mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-01-22 07:53:11 -05:00
Miscellaneous x86 cleanups and typo fixes, and also the removal
of the "disablelapic" boot parameter. Signed-off-by: Ingo Molnar <mingo@kernel.org> -----BEGIN PGP SIGNATURE----- iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmePTD8RHG1pbmdvQGtl cm5lbC5vcmcACgkQEnMQ0APhK1jf5g//Wo1WKUXukRrBANr2nIlx9B7xJliRmUxv mJ0VKo49YPl6C34fjSHhBs3+nPbYD+CyWVKAz5PqkfkFRGBgpQi26EnyKaIhLVFW HWhW5vQm/FJfzBIrfFg7g/H1PK+rEYa4mv8JF9vhwp7BOfuqx4ABGKWQnrvOGg2B VivE5k7/kxWRPTg45Kgb1iwlS2gcfWCRi9qdCzdJgY/4XYE6k6hKeV0PgTT3Vojf pZKsgZRq8tzMaX75obtyyrX3TWj0nkRec0XbgyXBFvlFh/l3e0RswxzGGAjrC1XP R+qmscdCkczUwRGc1mGj9MoCqMRRffU6/hTNsjqu8o7Q2gzZzXWHcUc+X7UwOeKZ 2guxOj4iagdn7+mIso6uAjY+OOdFVw7/C8ysbCmwo3MiaDsfaK2NkdBoT2xDWuIw NP/45RMpTIsgL0wG6upzXXApKgYxfWhNSq+oHDF4/TjWY4i779hjMghvtX1BI7yb LXIh2SsRcnmEPl42UGaz6xmdmkulWZPPxI5rghixU48Eazkngfp7ZTHYpm5NFoRP Qc3JNcKo7rGmkoo/sA7uwawjnaTz/H77SDNjfAufzjVAKidvUqW6xaK/8JM1fq0n du+9sQN5MrAqdKx5Lu624s/7ektwkDeUdQFGazqS9y0GBT25T9Rw+LQDuec7BG3p v8sok4IaPA0= =Hzj3 -----END PGP SIGNATURE----- Merge tag 'x86-cleanups-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 cleanups from Ingo Molnar: "Miscellaneous x86 cleanups and typo fixes, and also the removal of the 'disablelapic' boot parameter" * tag 'x86-cleanups-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/ioapic: Remove a stray tab in the IO-APIC type string x86/cpufeatures: Remove "AMD" from the comments to the AMD-specific leaf Documentation/kernel-parameters: Fix a typo in kvm.enable_virt_at_load text x86/cpu: Fix typo in x86_match_cpu()'s doc x86/apic: Remove "disablelapic" cmdline option Documentation: Merge x86-specific boot options doc into kernel-parameters.txt x86/ioremap: Remove unused size parameter in remapping functions x86/ioremap: Simplify setup_data mapping variants x86/boot/compressed: Remove unused header includes from kaslr.c
This commit is contained in:
Linus Torvalds
commit
858df1de21
14 changed files with 278 additions and 435 deletions
|
|
@ -194,8 +194,6 @@ is applicable::
|
|||
WDT Watchdog support is enabled.
|
||||
X86-32 X86-32, aka i386 architecture is enabled.
|
||||
X86-64 X86-64 architecture is enabled.
|
||||
More X86-64 boot options can be found in
|
||||
Documentation/arch/x86/x86_64/boot-options.rst.
|
||||
X86 Either 32-bit or 64-bit x86 (same as X86-32+X86-64)
|
||||
X86_UV SGI UV support is enabled.
|
||||
XEN Xen support is enabled
|
||||
|
|
@ -213,7 +211,6 @@ Do not modify the syntax of boot loader parameters without extreme
|
|||
need or coordination with <Documentation/arch/x86/boot.rst>.
|
||||
|
||||
There are also arch-specific kernel-parameters not documented here.
|
||||
See for example <Documentation/arch/x86/x86_64/boot-options.rst>.
|
||||
|
||||
Note that ALL kernel parameters listed below are CASE SENSITIVE, and that
|
||||
a trailing = on the name of any parameter states that that parameter will
|
||||
|
|
|
|||
|
|
@ -21,6 +21,10 @@
|
|||
strictly ACPI specification compliant.
|
||||
rsdt -- prefer RSDT over (default) XSDT
|
||||
copy_dsdt -- copy DSDT to memory
|
||||
nocmcff -- Disable firmware first mode for corrected
|
||||
errors. This disables parsing the HEST CMC error
|
||||
source to check if firmware has set the FF flag. This
|
||||
may result in duplicate corrected error reports.
|
||||
nospcr -- disable console in ACPI SPCR table as
|
||||
default _serial_ console on ARM64
|
||||
For ARM64, ONLY "acpi=off", "acpi=on", "acpi=force" or
|
||||
|
|
@ -405,6 +409,8 @@
|
|||
not play well with APC CPU idle - disable it if you have
|
||||
APC and your system crashes randomly.
|
||||
|
||||
apic [APIC,X86-64] Use IO-APIC. Default.
|
||||
|
||||
apic= [APIC,X86,EARLY] Advanced Programmable Interrupt Controller
|
||||
Change the output verbosity while booting
|
||||
Format: { quiet (default) | verbose | debug }
|
||||
|
|
@ -424,6 +430,10 @@
|
|||
useful so that a dump capture kernel won't be
|
||||
shot down by NMI
|
||||
|
||||
apicpmtimer Do APIC timer calibration using the pmtimer. Implies
|
||||
apicmaintimer. Useful when your PIT timer is totally
|
||||
broken.
