 +27,107 @@ The ext4 superblock is laid out as follows in
- Name
- Description
* - 0x0
- \_\_le32
- s\_inodes\_count
- __le32
- s_inodes_count
- Total inode count.
* - 0x4
- \_\_le32
- s\_blocks\_count\_lo
- __le32
- s_blocks_count_lo
- Total block count.
* - 0x8
- \_\_le32
- s\_r\_blocks\_count\_lo
- __le32
- s_r_blocks_count_lo
- This number of blocks can only be allocated by the super-user.
* - 0xC
- \_\_le32
- s\_free\_blocks\_count\_lo
- __le32
- s_free_blocks_count_lo
- Free block count.
* - 0x10
- \_\_le32
- s\_free\_inodes\_count
- __le32
- s_free_inodes_count
- Free inode count.
* - 0x14
- \_\_le32
- s\_first\_data\_block
- __le32
- s_first_data_block
- First data block. This must be at least 1 for 1k-block filesystems and
is typically 0 for all other block sizes.
* - 0x18
- \_\_le32
- s\_log\_block\_size
- Block size is 2 ^ (10 + s\_log\_block\_size).
- __le32
- s_log_block_size
- Block size is 2 ^ (10 + s_log_block_size).
* - 0x1C
- \_\_le32
- s\_log\_cluster\_size
- Cluster size is 2 ^ (10 + s\_log\_cluster\_size) blocks if bigalloc is
enabled. Otherwise s\_log\_cluster\_size must equal s\_log\_block\_size.
- __le32
- s_log_cluster_size
- Cluster size is 2 ^ (10 + s_log_cluster_size) blocks if bigalloc is
enabled. Otherwise s_log_cluster_size must equal s_log_block_size.
* - 0x20
- \_\_le32
- s\_blocks\_per\_group
- __le32
- s_blocks_per_group
- Blocks per group.
* - 0x24
- \_\_le32
- s\_clusters\_per\_group
- __le32
- s_clusters_per_group
- Clusters per group, if bigalloc is enabled. Otherwise
s\_clusters\_per\_group must equal s\_blocks\_per\_group.
s_clusters_per_group must equal s_blocks_per_group.
* - 0x28
- \_\_le32
- s\_inodes\_per\_group
- __le32
- s_inodes_per_group
- Inodes per group.
* - 0x2C
- \_\_le32
- s\_mtime
- __le32
- s_mtime
- Mount time, in seconds since the epoch.
* - 0x30
- \_\_le32
- s\_wtime
- __le32
- s_wtime
- Write time, in seconds since the epoch.
* - 0x34
- \_\_le16
- s\_mnt\_count
- __le16
- s_mnt_count
- Number of mounts since the last fsck.
* - 0x36
- \_\_le16
- s\_max\_mnt\_count
- __le16
- s_max_mnt_count
- Number of mounts beyond which a fsck is needed.
* - 0x38
- \_\_le16
- s\_magic
- __le16
- s_magic
- Magic signature, 0xEF53
* - 0x3A
- \_\_le16
- s\_state
- __le16
- s_state
- File system state. See super_state_ for more info.
* - 0x3C
- \_\_le16
- s\_errors
- __le16
- s_errors
- Behaviour when detecting errors. See super_errors_ for more info.
* - 0x3E
- \_\_le16
- s\_minor\_rev\_level
- __le16
- s_minor_rev_level
- Minor revision level.
* - 0x40
- \_\_le32
- s\_lastcheck
- __le32
- s_lastcheck
- Time of last check, in seconds since the epoch.
* - 0x44
- \_\_le32
- s\_checkinterval
- __le32
- s_checkinterval
- Maximum time between checks, in seconds.
* - 0x48
- \_\_le32
- s\_creator\_os
- __le32
- s_creator_os
- Creator OS. See the table super_creator_ for more info.
* - 0x4C
- \_\_le32
- s\_rev\_level
- __le32
- s_rev_level
- Revision level. See the table super_revision_ for more info.
* - 0x50
- \_\_le16
- s\_def\_resuid
- __le16
- s_def_resuid
- Default uid for reserved blocks.
* - 0x52
- \_\_le16
- s\_def\_resgid
- __le16
- s_def_resgid
- Default gid for reserved blocks.
* -
-
@ -143,50 +143,50 @@ The ext4 superblock is laid out as follows in
about a feature in either the compatible or incompatible feature set, it
must abort and not try to meddle with things it doesn't understand...
* - 0x54
- \_\_le32
- s\_first\_ino
- __le32
- s_first_ino
- First non-reserved inode.
* - 0x58
- \_\_le16
- s\_inode\_size
- __le16
- s_inode_size
- Size of inode structure, in bytes.
* - 0x5A
- \_\_le16
- s\_block\_group\_nr
- __le16
- s_block_group_nr
- Block group # of this superblock.
* - 0x5C
- \_\_le32
- s\_feature\_compat
- __le32
- s_feature_compat
- Compatible feature set flags. Kernel can still read/write this fs even
if it doesn't understand a flag; fsck should not do that. See the
super_compat_ table for more info.
* - 0x60
- \_\_le32
- s\_feature\_incompat
- __le32
- s_feature_incompat
- Incompatible feature set. If the kernel or fsck doesn't understand one
of these bits, it should stop. See the super_incompat_ table for more
info.
* - 0x64
- \_\_le32
- s\_feature\_ro\_compat
- __le32
- s_feature_ro_compat
- Readonly-compatible feature set. If the kernel doesn't understand one of
these bits, it can still mount read-only. See the super_rocompat_ table
for more info.
* - 0x68
- \_\_u8
- s\_uuid[16]
- __u8
- s_uuid[16]
- 128-bit UUID for volume.
* - 0x78
- char
- s\_volume\_name[16]
- s_volume_name[16]
- Volume label.
* - 0x88
- char
- s\_last\_mounted[64]
- s_last_mounted[64]
- Directory where filesystem was last mounted.
* - 0xC8
- \_\_le32
- s\_algorithm\_usage\_bitmap
- __le32
- s_algorithm_usage_bitmap
- For compression (Not used in e2fsprogs/Linux)
* -
-
@ -194,18 +194,18 @@ The ext4 superblock is laid out as follows in
- Performance hints. Directory preallocation should only happen if the
EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
* - 0xCC
- \_\_u8
- s\_prealloc\_blocks
- __u8
- s_prealloc_blocks
- #. of blocks to try to preallocate for ... files? (Not used in
e2fsprogs/Linux)
* - 0xCD
- \_\_u8
- s\_prealloc\_dir\_blocks
- __u8
- s_prealloc_dir_blocks
- #. of blocks to preallocate for directories. (Not used in
e2fsprogs/Linux)
* - 0xCE
- \_\_le16
- s\_reserved\_gdt\_blocks
- __le16
- s_reserved_gdt_blocks
- Number of reserved GDT entries for future filesystem expansion.
* -
-
@ -213,281 +213,281 @@ The ext4 superblock is laid out as follows in
- Journalling support is valid only if EXT4_FEATURE_COMPAT_HAS_JOURNAL is
set.
* - 0xD0
- \_\_u8
- s\_journal\_uuid[16]
- __u8
- s_journal_uuid[16]
- UUID of journal superblock
* - 0xE0
- \_\_le32
- s\_journal\_inum
- __le32
- s_journal_inum
- inode number of journal file.
* - 0xE4
- \_\_le32
- s\_journal\_dev
- __le32
- s_journal_dev
- Device number of journal file, if the external journal feature flag is
set.
* - 0xE8
- \_\_le32
- s\_last\_orphan
- __le32
- s_last_orphan
- Start of list of orphaned inodes to delete.
* - 0xEC
- \_\_le32
- s\_hash\_seed[4]
- __le32
- s_hash_seed[4]
- HTREE hash seed.
* - 0xFC
- \_\_u8
- s\_def\_hash\_version
- __u8
- s_def_hash_version
- Default hash algorithm to use for directory hashes. See super_def_hash_
for more info.
* - 0xFD
- \_\_u8
- s\_jnl\_backup\_type
- If this value is 0 or EXT3\_JNL\_BACKUP\_BLOCKS (1), then the
- __u8
- s_jnl_backup_type
- If this value is 0 or EXT3_JNL_BACKUP_BLOCKS (1), then the
``s_jnl_blocks`` field contains a duplicate copy of the inode's
``i_block[]`` array and ``i_size``.
* - 0xFE
- \_\_le16
- s\_desc\_size
- __le16
- s_desc_size
- Size of group descriptors, in bytes, if the 64bit incompat feature flag
is set.
* - 0x100
- \_\_le32
- s\_default\_mount\_opts
- __le32
- s_default_mount_opts
- Default mount options. See the super_mountopts_ table for more info.
* - 0x104
- \_\_le32
- s\_first\_meta\_bg
- First metablock block group, if the meta\_bg feature is enabled.
- __le32
- s_first_meta_bg
- First metablock block group, if the meta_bg feature is enabled.
* - 0x108
- \_\_le32
- s\_mkfs\_time
- __le32
- s_mkfs_time
- When the filesystem was created, in seconds since the epoch.
* - 0x10C
- \_\_le32
- s\_jnl\_blocks[17]
- __le32
- s_jnl_blocks[17]
- Backup copy of the journal inode's ``i_block[]`` array in the first 15
elements and i\_size\_high and i\_size in the 16th and 17th elements,
elements and i_size_high and i_size in the 16th and 17th elements,
respectively.
* -
-
-
- 64bit support is valid only if EXT4_FEATURE_COMPAT_64BIT is set.
* - 0x150
- \_\_le32
- s\_blocks\_count\_hi
- __le32
- s_blocks_count_hi
- High 32-bits of the block count.
* - 0x154
- \_\_le32
- s\_r\_blocks\_count\_hi
- __le32
- s_r_blocks_count_hi
- High 32-bits of the reserved block count.
* - 0x158
- \_\_le32
- s\_free\_blocks\_count\_hi
- __le32
- s_free_blocks_count_hi
- High 32-bits of the free block count.
* - 0x15C
- \_\_le16
- s\_min\_extra\_isize
- __le16
- s_min_extra_isize
- All inodes have at least # bytes.
* - 0x15E
- \_\_le16
- s\_want\_extra\_isize
- __le16
- s_want_extra_isize
- New inodes should reserve # bytes.
* - 0x160
- \_\_le32
- s\_flags
- __le32
- s_flags
- Miscellaneous flags. See the super_flags_ table for more info.
* - 0x164
- \_\_le16
- s\_raid\_stride
- __le16
- s_raid_stride
- RAID stride. This is the number of logical blocks read from or written
to the disk before moving to the next disk. This affects the placement
of filesystem metadata, which will hopefully make RAID storage faster.
* - 0x166
- \_\_le16
- s\_mmp\_interval
- __le16
- s_mmp_interval
- #. seconds to wait in multi-mount prevention (MMP) checking. In theory,
MMP is a mechanism to record in the superblock which host and device
have mounted the filesystem, in order to prevent multiple mounts. This
feature does not seem to be implemented...
* - 0x168
- \_\_le64
- s\_mmp\_block
- __le64
- s_mmp_block
- Block # for multi-mount protection data.
* - 0x170
- \_\_le32
- s\_raid\_stripe\_width
- __le32
- s_raid_stripe_width
- RAID stripe width. This is the number of logical blocks read from or
written to the disk before coming back to the current disk. This is used
by the block allocator to try to reduce the number of read-modify-write
operations in a RAID5/6.
* - 0x174
- \_\_u8
- s\_log\_groups\_per\_flex
- __u8
- s_log_groups_per_flex
- Size of a flexible block group is 2 ^ ``s_log_groups_per_flex``.
* - 0x175
- \_\_u8
- s\_checksum\_type
- __u8
- s_checksum_type
- Metadata checksum algorithm type. The only valid value is 1 (crc32c).
* - 0x176
- \_\_le16
- s\_reserved\_pad
- __le16
- s_reserved_pad
-
* - 0x178
- \_\_le64
- s\_kbytes\_written
- __le64
- s_kbytes_written
- Number of KiB written to this filesystem over its lifetime.
* - 0x180
- \_\_le32
- s\_snapshot\_inum
- __le32
- s_snapshot_inum
- inode number of active snapshot. (Not used in e2fsprogs/Linux.)
* - 0x184
- \_\_le32
- s\_snapshot\_id
- __le32
- s_snapshot_id
- Sequential ID of active snapshot. (Not used in e2fsprogs/Linux.)
* - 0x188
- \_\_le64
- s\_snapshot\_r\_blocks\_count
- __le64
- s_snapshot_r_blocks_count
- Number of blocks reserved for active snapshot's future use. (Not used in
e2fsprogs/Linux.)
* - 0x190
- \_\_le32
- s\_snapshot\_list
- __le32
- s_snapshot_list
- inode number of the head of the on-disk snapshot list. (Not used in
e2fsprogs/Linux.)
* - 0x194
- \_\_le32
- s\_error\_count
- __le32
- s_error_count
- Number of errors seen.
* - 0x198
- \_\_le32
- s\_first\_error\_time
- __le32
- s_first_error_time
- First time an error happened, in seconds since the epoch.
* - 0x19C
- \_\_le32
- s\_first\_error\_ino
- __le32
- s_first_error_ino
- inode involved in first error.
* - 0x1A0
- \_\_le64
- s\_first\_error\_block
- __le64
- s_first_error_block
- Number of block involved of first error.
* - 0x1A8
- \_\_u8
- s\_first\_error\_func[32]
- __u8
- s_first_error_func[32]
- Name of function where the error happened.
* - 0x1C8
- \_\_le32
- s\_first\_error\_line
- __le32
- s_first_error_line
- Line number where error happened.
* - 0x1CC
- \_\_le32
- s\_last\_error\_time
- __le32
- s_last_error_time
- Time of most recent error, in seconds since the epoch.
* - 0x1D0
- \_\_le32
- s\_last\_error\_ino
- __le32
- s_last_error_ino
- inode involved in most recent error.
* - 0x1D4
- \_\_le32
- s\_last\_error\_line
- __le32
- s_last_error_line
- Line number where most recent error happened.
* - 0x1D8
- \_\_le64
- s\_last\_error\_block
- __le64
- s_last_error_block
- Number of block involved in most recent error.
* - 0x1E0
- \_\_u8
- s\_last\_error\_func[32]
- __u8
- s_last_error_func[32]
- Name of function where the most recent error happened.
* - 0x200
- \_\_u8
- s\_mount\_opts[64]
- __u8
- s_mount_opts[64]
- ASCIIZ string of mount options.
* - 0x240
- \_\_le32
- s\_usr\_quota\_inum
- __le32
- s_usr_quota_inum
- Inode number of user `quota <quota>`__ file.
* - 0x244
- \_\_le32
- s\_grp\_quota\_inum
- __le32
- s_grp_quota_inum
- Inode number of group `quota <quota>`__ file.
* - 0x248
- \_\_le32
- s\_overhead\_blocks
- __le32
- s_overhead_blocks
- Overhead blocks/clusters in fs. (Huh? This field is always zero, which
means that the kernel calculates it dynamically.)
* - 0x24C
- \_\_le32
- s\_backup\_bgs[2]
- Block groups containing superblock backups (if sparse\_super2)
- __le32
- s_backup_bgs[2]
- Block groups containing superblock backups (if sparse_super2)
* - 0x254
- \_\_u8
- s\_encrypt\_algos[4]
- __u8
- s_encrypt_algos[4]
- Encryption algorithms in use. There can be up to four algorithms in use
at any time; valid algorithm codes are given in the super_encrypt_ table
below.
* - 0x258
- \_\_u8
- s\_encrypt\_pw\_salt[16]
- __u8
- s_encrypt_pw_salt[16]
- Salt for the string2key algorithm for encryption.
* - 0x268
- \_\_le32
- s\_lpf\_ino
- __le32
- s_lpf_ino
- Inode number of lost+found
* - 0x26C
- \_\_le32
- s\_prj\_quota\_inum
- __le32
- s_prj_quota_inum
- Inode that tracks project quotas.
* - 0x270
- \_\_le32
- s\_checksum\_seed
- Checksum seed used for metadata\_csum calculations. This value is
crc32c(~0, $orig\_fs\_uuid).
- __le32
- s_checksum_seed
- Checksum seed used for metadata_csum calculations. This value is
crc32c(~0, $orig_fs_uuid).
* - 0x274
- \_\_u8
- s\_wtime_hi
- __u8
- s_wtime_hi
- Upper 8 bits of the s_wtime field.
* - 0x275
- \_\_u8
- s\_mtime_hi
- __u8
- s_mtime_hi
- Upper 8 bits of the s_mtime field.
* - 0x276
- \_\_u8
- s\_mkfs_time_hi
- __u8
- s_mkfs_time_hi
- Upper 8 bits of the s_mkfs_time field.
* - 0x277
- \_\_u8
- s\_lastcheck_hi
- __u8
- s_lastcheck_hi
- Upper 8 bits of the s_lastcheck_hi field.
* - 0x278
- \_\_u8
- s\_first_error_time_hi
- __u8
- s_first_error_time_hi
- Upper 8 bits of the s_first_error_time_hi field.
* - 0x279
- \_\_u8
- s\_last_error_time_hi
- __u8
- s_last_error_time_hi
- Upper 8 bits of the s_last_error_time_hi field.
* - 0x27A
- \_\_u8
- s\_pad[2]
- __u8
- s_pad[2]
- Zero padding.
* - 0x27C
- \_\_le16
- s\_encoding
- __le16
- s_encoding
- Filename charset encoding.
* - 0x27E
- \_\_le16
- s\_encoding_flags
- __le16
- s_encoding_flags
- Filename charset encoding flags.
* - 0x280
- \_\_le32
- s\_orphan\_file\_inum
- __le32
- s_orphan_file_inum
- Orphan file inode number.
* - 0x284
- \_\_le32
- s\_reserved[94]
- __le32
- s_reserved[94]
- Padding to the end of the block.
* - 0x3FC
- \_\_le32
- s\_checksum
- __le32
- s_checksum
- Superblock checksum.
.. _super_state:
@ -574,44 +574,44 @@ following:
* - Value
- Description
* - 0x1
- Directory preallocation (COMPAT\_DIR\_PREALLOC).
- Directory preallocation (COMPAT_DIR_PREALLOC).
* - 0x2
- “imagic inodes”. Not clear from the code what this does
(COMPAT\_IMAGIC\_INODES).
(COMPAT_IMAGIC_INODES).
* - 0x4
- Has a journal (COMPAT\_HAS\_JOURNAL).
- Has a journal (COMPAT_HAS_JOURNAL).
* - 0x8
- Supports extended attributes (COMPAT\_EXT\_ATTR).
- Supports extended attributes (COMPAT_EXT_ATTR).
* - 0x10
- Has reserved GDT blocks for filesystem expansion
(COMPAT\_RESIZE\_INODE). Requires RO\_COMPAT\_SPARSE\_SUPER.
(COMPAT_RESIZE_INODE). Requires RO_COMPAT_SPARSE_SUPER.
* - 0x20
- Has directory indices (COMPAT\_DIR\_INDEX).
- Has directory indices (COMPAT_DIR_INDEX).
* - 0x40
- “Lazy BG”. Not in Linux kernel, seems to have been for uninitialized
block groups? (COMPAT\_LAZY\_BG)
block groups? (COMPAT_LAZY_BG)
* - 0x80
- “Exclude inode”. Not used. (COMPAT\_EXCLUDE\_INODE).
- “Exclude inode”. Not used. (COMPAT_EXCLUDE_INODE).
* - 0x100
- “Exclude bitmap”. Seems to be used to indicate the presence of
snapshot-related exclude bitmaps? Not defined in kernel or used in
e2fsprogs (COMPAT\_EXCLUDE\_BITMAP).
e2fsprogs (COMPAT_EXCLUDE_BITMAP).
* - 0x200
- Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
- Sparse Super Block, v2. If this flag is set, the SB field s_backup_bgs
points to the two block groups that contain backup superblocks
(COMPAT\_SPARSE\_SUPER2).
(COMPAT_SPARSE_SUPER2).
* - 0x400
- Fast commits supported. Although fast commits blocks are
backward incompatible, fast commit blocks are not always
present in the journal. If fast commit blocks are present in
the journal, JBD2 incompat feature
(JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
set (COMPAT\_FAST\_COMMIT).
(JBD2_FEATURE_INCOMPAT_FAST_COMMIT) gets
set (COMPAT_FAST_COMMIT).
* - 0x1000
- Orphan file allocated. This is the special file for more efficient
tracking of unlinked but still open inodes. When there may be any
entries in the file, we additionally set proper rocompat feature
(RO\_COMPAT\_ORPHAN\_PRESENT).
(RO_COMPAT_ORPHAN_PRESENT).
.. _super_incompat:
@ -625,45 +625,45 @@ following:
* - Value
- Description
* - 0x1
- Compression (INCOMPAT\_COMPRESSION).
- Compression (INCOMPAT_COMPRESSION).
* - 0x2
- Directory entries record the file type. See ext4\_dir\_entry\_2 below
(INCOMPAT\_FILETYPE).
- Directory entries record the file type. See ext4_dir_entry_2 below
(INCOMPAT_FILETYPE).
* - 0x4
- Filesystem needs recovery (INCOMPAT\_RECOVER).
- Filesystem needs recovery (INCOMPAT_RECOVER).
* - 0x8
- Filesystem has a separate journal device (INCOMPAT\_JOURNAL\_DEV).
- Filesystem has a separate journal device (INCOMPAT_JOURNAL_DEV).
* - 0x10
- Meta block groups. See the earlier discussion of this feature
(INCOMPAT\_META\_BG).
(INCOMPAT_META_BG).
* - 0x40
- Files in this filesystem use extents (INCOMPAT\_EXTENTS).
- Files in this filesystem use extents (INCOMPAT_EXTENTS).
* - 0x80
- Enable a filesystem size of 2^64 blocks (INCOMPAT\_64BIT).
- Enable a filesystem size of 2^64 blocks (INCOMPAT_64BIT).
* - 0x100
- Multiple mount protection (INCOMPAT\_MMP).
- Multiple mount protection (INCOMPAT_MMP).
* - 0x200
- Flexible block groups. See the earlier discussion of this feature
(INCOMPAT\_FLEX\_BG).
(INCOMPAT_FLEX_BG).
* - 0x400
- Inodes can be used to store large extended attribute values
(INCOMPAT\_EA\_INODE).
(INCOMPAT_EA_INODE).
* - 0x1000
- Data in directory entry (INCOMPAT\_DIRDATA). (Not implemented?)
- Data in directory entry (INCOMPAT_DIRDATA). (Not implemented?)
* - 0x2000
- Metadata checksum seed is stored in the superblock. This feature enables
the administrator to change the UUID of a metadata\_csum filesystem
the administrator to change the UUID of a metadata_csum filesystem
while the filesystem is mounted; without it, the checksum definition
requires all metadata blocks to be rewritten (INCOMPAT\_CSUM\_SEED).
requires all metadata blocks to be rewritten (INCOMPAT_CSUM_SEED).
* - 0x4000
- Large directory >2GB or 3-level htree (INCOMPAT\_LARGEDIR). Prior to
- Large directory >2GB or 3-level htree (INCOMPAT_LARGEDIR). Prior to
this feature, directories could not be larger than 4GiB and could not
have an htree more than 2 levels deep. If this feature is enabled,
directories can be larger than 4GiB and have a maximum htree depth of 3.
* - 0x8000
- Data in inode (INCOMPAT\_INLINE\_DATA).
- Data in inode (INCOMPAT_INLINE_DATA).
* - 0x10000
- Encrypted inodes are present on the filesystem. (INCOMPAT\_ENCRYPT).
- Encrypted inodes are present on the filesystem. (INCOMPAT_ENCRYPT).
.. _super_rocompat:
@ -678,54 +678,54 @@ the following:
- Description
* - 0x1
- Sparse superblocks. See the earlier discussion of this feature
(RO\_COMPAT\_SPARSE\_SUPER).
(RO_COMPAT_SPARSE_SUPER).
* - 0x2
- This filesystem has been used to store a file greater than 2GiB
(RO\_COMPAT\_LARGE\_FILE).
(RO_COMPAT_LARGE_FILE).
* - 0x4
- Not used in kernel or e2fsprogs (RO\_COMPAT\_BTREE\_DIR).
- Not used in kernel or e2fsprogs (RO_COMPAT_BTREE_DIR).
* - 0x8
- This filesystem has files whose sizes are represented in units of
logical blocks, not 512-byte sectors. This implies a very large file
indeed! (RO\_COMPAT\_HUGE\_FILE)
indeed! (RO_COMPAT_HUGE_FILE)
* - 0x10
- Group descriptors have checksums. In addition to detecting corruption,
this is useful for lazy formatting with uninitialized groups
(RO\_COMPAT\_GDT\_CSUM).
(RO_COMPAT_GDT_CSUM).
* - 0x20
- Indicates that the old ext3 32,000 subdirectory limit no longer applies
(RO\_COMPAT\_DIR\_NLINK). A directory's i\_links\_count will be set to 1
(RO_COMPAT_DIR_NLINK). A directory's i_links_count will be set to 1
if it is incremented past 64,999.
* - 0x40
- Indicates that large inodes exist on this filesystem
(RO\_COMPAT\_EXTRA\_ISIZE).
(RO_COMPAT_EXTRA_ISIZE).
* - 0x80
- This filesystem has a snapshot (RO\_COMPAT\_HAS\_SNAPSHOT).
- This filesystem has a snapshot (RO_COMPAT_HAS_SNAPSHOT).
* - 0x100
- `Quota <Quota>`__ (RO\_COMPAT\_QUOTA).
- `Quota <Quota>`__ (RO_COMPAT_QUOTA).
* - 0x200
- This filesystem supports “bigalloc”, which means that file extents are
tracked in units of clusters (of blocks) instead of blocks
(RO\_COMPAT\_BIGALLOC).
(RO_COMPAT_BIGALLOC).
* - 0x400
- This filesystem supports metadata checksumming.
(RO\_COMPAT\_METADATA\_CSUM; implies RO\_COMPAT\_GDT\_CSUM, though
GDT\_CSUM must not be set)
(RO_COMPAT_METADATA_CSUM; implies RO_COMPAT_GDT_CSUM, though
GDT_CSUM must not be set)
* - 0x800
- Filesystem supports replicas. This feature is neither in the kernel nor
e2fsprogs. (RO\_COMPAT\_REPLICA)
e2fsprogs. (RO_COMPAT_REPLICA)
* - 0x1000
- Read-only filesystem image; the kernel will not mount this image
read-write and most tools will refuse to write to the image.
(RO\_COMPAT\_READONLY)
(RO_COMPAT_READONLY)
* - 0x2000
- Filesystem tracks project quotas. (RO\_COMPAT\_PROJECT)
- Filesystem tracks project quotas. (RO_COMPAT_PROJECT)
* - 0x8000
- Verity inodes may be present on the filesystem. (RO\_COMPAT\_VERITY)
- Verity inodes may be present on the filesystem. (RO_COMPAT_VERITY)
* - 0x10000
- Indicates orphan file may have valid orphan entries and thus we need
to clean them up when mounting the filesystem
(RO\_COMPAT\_ORPHAN\_PRESENT).
(RO_COMPAT_ORPHAN_PRESENT).
.. _super_def_hash:
@ -761,36 +761,36 @@ The ``s_default_mount_opts`` field is any combination of the following:
* - Value
- Description
* - 0x0001
- Print debugging info upon (re)mount. (EXT4\_DEFM\_DEBUG)
- Print debugging info upon (re)mount. (EXT4_DEFM_DEBUG)
* - 0x0002
- New files take the gid of the containing directory (instead of the fsgid
of the current process). (EXT4\_DEFM\_BSDGROUPS)
of the current process). (EXT4_DEFM_BSDGROUPS)
* - 0x0004
- Support userspace-provided extended attributes. (EXT4\_DEFM\_XATTR\_USER)
- Support userspace-provided extended attributes. (EXT4_DEFM_XATTR_USER)
* - 0x0008
- Support POSIX access control lists (ACLs). (EXT4\_DEFM\_ACL)
- Support POSIX access control lists (ACLs). (EXT4_DEFM_ACL)
* - 0x0010
- Do not support 32-bit UIDs. (EXT4\_DEFM\_UID16)
- Do not support 32-bit UIDs. (EXT4_DEFM_UID16)
* - 0x0020
- All data and metadata are commited to the journal.
(EXT4\_DEFM\_JMODE\_DATA)
(EXT4_DEFM_JMODE_DATA)
* - 0x0040
- All data are flushed to the disk before metadata are committed to the
journal. (EXT4\_DEFM\_JMODE\_ORDERED)
journal. (EXT4_DEFM_JMODE_ORDERED)
* - 0x0060
- Data ordering is not preserved; data may be written after the metadata
has been written. (EXT4\_DEFM\_JMODE\_WBACK)
has been written. (EXT4_DEFM_JMODE_WBACK)
* - 0x0100
- Disable write flushes. (EXT4\_DEFM\_NOBARRIER)
- Disable write flushes. (EXT4_DEFM_NOBARRIER)
* - 0x0200
- Track which blocks in a filesystem are metadata and therefore should not
be used as data blocks. This option will be enabled by default on 3.18,
hopefully. (EXT4\_DEFM\_BLOCK\_VALIDITY)
hopefully. (EXT4_DEFM_BLOCK_VALIDITY)
* - 0x0400
- Enable DISCARD support, where the storage device is told about blocks
becoming unused. (EXT4\_DEFM\_DISCARD)
becoming unused. (EXT4_DEFM_DISCARD)
* - 0x0800
- Disable delayed allocation. (EXT4\_DEFM\_NODELALLOC)
- Disable delayed allocation. (EXT4_DEFM_NODELALLOC)
.. _super_flags:
@ -820,12 +820,12 @@ The ``s_encrypt_algos`` list can contain any of the following:
* - Value
- Description
* - 0
- Invalid algorithm (ENCRYPTION\_MODE\_INVALID).
- Invalid algorithm (ENCRYPTION_MODE_INVALID).
* - 1
- 256-bit AES in XTS mode (ENCRYPTION\_MODE\_AES\_256\_XTS).
- 256-bit AES in XTS mode (ENCRYPTION_MODE_AES_256_XTS).
* - 2
- 256-bit AES in GCM mode (ENCRYPTION\_MODE\_AES\_256\_GCM).
- 256-bit AES in GCM mode (ENCRYPTION_MODE_AES_256_GCM).
* - 3
- 256-bit AES in CBC mode (ENCRYPTION\_MODE\_AES\_256\_CBC).
- 256-bit AES in CBC mode (ENCRYPTION_MODE_AES_256_CBC).
Total size of the superblock is 1024 bytes.

