On laptops with core i5/i7, there were reports that after resume
graphics workloads were performing poorly on a specific AP, while
the other cpu's were ok. This was observed on a 32bit kernel
specifically.
Debug showed that the PAT init was not happening on that AP
during resume and hence it contributing to the poor workload
performance on that cpu.
On this system, resume flow looked like this:
1. BP starts the resume sequence and we reinit BP's MTRR's/PAT
early on using mtrr_bp_restore()
2. Resume sequence brings all AP's online
3. Resume sequence now kicks off the MTRR reinit on all the AP's.
4. For some reason, between point 2 and 3, we moved from BP
to one of the AP's. My guess is that printk() during resume
sequence is contributing to this. We don't see similar
behavior with the 64bit kernel but there is no guarantee that
at this point the remaining resume sequence (after AP's bringup)
has to happen on BP.
5. set_mtrr() was assuming that we are still on BP and skipped the
MTRR/PAT init on that cpu (because of 1 above)
6. But we were on an AP and this led to not reprogramming PAT
on this cpu leading to bad performance.
Fix this by doing unconditional mtrr_if->set_all() in set_mtrr()
during MTRR/PAT init. This might be unnecessary if we are still
running on BP. But it is of no harm and will guarantee that after
resume, all the cpu's will be in sync with respect to the
MTRR/PAT registers.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <1301438292-28370-1-git-send-email-eric@anholt.net>
Signed-off-by: Eric Anholt <eric@anholt.net>
Tested-by: Keith Packard <keithp@keithp.com>
Cc: stable@kernel.org [v2.6.32+]
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Some subsystems in the x86 tree need to carry out suspend/resume and
shutdown operations with one CPU on-line and interrupts disabled and
they define sysdev classes and sysdevs or sysdev drivers for this
purpose. This leads to unnecessarily complicated code and excessive
memory usage, so switch them to using struct syscore_ops objects for
this purpose instead.
Generally, there are three categories of subsystems that use
sysdevs for implementing PM operations: (1) subsystems whose
suspend/resume callbacks ignore their arguments entirely (the
majority), (2) subsystems whose suspend/resume callbacks use their
struct sys_device argument, but don't really need to do that,
because they can be implemented differently in an arguably simpler
way (io_apic.c), and (3) subsystems whose suspend/resume callbacks
use their struct sys_device argument, but the value of that argument
is always the same and could be ignored (microcode_core.c). In all
of these cases the subsystems in question may be readily converted to
using struct syscore_ops objects for power management and shutdown.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Markus Kohn ran into a hard hang regression on an acer aspire
1310, when acpi is enabled. git bisect showed the following
commit as the bad one that introduced the boot regression.
commit d0af9eed5a
Author: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Wed Aug 19 18:05:36 2009 -0700
x86, pat/mtrr: Rendezvous all the cpus for MTRR/PAT init
Because of the UP configuration of that platform,
native_smp_prepare_cpus() bailed out (in smp_sanity_check())
before doing the set_mtrr_aps_delayed_init()
Further down the boot path, native_smp_cpus_done() will call the
delayed MTRR initialization for the AP's (mtrr_aps_init()) with
mtrr_aps_delayed_init not set. This resulted in the boot
processor reprogramming its MTRR's to the values seen during the
start of the OS boot. While this is not needed ideally, this
shouldn't have caused any side-effects. This is because the
reprogramming of MTRR's (set_mtrr_state() that gets called via
set_mtrr()) will check if the live register contents are
different from what is being asked to write and will do the actual
write only if they are different.
BP's mtrr state is read during the start of the OS boot and
typically nothing would have changed when we ask to reprogram it
on BP again because of the above scenario on an UP platform. So
on a normal UP platform no reprogramming of BP MTRR MSR's
happens and all is well.
However, on this platform, bios seems to be modifying the fixed
mtrr range registers between the start of OS boot and when we
double check the live registers for reprogramming BP MTRR
registers. And as the live registers are modified, we end up
reprogramming the MTRR's to the state seen during the start of
the OS boot.
During ACPI initialization, something in the bios (probably smi
handler?) don't like this fact and results in a hard lockup.