|
||||
|
||||
autoconf= [IPV6]
|
||||
See Documentation/networking/ipv6.rst.
|
||||
|
||||
|
|
@ -1726,6 +1736,8 @@
|
|||
|
||||
off: Disable GDS mitigation.
|
||||
|
||||
gbpages [X86] Use GB pages for kernel direct mappings.
|
||||
|
||||
gcov_persist= [GCOV] When non-zero (default), profiling data for
|
||||
kernel modules is saved and remains accessible via
|
||||
debugfs, even when the module is unloaded/reloaded.
|
||||
|
|
@ -2008,12 +2020,21 @@
|
|||
|
||||
idle= [X86,EARLY]
|
||||
Format: idle=poll, idle=halt, idle=nomwait
|
||||
Poll forces a polling idle loop that can slightly
|
||||
improve the performance of waking up a idle CPU, but
|
||||
will use a lot of power and make the system run hot.
|
||||
Not recommended.
|
||||
|
||||
idle=poll: Don't do power saving in the idle loop
|
||||
using HLT, but poll for rescheduling event. This will
|
||||
make the CPUs eat a lot more power, but may be useful
|
||||
to get slightly better performance in multiprocessor
|
||||
benchmarks. It also makes some profiling using
|
||||
performance counters more accurate. Please note that
|
||||
on systems with MONITOR/MWAIT support (like Intel
|
||||
EM64T CPUs) this option has no performance advantage
|
||||
over the normal idle loop. It may also interact badly
|
||||
with hyperthreading.
|
||||
|
||||
idle=halt: Halt is forced to be used for CPU idle.
|
||||
In such case C2/C3 won't be used again.
|
||||
|
||||
idle=nomwait: Disable mwait for CPU C-states
|
||||
|
||||
idxd.sva= [HW]
|
||||
|
|
@ -2311,20 +2332,73 @@
|
|||
relaxed
|
||||
|
||||
iommu= [X86,EARLY]
|
||||
|
||||
off
|
||||
Don't initialize and use any kind of IOMMU.
|
||||
|
||||
force
|
||||
Force the use of the hardware IOMMU even when
|
||||
it is not actually needed (e.g. because < 3 GB
|
||||
memory).
|
||||
|
||||
noforce
|
||||
Don't force hardware IOMMU usage when it is not
|
||||
needed. (default).
|
||||
|
||||
biomerge
|
||||
panic
|
||||
nopanic
|
||||
merge
|
||||
nomerge
|
||||
|
||||
soft
|
||||
pt [X86]
|
||||
nopt [X86]
|
||||
nobypass [PPC/POWERNV]
|
||||
Use software bounce buffering (SWIOTLB) (default for
|
||||
Intel machines). This can be used to prevent the usage
|
||||
of an available hardware IOMMU.
|
||||
|
||||
[X86]
|
||||
pt
|
||||
[X86]
|
||||
nopt
|
||||
[PPC/POWERNV]
|
||||
nobypass
|
||||
Disable IOMMU bypass, using IOMMU for PCI devices.
|
||||
|
||||
[X86]
|
||||
AMD Gart HW IOMMU-specific options:
|
||||
|
||||
<size>
|
||||
Set the size of the remapping area in bytes.
|
||||
|
||||
allowed
|
||||
Overwrite iommu off workarounds for specific chipsets
|
||||
|
||||
fullflush
|
||||
Flush IOMMU on each allocation (default).
|
||||
|
||||
nofullflush
|
||||
Don't use IOMMU fullflush.
|
||||
|
||||
memaper[=<order>]
|
||||
Allocate an own aperture over RAM with size
|
||||
32MB<<order. (default: order=1, i.e. 64MB)
|
||||
|
||||
merge
|
||||
Do scatter-gather (SG) merging. Implies "force"
|
||||
(experimental).
|
||||
|
||||
nomerge
|
||||
Don't do scatter-gather (SG) merging.
|
||||
|
||||
noaperture
|
||||
Ask the IOMMU not to touch the aperture for AGP.
|
||||
|
||||
noagp
|
||||
Don't initialize the AGP driver and use full aperture.
|
||||
|
||||
panic
|
||||
Always panic when IOMMU overflows.
|
||||
|
||||
iommu.forcedac= [ARM64,X86,EARLY] Control IOVA allocation for PCI devices.
|
||||
Format: { "0" | "1" }
|
||||
0 - Try to allocate a 32-bit DMA address first, before
|
||||
|
|
@ -2695,7 +2769,7 @@
|
|||
VMs, i.e. on the 0=>1 and 1=>0 transitions of the
|
||||
number of VMs.
|
||||
|
||||
Enabling virtualization at module lode avoids potential
|
||||
Enabling virtualization at module load avoids potential
|
||||
latency for creation of the 0=>1 VM, as KVM serializes
|
||||
virtualization enabling across all online CPUs. The
|
||||
"cost" of enabling virtualization when KVM is loaded,
|
||||
|
|
@ -3259,9 +3333,77 @@
|
|||
devices can be requested on-demand with the
|
||||
/dev/loop-control interface.
|
||||
|
||||
mce [X86-32] Machine Check Exception
|
||||
mce= [X86-{32,64}]
|
||||
|
||||
Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables.