15
Documentation/loongarch/introduction.rst
View File

@ -45,10 +45,12 @@ Name Alias Usage Preserved
``$r23``-``$r31`` ``$s0``-``$s8`` Static registers Yes
================= =============== =================== ============
Note: The register ``$r21`` is reserved in the ELF psABI, but used by the Linux
kernel for storing the percpu base address. It normally has no ABI name, but is
called ``$u0`` in the kernel. You may also see ``$v0`` or ``$v1`` in some old code,
however they are deprecated aliases of ``$a0`` and ``$a1`` respectively.
.. Note::
The register ``$r21`` is reserved in the ELF psABI, but used by the Linux
kernel for storing the percpu base address. It normally has no ABI name,
but is called ``$u0`` in the kernel. You may also see ``$v0`` or ``$v1``
in some old code,however they are deprecated aliases of ``$a0`` and ``$a1``
respectively.
FPRs
----
@ -69,8 +71,9 @@ Name Alias Usage Preserved
``$f24``-``$f31`` ``$fs0``-``$fs7`` Static registers Yes
================= ================== =================== ============
Note: You may see ``$fv0`` or ``$fv1`` in some old code, however they are deprecated
aliases of ``$fa0`` and ``$fa1`` respectively.
.. Note::
You may see ``$fv0`` or ``$fv1`` in some old code, however they are
deprecated aliases of ``$fa0`` and ``$fa1`` respectively.
VRs
----

22
Documentation/loongarch/irq-chip-model.rst
View File

@ -145,12 +145,16 @@ Documentation of Loongson's LS7A chipset:
https://github.com/loongson/LoongArch-Documentation/releases/latest/download/Loongson-7A1000-usermanual-2.00-EN.pdf (in English)
Note: CPUINTC is CSR.ECFG/CSR.ESTAT and its interrupt controller described
in Section 7.4 of "LoongArch Reference Manual, Vol 1"; LIOINTC is "Legacy I/O
Interrupts" described in Section 11.1 of "Loongson 3A5000 Processor Reference
Manual"; EIOINTC is "Extended I/O Interrupts" described in Section 11.2 of
"Loongson 3A5000 Processor Reference Manual"; HTVECINTC is "HyperTransport
Interrupts" described in Section 14.3 of "Loongson 3A5000 Processor Reference
Manual"; PCH-PIC/PCH-MSI is "Interrupt Controller" described in Section 5 of
"Loongson 7A1000 Bridge User Manual"; PCH-LPC is "LPC Interrupts" described in
Section 24.3 of "Loongson 7A1000 Bridge User Manual".
.. Note::
- CPUINTC is CSR.ECFG/CSR.ESTAT and its interrupt controller described
in Section 7.4 of "LoongArch Reference Manual, Vol 1";
- LIOINTC is "Legacy I/OInterrupts" described in Section 11.1 of
"Loongson 3A5000 Processor Reference Manual";
- EIOINTC is "Extended I/O Interrupts" described in Section 11.2 of
"Loongson 3A5000 Processor Reference Manual";
- HTVECINTC is "HyperTransport Interrupts" described in Section 14.3 of
"Loongson 3A5000 Processor Reference Manual";
- PCH-PIC/PCH-MSI is "Interrupt Controller" described in Section 5 of
"Loongson 7A1000 Bridge User Manual";
- PCH-LPC is "LPC Interrupts" described in Section 24.3 of
"Loongson 7A1000 Bridge User Manual".