We didn't see this boot hang issue on this platform before the
commit d0af9eed5a, because only
the AP's (if any) will program its MTRR's to the value that BP
had at the start of the OS boot.
Fix this issue by checking mtrr_aps_delayed_init before
continuing further in the mtrr_aps_init(). Now, only AP's (if
any) will program its MTRR's to the BP values during boot.
Addresses https://bugzilla.novell.com/show_bug.cgi?id=623393
[ By the way, this behavior of the bios modifying MTRR's after the start
of the OS boot is not common and the kernel is not prepared to
handle this situation well. Irrespective of this issue, during
suspend/resume, linux kernel will try to reprogram the BP's MTRR values
to the values seen during the start of the OS boot. So suspend/resume might
be already broken on this platform for all linux kernel versions. ]
Reported-and-bisected-by: Markus Kohn <jabber@gmx.org>
Tested-by: Markus Kohn <jabber@gmx.org>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Thomas Renninger <trenn@novell.com>
Cc: Rafael Wysocki <rjw@novell.com>
Cc: Venkatesh Pallipadi <venki@google.com>
Cc: stable@kernel.org # [v2.6.32+]
LKML-Reference: <1296694975.4418.402.camel@sbsiddha-MOBL3.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the stop machine context rather than IPI's to rendezvous all the cpus for
MTRR initialization that happens during cpu bringup or for MTRR modifications
during runtime.
This avoids deadlock scenario (reported by Prarit) like:
cpu A holds a read_lock (tasklist_lock for example) with irqs enabled
cpu B waits for the same lock with irqs disabled using write_lock_irq
cpu C doing set_mtrr() (during AP bringup for example), which will try to
rendezvous all the cpus using IPI's
This will result in C and A come to the rendezvous point and waiting
for B. B is stuck forever waiting for the lock and thus not
reaching the rendezvous point.
Using stop cpu (run in the process context of per cpu based keventd) to do
this rendezvous, avoids this deadlock scenario.
Also make sure all the cpu's are in the rendezvous handler before we proceed
with the local_irq_save() on each cpu. This lock step disabling irqs on all
the cpus will avoid other deadlock scenarios (for example involving
with the blocking smp_call_function's etc).
[ This problem is very old. Marking -stable only for 2.6.35 as the
stop_one_cpu_nowait() API is present only in 2.6.35. Any older
kernel interested in this fix need to do some more work in backporting
this patch. ]
Reported-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <1280515602.2682.10.camel@sbsiddha-MOBL3.sc.intel.com>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Cc: stable@kernel.org [2.6.35]
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Fix missing kernel-doc notation in mtrr/main.c:
Warning(arch/x86/kernel/cpu/mtrr/main.c:152): No description found for parameter 'info'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is part of the ops structure constification
effort started by Arjan van de Ven et al.
Benefits of this constification:
* prevents modification of data that is shared
(referenced) by many other structure instances
at runtime
* detects/prevents accidental (but not intentional)
modification attempts on archs that enforce
read-only kernel data at runtime
* potentially better optimized code as the compiler
can assume that the const data cannot be changed
* the compiler/linker move const data into .rodata
and therefore exclude them from false sharing
Signed-off-by: Emese Revfy <re.emese@gmail.com>
LKML-Reference: <4B65D712.3080804@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
mtr_aps_delayed_init was declared u32 and made global, but it only
ever takes boolean values and is only ever used in
arch/x86/kernel/cpu/mtrr/main.c. Declare it "static bool" and remove
external references.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
SDM Vol 3a section titled "MTRR considerations in MP systems" specifies
the need for synchronizing the logical cpu's while initializing/updating
MTRR.
Currently Linux kernel does the synchronization of all cpu's only when
a single MTRR register is programmed/updated. During an AP online
(during boot/cpu-online/resume) where we initialize all the MTRR/PAT registers,
we don't follow this synchronization algorithm.
This can lead to scenarios where during a dynamic cpu online, that logical cpu
is initializing MTRR/PAT with cache disabled (cr0.cd=1) etc while other logical
HT sibling continue to run (also with cache disabled because of cr0.cd=1
on its sibling).