|
||||
|
||||
off
|
||||
disable machine check
|
||||
|
||||
no_cmci
|
||||
disable CMCI(Corrected Machine Check Interrupt) that
|
||||
Intel processor supports. Usually this disablement is
|
||||
not recommended, but it might be handy if your
|
||||
hardware is misbehaving.
|
||||
|
||||
Note that you'll get more problems without CMCI than
|
||||
with due to the shared banks, i.e. you might get
|
||||
duplicated error logs.
|
||||
|
||||
dont_log_ce
|
||||
don't make logs for corrected errors. All events
|
||||
reported as corrected are silently cleared by OS. This
|
||||
option will be useful if you have no interest in any
|
||||
of corrected errors.
|
||||
|
||||
ignore_ce
|
||||
disable features for corrected errors, e.g.
|
||||
polling timer and CMCI. All events reported as
|
||||
corrected are not cleared by OS and remained in its
|
||||
error banks.
|
||||
|
||||
Usually this disablement is not recommended, however
|
||||
if there is an agent checking/clearing corrected
|
||||
errors (e.g. BIOS or hardware monitoring
|
||||
applications), conflicting with OS's error handling,
|
||||
and you cannot deactivate the agent, then this option
|
||||
will be a help.
|
||||
|
||||
no_lmce
|
||||
do not opt-in to Local MCE delivery. Use legacy method
|
||||
to broadcast MCEs.
|
||||
|
||||
bootlog
|
||||
enable logging of machine checks left over from
|
||||
booting. Disabled by default on AMD Fam10h and older
|
||||
because some BIOS leave bogus ones.
|
||||
|
||||
If your BIOS doesn't do that it's a good idea to
|
||||
enable though to make sure you log even machine check
|
||||
events that result in a reboot. On Intel systems it is
|
||||
enabled by default.
|
||||
|
||||
nobootlog
|
||||
disable boot machine check logging.
|
||||
|
||||
monarchtimeout (number)
|
||||
sets the time in us to wait for other CPUs on machine
|
||||
checks. 0 to disable.
|
||||
|
||||
bios_cmci_threshold
|
||||
don't overwrite the bios-set CMCI threshold. This boot
|
||||
option prevents Linux from overwriting the CMCI
|
||||
threshold set by the bios. Without this option, Linux
|
||||
always sets the CMCI threshold to 1. Enabling this may
|
||||
make memory predictive failure analysis less effective
|
||||
if the bios sets thresholds for memory errors since we
|
||||
will not see details for all errors.
|
||||
|
||||
recovery
|
||||
force-enable recoverable machine check code paths
|
||||
|
||||
Everything else is in sysfs now.
|
||||
|
||||
mce=option [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
|
||||
|
||||
md= [HW] RAID subsystems devices and level
|
||||
See Documentation/admin-guide/md.rst.
|
||||
|
|
@ -3887,6 +4029,8 @@
|
|||
noapic [SMP,APIC,EARLY] Tells the kernel to not make use of any
|
||||
IOAPICs that may be present in the system.
|
||||
|
||||
noapictimer [APIC,X86] Don't set up the APIC timer
|
||||
|
||||
noautogroup Disable scheduler automatic task group creation.
|
||||
|
||||
nocache [ARM,EARLY]
|
||||
|
|
@ -3934,6 +4078,8 @@
|
|||
register save and restore. The kernel will only save
|
||||
legacy floating-point registers on task switch.
|
||||
|
||||
nogbpages [X86] Do not use GB pages for kernel direct mappings.
|
||||
|
||||
no_hash_pointers
|
||||
[KNL,EARLY]
|
||||
Force pointers printed to the console or buffers to be
|
||||
|
|
@ -3960,6 +4106,8 @@
|
|||
the impact of the sleep instructions. This is also
|
||||
useful when using JTAG debugger.
|
||||
|
||||
nohpet [X86] Don't use the HPET timer.
|
||||
|
||||
nohugeiomap [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge I/O mappings.
|
||||
|
||||
nohugevmalloc [KNL,X86,PPC,ARM64,EARLY] Disable kernel huge vmalloc mappings.
|
||||
|
|
@ -4111,8 +4259,10 @@
|
|||
|
||||
nosync [HW,M68K] Disables sync negotiation for all devices.
|
||||
|
||||
no_timer_check [X86,APIC] Disables the code which tests for
|
||||
broken timer IRQ sources.
|
||||
no_timer_check [X86,APIC] Disables the code which tests for broken
|
||||
timer IRQ sources, i.e., the IO-APIC timer. This can
|
||||
work around problems with incorrect timer
|
||||
initialization on some boards.
|
||||
|
||||
no_uaccess_flush
|
||||
[PPC,EARLY] Don't flush the L1-D cache after accessing user data.
|
||||
|
|
@ -4192,6 +4342,11 @@
|
|||
If given as an integer followed by 'U', it will
|
||||
divide each physical node into N emulated nodes.
|
||||
|
||||
numa=noacpi [X86] Don't parse the SRAT table for NUMA setup
|
||||
|
||||
numa=nohmat [X86] Don't parse the HMAT table for NUMA setup, or
|
||||
soft-reserved memory partitioning.
|
||||
|
||||
numa_balancing= [KNL,ARM64,PPC,RISCV,S390,X86] Enable or disable automatic
|
||||
NUMA balancing.
|
||||
Allowed values are enable and disable
|
||||
|
|
@ -5715,6 +5870,55 @@
|
|||
reboot_cpu is s[mp]#### with #### being the processor
|
||||
to be used for rebooting.