37
Documentation/networking/ip-sysctl.rst
View File

@ -2925,6 +2925,43 @@ plpmtud_probe_interval - INTEGER
Default: 0
reconf_enable - BOOLEAN
Enable or disable extension of Stream Reconfiguration functionality
specified in RFC6525. This extension provides the ability to "reset"
a stream, and it includes the Parameters of "Outgoing/Incoming SSN
Reset", "SSN/TSN Reset" and "Add Outgoing/Incoming Streams".
- 1: Enable extension.
- 0: Disable extension.
Default: 0
intl_enable - BOOLEAN
Enable or disable extension of User Message Interleaving functionality
specified in RFC8260. This extension allows the interleaving of user
messages sent on different streams. With this feature enabled, I-DATA
chunk will replace DATA chunk to carry user messages if also supported
by the peer. Note that to use this feature, one needs to set this option
to 1 and also needs to set socket options SCTP_FRAGMENT_INTERLEAVE to 2
and SCTP_INTERLEAVING_SUPPORTED to 1.
- 1: Enable extension.
- 0: Disable extension.
Default: 0
ecn_enable - BOOLEAN
Control use of Explicit Congestion Notification (ECN) by SCTP.
Like in TCP, ECN is used only when both ends of the SCTP connection
indicate support for it. This feature is useful in avoiding losses
due to congestion by allowing supporting routers to signal congestion
before having to drop packets.
1: Enable ecn.
0: Disable ecn.
Default: 1
``/proc/sys/net/core/*``
========================

2
Documentation/networking/phy.rst
View File

@ -104,7 +104,7 @@ Whenever possible, use the PHY side RGMII delay for these reasons:
* PHY device drivers in PHYLIB being reusable by nature, being able to
configure correctly a specified delay enables more designs with similar delay
requirements to be operate correctly
requirements to be operated correctly
For cases where the PHY is not capable of providing this delay, but the
Ethernet MAC driver is capable of doing so, the correct phy_interface_t value

14
Documentation/translations/zh_CN/loongarch/introduction.rst
View File

@ -46,10 +46,11 @@ LA64中每个寄存器为64位宽。 ``$r0`` 的内容总是固定为0，而其
``$r23``-``$r31`` ``$s0``-``$s8`` 静态寄存器 是
================= =============== =================== ==========
注意：``$r21``寄存器在ELF psABI中保留未使用，但是在Linux内核用于保存每CPU
变量基地址。该寄存器没有ABI命名，不过在内核中称为``$u0``。在一些遗留代码
中有时可能见到``$v0``和``$v1``，它们是``$a0``和``$a1``的别名，属于已经废弃
的用法。
.. note::
注意： ``$r21`` 寄存器在ELF psABI中保留未使用，但是在Linux内核用于保
存每CPU变量基地址。该寄存器没有ABI命名，不过在内核中称为 ``$u0`` 。在
一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 ``$a0`` 和
``$a1`` 的别名，属于已经废弃的用法。
浮点寄存器
----------
@ -68,8 +69,9 @@ LA64中每个寄存器为64位宽。 ``$r0`` 的内容总是固定为0，而其
``$f24``-``$f31`` ``$fs0``-``$fs7`` 静态寄存器 是
================= ================== =================== ==========
注意：在一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是 ``$a0``
和 ``$a1`` 的别名，属于已经废弃的用法。
.. note::
注意：在一些遗留代码中有时可能见到 ``$v0`` 和 ``$v1`` ，它们是
``$a0`` 和 ``$a1`` 的别名，属于已经废弃的用法。
向量寄存器

14
Documentation/translations/zh_CN/loongarch/irq-chip-model.rst
View File

@ -147,9 +147,11 @@ PCH-LPC::
https://github.com/loongson/LoongArch-Documentation/releases/latest/download/Loongson-7A1000-usermanual-2.00-EN.pdf (英文版)
注：CPUINTC即《龙芯架构参考手册卷一》第7.4节所描述的CSR.ECFG/CSR.ESTAT寄存器及其中断
控制逻辑；LIOINTC即《龙芯3A5000处理器使用手册》第11.1节所描述的“传统I/O中断”；EIOINTC
即《龙芯3A5000处理器使用手册》第11.2节所描述的“扩展I/O中断”；HTVECINTC即《龙芯3A5000
处理器使用手册》第14.3节所描述的“HyperTransport中断”；PCH-PIC/PCH-MSI即《龙芯7A1000桥
片用户手册》第5章所描述的“中断控制器”；PCH-LPC即《龙芯7A1000桥片用户手册》第24.3节所
描述的“LPC中断”。
.. note::
- CPUINTC：即《龙芯架构参考手册卷一》第7.4节所描述的CSR.ECFG/CSR.ESTAT寄存器及其
中断控制逻辑；
- LIOINTC：即《龙芯3A5000处理器使用手册》第11.1节所描述的“传统I/O中断”；
- EIOINTC：即《龙芯3A5000处理器使用手册》第11.2节所描述的“扩展I/O中断”；
- HTVECINTC：即《龙芯3A5000处理器使用手册》第14.3节所描述的“HyperTransport中断”；
- PCH-PIC/PCH-MSI：即《龙芯7A1000桥片用户手册》第5章所描述的“中断控制器”；
- PCH-LPC：即《龙芯7A1000桥片用户手册》第24.3节所描述的“LPC中断”。

6
MAINTAINERS
View File

@ -9276,6 +9276,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
F: Documentation/devicetree/bindings/i2c/i2c.txt
F: Documentation/i2c/
F: drivers/i2c/*
F: include/dt-bindings/i2c/i2c.h
F: include/linux/i2c-dev.h
F: include/linux/i2c-smbus.h
F: include/linux/i2c.h
@ -9291,6 +9292,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
F: Documentation/devicetree/bindings/i2c/
F: drivers/i2c/algos/
F: drivers/i2c/busses/
F: include/dt-bindings/i2c/
I2C-TAOS-EVM DRIVER
M: Jean Delvare <jdelvare@suse.com>
@ -10872,7 +10874,6 @@ F: arch/riscv/include/asm/kvm*
F: arch/riscv/include/uapi/asm/kvm*
F: arch/riscv/kvm/
F: tools/testing/selftests/kvm/*/riscv/
F: tools/testing/selftests/kvm/riscv/
KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
M: Christian Borntraeger <borntraeger@linux.ibm.com>
@ -13801,6 +13802,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
F: Documentation/devicetree/bindings/net/
F: drivers/connector/
F: drivers/net/
F: include/dt-bindings/net/
F: include/linux/etherdevice.h
F: include/linux/fcdevice.h
F: include/linux/fddidevice.h
@ -19305,7 +19307,7 @@ R: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
R: Mika Westerberg <mika.westerberg@linux.intel.com>
R: Jan Dabros <jsd@semihalf.com>
L: linux-i2c@vger.kernel.org
S: Maintained
S: Supported
F: drivers/i2c/busses/i2c-designware-*
SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER

2
Makefile
View File

@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 19
SUBLEVEL = 0
EXTRAVERSION = -rc2
EXTRAVERSION = -rc3
NAME = Superb Owl
# *DOCUMENTATION*

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

@ -60,7 +60,7 @@ int irq_select_affinity(unsigned int irq)
cpu = (cpu < (NR_CPUS-1) ? cpu + 1 : 0);
last_cpu = cpu;
cpumask_copy(irq_data_get_affinity_mask(data), cpumask_of(cpu));
irq_data_update_affinity(data, cpumask_of(cpu));
chip->irq_set_affinity(data, cpumask_of(cpu), false);
return 0;
}

5
arch/arm/boot/dts/at91-sama5d3_ksz9477_evb.dts
View File

@ -120,26 +120,31 @@
port@0 {
reg = <0>;
label = "lan1";
phy-mode = "internal";
};
port@1 {
reg = <1>;
label = "lan2";
phy-mode = "internal";
};
port@2 {
reg = <2>;
label = "lan3";
phy-mode = "internal";
};
port@3 {
reg = <3>;
label = "lan4";
phy-mode = "internal";
};
port@4 {
reg = <4>;
label = "lan5";
phy-mode = "internal";
};
port@5 {

2
arch/arm/mach-hisi/Kconfig
View File

@ -40,7 +40,7 @@ config ARCH_HIP04
select HAVE_ARM_ARCH_TIMER
select MCPM if SMP
select MCPM_QUAD_CLUSTER if SMP
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP
help
Support for Hisilicon HiP04 SoC family

2
arch/arm/mach-mmp/mmp2.h
View File

@ -5,13 +5,13 @@
#include <linux/platform_data/pxa_sdhci.h>
extern void mmp2_timer_init(void);
extern void __init mmp2_init_icu(void);
extern void __init mmp2_init_irq(void);
extern void mmp2_clear_pmic_int(void);
#include <linux/i2c.h>
#include <linux/platform_data/i2c-pxa.h>
#include <linux/platform_data/dma-mmp_tdma.h>
#include <linux/irqchip/mmp.h>
#include "devices.h"

2
arch/arm/mach-mmp/pxa168.h
View File

@ -5,7 +5,6 @@
#include <linux/reboot.h>
extern void pxa168_timer_init(void);
extern void __init icu_init_irq(void);
extern void __init pxa168_init_irq(void);
extern void pxa168_restart(enum reboot_mode, const char *);
extern void pxa168_clear_keypad_wakeup(void);
@ -18,6 +17,7 @@ extern void pxa168_clear_keypad_wakeup(void);
#include <linux/pxa168_eth.h>
#include <linux/platform_data/mv_usb.h>
#include <linux/soc/mmp/cputype.h>
#include <linux/irqchip/mmp.h>
#include "devices.h"

2
arch/arm/mach-mmp/pxa910.h
View File

@ -3,13 +3,13 @@
#define __ASM_MACH_PXA910_H
extern void pxa910_timer_init(void);
extern void __init icu_init_irq(void);
extern void __init pxa910_init_irq(void);
#include <linux/i2c.h>
#include <linux/platform_data/i2c-pxa.h>
#include <linux/platform_data/mtd-nand-pxa3xx.h>
#include <video/mmp_disp.h>
#include <linux/irqchip/mmp.h>
#include "devices.h"

5
arch/arm64/include/asm/kvm_host.h
View File

@ -362,11 +362,6 @@ struct kvm_vcpu_arch {
struct arch_timer_cpu timer_cpu;
struct kvm_pmu pmu;
/*
* Anything that is not used directly from assembly code goes
* here.
*/
/*
* Guest registers we preserve during guest debugging.
*

3
arch/arm64/include/asm/virt.h
View File

@ -113,6 +113,9 @@ static __always_inline bool has_vhe(void)
/*
* Code only run in VHE/NVHE hyp context can assume VHE is present or
* absent. Otherwise fall back to caps.
* This allows the compiler to discard VHE-specific code from the
* nVHE object, reducing the number of external symbol references
* needed to link.
*/
if (is_vhe_hyp_code())
return true;

11
arch/arm64/kernel/cpufeature.c
View File

@ -1974,15 +1974,7 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap)
#ifdef CONFIG_KVM
static bool is_kvm_protected_mode(const struct arm64_cpu_capabilities *entry, int __unused)
{
if (kvm_get_mode() != KVM_MODE_PROTECTED)
return false;
if (is_kernel_in_hyp_mode()) {
pr_warn("Protected KVM not available with VHE\n");
return false;
}
return true;
return kvm_get_mode() == KVM_MODE_PROTECTED;
}
#endif /* CONFIG_KVM */
@ -3109,7 +3101,6 @@ void cpu_set_feature(unsigned int num)
WARN_ON(num >= MAX_CPU_FEATURES);
elf_hwcap |= BIT(num);
}
EXPORT_SYMBOL_GPL(cpu_set_feature);
bool cpu_have_feature(unsigned int num)
{

1
arch/arm64/kernel/entry-ftrace.S
View File

@ -102,7 +102,6 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
* x19-x29 per the AAPCS, and we created frame records upon entry, so we need
* to restore x0-x8, x29, and x30.
*/
ftrace_common_return:
/* Restore function arguments */
ldp x0, x1, [sp]
ldp x2, x3, [sp, #S_X2]

147
arch/arm64/kernel/ftrace.c
View File

@ -77,6 +77,66 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr)
return NULL;
}
/*
* Find the address the callsite must branch to in order to reach '*addr'.
*
* Due to the limited range of 'BL' instructions, modules may be placed too far
* away to branch directly and must use a PLT.
*
* Returns true when '*addr' contains a reachable target address, or has been
* modified to contain a PLT address. Returns false otherwise.
*/
static bool ftrace_find_callable_addr(struct dyn_ftrace *rec,
struct module *mod,
unsigned long *addr)
{
unsigned long pc = rec->ip;
long offset = (long)*addr - (long)pc;
struct plt_entry *plt;
/*
* When the target is within range of the 'BL' instruction, use 'addr'
* as-is and branch to that directly.
*/
if (offset >= -SZ_128M && offset < SZ_128M)
return true;
/*
* When the target is outside of the range of a 'BL' instruction, we
* must use a PLT to reach it. We can only place PLTs for modules, and
* only when module PLT support is built-in.
*/
if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
return false;
/*
* 'mod' is only set at module load time, but if we end up
* dealing with an out-of-range condition, we can assume it
* is due to a module being loaded far away from the kernel.
*
* NOTE: __module_text_address() must be called with preemption
* disabled, but we can rely on ftrace_lock to ensure that 'mod'
* retains its validity throughout the remainder of this code.
*/
if (!mod) {
preempt_disable();
mod = __module_text_address(pc);
preempt_enable();
}
if (WARN_ON(!mod))
return false;
plt = get_ftrace_plt(mod, *addr);
if (!plt) {
pr_err("ftrace: no module PLT for %ps\n", (void *)*addr);
return false;
}
*addr = (unsigned long)plt;
return true;
}
/*
* Turn on the call to ftrace_caller() in instrumented function
*/
@ -84,40 +144,9 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
{
unsigned long pc = rec->ip;
u32 old, new;
long offset = (long)pc - (long)addr;
if (offset < -SZ_128M || offset >= SZ_128M) {
struct module *mod;
struct plt_entry *plt;
if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
return -EINVAL;
/*
* On kernels that support module PLTs, the offset between the
* branch instruction and its target may legally exceed the
* range of an ordinary relative 'bl' opcode. In this case, we
* need to branch via a trampoline in the module.
*
* NOTE: __module_text_address() must be called with preemption
* disabled, but we can rely on ftrace_lock to ensure that 'mod'
* retains its validity throughout the remainder of this code.
*/
preempt_disable();
mod = __module_text_address(pc);
preempt_enable();
if (WARN_ON(!mod))
return -EINVAL;
plt = get_ftrace_plt(mod, addr);
if (!plt) {
pr_err("ftrace: no module PLT for %ps\n", (void *)addr);
return -EINVAL;
}
addr = (unsigned long)plt;
}
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
old = aarch64_insn_gen_nop();
new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
@ -132,6 +161,11 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
unsigned long pc = rec->ip;
u32 old, new;
if (!ftrace_find_callable_addr(rec, NULL, &old_addr))
return -EINVAL;
if (!ftrace_find_callable_addr(rec, NULL, &addr))
return -EINVAL;
old = aarch64_insn_gen_branch_imm(pc, old_addr,
AARCH64_INSN_BRANCH_LINK);
new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
@ -181,54 +215,15 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec,
unsigned long addr)
{
unsigned long pc = rec->ip;
bool validate = true;
u32 old = 0, new;
long offset = (long)pc - (long)addr;
if (offset < -SZ_128M || offset >= SZ_128M) {
u32 replaced;
if (!IS_ENABLED(CONFIG_ARM64_MODULE_PLTS))
return -EINVAL;
/*
* 'mod' is only set at module load time, but if we end up
* dealing with an out-of-range condition, we can assume it
* is due to a module being loaded far away from the kernel.
*/
if (!mod) {
preempt_disable();
mod = __module_text_address(pc);
preempt_enable();
if (WARN_ON(!mod))
return -EINVAL;
}
/*
* The instruction we are about to patch may be a branch and
* link instruction that was redirected via a PLT entry. In
* this case, the normal validation will fail, but we can at
* least check that we are dealing with a branch and link
* instruction that points into the right module.
*/
if (aarch64_insn_read((void *)pc, &replaced))
return -EFAULT;
if (!aarch64_insn_is_bl(replaced) ||
!within_module(pc + aarch64_get_branch_offset(replaced),
mod))
return -EINVAL;
validate = false;
} else {
old = aarch64_insn_gen_branch_imm(pc, addr,
AARCH64_INSN_BRANCH_LINK);
}
if (!ftrace_find_callable_addr(rec, mod, &addr))
return -EINVAL;
old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK);
new = aarch64_insn_gen_nop();
return ftrace_modify_code(pc, old, new, validate);
return ftrace_modify_code(pc, old, new, true);
}
void arch_ftrace_update_code(int command)