Starting from Westmere, VMX transitions with cr0.cd=1 don't work properly
(because of some VMX performance optimizations) and the above scenario
(with one logical cpu doing VMX activity and another logical cpu coming online)
can result in system crash.
Fix the MTRR initialization by doing rendezvous of all the cpus. During
boot and resume, we delay the MTRR/PAT init for APs till all the
logical cpu's come online and the rendezvous process at the end of AP's bringup,
will initialize the MTRR/PAT for all AP's.
For dynamic single cpu online, we synchronize all the logical cpus and
do the MTRR/PAT init on the AP that is coming online.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Fix following trivial style problems:
ERROR: trailing whitespace X 25
WARNING: Use #include <linux/uaccess.h> instead of <asm/uaccess.h>
WARNING: Use #include <linux/kvm_para.h> instead of <asm/kvm_para.h>
ERROR: do not initialise externals to 0 or NULL X 2
ERROR: "foo * bar" should be "foo *bar" X 5
ERROR: do not use assignment in if condition X 2
WARNING: line over 80 characters X 8
ERROR: return is not a function, parentheses are not required
WARNING: braces {} are not necessary for any arm of this statement
ERROR: space required before the open parenthesis '(' X 2
ERROR: open brace '{' following function declarations go on the next line
ERROR: space required after that ',' (ctx:VxV) X 8
ERROR: space required before the open parenthesis '(' X 3
ERROR: else should follow close brace '}'
WARNING: space prohibited between function name and open parenthesis '('
WARNING: EXPORT_SYMBOL(foo); should immediately follow its function/variable X 2
Also use pr_debug and pr_warning where possible.
total: 50 errors, 14 warnings
arch/x86/kernel/cpu/mtrr/main.o:
text data bss dec hex filename
3668 116 4156 7940 1f04 main.o.before
3668 116 4156 7940 1f04 main.o.after
md5:
e01af2fd28deef77c8d01e71acfbd365 main.o.before.asm
e01af2fd28deef77c8d01e71acfbd365 main.o.after.asm
Suggested-by: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <20090703164225.GA21447@elte.hu>
Cc: Avi Kivity <avi@redhat.com> # Avi, please have a look at the kvm_para.h bit
[ More cleanups ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use standard msr-index.h's MSR declaration and no need to declare again.
[ Impact: cleanup, no object code change ]
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Impact: don't trim e820 according to wrong mtrr
Ozan reports that his server emits strange warning.
it turns out the BIOS sets the MTRRs incorrectly.
Ignore those strange ranges, and don't trim e820,
just emit one warning about BIOS
Reported-by: Ozan Çağlayan <ozan@pardus.org.tr>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <49BEE1E7.7020706@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
mtrr main.c is too big, seperate mtrr cleanup and mtrr e820 trim
code to another file.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <49B87C7B.80809@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: print more debug info
Keep it consistent with autodetect version.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
LKML-Reference: <49B87C0A.4010105@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
kerneloops.org is reporting a lot of these warnings that come due to
vmware not setting up any MTRRs for emulated CPUs:
| Reported 709 times (14696 total reports)
| BIOS bug (often in VMWare) where the MTRR's are set up incorrectly
| or not at all
|
| This warning was last seen in version 2.6.29-rc2-git1, and first
| seen in 2.6.24.
|
| More info:
| http://www.kerneloops.org/searchweek.php?search=mtrr_trim_uncached_memory
Keep a one-liner KERN_INFO about it - so that we have so notice if empty
MTRRs are caused by native hardware/BIOS weirdness.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
enable_mtrr_cleanup is static, and is never set to anything but 0 or 1.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Ingo said mtrr_cleanup() is big and ugly.
so break it up into more functions and make it more readable.
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For the purpose of MTRR canonicalization, treat WRPROT as UNCACHEABLE.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
The first 1M is don't care when it comes to the variables MTRRs.