|
||||
|
||||
acpi
|
||||
Use the ACPI RESET_REG in the FADT. If ACPI is not
|
||||
configured or the ACPI reset does not work, the reboot
|
||||
path attempts the reset using the keyboard controller.
|
||||
|
||||
bios
|
||||
Use the CPU reboot vector for warm reset
|
||||
|
||||
cold
|
||||
Set the cold reboot flag
|
||||
|
||||
default
|
||||
There are some built-in platform specific "quirks"
|
||||
- you may see: "reboot: <name> series board detected.
|
||||
Selecting <type> for reboots." In the case where you
|
||||
think the quirk is in error (e.g. you have newer BIOS,
|
||||
or newer board) using this option will ignore the
|
||||
built-in quirk table, and use the generic default
|
||||
reboot actions.
|
||||
|
||||
efi
|
||||
Use efi reset_system runtime service. If EFI is not
|
||||
configured or the EFI reset does not work, the reboot
|
||||
path attempts the reset using the keyboard controller.
|
||||
|
||||
force
|
||||
Don't stop other CPUs on reboot. This can make reboot
|
||||
more reliable in some cases.
|
||||
|
||||
kbd
|
||||
Use the keyboard controller. cold reset (default)
|
||||
|
||||
pci
|
||||
Use a write to the PCI config space register 0xcf9 to
|
||||
trigger reboot.
|
||||
|
||||
triple
|
||||
Force a triple fault (init)
|
||||
|
||||
warm
|
||||
Don't set the cold reboot flag
|
||||
|
||||
Using warm reset will be much faster especially on big
|
||||
memory systems because the BIOS will not go through
|
||||
the memory check. Disadvantage is that not all
|
||||
hardware will be completely reinitialized on reboot so
|
||||
there may be boot problems on some systems.
|
||||
|
||||
|
||||
refscale.holdoff= [KNL]
|
||||
Set test-start holdoff period. The purpose of
|
||||
this parameter is to delay the start of the
|
||||
|
|
@ -6106,7 +6310,16 @@
|
|||
|
||||
serialnumber [BUGS=X86-32]
|
||||
|
||||
sev=option[,option...] [X86-64] See Documentation/arch/x86/x86_64/boot-options.rst
|
||||
sev=option[,option...] [X86-64]
|
||||
|
||||
debug
|
||||
Enable debug messages.
|
||||
|
||||
nosnp
|
||||
Do not enable SEV-SNP (applies to host/hypervisor
|
||||
only). Setting 'nosnp' avoids the RMP check overhead
|
||||
in memory accesses when users do not want to run
|
||||
SEV-SNP guests.
|
||||
|
||||
shapers= [NET]
|
||||
Maximal number of shapers.
|
||||
|
|
|
|||
|
|
@ -1,312 +0,0 @@
|
|||
.. SPDX-License-Identifier: GPL-2.0
|
||||
|
||||
===========================
|
||||
AMD64 Specific Boot Options
|
||||
===========================
|
||||
|
||||
There are many others (usually documented in driver documentation), but
|
||||
only the AMD64 specific ones are listed here.
|
||||
|
||||
Machine check
|
||||
=============
|
||||
Please see Documentation/arch/x86/x86_64/machinecheck.rst for sysfs runtime tunables.
|
||||
|
||||
mce=off
|
||||
Disable machine check
|
||||
mce=no_cmci
|
||||
Disable CMCI(Corrected Machine Check Interrupt) that
|
||||
Intel processor supports. Usually this disablement is
|
||||
not recommended, but it might be handy if your hardware
|
||||
is misbehaving.
|
||||
Note that you'll get more problems without CMCI than with
|
||||
due to the shared banks, i.e. you might get duplicated
|
||||
error logs.
|
||||
mce=dont_log_ce
|
||||
Don't make logs for corrected errors. All events reported
|
||||
as corrected are silently cleared by OS.
|
||||
This option will be useful if you have no interest in any
|
||||
of corrected errors.
|
||||
mce=ignore_ce
|
||||
Disable features for corrected errors, e.g. polling timer
|
||||
and CMCI. All events reported as corrected are not cleared
|
||||
by OS and remained in its error banks.
|
||||
Usually this disablement is not recommended, however if
|
||||
there is an agent checking/clearing corrected errors
|
||||
(e.g. BIOS or hardware monitoring applications), conflicting
|
||||
with OS's error handling, and you cannot deactivate the agent,
|
||||
then this option will be a help.
|
||||
mce=no_lmce
|
||||
Do not opt-in to Local MCE delivery. Use legacy method
|
||||
to broadcast MCEs.
|
||||
mce=bootlog
|
||||
Enable logging of machine checks left over from booting.
|
||||
Disabled by default on AMD Fam10h and older because some BIOS
|
||||
leave bogus ones.
|
||||
If your BIOS doesn't do that it's a good idea to enable though
|
||||
to make sure you log even machine check events that result
|
||||
in a reboot. On Intel systems it is enabled by default.
|
||||
mce=nobootlog
|
||||
Disable boot machine check logging.
|
||||
mce=monarchtimeout (number)
|
||||
monarchtimeout:
|
||||
Sets the time in us to wait for other CPUs on machine checks. 0
|
||||
to disable.
|
||||
mce=bios_cmci_threshold
|
||||
Don't overwrite the bios-set CMCI threshold. This boot option
|
||||
prevents Linux from overwriting the CMCI threshold set by the
|
||||
bios. Without this option, Linux always sets the CMCI
|
||||
threshold to 1. Enabling this may make memory predictive failure
|
||||
analysis less effective if the bios sets thresholds for memory
|
||||
errors since we will not see details for all errors.