11
arch/arm64/kernel/setup.c
View File

@ -303,14 +303,13 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
early_fixmap_init();
early_ioremap_init();
/*
* Initialise the static keys early as they may be enabled by the
* cpufeature code, early parameters, and DT setup.
*/
jump_label_init();
setup_machine_fdt(__fdt_pointer);
/*
* Initialise the static keys early as they may be enabled by the
* cpufeature code and early parameters.
*/
jump_label_init();
parse_early_param();
/*

3
arch/arm64/kvm/arch_timer.c
View File

@ -1230,6 +1230,9 @@ bool kvm_arch_timer_get_input_level(int vintid)
struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
struct arch_timer_context *timer;
if (WARN(!vcpu, "No vcpu context!\n"))
return false;
if (vintid == vcpu_vtimer(vcpu)->irq.irq)
timer = vcpu_vtimer(vcpu);
else if (vintid == vcpu_ptimer(vcpu)->irq.irq)

10
arch/arm64/kvm/arm.c
View File

@ -150,8 +150,10 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (ret)
goto out_free_stage2_pgd;
if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL))
if (!zalloc_cpumask_var(&kvm->arch.supported_cpus, GFP_KERNEL)) {
ret = -ENOMEM;
goto out_free_stage2_pgd;
}
cpumask_copy(kvm->arch.supported_cpus, cpu_possible_mask);
kvm_vgic_early_init(kvm);
@ -2271,7 +2273,11 @@ static int __init early_kvm_mode_cfg(char *arg)
return -EINVAL;
if (strcmp(arg, "protected") == 0) {
kvm_mode = KVM_MODE_PROTECTED;
if (!is_kernel_in_hyp_mode())
kvm_mode = KVM_MODE_PROTECTED;
else
pr_warn_once("Protected KVM not available with VHE\n");
return 0;
}

2
arch/arm64/kvm/fpsimd.c
View File

@ -80,6 +80,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
vcpu->arch.flags &= ~KVM_ARM64_FP_ENABLED;
vcpu->arch.flags |= KVM_ARM64_FP_HOST;
vcpu->arch.flags &= ~KVM_ARM64_HOST_SVE_ENABLED;
if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
vcpu->arch.flags |= KVM_ARM64_HOST_SVE_ENABLED;
@ -93,6 +94,7 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
* operations. Do this for ZA as well for now for simplicity.
*/
if (system_supports_sme()) {
vcpu->arch.flags &= ~KVM_ARM64_HOST_SME_ENABLED;
if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
vcpu->arch.flags |= KVM_ARM64_HOST_SME_ENABLED;

4
arch/arm64/kvm/hyp/nvhe/mem_protect.c
View File

@ -314,15 +314,11 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
enum kvm_pgtable_prot prot)
{
hyp_assert_lock_held(&host_kvm.lock);
return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
}
int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
{
hyp_assert_lock_held(&host_kvm.lock);
return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt,
addr, size, &host_s2_pool, owner_id);
}

42
arch/arm64/kvm/hyp/nvhe/sys_regs.c
View File

@ -243,15 +243,9 @@ u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
case SYS_ID_AA64MMFR2_EL1:
return get_pvm_id_aa64mmfr2(vcpu);
default:
/*
* Should never happen because all cases are covered in
* pvm_sys_reg_descs[].
*/
WARN_ON(1);
break;
/* Unhandled ID register, RAZ */
return 0;
}
return 0;
}
static u64 read_id_reg(const struct kvm_vcpu *vcpu,
@ -332,6 +326,16 @@ static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
/* Mark the specified system register as an AArch64 feature id register. */
#define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }
/*
* sys_reg_desc initialiser for architecturally unallocated cpufeature ID
* register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2
* (1 <= crm < 8, 0 <= Op2 < 8).
*/
#define ID_UNALLOCATED(crm, op2) { \
Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \
.access = pvm_access_id_aarch64, \
}
/* Mark the specified system register as Read-As-Zero/Write-Ignored */
#define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }
@ -375,24 +379,46 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = {
AARCH32(SYS_MVFR0_EL1),
AARCH32(SYS_MVFR1_EL1),
AARCH32(SYS_MVFR2_EL1),
ID_UNALLOCATED(3,3),
AARCH32(SYS_ID_PFR2_EL1),
AARCH32(SYS_ID_DFR1_EL1),
AARCH32(SYS_ID_MMFR5_EL1),
ID_UNALLOCATED(3,7),
/* AArch64 ID registers */
/* CRm=4 */
AARCH64(SYS_ID_AA64PFR0_EL1),
AARCH64(SYS_ID_AA64PFR1_EL1),
ID_UNALLOCATED(4,2),
ID_UNALLOCATED(4,3),
AARCH64(SYS_ID_AA64ZFR0_EL1),
ID_UNALLOCATED(4,5),
ID_UNALLOCATED(4,6),
ID_UNALLOCATED(4,7),
AARCH64(SYS_ID_AA64DFR0_EL1),
AARCH64(SYS_ID_AA64DFR1_EL1),
ID_UNALLOCATED(5,2),
ID_UNALLOCATED(5,3),
AARCH64(SYS_ID_AA64AFR0_EL1),
AARCH64(SYS_ID_AA64AFR1_EL1),
ID_UNALLOCATED(5,6),
ID_UNALLOCATED(5,7),
AARCH64(SYS_ID_AA64ISAR0_EL1),
AARCH64(SYS_ID_AA64ISAR1_EL1),
AARCH64(SYS_ID_AA64ISAR2_EL1),
ID_UNALLOCATED(6,3),
ID_UNALLOCATED(6,4),
ID_UNALLOCATED(6,5),
ID_UNALLOCATED(6,6),
ID_UNALLOCATED(6,7),
AARCH64(SYS_ID_AA64MMFR0_EL1),
AARCH64(SYS_ID_AA64MMFR1_EL1),
AARCH64(SYS_ID_AA64MMFR2_EL1),
ID_UNALLOCATED(7,3),
ID_UNALLOCATED(7,4),
ID_UNALLOCATED(7,5),
ID_UNALLOCATED(7,6),
ID_UNALLOCATED(7,7),
/* Scalable Vector Registers are restricted. */

4
arch/arm64/kvm/vgic/vgic-mmio-v2.c
View File

@ -429,11 +429,11 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = {
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET,
vgic_mmio_read_pending, vgic_mmio_write_spending,
NULL, vgic_uaccess_write_spending, 1,
vgic_uaccess_read_pending, vgic_uaccess_write_spending, 1,
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR,
vgic_mmio_read_pending, vgic_mmio_write_cpending,
NULL, vgic_uaccess_write_cpending, 1,
vgic_uaccess_read_pending, vgic_uaccess_write_cpending, 1,
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET,
vgic_mmio_read_active, vgic_mmio_write_sactive,

40
arch/arm64/kvm/vgic/vgic-mmio-v3.c
View File

@ -353,42 +353,6 @@ static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
return 0;
}
static unsigned long vgic_v3_uaccess_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
int i;
/*
* pending state of interrupt is latched in pending_latch variable.
* Userspace will save and restore pending state and line_level
* separately.
* Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
* for handling of ISPENDR and ICPENDR.
*/
for (i = 0; i < len * 8; i++) {
struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
bool state = irq->pending_latch;
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
int err;
err = irq_get_irqchip_state(irq->host_irq,
IRQCHIP_STATE_PENDING,
&state);
WARN_ON(err);
}
if (state)
value |= (1U << i);
vgic_put_irq(vcpu->kvm, irq);
}
return value;
}
static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val)
@ -666,7 +630,7 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = {
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
vgic_mmio_read_pending, vgic_mmio_write_spending,
vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR,
vgic_mmio_read_pending, vgic_mmio_write_cpending,
@ -750,7 +714,7 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = {
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0,
vgic_mmio_read_pending, vgic_mmio_write_spending,
vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
vgic_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
VGIC_ACCESS_32bit),
REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0,
vgic_mmio_read_pending, vgic_mmio_write_cpending,

40
arch/arm64/kvm/vgic/vgic-mmio.c
View File

@ -226,8 +226,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
return 0;
}
unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
static unsigned long __read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
bool is_user)
{
u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
u32 value = 0;
@ -239,6 +240,15 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
unsigned long flags;
bool val;
/*
* When used from userspace with a GICv3 model:
*
* Pending state of interrupt is latched in pending_latch
* variable. Userspace will save and restore pending state
* and line_level separately.
* Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
* for handling of ISPENDR and ICPENDR.
*/
raw_spin_lock_irqsave(&irq->irq_lock, flags);
if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
int err;
@ -248,10 +258,20 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
IRQCHIP_STATE_PENDING,
&val);
WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
} else if (vgic_irq_is_mapped_level(irq)) {
} else if (!is_user && vgic_irq_is_mapped_level(irq)) {
val = vgic_get_phys_line_level(irq);
} else {
val = irq_is_pending(irq);
switch (vcpu->kvm->arch.vgic.vgic_model) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
if (is_user) {
val = irq->pending_latch;
break;
}
fallthrough;
default:
val = irq_is_pending(irq);
break;
}
}
value |= ((u32)val << i);
@ -263,6 +283,18 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
return value;
}
unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return __read_pending(vcpu, addr, len, false);
}
unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len)
{
return __read_pending(vcpu, addr, len, true);
}
static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
return (vgic_irq_is_sgi(irq->intid) &&

3
arch/arm64/kvm/vgic/vgic-mmio.h
View File

@ -149,6 +149,9 @@ int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len);
unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len);
void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
gpa_t addr, unsigned int len,
unsigned long val);

2
arch/arm64/kvm/vmid.c
View File

@ -66,7 +66,7 @@ static void flush_context(void)
* the next context-switch, we broadcast TLB flush + I-cache
* invalidation over the inner shareable domain on rollover.
*/
kvm_call_hyp(__kvm_flush_vm_context);
kvm_call_hyp(__kvm_flush_vm_context);
}
static bool check_update_reserved_vmid(u64 vmid, u64 newvmid)

2
arch/arm64/mm/cache.S
View File

@ -218,8 +218,6 @@ SYM_FUNC_ALIAS(__dma_flush_area, __pi___dma_flush_area)
*/
SYM_FUNC_START(__pi___dma_map_area)
add x1, x0, x1
cmp w2, #DMA_FROM_DEVICE
b.eq __pi_dcache_inval_poc
b __pi_dcache_clean_poc
SYM_FUNC_END(__pi___dma_map_area)
SYM_FUNC_ALIAS(__dma_map_area, __pi___dma_map_area)

2
arch/ia64/kernel/iosapic.c
View File

@ -834,7 +834,7 @@ iosapic_unregister_intr (unsigned int gsi)
if (iosapic_intr_info[irq].count == 0) {
#ifdef CONFIG_SMP
/* Clear affinity */
cpumask_setall(irq_get_affinity_mask(irq));
irq_data_update_affinity(irq_get_irq_data(irq), cpu_all_mask);
#endif
/* Clear the interrupt information */
iosapic_intr_info[irq].dest = 0;

4
arch/ia64/kernel/irq.c
View File

@ -57,8 +57,8 @@ static char irq_redir [NR_IRQS]; // = { [0 ... NR_IRQS-1] = 1 };
void set_irq_affinity_info (unsigned int irq, int hwid, int redir)
{
if (irq < NR_IRQS) {
cpumask_copy(irq_get_affinity_mask(irq),
cpumask_of(cpu_logical_id(hwid)));
irq_data_update_affinity(irq_get_irq_data(irq),
cpumask_of(cpu_logical_id(hwid)));
irq_redir[irq] = (char) (redir & 0xff);
}
}

4
arch/ia64/kernel/msi_ia64.c
View File

@ -37,7 +37,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
msg.data = data;
pci_write_msi_msg(irq, &msg);
cpumask_copy(irq_data_get_affinity_mask(idata), cpumask_of(cpu));
irq_data_update_affinity(idata, cpumask_of(cpu));
return 0;
}
@ -132,7 +132,7 @@ static int dmar_msi_set_affinity(struct irq_data *data,
msg.address_lo |= MSI_ADDR_DEST_ID_CPU(cpu_physical_id(cpu));
dmar_msi_write(irq, &msg);
cpumask_copy(irq_data_get_affinity_mask(data), mask);
irq_data_update_affinity(data, mask);
return 0;
}

1
arch/loongarch/Kconfig
View File

@ -2,6 +2,7 @@
config LOONGARCH
bool
default y
select ACPI_GENERIC_GSI if ACPI
select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
select ARCH_BINFMT_ELF_STATE
select ARCH_ENABLE_MEMORY_HOTPLUG

142
arch/loongarch/include/asm/acpi.h
View File

@ -31,6 +31,148 @@ static inline bool acpi_has_cpu_in_madt(void)
extern struct list_head acpi_wakeup_device_list;
/*
* Temporary definitions until the core ACPICA code gets updated (see
* 1656837932-18257-1-git-send-email-lvjianmin@loongson.cn and its
* follow-ups for the "rationale").
*
* Once the "legal reasons" are cleared and that the code is merged,
* this can be dropped entierely.
*/
#if (ACPI_CA_VERSION == 0x20220331 && !defined(LOONGARCH_ACPICA_EXT))
#define LOONGARCH_ACPICA_EXT 1
#define ACPI_MADT_TYPE_CORE_PIC 17
#define ACPI_MADT_TYPE_LIO_PIC 18
#define ACPI_MADT_TYPE_HT_PIC 19
#define ACPI_MADT_TYPE_EIO_PIC 20
#define ACPI_MADT_TYPE_MSI_PIC 21
#define ACPI_MADT_TYPE_BIO_PIC 22
#define ACPI_MADT_TYPE_LPC_PIC 23
/* Values for Version field above */
enum acpi_madt_core_pic_version {
ACPI_MADT_CORE_PIC_VERSION_NONE = 0,
ACPI_MADT_CORE_PIC_VERSION_V1 = 1,
ACPI_MADT_CORE_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_lio_pic_version {
ACPI_MADT_LIO_PIC_VERSION_NONE = 0,
ACPI_MADT_LIO_PIC_VERSION_V1 = 1,
ACPI_MADT_LIO_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_eio_pic_version {
ACPI_MADT_EIO_PIC_VERSION_NONE = 0,
ACPI_MADT_EIO_PIC_VERSION_V1 = 1,
ACPI_MADT_EIO_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_ht_pic_version {
ACPI_MADT_HT_PIC_VERSION_NONE = 0,
ACPI_MADT_HT_PIC_VERSION_V1 = 1,
ACPI_MADT_HT_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_bio_pic_version {
ACPI_MADT_BIO_PIC_VERSION_NONE = 0,
ACPI_MADT_BIO_PIC_VERSION_V1 = 1,
ACPI_MADT_BIO_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_msi_pic_version {
ACPI_MADT_MSI_PIC_VERSION_NONE = 0,
ACPI_MADT_MSI_PIC_VERSION_V1 = 1,
ACPI_MADT_MSI_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
enum acpi_madt_lpc_pic_version {
ACPI_MADT_LPC_PIC_VERSION_NONE = 0,
ACPI_MADT_LPC_PIC_VERSION_V1 = 1,
ACPI_MADT_LPC_PIC_VERSION_RESERVED = 2 /* 2 and greater are reserved */
};
#pragma pack(1)
/* Core Interrupt Controller */
struct acpi_madt_core_pic {
struct acpi_subtable_header header;
u8 version;
u32 processor_id;
u32 core_id;
u32 flags;
};
/* Legacy I/O Interrupt Controller */
struct acpi_madt_lio_pic {
struct acpi_subtable_header header;
u8 version;
u64 address;
u16 size;
u8 cascade[2];
u32 cascade_map[2];
};
/* Extend I/O Interrupt Controller */
struct acpi_madt_eio_pic {
struct acpi_subtable_header header;
u8 version;
u8 cascade;
u8 node;
u64 node_map;
};
/* HT Interrupt Controller */
struct acpi_madt_ht_pic {
struct acpi_subtable_header header;
u8 version;
u64 address;
u16 size;
u8 cascade[8];
};
/* Bridge I/O Interrupt Controller */
struct acpi_madt_bio_pic {
struct acpi_subtable_header header;
u8 version;
u64 address;
u16 size;
u16 id;
u16 gsi_base;
};
/* MSI Interrupt Controller */
struct acpi_madt_msi_pic {
struct acpi_subtable_header header;
u8 version;
u64 msg_address;
u32 start;
u32 count;
};
/* LPC Interrupt Controller */
struct acpi_madt_lpc_pic {
struct acpi_subtable_header header;
u8 version;
u64 address;
u16 size;
u8 cascade;
};
#pragma pack()
#endif
#endif /* !CONFIG_ACPI */
#define ACPI_TABLE_UPGRADE_MAX_PHYS ARCH_LOW_ADDRESS_LIMIT