Cover it as WB as a heuristic approximation; this is generally what we
want to minimize the number of registers.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Print out the correct type when the Write Protected (WP) type is seen.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Delay exit to make sure we can actually get the optimal result in as
many cases as possible.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
v2: should check with half of range0 size instead of chunk_size
So don't have silly big hole.
in hpa's case we could auto detect instead of adding mtrr_chunk_size in
command line.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
add mtrr_cleanup_debug to print out more info about layout
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
change back chunksize max to 2g
otherwise will get strange layout in 2G ram system like
0 - 4g WB, 2040M - 2048M UC, 2048M - 4G NC
instead of
0 - 2g WB, 2040M - 2048M UC
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix this warning reported by Andrew Morton:
> arch/x86/kernel/cpu/mtrr/main.c: In function 'mtrr_bp_init':
> arch/x86/kernel/cpu/mtrr/main.c:1170: warning: 'extra_remove_base' may be used uninitialized in this function
the warning is bogus but the logic that prevents uninitialized use
is a bit convoluted so simplify it all.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use WARN() instead of a printk+WARN_ON() pair; this way the message
becomes part of the warning section for better reporting/collection.
This also allowed the folding of some if()'s into the WARN()
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: akpm@linux-foundation.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
rename update_memory_range to e820_update_range
rename add_memory_region to e820_add_region
to make it more clear that they are about e820 map operations.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
disable the noisy print out.
also use the one the less spare mtrr reg.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Loop through mtrr chunk_size and gran_size from 1M to 2G to find out
the optimal value so user does not need to add mtrr_chunk_size and
mtrr_gran_size to the kernel command line.
If optimal value is not found, print out all list to help select less
optimal value.
Add mtrr_spare_reg_nr= so user could set 2 instead of 1, if the card
need more entries.
v2: find the one with more spare entries
v3: fix hole_basek offset
v4: tight the compare between range and range_new
loop stop with 4g
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Gabriel C <nix.or.die@googlemail.com>
Cc: Mika Fischer <mika.fischer@zoopnet.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
v9: address format change requests by Ingo
more case handling in range_to_var_with_hole
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
v2: process hole then end_pfn
fix update_memory_range with whole cover comparing
Signed-off-by: Yinghai Lu <yinghai.lu@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
converting MTRR layout from continous to discrete, some time could run out of
MTRRs. So add gran_sizek to prevent that by dumpping small RAM piece less than
gran_sizek.
previous trimming only can handle highest_pfn from mtrr to end_pfn from e820.
when have more than 4g RAM installed, there will be holes below 4g. so need to
check ram below 4g is coverred well.
need to be applied after
[PATCH] x86: mtrr cleanup for converting continuous to discrete layout v7
Signed-off-by: Yinghai Lu <yinghai.lu@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
some BIOS like to use continus MTRR layout, and X driver can not add
WB entries for graphical cards when 4g or more RAM installed.
the patch will change MTRR to discrete.
mtrr_chunk_size= could be used to have smaller continuous block to hold holes.
default is 256m, could be set according to size of graphics card memory.
mtrr_gran_size= could be used to send smallest mtrr block to avoid run out of MTRRs
v2: fix -1 for UC checking
v3: default to disable, and need use enable_mtrr_cleanup to enable this feature
skip the var state change warning.
remove next_basek in range_to_mtrr()
v4: correct warning mask.
v5: CONFIG_MTRR_SANITIZER
v6: fix 1g, 2g, 512 aligment with extra hole
v7: gran_sizek to prevent running out of MTRRs.
v8: fix hole_basek caculation caused when removing next_basek
gran_sizek using when basek is 0.
need to apply
[PATCH] x86: fix trimming e820 with MTRR holes.
right after this one.
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
make known_pat_cpu to think amd k8 and fam10h is ok too.
also make tom2 below to be WRBACK
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix the bug reported here:
http://bugzilla.kernel.org/show_bug.cgi?id=10232
use update_memory_range() instead of add_memory_range() directly
to avoid closing the gap.
( the new code only affects and runs on systems where the MTRR
workaround triggers. )
Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Inside a KVM virtual machine the MTRRs are usually blank. This confuses Linux
and causes a warning message at boot. This patch removes that warning message
when running Linux as a KVM guest.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Fix mtrr kernel-doc warning:
Warning(linux-2.6.24-git12//arch/x86/kernel/cpu/mtrr/main.c:677): No description found for parameter 'end_pfn'
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