|
||||
mce=recovery
|
||||
Force-enable recoverable machine check code paths
|
||||
|
||||
nomce (for compatibility with i386)
|
||||
same as mce=off
|
||||
|
||||
Everything else is in sysfs now.
|
||||
|
||||
APICs
|
||||
=====
|
||||
|
||||
apic
|
||||
Use IO-APIC. Default
|
||||
|
||||
noapic
|
||||
Don't use the IO-APIC.
|
||||
|
||||
disableapic
|
||||
Don't use the local APIC
|
||||
|
||||
nolapic
|
||||
Don't use the local APIC (alias for i386 compatibility)
|
||||
|
||||
pirq=...
|
||||
See Documentation/arch/x86/i386/IO-APIC.rst
|
||||
|
||||
noapictimer
|
||||
Don't set up the APIC timer
|
||||
|
||||
no_timer_check
|
||||
Don't check the IO-APIC timer. This can work around
|
||||
problems with incorrect timer initialization on some boards.
|
||||
|
||||
apicpmtimer
|
||||
Do APIC timer calibration using the pmtimer. Implies
|
||||
apicmaintimer. Useful when your PIT timer is totally broken.
|
||||
|
||||
Timing
|
||||
======
|
||||
|
||||
notsc
|
||||
Deprecated, use tsc=unstable instead.
|
||||
|
||||
nohpet
|
||||
Don't use the HPET timer.
|
||||
|
||||
Idle loop
|
||||
=========
|
||||
|
||||
idle=poll
|
||||
Don't do power saving in the idle loop using HLT, but poll for rescheduling
|
||||
event. This will make the CPUs eat a lot more power, but may be useful
|
||||
to get slightly better performance in multiprocessor benchmarks. It also
|
||||
makes some profiling using performance counters more accurate.
|
||||
Please note that on systems with MONITOR/MWAIT support (like Intel EM64T
|
||||
CPUs) this option has no performance advantage over the normal idle loop.
|
||||
It may also interact badly with hyperthreading.
|
||||
|
||||
Rebooting
|
||||
=========
|
||||
|
||||
reboot=b[ios] | t[riple] | k[bd] | a[cpi] | e[fi] | p[ci] [, [w]arm | [c]old]
|
||||
bios
|
||||
Use the CPU reboot vector for warm reset
|
||||
warm
|
||||
Don't set the cold reboot flag
|
||||
cold
|
||||
Set the cold reboot flag
|
||||
triple
|
||||
Force a triple fault (init)
|
||||
kbd
|
||||
Use the keyboard controller. cold reset (default)
|
||||
acpi
|
||||
Use the ACPI RESET_REG in the FADT. If ACPI is not configured or
|
||||
the ACPI reset does not work, the reboot path attempts the reset
|
||||
using the keyboard controller.
|
||||
efi
|
||||
Use efi reset_system runtime service. If EFI is not configured or
|
||||
the EFI reset does not work, the reboot path attempts the reset using
|
||||
the keyboard controller.
|
||||
pci
|
||||
Use a write to the PCI config space register 0xcf9 to trigger reboot.
|
||||
|
||||
Using warm reset will be much faster especially on big memory
|
||||
systems because the BIOS will not go through the memory check.
|
||||
Disadvantage is that not all hardware will be completely reinitialized
|
||||
on reboot so there may be boot problems on some systems.
|
||||
|
||||
reboot=force
|
||||
Don't stop other CPUs on reboot. This can make reboot more reliable
|
||||
in some cases.
|
||||
|
||||
reboot=default
|
||||
There are some built-in platform specific "quirks" - you may see:
|
||||
"reboot: <name> series board detected. Selecting <type> for reboots."
|
||||
In the case where you think the quirk is in error (e.g. you have
|
||||
newer BIOS, or newer board) using this option will ignore the built-in
|
||||
quirk table, and use the generic default reboot actions.
|
||||
|
||||
NUMA
|
||||
====
|
||||
|
||||
numa=off
|
||||
Only set up a single NUMA node spanning all memory.
|
||||
|
||||
numa=noacpi
|
||||
Don't parse the SRAT table for NUMA setup
|
||||
|
||||
numa=nohmat
|
||||
Don't parse the HMAT table for NUMA setup, or soft-reserved memory
|
||||
partitioning.
|
||||
|
||||
ACPI
|
||||
====
|
||||
|
||||
acpi=off
|
||||
Don't enable ACPI
|
||||
acpi=ht
|
||||
Use ACPI boot table parsing, but don't enable ACPI interpreter
|
||||
acpi=force
|
||||
Force ACPI on (currently not needed)
|
||||
acpi=strict
|
||||
Disable out of spec ACPI workarounds.
|
||||
acpi_sci={edge,level,high,low}
|
||||
Set up ACPI SCI interrupt.
|
||||
acpi=noirq
|
||||
Don't route interrupts
|
||||
acpi=nocmcff
|
||||
Disable firmware first mode for corrected errors. This
|
||||
disables parsing the HEST CMC error source to check if
|
||||
firmware has set the FF flag. This may result in
|
||||
duplicate corrected error reports.
|
||||
|
||||
PCI
|
||||
===
|
||||
|
||||
pci=off
|
||||
Don't use PCI
|
||||
pci=conf1
|
||||
Use conf1 access.