51
arch/loongarch/include/asm/irq.h
View File

@ -35,9 +35,6 @@ static inline bool on_irq_stack(int cpu, unsigned long sp)
return (low <= sp && sp <= high);
}
int get_ipi_irq(void);
int get_pmc_irq(void);
int get_timer_irq(void);
void spurious_interrupt(void);
#define NR_IRQS_LEGACY 16
@ -48,6 +45,14 @@ void arch_trigger_cpumask_backtrace(const struct cpumask *mask, bool exclude_sel
#define MAX_IO_PICS 2
#define NR_IRQS (64 + (256 * MAX_IO_PICS))
struct acpi_vector_group {
int node;
int pci_segment;
struct irq_domain *parent;
};
extern struct acpi_vector_group pch_group[MAX_IO_PICS];
extern struct acpi_vector_group msi_group[MAX_IO_PICS];
#define CORES_PER_EIO_NODE 4
#define LOONGSON_CPU_UART0_VEC 10 /* CPU UART0 */
@ -79,15 +84,6 @@ void arch_trigger_cpumask_backtrace(const struct cpumask *mask, bool exclude_sel
extern int find_pch_pic(u32 gsi);
extern int eiointc_get_node(int id);
static inline void eiointc_enable(void)
{
uint64_t misc;
misc = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC);
misc |= IOCSR_MISC_FUNC_EXT_IOI_EN;
iocsr_write64(misc, LOONGARCH_IOCSR_MISC_FUNC);
}
struct acpi_madt_lio_pic;
struct acpi_madt_eio_pic;
struct acpi_madt_ht_pic;
@ -95,21 +91,29 @@ struct acpi_madt_bio_pic;
struct acpi_madt_msi_pic;
struct acpi_madt_lpc_pic;
struct irq_domain *loongarch_cpu_irq_init(void);
struct irq_domain *liointc_acpi_init(struct irq_domain *parent,
int liointc_acpi_init(struct irq_domain *parent,
struct acpi_madt_lio_pic *acpi_liointc);
struct irq_domain *eiointc_acpi_init(struct irq_domain *parent,
int eiointc_acpi_init(struct irq_domain *parent,
struct acpi_madt_eio_pic *acpi_eiointc);
struct irq_domain *htvec_acpi_init(struct irq_domain *parent,
struct acpi_madt_ht_pic *acpi_htvec);
struct irq_domain *pch_lpc_acpi_init(struct irq_domain *parent,
int pch_lpc_acpi_init(struct irq_domain *parent,
struct acpi_madt_lpc_pic *acpi_pchlpc);
struct irq_domain *pch_msi_acpi_init(struct irq_domain *parent,
#if IS_ENABLED(CONFIG_LOONGSON_PCH_MSI)
int pch_msi_acpi_init(struct irq_domain *parent,
struct acpi_madt_msi_pic *acpi_pchmsi);
struct irq_domain *pch_pic_acpi_init(struct irq_domain *parent,
#else
static inline int pch_msi_acpi_init(struct irq_domain *parent,
struct acpi_madt_msi_pic *acpi_pchmsi)
{
return 0;
}
#endif
int pch_pic_acpi_init(struct irq_domain *parent,
struct acpi_madt_bio_pic *acpi_pchpic);
int find_pch_pic(u32 gsi);
struct fwnode_handle *get_pch_msi_handle(int pci_segment);
extern struct acpi_madt_lio_pic *acpi_liointc;
extern struct acpi_madt_eio_pic *acpi_eiointc[MAX_IO_PICS];
@ -119,11 +123,10 @@ extern struct acpi_madt_lpc_pic *acpi_pchlpc;
extern struct acpi_madt_msi_pic *acpi_pchmsi[MAX_IO_PICS];
extern struct acpi_madt_bio_pic *acpi_pchpic[MAX_IO_PICS];
extern struct irq_domain *cpu_domain;
extern struct irq_domain *liointc_domain;
extern struct irq_domain *pch_lpc_domain;
extern struct irq_domain *pch_msi_domain[MAX_IO_PICS];
extern struct irq_domain *pch_pic_domain[MAX_IO_PICS];
extern struct fwnode_handle *cpuintc_handle;
extern struct fwnode_handle *liointc_handle;
extern struct fwnode_handle *pch_lpc_handle;
extern struct fwnode_handle *pch_pic_handle[MAX_IO_PICS];
extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev);

65
arch/loongarch/kernel/acpi.c
View File

@ -25,7 +25,6 @@ EXPORT_SYMBOL(acpi_pci_disabled);
int acpi_strict = 1; /* We have no workarounds on LoongArch */
int num_processors;
int disabled_cpus;
enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PLATFORM;
u64 acpi_saved_sp;
@ -33,70 +32,6 @@ u64 acpi_saved_sp;
#define PREFIX "ACPI: "
int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
{
if (irqp != NULL)
*irqp = acpi_register_gsi(NULL, gsi, -1, -1);
return (*irqp >= 0) ? 0 : -EINVAL;
}
EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
int acpi_isa_irq_to_gsi(unsigned int isa_irq, u32 *gsi)
{
if (gsi)
*gsi = isa_irq;
return 0;
}
/*
* success: return IRQ number (>=0)
* failure: return < 0
*/
int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
{
struct irq_fwspec fwspec;
switch (gsi) {
case GSI_MIN_CPU_IRQ ... GSI_MAX_CPU_IRQ:
fwspec.fwnode = liointc_domain->fwnode;
fwspec.param[0] = gsi - GSI_MIN_CPU_IRQ;
fwspec.param_count = 1;
return irq_create_fwspec_mapping(&fwspec);
case GSI_MIN_LPC_IRQ ... GSI_MAX_LPC_IRQ:
if (!pch_lpc_domain)
return -EINVAL;
fwspec.fwnode = pch_lpc_domain->fwnode;
fwspec.param[0] = gsi - GSI_MIN_LPC_IRQ;
fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity);
fwspec.param_count = 2;
return irq_create_fwspec_mapping(&fwspec);
case GSI_MIN_PCH_IRQ ... GSI_MAX_PCH_IRQ:
if (!pch_pic_domain[0])
return -EINVAL;
fwspec.fwnode = pch_pic_domain[0]->fwnode;
fwspec.param[0] = gsi - GSI_MIN_PCH_IRQ;
fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH;
fwspec.param_count = 2;
return irq_create_fwspec_mapping(&fwspec);
}
return -EINVAL;
}
EXPORT_SYMBOL_GPL(acpi_register_gsi);
void acpi_unregister_gsi(u32 gsi)
{
}
EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
void __init __iomem * __acpi_map_table(unsigned long phys, unsigned long size)
{

58
arch/loongarch/kernel/irq.c
View File

@ -25,12 +25,8 @@ DEFINE_PER_CPU(unsigned long, irq_stack);
DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
struct irq_domain *cpu_domain;
struct irq_domain *liointc_domain;
struct irq_domain *pch_lpc_domain;
struct irq_domain *pch_msi_domain[MAX_IO_PICS];
struct irq_domain *pch_pic_domain[MAX_IO_PICS];
struct acpi_vector_group pch_group[MAX_IO_PICS];
struct acpi_vector_group msi_group[MAX_IO_PICS];
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
* each architecture has to answer this themselves.
@ -56,6 +52,51 @@ int arch_show_interrupts(struct seq_file *p, int prec)
return 0;
}
static int __init early_pci_mcfg_parse(struct acpi_table_header *header)
{
struct acpi_table_mcfg *mcfg;
struct acpi_mcfg_allocation *mptr;
int i, n;
if (header->length < sizeof(struct acpi_table_mcfg))
return -EINVAL;
n = (header->length - sizeof(struct acpi_table_mcfg)) /
sizeof(struct acpi_mcfg_allocation);
mcfg = (struct acpi_table_mcfg *)header;
mptr = (struct acpi_mcfg_allocation *) &mcfg[1];
for (i = 0; i < n; i++, mptr++) {
msi_group[i].pci_segment = mptr->pci_segment;
pch_group[i].node = msi_group[i].node = (mptr->address >> 44) & 0xf;
}
return 0;
}
static void __init init_vec_parent_group(void)
{
int i;
for (i = 0; i < MAX_IO_PICS; i++) {
msi_group[i].pci_segment = -1;
msi_group[i].node = -1;
pch_group[i].node = -1;
}
acpi_table_parse(ACPI_SIG_MCFG, early_pci_mcfg_parse);
}
static int __init get_ipi_irq(void)
{
struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
if (d)
return irq_create_mapping(d, EXCCODE_IPI - EXCCODE_INT_START);
return -EINVAL;
}
void __init init_IRQ(void)
{
int i;
@ -69,9 +110,12 @@ void __init init_IRQ(void)
clear_csr_ecfg(ECFG0_IM);
clear_csr_estat(ESTATF_IP);
init_vec_parent_group();
irqchip_init();
#ifdef CONFIG_SMP
ipi_irq = EXCCODE_IPI - EXCCODE_INT_START;
ipi_irq = get_ipi_irq();
if (ipi_irq < 0)
panic("IPI IRQ mapping failed\n");
irq_set_percpu_devid(ipi_irq);
r = request_percpu_irq(ipi_irq, loongson3_ipi_interrupt, "IPI", &ipi_dummy_dev);
if (r < 0)

14
arch/loongarch/kernel/time.c
View File

@ -123,6 +123,16 @@ void sync_counter(void)
csr_write64(-init_timeval, LOONGARCH_CSR_CNTC);
}
static int get_timer_irq(void)
{
struct irq_domain *d = irq_find_matching_fwnode(cpuintc_handle, DOMAIN_BUS_ANY);
if (d)
return irq_create_mapping(d, EXCCODE_TIMER - EXCCODE_INT_START);
return -EINVAL;
}
int constant_clockevent_init(void)
{
unsigned int irq;
@ -132,7 +142,9 @@ int constant_clockevent_init(void)
struct clock_event_device *cd;
static int timer_irq_installed = 0;
irq = EXCCODE_TIMER - EXCCODE_INT_START;
irq = get_timer_irq();
if (irq < 0)
pr_err("Failed to map irq %d (timer)\n", irq);
cd = &per_cpu(constant_clockevent_device, cpu);

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

@ -101,6 +101,7 @@ SECTIONS
STABS_DEBUG
DWARF_DEBUG
ELF_DETAILS
.gptab.sdata : {
*(.gptab.data)

4
arch/mips/cavium-octeon/octeon-irq.c
View File

@ -263,7 +263,7 @@ static int next_cpu_for_irq(struct irq_data *data)
#ifdef CONFIG_SMP
int cpu;
struct cpumask *mask = irq_data_get_affinity_mask(data);
const struct cpumask *mask = irq_data_get_affinity_mask(data);
int weight = cpumask_weight(mask);
struct octeon_ciu_chip_data *cd = irq_data_get_irq_chip_data(data);
@ -758,7 +758,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
{
int cpu = smp_processor_id();
cpumask_t new_affinity;
struct cpumask *mask = irq_data_get_affinity_mask(data);
const struct cpumask *mask = irq_data_get_affinity_mask(data);
if (!cpumask_test_cpu(cpu, mask))
return;

3
arch/mips/include/asm/mach-loongson64/irq.h
View File

@ -7,8 +7,9 @@
#define NR_MIPS_CPU_IRQS 8
#define NR_MAX_CHAINED_IRQS 40 /* Chained IRQs means those not directly used by devices */
#define NR_IRQS (NR_IRQS_LEGACY + NR_MIPS_CPU_IRQS + NR_MAX_CHAINED_IRQS + 256)
#define MAX_IO_PICS 1
#define MIPS_CPU_IRQ_BASE NR_IRQS_LEGACY
#define GSI_MIN_CPU_IRQ 0
#include <asm/mach-generic/irq.h>

2
arch/parisc/kernel/irq.c
View File

@ -315,7 +315,7 @@ unsigned long txn_affinity_addr(unsigned int irq, int cpu)
{
#ifdef CONFIG_SMP
struct irq_data *d = irq_get_irq_data(irq);
cpumask_copy(irq_data_get_affinity_mask(d), cpumask_of(cpu));
irq_data_update_affinity(d, cpumask_of(cpu));
#endif
return per_cpu(cpu_data, cpu).txn_addr;

9
arch/riscv/Kconfig
View File

@ -364,8 +364,13 @@ config RISCV_ISA_SVPBMT
select RISCV_ALTERNATIVE
default y
help
Adds support to dynamically detect the presence of the SVPBMT extension
(Supervisor-mode: page-based memory types) and enable its usage.
Adds support to dynamically detect the presence of the SVPBMT
ISA-extension (Supervisor-mode: page-based memory types) and
enable its usage.
The memory type for a page contains a combination of attributes
that indicate the cacheability, idempotency, and ordering
properties for access to that page.
The SVPBMT extension is only available on 64Bit cpus.

1
arch/riscv/Kconfig.erratas
View File

@ -35,6 +35,7 @@ config ERRATA_SIFIVE_CIP_1200
config ERRATA_THEAD
bool "T-HEAD errata"
depends on !XIP_KERNEL
select RISCV_ALTERNATIVE
help
All T-HEAD errata Kconfig depend on this Kconfig. Disabling

9
arch/riscv/boot/dts/microchip/mpfs.dtsi
View File

@ -192,6 +192,15 @@
riscv,ndev = <186>;
};
pdma: dma-controller@3000000 {
compatible = "sifive,fu540-c000-pdma", "sifive,pdma0";
reg = <0x0 0x3000000 0x0 0x8000>;
interrupt-parent = <&plic>;
interrupts = <5 6>, <7 8>, <9 10>, <11 12>;
dma-channels = <4>;
#dma-cells = <1>;
};
clkcfg: clkcfg@20002000 {
compatible = "microchip,mpfs-clkcfg";
reg = <0x0 0x20002000 0x0 0x1000>, <0x0 0x3E001000 0x0 0x1000>;

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

@ -293,7 +293,6 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
unsigned int stage)
{
u32 cpu_req_feature = cpufeature_probe(stage);
u32 cpu_apply_feature = 0;
struct alt_entry *alt;
u32 tmp;
@ -307,10 +306,8 @@ void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin,
}
tmp = (1U << alt->errata_id);
if (cpu_req_feature & tmp) {
if (cpu_req_feature & tmp)
patch_text_nosync(alt->old_ptr, alt->alt_ptr, alt->alt_len);
cpu_apply_feature |= tmp;
}
}
}
#endif

2
arch/riscv/kvm/vmid.c
View File

@ -97,7 +97,7 @@ void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu)
* We ran out of VMIDs so we increment vmid_version and
* start assigning VMIDs from 1.
*
* This also means existing VMIDs assignement to all Guest
* This also means existing VMIDs assignment to all Guest
* instances is invalid and we have force VMID re-assignement
* for all Guest instances. The Guest instances that were not
* running will automatically pick-up new VMIDs because will

7
arch/sh/kernel/irq.c
View File

@ -230,16 +230,17 @@ void migrate_irqs(void)
struct irq_data *data = irq_get_irq_data(irq);
if (irq_data_get_node(data) == cpu) {
struct cpumask *mask = irq_data_get_affinity_mask(data);
const struct cpumask *mask = irq_data_get_affinity_mask(data);
unsigned int newcpu = cpumask_any_and(mask,
cpu_online_mask);
if (newcpu >= nr_cpu_ids) {
pr_info_ratelimited("IRQ%u no longer affine to CPU%u\n",
irq, cpu);
cpumask_setall(mask);
irq_set_affinity(irq, cpu_all_mask);
} else {
irq_set_affinity(irq, mask);
}
irq_set_affinity(irq, mask);
}
}
}