|
||||
pci=conf2
|
||||
Use conf2 access.
|
||||
pci=rom
|
||||
Assign ROMs.
|
||||
pci=assign-busses
|
||||
Assign busses
|
||||
pci=irqmask=MASK
|
||||
Set PCI interrupt mask to MASK
|
||||
pci=lastbus=NUMBER
|
||||
Scan up to NUMBER busses, no matter what the mptable says.
|
||||
pci=noacpi
|
||||
Don't use ACPI to set up PCI interrupt routing.
|
||||
|
||||
IOMMU (input/output memory management unit)
|
||||
===========================================
|
||||
Multiple x86-64 PCI-DMA mapping implementations exist, for example:
|
||||
|
||||
1. <kernel/dma/direct.c>: use no hardware/software IOMMU at all
|
||||
(e.g. because you have < 3 GB memory).
|
||||
Kernel boot message: "PCI-DMA: Disabling IOMMU"
|
||||
|
||||
2. <arch/x86/kernel/amd_gart_64.c>: AMD GART based hardware IOMMU.
|
||||
Kernel boot message: "PCI-DMA: using GART IOMMU"
|
||||
|
||||
3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used
|
||||
e.g. if there is no hardware IOMMU in the system and it is need because
|
||||
you have >3GB memory or told the kernel to us it (iommu=soft))
|
||||
Kernel boot message: "PCI-DMA: Using software bounce buffering
|
||||
for IO (SWIOTLB)"
|
||||
|
||||
::
|
||||
|
||||
iommu=[<size>][,noagp][,off][,force][,noforce]
|
||||
[,memaper[=<order>]][,merge][,fullflush][,nomerge]
|
||||
[,noaperture]
|
||||
|
||||
General iommu options:
|
||||
|
||||
off
|
||||
Don't initialize and use any kind of IOMMU.
|
||||
noforce
|
||||
Don't force hardware IOMMU usage when it is not needed. (default).
|
||||
force
|
||||
Force the use of the hardware IOMMU even when it is
|
||||
not actually needed (e.g. because < 3 GB memory).
|
||||
soft
|
||||
Use software bounce buffering (SWIOTLB) (default for
|
||||
Intel machines). This can be used to prevent the usage
|
||||
of an available hardware IOMMU.
|
||||
|
||||
iommu options only relevant to the AMD GART hardware IOMMU:
|
||||
|
||||
<size>
|
||||
Set the size of the remapping area in bytes.
|
||||
allowed
|
||||
Overwrite iommu off workarounds for specific chipsets.
|
||||
fullflush
|
||||
Flush IOMMU on each allocation (default).
|
||||
nofullflush
|
||||
Don't use IOMMU fullflush.
|
||||
memaper[=<order>]
|
||||
Allocate an own aperture over RAM with size 32MB<<order.
|
||||
(default: order=1, i.e. 64MB)
|
||||
merge
|
||||
Do scatter-gather (SG) merging. Implies "force" (experimental).
|
||||
nomerge
|
||||
Don't do scatter-gather (SG) merging.
|
||||
noaperture
|
||||
Ask the IOMMU not to touch the aperture for AGP.
|
||||
noagp
|
||||
Don't initialize the AGP driver and use full aperture.
|
||||
panic
|
||||
Always panic when IOMMU overflows.
|
||||
|
||||
iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU
|
||||
implementation:
|
||||
|
||||
swiotlb=<slots>[,force,noforce]
|
||||
<slots>
|
||||
Prereserve that many 2K slots for the software IO bounce buffering.
|
||||
force
|
||||
Force all IO through the software TLB.
|
||||
noforce
|
||||
Do not initialize the software TLB.
|
||||
|
||||
|
||||
Miscellaneous
|
||||
=============
|
||||
|
||||
nogbpages
|
||||
Do not use GB pages for kernel direct mappings.
|
||||
gbpages
|
||||
Use GB pages for kernel direct mappings.
|
||||
|
||||
|
||||
AMD SEV (Secure Encrypted Virtualization)
|
||||
=========================================
|
||||
Options relating to AMD SEV, specified via the following format:
|
||||
|
||||
::
|
||||
|
||||
sev=option1[,option2]
|
||||
|
||||
The available options are:
|
||||
|
||||
debug
|
||||
Enable debug messages.
|
||||
|
||||
nosnp
|
||||
Do not enable SEV-SNP (applies to host/hypervisor only). Setting
|
||||
'nosnp' avoids the RMP check overhead in memory accesses when
|
||||
users do not want to run SEV-SNP guests.
|
||||
|
|
@ -18,7 +18,7 @@ For more information on the features of cpusets, see
|
|||
Documentation/admin-guide/cgroup-v1/cpusets.rst.
|
||||
There are a number of different configurations you can use for your needs. For
|
||||
more information on the numa=fake command line option and its various ways of
|
||||
configuring fake nodes, see Documentation/arch/x86/x86_64/boot-options.rst.
|
||||
configuring fake nodes, see Documentation/admin-guide/kernel-parameters.txt
|
||||
|
||||
For the purposes of this introduction, we'll assume a very primitive NUMA
|
||||
emulation setup of "numa=fake=4*512,". This will split our system memory into
|
||||
|
|
|
|||
|
|
@ -7,7 +7,6 @@ x86_64 Support
|
|||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
||||
boot-options
|
||||
uefi
|
||||
mm
|
||||
5level-paging
|
||||
|
|
|
|||
|
|
@ -97,7 +97,7 @@ config IOMMU_DEBUG
|
|||
code. When you use it make sure you have a big enough
|
||||
IOMMU/AGP aperture. Most of the options enabled by this can
|
||||
be set more finegrained using the iommu= command line
|
||||
options. See Documentation/arch/x86/x86_64/boot-options.rst for more
|
||||
options. See Documentation/admin-guide/kernel-parameters.txt for more
|
||||
details.