187
arch/x86/coco/tdx/tdx.c
View File

@ -124,6 +124,51 @@ static u64 get_cc_mask(void)
return BIT_ULL(gpa_width - 1);
}
/*
* The TDX module spec states that #VE may be injected for a limited set of
* reasons:
*
* - Emulation of the architectural #VE injection on EPT violation;
*
* - As a result of guest TD execution of a disallowed instruction,
* a disallowed MSR access, or CPUID virtualization;
*
* - A notification to the guest TD about anomalous behavior;
*
* The last one is opt-in and is not used by the kernel.
*
* The Intel Software Developer's Manual describes cases when instruction
* length field can be used in section "Information for VM Exits Due to
* Instruction Execution".
*
* For TDX, it ultimately means GET_VEINFO provides reliable instruction length
* information if #VE occurred due to instruction execution, but not for EPT
* violations.
*/
static int ve_instr_len(struct ve_info *ve)
{
switch (ve->exit_reason) {
case EXIT_REASON_HLT:
case EXIT_REASON_MSR_READ:
case EXIT_REASON_MSR_WRITE:
case EXIT_REASON_CPUID:
case EXIT_REASON_IO_INSTRUCTION:
/* It is safe to use ve->instr_len for #VE due instructions */
return ve->instr_len;
case EXIT_REASON_EPT_VIOLATION:
/*
* For EPT violations, ve->insn_len is not defined. For those,
* the kernel must decode instructions manually and should not
* be using this function.
*/
WARN_ONCE(1, "ve->instr_len is not defined for EPT violations");
return 0;
default:
WARN_ONCE(1, "Unexpected #VE-type: %lld\n", ve->exit_reason);
return ve->instr_len;
}
}
static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
{
struct tdx_hypercall_args args = {
@ -147,7 +192,7 @@ static u64 __cpuidle __halt(const bool irq_disabled, const bool do_sti)
return __tdx_hypercall(&args, do_sti ? TDX_HCALL_ISSUE_STI : 0);
}
static bool handle_halt(void)
static int handle_halt(struct ve_info *ve)
{
/*
* Since non safe halt is mainly used in CPU offlining
@ -158,9 +203,9 @@ static bool handle_halt(void)
const bool do_sti = false;
if (__halt(irq_disabled, do_sti))
return false;
return -EIO;
return true;
return ve_instr_len(ve);
}
void __cpuidle tdx_safe_halt(void)
@ -180,7 +225,7 @@ void __cpuidle tdx_safe_halt(void)
WARN_ONCE(1, "HLT instruction emulation failed\n");
}
static bool read_msr(struct pt_regs *regs)
static int read_msr(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@ -194,14 +239,14 @@ static bool read_msr(struct pt_regs *regs)
* (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>".
*/
if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
return false;
return -EIO;
regs->ax = lower_32_bits(args.r11);
regs->dx = upper_32_bits(args.r11);
return true;
return ve_instr_len(ve);
}
static bool write_msr(struct pt_regs *regs)
static int write_msr(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@ -215,10 +260,13 @@ static bool write_msr(struct pt_regs *regs)
* can be found in TDX Guest-Host-Communication Interface
* (GHCI) section titled "TDG.VP.VMCALL<Instruction.WRMSR>".
*/
return !__tdx_hypercall(&args, 0);
if (__tdx_hypercall(&args, 0))
return -EIO;
return ve_instr_len(ve);
}
static bool handle_cpuid(struct pt_regs *regs)
static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve)
{
struct tdx_hypercall_args args = {
.r10 = TDX_HYPERCALL_STANDARD,
@ -236,7 +284,7 @@ static bool handle_cpuid(struct pt_regs *regs)
*/
if (regs->ax < 0x40000000 || regs->ax > 0x4FFFFFFF) {
regs->ax = regs->bx = regs->cx = regs->dx = 0;
return true;
return ve_instr_len(ve);
}
/*
@ -245,7 +293,7 @@ static bool handle_cpuid(struct pt_regs *regs)
* (GHCI), section titled "VP.VMCALL<Instruction.CPUID>".
*/
if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
return false;
return -EIO;
/*
* As per TDX GHCI CPUID ABI, r12-r15 registers contain contents of
@ -257,7 +305,7 @@ static bool handle_cpuid(struct pt_regs *regs)
regs->cx = args.r14;
regs->dx = args.r15;
return true;
return ve_instr_len(ve);
}
static bool mmio_read(int size, unsigned long addr, unsigned long *val)
@ -283,10 +331,10 @@ static bool mmio_write(int size, unsigned long addr, unsigned long val)
EPT_WRITE, addr, val);
}
static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
{
unsigned long *reg, val, vaddr;
char buffer[MAX_INSN_SIZE];
unsigned long *reg, val;
struct insn insn = {};
enum mmio_type mmio;
int size, extend_size;
@ -294,34 +342,49 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
/* Only in-kernel MMIO is supported */
if (WARN_ON_ONCE(user_mode(regs)))
return false;
return -EFAULT;
if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE))
return false;
return -EFAULT;
if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64))
return false;
return -EINVAL;
mmio = insn_decode_mmio(&insn, &size);
if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
return false;
return -EINVAL;
if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
reg = insn_get_modrm_reg_ptr(&insn, regs);
if (!reg)
return false;
return -EINVAL;
}
ve->instr_len = insn.length;
/*
* Reject EPT violation #VEs that split pages.
*
* MMIO accesses are supposed to be naturally aligned and therefore
* never cross page boundaries. Seeing split page accesses indicates
* a bug or a load_unaligned_zeropad() that stepped into an MMIO page.
*
* load_unaligned_zeropad() will recover using exception fixups.
*/
vaddr = (unsigned long)insn_get_addr_ref(&insn, regs);
if (vaddr / PAGE_SIZE != (vaddr + size - 1) / PAGE_SIZE)
return -EFAULT;
/* Handle writes first */
switch (mmio) {
case MMIO_WRITE:
memcpy(&val, reg, size);
return mmio_write(size, ve->gpa, val);
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
case MMIO_WRITE_IMM:
val = insn.immediate.value;
return mmio_write(size, ve->gpa, val);
if (!mmio_write(size, ve->gpa, val))
return -EIO;
return insn.length;
case MMIO_READ:
case MMIO_READ_ZERO_EXTEND:
case MMIO_READ_SIGN_EXTEND:
@ -334,15 +397,15 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
* decoded or handled properly. It was likely not using io.h
* helpers or accessed MMIO accidentally.
*/
return false;
return -EINVAL;
default:
WARN_ONCE(1, "Unknown insn_decode_mmio() decode value?");
return false;
return -EINVAL;
}
/* Handle reads */
if (!mmio_read(size, ve->gpa, &val))
return false;
return -EIO;
switch (mmio) {
case MMIO_READ:
@ -364,13 +427,13 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
default:
/* All other cases has to be covered with the first switch() */
WARN_ON_ONCE(1);
return false;
return -EINVAL;
}
if (extend_size)
memset(reg, extend_val, extend_size);
memcpy(reg, &val, size);
return true;
return insn.length;
}
static bool handle_in(struct pt_regs *regs, int size, int port)
@ -421,13 +484,14 @@ static bool handle_out(struct pt_regs *regs, int size, int port)
*
* Return True on success or False on failure.
*/
static bool handle_io(struct pt_regs *regs, u32 exit_qual)
static int handle_io(struct pt_regs *regs, struct ve_info *ve)
{
u32 exit_qual = ve->exit_qual;
int size, port;
bool in;
bool in, ret;
if (VE_IS_IO_STRING(exit_qual))
return false;
return -EIO;
in = VE_IS_IO_IN(exit_qual);
size = VE_GET_IO_SIZE(exit_qual);
@ -435,9 +499,13 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual)
if (in)
return handle_in(regs, size, port);
ret = handle_in(regs, size, port);
else
return handle_out(regs, size, port);
ret = handle_out(regs, size, port);
if (!ret)
return -EIO;
return ve_instr_len(ve);
}
/*
@ -447,13 +515,19 @@ static bool handle_io(struct pt_regs *regs, u32 exit_qual)
__init bool tdx_early_handle_ve(struct pt_regs *regs)
{
struct ve_info ve;
int insn_len;
tdx_get_ve_info(&ve);
if (ve.exit_reason != EXIT_REASON_IO_INSTRUCTION)
return false;
return handle_io(regs, ve.exit_qual);
insn_len = handle_io(regs, &ve);
if (insn_len < 0)
return false;
regs->ip += insn_len;
return true;
}
void tdx_get_ve_info(struct ve_info *ve)
@ -486,54 +560,65 @@ void tdx_get_ve_info(struct ve_info *ve)
ve->instr_info = upper_32_bits(out.r10);
}
/* Handle the user initiated #VE */
static bool virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
/*
* Handle the user initiated #VE.
*
* On success, returns the number of bytes RIP should be incremented (>=0)
* or -errno on error.
*/
static int virt_exception_user(struct pt_regs *regs, struct ve_info *ve)
{
switch (ve->exit_reason) {
case EXIT_REASON_CPUID:
return handle_cpuid(regs);
return handle_cpuid(regs, ve);
default:
pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
return false;
return -EIO;
}
}
/* Handle the kernel #VE */
static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
/*
* Handle the kernel #VE.
*
* On success, returns the number of bytes RIP should be incremented (>=0)
* or -errno on error.
*/
static int virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
{
switch (ve->exit_reason) {
case EXIT_REASON_HLT:
return handle_halt();
return handle_halt(ve);
case EXIT_REASON_MSR_READ:
return read_msr(regs);
return read_msr(regs, ve);
case EXIT_REASON_MSR_WRITE:
return write_msr(regs);
return write_msr(regs, ve);
case EXIT_REASON_CPUID:
return handle_cpuid(regs);
return handle_cpuid(regs, ve);
case EXIT_REASON_EPT_VIOLATION:
return handle_mmio(regs, ve);
case EXIT_REASON_IO_INSTRUCTION:
return handle_io(regs, ve->exit_qual);
return handle_io(regs, ve);
default:
pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
return false;
return -EIO;
}
}
bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve)
{
bool ret;
int insn_len;
if (user_mode(regs))
ret = virt_exception_user(regs, ve);
insn_len = virt_exception_user(regs, ve);
else
ret = virt_exception_kernel(regs, ve);
insn_len = virt_exception_kernel(regs, ve);
if (insn_len < 0)
return false;
/* After successful #VE handling, move the IP */
if (ret)
regs->ip += ve->instr_len;
regs->ip += insn_len;
return ret;
return true;
}
static bool tdx_tlb_flush_required(bool private)

6
arch/x86/hyperv/hv_init.c
View File

@ -13,6 +13,7 @@
#include <linux/io.h>
#include <asm/apic.h>
#include <asm/desc.h>
#include <asm/sev.h>
#include <asm/hypervisor.h>
#include <asm/hyperv-tlfs.h>
#include <asm/mshyperv.h>
@ -405,6 +406,11 @@ void __init hyperv_init(void)
}
if (hv_isolation_type_snp()) {
/* Negotiate GHCB Version. */
if (!hv_ghcb_negotiate_protocol())
hv_ghcb_terminate(SEV_TERM_SET_GEN,
GHCB_SEV_ES_PROT_UNSUPPORTED);
hv_ghcb_pg = alloc_percpu(union hv_ghcb *);
if (!hv_ghcb_pg)
goto free_vp_assist_page;

2
arch/x86/hyperv/irqdomain.c
View File

@ -192,7 +192,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
struct pci_dev *dev;
struct hv_interrupt_entry out_entry, *stored_entry;
struct irq_cfg *cfg = irqd_cfg(data);
cpumask_t *affinity;
const cpumask_t *affinity;
int cpu;
u64 status;

84
arch/x86/hyperv/ivm.c
View File

@ -53,6 +53,8 @@ union hv_ghcb {
} hypercall;
} __packed __aligned(HV_HYP_PAGE_SIZE);
static u16 hv_ghcb_version __ro_after_init;
u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
{
union hv_ghcb *hv_ghcb;
@ -96,12 +98,85 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
return status;
}
static inline u64 rd_ghcb_msr(void)
{
return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
}
static inline void wr_ghcb_msr(u64 val)
{
native_wrmsrl(MSR_AMD64_SEV_ES_GHCB, val);
}
static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code,
u64 exit_info_1, u64 exit_info_2)
{
/* Fill in protocol and format specifiers */
ghcb->protocol_version = hv_ghcb_version;
ghcb->ghcb_usage = GHCB_DEFAULT_USAGE;
ghcb_set_sw_exit_code(ghcb, exit_code);
ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
VMGEXIT();
if (ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0))
return ES_VMM_ERROR;
else
return ES_OK;
}
void hv_ghcb_terminate(unsigned int set, unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
/* Tell the hypervisor what went wrong. */
val |= GHCB_SEV_TERM_REASON(set, reason);
/* Request Guest Termination from Hypvervisor */
wr_ghcb_msr(val);
VMGEXIT();
while (true)
asm volatile("hlt\n" : : : "memory");
}
bool hv_ghcb_negotiate_protocol(void)
{
u64 ghcb_gpa;
u64 val;
/* Save ghcb page gpa. */
ghcb_gpa = rd_ghcb_msr();
/* Do the GHCB protocol version negotiation */
wr_ghcb_msr(GHCB_MSR_SEV_INFO_REQ);
VMGEXIT();
val = rd_ghcb_msr();
if (GHCB_MSR_INFO(val) != GHCB_MSR_SEV_INFO_RESP)
return false;
if (GHCB_MSR_PROTO_MAX(val) < GHCB_PROTOCOL_MIN ||
GHCB_MSR_PROTO_MIN(val) > GHCB_PROTOCOL_MAX)
return false;
hv_ghcb_version = min_t(size_t, GHCB_MSR_PROTO_MAX(val),
GHCB_PROTOCOL_MAX);
/* Write ghcb page back after negotiating protocol. */
wr_ghcb_msr(ghcb_gpa);
VMGEXIT();
return true;
}
void hv_ghcb_msr_write(u64 msr, u64 value)
{
union hv_ghcb *hv_ghcb;
void **ghcb_base;
unsigned long flags;
struct es_em_ctxt ctxt;
if (!hv_ghcb_pg)
return;
@ -120,8 +195,7 @@ void hv_ghcb_msr_write(u64 msr, u64 value)
ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value));
ghcb_set_rdx(&hv_ghcb->ghcb, upper_32_bits(value));
if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt,
SVM_EXIT_MSR, 1, 0))
if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 1, 0))
pr_warn("Fail to write msr via ghcb %llx.\n", msr);
local_irq_restore(flags);
@ -133,7 +207,6 @@ void hv_ghcb_msr_read(u64 msr, u64 *value)
union hv_ghcb *hv_ghcb;
void **ghcb_base;
unsigned long flags;
struct es_em_ctxt ctxt;
/* Check size of union hv_ghcb here. */
BUILD_BUG_ON(sizeof(union hv_ghcb) != HV_HYP_PAGE_SIZE);
@ -152,8 +225,7 @@ void hv_ghcb_msr_read(u64 msr, u64 *value)
}
ghcb_set_rcx(&hv_ghcb->ghcb, msr);
if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt,
SVM_EXIT_MSR, 0, 0))
if (hv_ghcb_hv_call(&hv_ghcb->ghcb, SVM_EXIT_MSR, 0, 0))
pr_warn("Fail to read msr via ghcb %llx.\n", msr);
else
*value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax)

1
arch/x86/include/asm/cpufeatures.h
View File

@ -446,5 +446,6 @@
#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 */
#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
#endif /* _ASM_X86_CPUFEATURES_H */

5
arch/x86/include/asm/e820/api.h
View File

@ -4,9 +4,6 @@
#include <asm/e820/types.h>
struct device;
struct resource;
extern struct e820_table *e820_table;
extern struct e820_table *e820_table_kexec;
extern struct e820_table *e820_table_firmware;
@ -46,8 +43,6 @@ extern void e820__register_nosave_regions(unsigned long limit_pfn);
extern int e820__get_entry_type(u64 start, u64 end);
extern void remove_e820_regions(struct device *dev, struct resource *avail);
/*
* Returns true iff the specified range [start,end) is completely contained inside
* the ISA region.

73
arch/x86/include/asm/kvm_host.h
View File

@ -1047,14 +1047,77 @@ struct kvm_x86_msr_filter {
};
enum kvm_apicv_inhibit {
/********************************************************************/
/* INHIBITs that are relevant to both Intel's APICv and AMD's AVIC. */
/********************************************************************/
/*
* APIC acceleration is disabled by a module parameter
* and/or not supported in hardware.
*/
APICV_INHIBIT_REASON_DISABLE,
/*
* APIC acceleration is inhibited because AutoEOI feature is
* being used by a HyperV guest.
*/
APICV_INHIBIT_REASON_HYPERV,
APICV_INHIBIT_REASON_NESTED,
APICV_INHIBIT_REASON_IRQWIN,
APICV_INHIBIT_REASON_PIT_REINJ,
APICV_INHIBIT_REASON_X2APIC,
APICV_INHIBIT_REASON_BLOCKIRQ,
/*
* APIC acceleration is inhibited because the userspace didn't yet
* enable the kernel/split irqchip.
*/
APICV_INHIBIT_REASON_ABSENT,
/* APIC acceleration is inhibited because KVM_GUESTDBG_BLOCKIRQ
* (out of band, debug measure of blocking all interrupts on this vCPU)
* was enabled, to avoid AVIC/APICv bypassing it.
*/
APICV_INHIBIT_REASON_BLOCKIRQ,
/*
* For simplicity, the APIC acceleration is inhibited
* first time either APIC ID or APIC base are changed by the guest
* from their reset values.
*/
APICV_INHIBIT_REASON_APIC_ID_MODIFIED,
APICV_INHIBIT_REASON_APIC_BASE_MODIFIED,
/******************************************************/
/* INHIBITs that are relevant only to the AMD's AVIC. */
/******************************************************/
/*
* AVIC is inhibited on a vCPU because it runs a nested guest.
*
* This is needed because unlike APICv, the peers of this vCPU
* cannot use the doorbell mechanism to signal interrupts via AVIC when
* a vCPU runs nested.
*/
APICV_INHIBIT_REASON_NESTED,
/*
* On SVM, the wait for the IRQ window is implemented with pending vIRQ,
* which cannot be injected when the AVIC is enabled, thus AVIC
* is inhibited while KVM waits for IRQ window.
*/
APICV_INHIBIT_REASON_IRQWIN,
/*
* PIT (i8254) 're-inject' mode, relies on EOI intercept,
* which AVIC doesn't support for edge triggered interrupts.
*/
APICV_INHIBIT_REASON_PIT_REINJ,
/*
* AVIC is inhibited because the guest has x2apic in its CPUID.
*/
APICV_INHIBIT_REASON_X2APIC,
/*
* AVIC is disabled because SEV doesn't support it.
*/
APICV_INHIBIT_REASON_SEV,
};

4
arch/x86/include/asm/mshyperv.h
View File

@ -179,9 +179,13 @@ int hv_set_mem_host_visibility(unsigned long addr, int numpages, bool visible);
#ifdef CONFIG_AMD_MEM_ENCRYPT
void hv_ghcb_msr_write(u64 msr, u64 value);
void hv_ghcb_msr_read(u64 msr, u64 *value);
bool hv_ghcb_negotiate_protocol(void);
void hv_ghcb_terminate(unsigned int set, unsigned int reason);
#else
static inline void hv_ghcb_msr_write(u64 msr, u64 value) {}
static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {}
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
#endif
extern bool hv_isolation_type_snp(void);

25
arch/x86/include/asm/msr-index.h
View File

@ -116,6 +116,30 @@
* Not susceptible to
* TSX Async Abort (TAA) vulnerabilities.
*/
#define ARCH_CAP_SBDR_SSDP_NO BIT(13) /*
* Not susceptible to SBDR and SSDP
* variants of Processor MMIO stale data
* vulnerabilities.
*/
#define ARCH_CAP_FBSDP_NO BIT(14) /*
* Not susceptible to FBSDP variant of
* Processor MMIO stale data
* vulnerabilities.
*/
#define ARCH_CAP_PSDP_NO BIT(15) /*
* Not susceptible to PSDP variant of
* Processor MMIO stale data
* vulnerabilities.
*/
#define ARCH_CAP_FB_CLEAR BIT(17) /*
* VERW clears CPU fill buffer
* even on MDS_NO CPUs.
*/
#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /*
* MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS]
* bit available to control VERW
* behavior.
*/
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
@ -133,6 +157,7 @@
#define MSR_IA32_MCU_OPT_CTRL 0x00000123
#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */
#define RTM_ALLOW BIT(1) /* TSX development mode */
#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175

2
arch/x86/include/asm/nospec-branch.h
View File

@ -269,6 +269,8 @@ DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
#include <asm/segment.h>
/**

8
arch/x86/include/asm/pci_x86.h
View File

@ -69,6 +69,8 @@ void pcibios_scan_specific_bus(int busn);
/* pci-irq.c */
struct pci_dev;
struct irq_info {
u8 bus, devfn; /* Bus, device and function */
struct {
@ -246,3 +248,9 @@ static inline void mmio_config_writel(void __iomem *pos, u32 val)
# define x86_default_pci_init_irq NULL
# define x86_default_pci_fixup_irqs NULL
#endif
#if defined(CONFIG_PCI) && defined(CONFIG_ACPI)
extern bool pci_use_e820;
#else
#define pci_use_e820 false
#endif

38
arch/x86/include/asm/setup.h
View File

@ -108,19 +108,16 @@ extern unsigned long _brk_end;
void *extend_brk(size_t size, size_t align);
/*
* Reserve space in the brk section. The name must be unique within the file,
* and somewhat descriptive. The size is in bytes.
* Reserve space in the .brk section, which is a block of memory from which the
* caller is allowed to allocate very early (before even memblock is available)
* by calling extend_brk(). All allocated memory will be eventually converted
* to memblock. Any leftover unallocated memory will be freed.
*
* The allocation is done using inline asm (rather than using a section
* attribute on a normal variable) in order to allow the use of @nobits, so
* that it doesn't take up any space in the vmlinux file.
* The size is in bytes.
*/
#define RESERVE_BRK(name, size) \
asm(".pushsection .brk_reservation,\"aw\",@nobits\n\t" \
".brk." #name ":\n\t" \
".skip " __stringify(size) "\n\t" \
".size .brk." #name ", " __stringify(size) "\n\t" \
".popsection\n\t")
#define RESERVE_BRK(name, size) \
__section(".bss..brk") __aligned(1) __used \
static char __brk_##name[size]
extern void probe_roms(void);
#ifdef __i386__
@ -133,12 +130,19 @@ asmlinkage void __init x86_64_start_reservations(char *real_mode_data);
#endif /* __i386__ */
#endif /* _SETUP */
#else
#define RESERVE_BRK(name,sz) \
.pushsection .brk_reservation,"aw",@nobits; \
.brk.name: \
1: .skip sz; \
.size .brk.name,.-1b; \
#else /* __ASSEMBLY */
.macro __RESERVE_BRK name, size
.pushsection .bss..brk, "aw"
SYM_DATA_START(__brk_\name)
.skip \size
SYM_DATA_END(__brk_\name)
.popsection
.endm
#define RESERVE_BRK(name, size) __RESERVE_BRK name, size
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SETUP_H */

4
arch/x86/kernel/Makefile
View File

@ -36,10 +36,6 @@ KCSAN_SANITIZE := n
OBJECT_FILES_NON_STANDARD_test_nx.o := y
ifdef CONFIG_FRAME_POINTER
OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y
endif
# If instrumentation of this dir is enabled, boot hangs during first second.
# Probably could be more selective here, but note that files related to irqs,
# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to

235
arch/x86/kernel/cpu/bugs.c
View File

@ -41,8 +41,10 @@ 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 mds_print_mitigation(void);
static void __init md_clear_update_mitigation(void);
static void __init md_clear_select_mitigation(void);
static void __init taa_select_mitigation(void);
static void __init mmio_select_mitigation(void);
static void __init srbds_select_mitigation(void);
static void __init l1d_flush_select_mitigation(void);
@ -85,6 +87,10 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
*/
DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */
DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
void __init check_bugs(void)
{
identify_boot_cpu();
@ -117,17 +123,10 @@ void __init check_bugs(void)
spectre_v2_select_mitigation();
ssb_select_mitigation();
l1tf_select_mitigation();
mds_select_mitigation();
taa_select_mitigation();
md_clear_select_mitigation();
srbds_select_mitigation();
l1d_flush_select_mitigation();
/*
* As MDS and TAA mitigations are inter-related, print MDS
* mitigation until after TAA mitigation selection is done.
*/
mds_print_mitigation();
arch_smt_update();
#ifdef CONFIG_X86_32
@ -267,14 +266,6 @@ static void __init mds_select_mitigation(void)
}
}
static void __init mds_print_mitigation(void)
{
if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
return;
pr_info("%s\n", mds_strings[mds_mitigation]);
}
static int __init mds_cmdline(char *str)
{
if (!boot_cpu_has_bug(X86_BUG_MDS))
@ -329,7 +320,7 @@ static void __init taa_select_mitigation(void)
/* TSX previously disabled by tsx=off */
if (!boot_cpu_has(X86_FEATURE_RTM)) {
taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
goto out;
return;
}
if (cpu_mitigations_off()) {
@ -343,7 +334,7 @@ static void __init taa_select_mitigation(void)
*/
if (taa_mitigation == TAA_MITIGATION_OFF &&
mds_mitigation == MDS_MITIGATION_OFF)
goto out;
return;
if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
taa_mitigation = TAA_MITIGATION_VERW;
@ -375,18 +366,6 @@ static void __init taa_select_mitigation(void)
if (taa_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
/*
* Update MDS mitigation, if necessary, as the mds_user_clear is
* now enabled for TAA mitigation.
*/
if (mds_mitigation == MDS_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_MDS)) {
mds_mitigation = MDS_MITIGATION_FULL;
mds_select_mitigation();
}
out:
pr_info("%s\n", taa_strings[taa_mitigation]);
}
static int __init tsx_async_abort_parse_cmdline(char *str)
@ -410,6 +389,151 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
}
early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
#undef pr_fmt
#define pr_fmt(fmt) "MMIO Stale Data: " fmt
enum mmio_mitigations {
MMIO_MITIGATION_OFF,
MMIO_MITIGATION_UCODE_NEEDED,
MMIO_MITIGATION_VERW,
};
/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW;
static bool mmio_nosmt __ro_after_init = false;
static const char * const mmio_strings[] = {
[MMIO_MITIGATION_OFF] = "Vulnerable",
[MMIO_MITIGATION_UCODE_NEEDED] = "Vulnerable: Clear CPU buffers attempted, no microcode",
[MMIO_MITIGATION_VERW] = "Mitigation: Clear CPU buffers",
};
static void __init mmio_select_mitigation(void)
{
u64 ia32_cap;
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
cpu_mitigations_off()) {
mmio_mitigation = MMIO_MITIGATION_OFF;
return;
}
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return;
ia32_cap = x86_read_arch_cap_msr();
/*
* Enable CPU buffer clear mitigation for host and VMM, if also affected
* by MDS or TAA. Otherwise, enable mitigation for VMM only.
*/
if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
boot_cpu_has(X86_FEATURE_RTM)))
static_branch_enable(&mds_user_clear);
else
static_branch_enable(&mmio_stale_data_clear);
/*
* If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can
* be propagated to uncore buffers, clearing the Fill buffers on idle
* is required irrespective of SMT state.
*/
if (!(ia32_cap & ARCH_CAP_FBSDP_NO))
static_branch_enable(&mds_idle_clear);
/*
* Check if the system has the right microcode.
*
* CPU Fill buffer clear mitigation is enumerated by either an explicit
* FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
* affected systems.
*/
if ((ia32_cap & ARCH_CAP_FB_CLEAR) ||
(boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
!(ia32_cap & ARCH_CAP_MDS_NO)))
mmio_mitigation = MMIO_MITIGATION_VERW;
else
mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
if (mmio_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
}
static int __init mmio_stale_data_parse_cmdline(char *str)
{
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
return 0;
if (!str)
return -EINVAL;
if (!strcmp(str, "off")) {
mmio_mitigation = MMIO_MITIGATION_OFF;
} else if (!strcmp(str, "full")) {
mmio_mitigation = MMIO_MITIGATION_VERW;
} else if (!strcmp(str, "full,nosmt")) {
mmio_mitigation = MMIO_MITIGATION_VERW;
mmio_nosmt = true;
}
return 0;
}
early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
#undef pr_fmt
#define pr_fmt(fmt) "" fmt
static void __init md_clear_update_mitigation(void)
{
if (cpu_mitigations_off())
return;
if (!static_key_enabled(&mds_user_clear))
goto out;
/*
* mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
* mitigation, if necessary.
*/
if (mds_mitigation == MDS_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_MDS)) {
mds_mitigation = MDS_MITIGATION_FULL;
mds_select_mitigation();
}
if (taa_mitigation == TAA_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_TAA)) {
taa_mitigation = TAA_MITIGATION_VERW;
taa_select_mitigation();
}
if (mmio_mitigation == MMIO_MITIGATION_OFF &&
boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
mmio_mitigation = MMIO_MITIGATION_VERW;
mmio_select_mitigation();
}
out:
if (boot_cpu_has_bug(X86_BUG_MDS))
pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
if (boot_cpu_has_bug(X86_BUG_TAA))
pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
}
static void __init md_clear_select_mitigation(void)
{
mds_select_mitigation();
taa_select_mitigation();
mmio_select_mitigation();
/*
* As MDS, TAA and MMIO Stale Data mitigations are inter-related, update
* and print their mitigation after MDS, TAA and MMIO Stale Data
* mitigation selection is done.
*/
md_clear_update_mitigation();
}
#undef pr_fmt
#define pr_fmt(fmt) "SRBDS: " fmt
@ -478,11 +602,13 @@ static void __init srbds_select_mitigation(void)
return;
/*
* Check to see if this is one of the MDS_NO systems supporting
* TSX that are only exposed to SRBDS when TSX is enabled.
* Check to see if this is one of the MDS_NO systems supporting TSX that
* are only exposed to SRBDS when TSX is enabled or when CPU is affected
* by Processor MMIO Stale Data vulnerability.
*/
ia32_cap = x86_read_arch_cap_msr();
if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
@ -1116,6 +1242,8 @@ static void update_indir_branch_cond(void)
/* Update the static key controlling the MDS CPU buffer clear in idle */
static void update_mds_branch_idle(void)
{
u64 ia32_cap = x86_read_arch_cap_msr();
/*
* Enable the idle clearing if SMT is active on CPUs which are
* affected only by MSBDS and not any other MDS variant.
@ -1127,14 +1255,17 @@ static void update_mds_branch_idle(void)
if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
return;
if (sched_smt_active())
if (sched_smt_active()) {
static_branch_enable(&mds_idle_clear);
else
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
(ia32_cap & ARCH_CAP_FBSDP_NO)) {
static_branch_disable(&mds_idle_clear);
}
}
#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"
#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
void cpu_bugs_smt_update(void)
{
@ -1179,6 +1310,16 @@ void cpu_bugs_smt_update(void)
break;
}
switch (mmio_mitigation) {
case MMIO_MITIGATION_VERW:
case MMIO_MITIGATION_UCODE_NEEDED:
if (sched_smt_active())
pr_warn_once(MMIO_MSG_SMT);
break;
case MMIO_MITIGATION_OFF:
break;
}
mutex_unlock(&spec_ctrl_mutex);
}
@ -1781,6 +1922,20 @@ static ssize_t tsx_async_abort_show_state(char *buf)
sched_smt_active() ? "vulnerable" : "disabled");
}
static ssize_t mmio_stale_data_show_state(char *buf)
{
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
return sysfs_emit(buf, "%s; SMT Host state unknown\n",
mmio_strings[mmio_mitigation]);
}
return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation],
sched_smt_active() ? "vulnerable" : "disabled");
}
static char *stibp_state(void)
{
if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
@ -1881,6 +2036,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_SRBDS:
return srbds_show_state(buf);
case X86_BUG_MMIO_STALE_DATA:
return mmio_stale_data_show_state(buf);
default:
break;
}
@ -1932,4 +2090,9 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
{
return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
}
ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
{
return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
}
#endif