|
||||
|
||||
config IOMMU_LEAK
|
||||
|
|
|
|||
|
|
@ -25,10 +25,6 @@
|
|||
#include "efi.h"
|
||||
|
||||
#include <generated/compile.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/uts.h>
|
||||
#include <linux/utsname.h>
|
||||
#include <linux/ctype.h>
|
||||
#include <generated/utsversion.h>
|
||||
#include <generated/utsrelease.h>
|
||||
|
||||
|
|
|
|||
|
|
@ -443,14 +443,14 @@
|
|||
#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */
|
||||
|
||||
/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
|
||||
#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */
|
||||
#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */
|
||||
#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */
|
||||
#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */
|
||||
#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */
|
||||
#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */
|
||||
#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */
|
||||
#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */
|
||||
#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */
|
||||
#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */
|
||||
#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */
|
||||
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */
|
||||
#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */
|
||||
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
|
||||
#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */
|
||||
#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */
|
||||
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
|
||||
|
|
|
|||
|
|
@ -2582,19 +2582,12 @@ int apic_is_clustered_box(void)
|
|||
/*
|
||||
* APIC command line parameters
|
||||
*/
|
||||
static int __init setup_disableapic(char *arg)
|
||||
static int __init setup_nolapic(char *arg)
|
||||
{
|
||||
apic_is_disabled = true;
|
||||
setup_clear_cpu_cap(X86_FEATURE_APIC);
|
||||
return 0;
|
||||
}
|
||||
early_param("disableapic", setup_disableapic);
|
||||
|
||||
/* same as disableapic, for compatibility */
|
||||
static int __init setup_nolapic(char *arg)
|
||||
{
|
||||
return setup_disableapic(arg);
|
||||
}
|
||||
early_param("nolapic", setup_nolapic);
|
||||
|
||||
static int __init parse_lapic_timer_c2_ok(char *arg)
|
||||
|
|
|
|||
|
|
@ -1165,7 +1165,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries)
|
|||
(entry.ir_index_15 << 15) | entry.ir_index_0_14, entry.ir_zero);
|
||||
} else {
|
||||
apic_dbg("%s, %s, D(%02X%02X), M(%1d)\n", buf,
|
||||
entry.dest_mode_logical ? "logical " : "physic al",
|
||||
entry.dest_mode_logical ? "logical " : "physical",
|
||||
entry.virt_destid_8_14, entry.destid_0_7, entry.delivery_mode);
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
#include <linux/slab.h>
|
||||
|
||||
/**
|
||||
* x86_match_cpu - match current CPU again an array of x86_cpu_ids
|
||||
* x86_match_cpu - match current CPU against an array of x86_cpu_ids
|
||||
* @match: Pointer to array of x86_cpu_ids. Last entry terminated with
|
||||
* {}.
|
||||
*
|
||||
|
|
|
|||
|
|
@ -428,7 +428,7 @@ void __init topology_apply_cmdline_limits_early(void)
|
|||
{
|
||||
unsigned int possible = nr_cpu_ids;
|
||||
|
||||
/* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */
|
||||
/* 'maxcpus=0' 'nosmp' 'nolapic' */
|
||||
if (!setup_max_cpus || apic_is_disabled)
|
||||
possible = 1;
|
||||
|
||||
|
|
|
|||
|
|
@ -108,10 +108,6 @@ void __init pci_iommu_alloc(void)
|
|||
swiotlb_init(x86_swiotlb_enable, x86_swiotlb_flags);
|
||||
}
|
||||
|
||||
/*
|
||||
* See <Documentation/arch/x86/x86_64/boot-options.rst> for the iommu kernel
|
||||
* parameter documentation.
|
||||
*/
|
||||
static __init int iommu_setup(char *p)
|
||||
{
|
||||
iommu_merge = 1;
|
||||
|
|
|
|||
|
|
@ -593,8 +593,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr,
|
|||
* Examine the physical address to determine if it is EFI data. Check
|
||||
* it against the boot params structure and EFI tables and memory types.
|
||||
*/
|
||||
static bool memremap_is_efi_data(resource_size_t phys_addr,
|
||||
unsigned long size)
|
||||
static bool memremap_is_efi_data(resource_size_t phys_addr)
|
||||
{
|
||||
u64 paddr;
|
||||
|
||||
|
|
@ -632,71 +631,9 @@ static bool memremap_is_efi_data(resource_size_t phys_addr,
|
|||
* Examine the physical address to determine if it is boot data by checking
|
||||
* it against the boot params setup_data chain.