52
arch/x86/kernel/cpu/common.c
View File

@ -1211,18 +1211,42 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
X86_FEATURE_ANY, issues)
#define SRBDS BIT(0)
/* CPU is affected by X86_BUG_MMIO_STALE_DATA */
#define MMIO BIT(1)
/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */
#define MMIO_SBDS BIT(2)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(HASWELL, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(HASWELL_L, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(HASWELL_G, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(HASWELL_X, BIT(2) | BIT(4), MMIO),
VULNBL_INTEL_STEPPINGS(BROADWELL_D, X86_STEPPINGS(0x3, 0x5), MMIO),
VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO),
VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO),
VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) |
BIT(7) | BIT(0xB), MMIO),
VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO),
VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0xC), SRBDS),
VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0xD), SRBDS),
VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO),
VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS),
VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO),
VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS),
VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO),
VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO),
VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO),
VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS),
{}
};
@ -1243,6 +1267,13 @@ u64 x86_read_arch_cap_msr(void)
return ia32_cap;
}
static bool arch_cap_mmio_immune(u64 ia32_cap)
{
return (ia32_cap & ARCH_CAP_FBSDP_NO &&
ia32_cap & ARCH_CAP_PSDP_NO &&
ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
}
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 ia32_cap = x86_read_arch_cap_msr();
@ -1296,12 +1327,27 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
/*
* SRBDS affects CPUs which support RDRAND or RDSEED and are listed
* in the vulnerability blacklist.
*
* Some of the implications and mitigation of Shared Buffers Data
* Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as
* SRBDS.
*/
if ((cpu_has(c, X86_FEATURE_RDRAND) ||
cpu_has(c, X86_FEATURE_RDSEED)) &&
cpu_matches(cpu_vuln_blacklist, SRBDS))
cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS))
setup_force_cpu_bug(X86_BUG_SRBDS);
/*
* Processor MMIO Stale Data bug enumeration
*
* Affected CPU list is generally enough to enumerate the vulnerability,
* but for virtualization case check for ARCH_CAP MSR bits also, VMM may
* not want the guest to enumerate the bug.
*/
if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
!arch_cap_mmio_immune(ia32_cap))
setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;

11
arch/x86/kernel/ftrace_64.S
View File

@ -175,6 +175,7 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
jmp ftrace_epilogue
SYM_FUNC_END(ftrace_caller);
STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
SYM_FUNC_START(ftrace_epilogue)
/*
@ -282,6 +283,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
jmp ftrace_epilogue
SYM_FUNC_END(ftrace_regs_caller)
STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
#else /* ! CONFIG_DYNAMIC_FTRACE */
@ -311,10 +313,14 @@ trace:
jmp ftrace_stub
SYM_FUNC_END(__fentry__)
EXPORT_SYMBOL(__fentry__)
STACK_FRAME_NON_STANDARD_FP(__fentry__)
#endif /* CONFIG_DYNAMIC_FTRACE */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
SYM_FUNC_START(return_to_handler)
SYM_CODE_START(return_to_handler)
UNWIND_HINT_EMPTY
ANNOTATE_NOENDBR
subq $16, %rsp
/* Save the return values */
@ -339,7 +345,6 @@ SYM_FUNC_START(return_to_handler)
int3
.Ldo_rop:
mov %rdi, (%rsp)
UNWIND_HINT_FUNC
RET
SYM_FUNC_END(return_to_handler)
SYM_CODE_END(return_to_handler)
#endif

14
arch/x86/kernel/resource.c
View File

@ -1,7 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/dev_printk.h>
#include <linux/ioport.h>
#include <linux/printk.h>
#include <asm/e820/api.h>
#include <asm/pci_x86.h>
static void resource_clip(struct resource *res, resource_size_t start,
resource_size_t end)
@ -24,14 +25,14 @@ static void resource_clip(struct resource *res, resource_size_t start,
res->start = end + 1;
}
void remove_e820_regions(struct device *dev, struct resource *avail)
static void remove_e820_regions(struct resource *avail)
{
int i;
struct e820_entry *entry;
u64 e820_start, e820_end;
struct resource orig = *avail;
if (!(avail->flags & IORESOURCE_MEM))
if (!pci_use_e820)
return;
for (i = 0; i < e820_table->nr_entries; i++) {
@ -41,7 +42,7 @@ void remove_e820_regions(struct device *dev, struct resource *avail)
resource_clip(avail, e820_start, e820_end);
if (orig.start != avail->start || orig.end != avail->end) {
dev_info(dev, "clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n",
pr_info("clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n",
&orig, avail, e820_start, e820_end);
orig = *avail;
}
@ -55,6 +56,9 @@ void arch_remove_reservations(struct resource *avail)
* the low 1MB unconditionally, as this area is needed for some ISA
* cards requiring a memory range, e.g. the i82365 PCMCIA controller.
*/
if (avail->flags & IORESOURCE_MEM)
if (avail->flags & IORESOURCE_MEM) {
resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
remove_e820_regions(avail);
}
}

5
arch/x86/kernel/setup.c
View File

@ -67,11 +67,6 @@ RESERVE_BRK(dmi_alloc, 65536);
#endif
/*
* Range of the BSS area. The size of the BSS area is determined
* at link time, with RESERVE_BRK() facility reserving additional
* chunks.
*/
unsigned long _brk_start = (unsigned long)__brk_base;
unsigned long _brk_end = (unsigned long)__brk_base;

4
arch/x86/kernel/vmlinux.lds.S
View File

@ -385,10 +385,10 @@ SECTIONS
__end_of_kernel_reserve = .;
. = ALIGN(PAGE_SIZE);
.brk : AT(ADDR(.brk) - LOAD_OFFSET) {
.brk (NOLOAD) : AT(ADDR(.brk) - LOAD_OFFSET) {
__brk_base = .;
. += 64 * 1024; /* 64k alignment slop space */
*(.brk_reservation) /* areas brk users have reserved */
*(.bss..brk) /* areas brk users have reserved */
__brk_limit = .;
}

27
arch/x86/kvm/lapic.c
View File

@ -2039,6 +2039,19 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
}
}
static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic)
{
struct kvm *kvm = apic->vcpu->kvm;
if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm))
return;
if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id)
return;
kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED);
}
static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
{
int ret = 0;
@ -2047,10 +2060,12 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
switch (reg) {
case APIC_ID: /* Local APIC ID */
if (!apic_x2apic_mode(apic))
if (!apic_x2apic_mode(apic)) {
kvm_apic_set_xapic_id(apic, val >> 24);
else
kvm_lapic_xapic_id_updated(apic);
} else {
ret = 1;
}
break;
case APIC_TASKPRI:
@ -2336,8 +2351,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
MSR_IA32_APICBASE_BASE;
if ((value & MSR_IA32_APICBASE_ENABLE) &&
apic->base_address != APIC_DEFAULT_PHYS_BASE)
pr_warn_once("APIC base relocation is unsupported by KVM");
apic->base_address != APIC_DEFAULT_PHYS_BASE) {
kvm_set_apicv_inhibit(apic->vcpu->kvm,
APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
}
}
void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
@ -2648,6 +2665,8 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
__kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
}
} else {
kvm_lapic_xapic_id_updated(vcpu->arch.apic);
}
return 0;

2
arch/x86/kvm/mmu/mmu.c
View File

@ -3411,7 +3411,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
root = mmu_alloc_root(vcpu, i << (30 - PAGE_SHIFT),
i << 30, PT32_ROOT_LEVEL, true);
mmu->pae_root[i] = root | PT_PRESENT_MASK |
shadow_me_mask;
shadow_me_value;
}
mmu->root.hpa = __pa(mmu->pae_root);
} else {

177
arch/x86/kvm/svm/avic.c
View File

@ -291,58 +291,91 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
u32 icrl, u32 icrh, u32 index)
{
u32 dest, apic_id;
struct kvm_vcpu *vcpu;
u32 l1_physical_id, dest;
struct kvm_vcpu *target_vcpu;
int dest_mode = icrl & APIC_DEST_MASK;
int shorthand = icrl & APIC_SHORT_MASK;
struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
u32 *avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
if (shorthand != APIC_DEST_NOSHORT)
return -EINVAL;
/*
* The AVIC incomplete IPI #vmexit info provides index into
* the physical APIC ID table, which can be used to derive
* guest physical APIC ID.
*/
if (dest_mode == APIC_DEST_PHYSICAL) {
apic_id = index;
} else {
if (!apic_x2apic_mode(source)) {
/* For xAPIC logical mode, the index is for logical APIC table. */
apic_id = avic_logical_id_table[index] & 0x1ff;
} else {
return -EINVAL;
}
}
/*
* Assuming vcpu ID is the same as physical apic ID,
* and use it to retrieve the target vCPU.
*/
vcpu = kvm_get_vcpu_by_id(kvm, apic_id);
if (!vcpu)
return -EINVAL;
if (apic_x2apic_mode(vcpu->arch.apic))
if (apic_x2apic_mode(source))
dest = icrh;
else
dest = GET_APIC_DEST_FIELD(icrh);
/*
* Try matching the destination APIC ID with the vCPU.
*/
if (kvm_apic_match_dest(vcpu, source, shorthand, dest, dest_mode)) {
vcpu->arch.apic->irr_pending = true;
svm_complete_interrupt_delivery(vcpu,
icrl & APIC_MODE_MASK,
icrl & APIC_INT_LEVELTRIG,
icrl & APIC_VECTOR_MASK);
return 0;
if (dest_mode == APIC_DEST_PHYSICAL) {
/* broadcast destination, use slow path */
if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST)
return -EINVAL;
if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
return -EINVAL;
l1_physical_id = dest;
if (WARN_ON_ONCE(l1_physical_id != index))
return -EINVAL;
} else {
u32 bitmap, cluster;
int logid_index;
if (apic_x2apic_mode(source)) {
/* 16 bit dest mask, 16 bit cluster id */
bitmap = dest & 0xFFFF0000;
cluster = (dest >> 16) << 4;
} else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) {
/* 8 bit dest mask*/
bitmap = dest;
cluster = 0;
} else {
/* 4 bit desk mask, 4 bit cluster id */
bitmap = dest & 0xF;
cluster = (dest >> 4) << 2;
}
if (unlikely(!bitmap))
/* guest bug: nobody to send the logical interrupt to */
return 0;
if (!is_power_of_2(bitmap))
/* multiple logical destinations, use slow path */
return -EINVAL;
logid_index = cluster + __ffs(bitmap);
if (apic_x2apic_mode(source)) {
l1_physical_id = logid_index;
} else {
u32 *avic_logical_id_table =
page_address(kvm_svm->avic_logical_id_table_page);
u32 logid_entry = avic_logical_id_table[logid_index];
if (WARN_ON_ONCE(index != logid_index))
return -EINVAL;
/* guest bug: non existing/reserved logical destination */
if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
return 0;
l1_physical_id = logid_entry &
AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
}
}
return -EINVAL;
target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
if (unlikely(!target_vcpu))
/* guest bug: non existing vCPU is a target of this IPI*/
return 0;
target_vcpu->arch.apic->irr_pending = true;
svm_complete_interrupt_delivery(target_vcpu,
icrl & APIC_MODE_MASK,
icrl & APIC_INT_LEVELTRIG,
icrl & APIC_VECTOR_MASK);
return 0;
}
static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
@ -508,35 +541,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
return ret;
}
static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
{
u64 *old, *new;
struct vcpu_svm *svm = to_svm(vcpu);
u32 id = kvm_xapic_id(vcpu->arch.apic);
if (vcpu->vcpu_id == id)
return 0;
old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
new = avic_get_physical_id_entry(vcpu, id);
if (!new || !old)
return 1;
/* We need to move physical_id_entry to new offset */
*new = *old;
*old = 0ULL;
to_svm(vcpu)->avic_physical_id_cache = new;
/*
* Also update the guest physical APIC ID in the logical
* APIC ID table entry if already setup the LDR.
*/
if (svm->ldr_reg)
avic_handle_ldr_update(vcpu);
return 0;
}
static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@ -555,10 +559,6 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu)
AVIC_UNACCEL_ACCESS_OFFSET_MASK;
switch (offset) {
case APIC_ID:
if (avic_handle_apic_id_update(vcpu))
return 0;
break;
case APIC_LDR:
if (avic_handle_ldr_update(vcpu))
return 0;
@ -650,8 +650,6 @@ int avic_init_vcpu(struct vcpu_svm *svm)
void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
{
if (avic_handle_apic_id_update(vcpu) != 0)
return;
avic_handle_dfr_update(vcpu);
avic_handle_ldr_update(vcpu);
}
@ -910,7 +908,9 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
BIT(APICV_INHIBIT_REASON_X2APIC) |
BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
BIT(APICV_INHIBIT_REASON_SEV);
BIT(APICV_INHIBIT_REASON_SEV) |
BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
return supported & BIT(reason);
}
@ -946,7 +946,7 @@ out:
return ret;
}
void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
u64 entry;
int h_physical_id = kvm_cpu_get_apicid(cpu);
@ -978,7 +978,7 @@ void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
}
void __avic_vcpu_put(struct kvm_vcpu *vcpu)
void avic_vcpu_put(struct kvm_vcpu *vcpu)
{
u64 entry;
struct vcpu_svm *svm = to_svm(vcpu);
@ -997,25 +997,6 @@ void __avic_vcpu_put(struct kvm_vcpu *vcpu)
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
}
static void avic_vcpu_load(struct kvm_vcpu *vcpu)
{
int cpu = get_cpu();
WARN_ON(cpu != vcpu->cpu);
__avic_vcpu_load(vcpu, cpu);
put_cpu();
}
static void avic_vcpu_put(struct kvm_vcpu *vcpu)
{
preempt_disable();
__avic_vcpu_put(vcpu);
preempt_enable();
}
void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
@ -1042,7 +1023,7 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
vmcb_mark_dirty(vmcb, VMCB_AVIC);
if (activated)
avic_vcpu_load(vcpu);
avic_vcpu_load(vcpu, vcpu->cpu);
else
avic_vcpu_put(vcpu);
@ -1075,5 +1056,5 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
if (!kvm_vcpu_apicv_active(vcpu))
return;
avic_vcpu_load(vcpu);
avic_vcpu_load(vcpu, vcpu->cpu);
}

39
arch/x86/kvm/svm/nested.c
View File

@ -616,6 +616,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
struct kvm_vcpu *vcpu = &svm->vcpu;
struct vmcb *vmcb01 = svm->vmcb01.ptr;
struct vmcb *vmcb02 = svm->nested.vmcb02.ptr;
u32 pause_count12;
u32 pause_thresh12;
/*
* Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2,
@ -671,27 +673,25 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm)
if (!nested_vmcb_needs_vls_intercept(svm))
vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
pause_count12 = svm->pause_filter_enabled ? svm->nested.ctl.pause_filter_count : 0;
pause_thresh12 = svm->pause_threshold_enabled ? svm->nested.ctl.pause_filter_thresh : 0;
if (kvm_pause_in_guest(svm->vcpu.kvm)) {
/* use guest values since host doesn't use them */
vmcb02->control.pause_filter_count =
svm->pause_filter_enabled ?
svm->nested.ctl.pause_filter_count : 0;
/* use guest values since host doesn't intercept PAUSE */
vmcb02->control.pause_filter_count = pause_count12;
vmcb02->control.pause_filter_thresh = pause_thresh12;
vmcb02->control.pause_filter_thresh =
svm->pause_threshold_enabled ?
svm->nested.ctl.pause_filter_thresh : 0;
} else if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
/* use host values when guest doesn't use them */
} else {
/* start from host values otherwise */
vmcb02->control.pause_filter_count = vmcb01->control.pause_filter_count;
vmcb02->control.pause_filter_thresh = vmcb01->control.pause_filter_thresh;
} else {
/*
* Intercept every PAUSE otherwise and
* ignore both host and guest values
*/
vmcb02->control.pause_filter_count = 0;
vmcb02->control.pause_filter_thresh = 0;
/* ... but ensure filtering is disabled if so requested. */
if (vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_PAUSE)) {
if (!pause_count12)
vmcb02->control.pause_filter_count = 0;
if (!pause_thresh12)
vmcb02->control.pause_filter_thresh = 0;
}
}
nested_svm_transition_tlb_flush(vcpu);
@ -951,8 +951,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
vmcb12->control.event_inj = svm->nested.ctl.event_inj;
vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err;
if (!kvm_pause_in_guest(vcpu->kvm) && vmcb02->control.pause_filter_count)
if (!kvm_pause_in_guest(vcpu->kvm)) {
vmcb01->control.pause_filter_count = vmcb02->control.pause_filter_count;
vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
}
nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);

8
arch/x86/kvm/svm/svm.c
View File

@ -921,7 +921,7 @@ static void grow_ple_window(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;
if (kvm_pause_in_guest(vcpu->kvm) || !old)
if (kvm_pause_in_guest(vcpu->kvm))
return;
control->pause_filter_count = __grow_ple_window(old,
@ -942,7 +942,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
int old = control->pause_filter_count;
if (kvm_pause_in_guest(vcpu->kvm) || !old)
if (kvm_pause_in_guest(vcpu->kvm))
return;
control->pause_filter_count =
@ -1400,13 +1400,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
indirect_branch_prediction_barrier();
}
if (kvm_vcpu_apicv_active(vcpu))
__avic_vcpu_load(vcpu, cpu);
avic_vcpu_load(vcpu, cpu);
}
static void svm_vcpu_put(struct kvm_vcpu *vcpu)
{
if (kvm_vcpu_apicv_active(vcpu))
__avic_vcpu_put(vcpu);
avic_vcpu_put(vcpu);
svm_prepare_host_switch(vcpu);

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