|
||||
*/
|
||||
static bool memremap_is_setup_data(resource_size_t phys_addr,
|
||||
unsigned long size)
|
||||
{
|
||||
struct setup_indirect *indirect;
|
||||
struct setup_data *data;
|
||||
u64 paddr, paddr_next;
|
||||
|
||||
paddr = boot_params.hdr.setup_data;
|
||||
while (paddr) {
|
||||
unsigned int len;
|
||||
|
||||
if (phys_addr == paddr)
|
||||
return true;
|
||||
|
||||
data = memremap(paddr, sizeof(*data),
|
||||
MEMREMAP_WB | MEMREMAP_DEC);
|
||||
if (!data) {
|
||||
pr_warn("failed to memremap setup_data entry\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
paddr_next = data->next;
|
||||
len = data->len;
|
||||
|
||||
if ((phys_addr > paddr) &&
|
||||
(phys_addr < (paddr + sizeof(struct setup_data) + len))) {
|
||||
memunmap(data);
|
||||
return true;
|
||||
}
|
||||
|
||||
if (data->type == SETUP_INDIRECT) {
|
||||
memunmap(data);
|
||||
data = memremap(paddr, sizeof(*data) + len,
|
||||
MEMREMAP_WB | MEMREMAP_DEC);
|
||||
if (!data) {
|
||||
pr_warn("failed to memremap indirect setup_data\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
indirect = (struct setup_indirect *)data->data;
|
||||
|
||||
if (indirect->type != SETUP_INDIRECT) {
|
||||
paddr = indirect->addr;
|
||||
len = indirect->len;
|
||||
}
|
||||
}
|
||||
|
||||
memunmap(data);
|
||||
|
||||
if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
|
||||
return true;
|
||||
|
||||
paddr = paddr_next;
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
/*
|
||||
* Examine the physical address to determine if it is boot data by checking
|
||||
* it against the boot params setup_data chain (early boot version).
|
||||
*/
|
||||
static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
|
||||
unsigned long size)
|
||||
static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early)
|
||||
{
|
||||
unsigned int setup_data_sz = sizeof(struct setup_data);
|
||||
struct setup_indirect *indirect;
|
||||
struct setup_data *data;
|
||||
u64 paddr, paddr_next;
|
||||
|
|
@ -708,29 +645,40 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
|
|||
if (phys_addr == paddr)
|
||||
return true;
|
||||
|
||||
data = early_memremap_decrypted(paddr, sizeof(*data));
|
||||
if (early)
|
||||
data = early_memremap_decrypted(paddr, setup_data_sz);
|
||||
else
|
||||
data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC);
|
||||
if (!data) {
|
||||
pr_warn("failed to early memremap setup_data entry\n");
|
||||
pr_warn("failed to remap setup_data entry\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
size = sizeof(*data);
|
||||
size = setup_data_sz;
|
||||
|
||||
paddr_next = data->next;
|
||||
len = data->len;
|
||||
|
||||
if ((phys_addr > paddr) &&
|
||||
(phys_addr < (paddr + sizeof(struct setup_data) + len))) {
|
||||
early_memunmap(data, sizeof(*data));
|
||||
(phys_addr < (paddr + setup_data_sz + len))) {
|
||||
if (early)
|
||||
early_memunmap(data, setup_data_sz);
|
||||
else
|
||||
memunmap(data);
|
||||
return true;
|
||||
}
|
||||
|
||||
if (data->type == SETUP_INDIRECT) {
|
||||
size += len;
|
||||
early_memunmap(data, sizeof(*data));
|
||||
data = early_memremap_decrypted(paddr, size);
|
||||
if (early) {
|
||||
early_memunmap(data, setup_data_sz);
|
||||
data = early_memremap_decrypted(paddr, size);
|
||||
} else {
|
||||
memunmap(data);
|
||||
data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC);
|
||||
}
|
||||
if (!data) {
|
||||
pr_warn("failed to early memremap indirect setup_data\n");
|
||||
pr_warn("failed to remap indirect setup_data\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
|
|
@ -742,7 +690,10 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
|
|||
}
|
||||
}
|
||||
|
||||
early_memunmap(data, size);
|
||||
if (early)
|
||||
early_memunmap(data, size);
|
||||
else
|
||||
memunmap(data);
|
||||
|
||||
if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
|
||||
return true;
|
||||
|
|
@ -753,6 +704,16 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
|
|||
return false;
|
||||
}
|
||||
|
||||
static bool memremap_is_setup_data(resource_size_t phys_addr)
|
||||
{
|
||||
return __memremap_is_setup_data(phys_addr, false);
|
||||
}
|
||||
|
||||
static bool __init early_memremap_is_setup_data(resource_size_t phys_addr)
|
||||
{
|
||||
return __memremap_is_setup_data(phys_addr, true);
|
||||
}
|
||||
|
||||
/*
|
||||
* Architecture function to determine if RAM remap is allowed. By default, a
|
||||
* RAM remap will map the data as encrypted. Determine if a RAM remap should
|
||||
|
|
@ -771,8 +732,8 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
|
|||
return false;
|
||||
|
||||
if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
|
||||
if (memremap_is_setup_data(phys_addr, size) ||
|
||||
memremap_is_efi_data(phys_addr, size))
|
||||
if (memremap_is_setup_data(phys_addr) ||
|
||||
memremap_is_efi_data(phys_addr))
|
||||
return false;
|
||||
}
|
||||
|
||||
|
|
@ -797,8 +758,8 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
|
|||
encrypted_prot = true;
|
||||
|
||||
if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
|
||||
if (early_memremap_is_setup_data(phys_addr, size) ||
|
||||
memremap_is_efi_data(phys_addr, size))
|
||||
if (early_memremap_is_setup_data(phys_addr) ||
|
||||
memremap_is_efi_data(phys_addr))
|
||||
encrypted_prot = false;
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue