Maintain a flag in the LSB of the ticket lock tail which indicates
whether anyone is in the lock slowpath and may need kicking when
the current holder unlocks. The flags are set when the first locker
enters the slowpath, and cleared when unlocking to an empty queue (ie,
no contention).
In the specific implementation of lock_spinning(), make sure to set
the slowpath flags on the lock just before blocking. We must do
this before the last-chance pickup test to prevent a deadlock
with the unlocker:
Unlocker Locker
test for lock pickup
-> fail
unlock
test slowpath
-> false
set slowpath flags
block
Whereas this works in any ordering:
Unlocker Locker
set slowpath flags
test for lock pickup
-> fail
block
unlock
test slowpath
-> true, kick
If the unlocker finds that the lock has the slowpath flag set but it is
actually uncontended (ie, head == tail, so nobody is waiting), then it
clears the slowpath flag.
The unlock code uses a locked add to update the head counter. This also
acts as a full memory barrier so that its safe to subsequently
read back the slowflag state, knowing that the updated lock is visible
to the other CPUs. If it were an unlocked add, then the flag read may
just be forwarded from the store buffer before it was visible to the other
CPUs, which could result in a deadlock.
Unfortunately this means we need to do a locked instruction when
unlocking with PV ticketlocks. However, if PV ticketlocks are not
enabled, then the old non-locked "add" is the only unlocking code.
Note: this code relies on gcc making sure that unlikely() code is out of
line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it
doesn't the generated code isn't too bad, but its definitely suboptimal.
Thanks to Srivatsa Vaddagiri for providing a bugfix to the original
version of this change, which has been folded in.
Thanks to Stephan Diestelhorst for commenting on some code which relied
on an inaccurate reading of the x86 memory ordering rules.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-11-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Stephan Diestelhorst <stephan.diestelhorst@amd.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Although the lock_spinning calls in the spinlock code are on the
uncommon path, their presence can cause the compiler to generate many
more register save/restores in the function pre/postamble, which is in
the fast path. To avoid this, convert it to using the pvops callee-save
calling convention, which defers all the save/restores until the actual
function is called, keeping the fastpath clean.
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-8-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Rather than outright replacing the entire spinlock implementation in
order to paravirtualize it, keep the ticket lock implementation but add
a couple of pvops hooks on the slow patch (long spin on lock, unlocking
a contended lock).
Ticket locks have a number of nice properties, but they also have some
surprising behaviours in virtual environments. They enforce a strict
FIFO ordering on cpus trying to take a lock; however, if the hypervisor
scheduler does not schedule the cpus in the correct order, the system can
waste a huge amount of time spinning until the next cpu can take the lock.
(See Thomas Friebel's talk "Prevent Guests from Spinning Around"
http://www.xen.org/files/xensummitboston08/LHP.pdf for more details.)
To address this, we add two hooks:
- __ticket_spin_lock which is called after the cpu has been
spinning on the lock for a significant number of iterations but has
failed to take the lock (presumably because the cpu holding the lock
has been descheduled). The lock_spinning pvop is expected to block
the cpu until it has been kicked by the current lock holder.
- __ticket_spin_unlock, which on releasing a contended lock
(there are more cpus with tail tickets), it looks to see if the next
cpu is blocked and wakes it if so.
When compiled with CONFIG_PARAVIRT_SPINLOCKS disabled, a set of stub
functions causes all the extra code to go away.
Results:
=======
setup: 32 core machine with 32 vcpu KVM guest (HT off) with 8GB RAM
base = 3.11-rc
patched = base + pvspinlock V12
+-----------------+----------------+--------+
dbench (Throughput in MB/sec. Higher is better)
+-----------------+----------------+--------+
| base (stdev %)|patched(stdev%) | %gain |
+-----------------+----------------+--------+
| 15035.3 (0.3) |15150.0 (0.6) | 0.8 |
| 1470.0 (2.2) | 1713.7 (1.9) | 16.6 |
| 848.6 (4.3) | 967.8 (4.3) | 14.0 |
| 652.9 (3.5) | 685.3 (3.7) | 5.0 |
+-----------------+----------------+--------+
pvspinlock shows benefits for overcommit ratio > 1 for PLE enabled cases,
and undercommits results are flat
Signed-off-by: Jeremy Fitzhardinge <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-2-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Attilio Rao <attilio.rao@citrix.com>
[ Raghavendra: Changed SPIN_THRESHOLD, fixed redefinition of arch_spinlock_t]
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Pull x86 paravirt update from Ingo Molnar:
"Various paravirtualization related changes - the biggest one makes
guest support optional via CONFIG_HYPERVISOR_GUEST"
* 'x86-paravirt-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86, wakeup, sleep: Use pvops functions for changing GDT entries
x86, xen, gdt: Remove the pvops variant of store_gdt.
x86-32, gdt: Store/load GDT for ACPI S3 or hibernation/resume path is not needed
x86-64, gdt: Store/load GDT for ACPI S3 or hibernate/resume path is not needed.
x86: Make Linux guest support optional
x86, Kconfig: Move PARAVIRT_DEBUG into the paravirt menu
The two use-cases where we needed to store the GDT were during ACPI S3 suspend
and resume. As the patches:
x86/gdt/i386: store/load GDT for ACPI S3 or hibernation/resume path is not needed
x86/gdt/64-bit: store/load GDT for ACPI S3 or hibernate/resume path is not needed.
have demonstrated - there are other mechanism by which the GDT is
saved and reloaded during early resume path.
Hence we do not need to worry about the pvops call-chain for saving the
GDT and can and can eliminate it. The other areas where the store_gdt is
used are never going to be hit when running under the pvops platforms.
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Link: http://lkml.kernel.org/r/1365194544-14648-4-git-send-email-konrad.wilk@oracle.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Invoking arch_flush_lazy_mmu_mode() results in calls to
preempt_enable()/disable() which may have performance impact.
Since lazy MMU is not used on bare metal we can patch away
arch_flush_lazy_mmu_mode() so that it is never called in such
environment.
[ hpa: the previous patch "Fix vmalloc_fault oops during lazy MMU
updates" may cause a minor performance regression on
bare metal. This patch resolves that performance regression. It is
somewhat unclear to me if this is a good -stable candidate. ]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: http://lkml.kernel.org/r/1364045796-10720-2-git-send-email-konrad.wilk@oracle.com
Tested-by: Josh Boyer <jwboyer@redhat.com>
Tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> SEE NOTE ABOVE
With CONFIG_PARAVIRT=y and CONFIG_TRANSPARENT_HUGEPAGE=n, the build breaks
because set_pmd_at() is undeclared:
mm/memory.c: In function 'do_pmd_numa_page':
mm/memory.c:3520: error: implicit declaration of function 'set_pmd_at'
mm/mprotect.c: In function 'change_pmd_protnuma':
mm/mprotect.c:120: error: implicit declaration of function 'set_pmd_at'
This is because paravirt defines set_pmd_at() only when
CONFIG_TRANSPARENT_HUGEPAGE=y and such a restriction is unneeded. The
fix is to define it for all CONFIG_PARAVIRT configurations.
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull x86/mm changes from Peter Anvin:
"The big change here is the patchset by Alex Shi to use INVLPG to flush
only the affected pages when we only need to flush a small page range.
It also removes the special INVALIDATE_TLB_VECTOR interrupts (32
vectors!) and replace it with an ordinary IPI function call."
Fix up trivial conflicts in arch/x86/include/asm/apic.h (added code next
to changed line)
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/tlb: Fix build warning and crash when building for !SMP
x86/tlb: do flush_tlb_kernel_range by 'invlpg'
x86/tlb: replace INVALIDATE_TLB_VECTOR by CALL_FUNCTION_VECTOR
x86/tlb: enable tlb flush range support for x86
mm/mmu_gather: enable tlb flush range in generic mmu_gather
x86/tlb: add tlb_flushall_shift knob into debugfs
x86/tlb: add tlb_flushall_shift for specific CPU
x86/tlb: fall back to flush all when meet a THP large page
x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range
x86/tlb_info: get last level TLB entry number of CPU
x86: Add read_mostly declaration/definition to variables from smp.h
x86: Define early read-mostly per-cpu macros
x86 has no flush_tlb_range support in instruction level. Currently the
flush_tlb_range just implemented by flushing all page table. That is not
the best solution for all scenarios. In fact, if we just use 'invlpg' to
flush few lines from TLB, we can get the performance gain from later
remain TLB lines accessing.
But the 'invlpg' instruction costs much of time. Its execution time can
compete with cr3 rewriting, and even a bit more on SNB CPU.
So, on a 512 4KB TLB entries CPU, the balance points is at:
(512 - X) * 100ns(assumed TLB refill cost) =
X(TLB flush entries) * 100ns(assumed invlpg cost)
Here, X is 256, that is 1/2 of 512 entries.
But with the mysterious CPU pre-fetcher and page miss handler Unit, the
assumed TLB refill cost is far lower then 100ns in sequential access. And
2 HT siblings in one core makes the memory access more faster if they are
accessing the same memory. So, in the patch, I just do the change when
the target entries is less than 1/16 of whole active tlb entries.
Actually, I have no data support for the percentage '1/16', so any
suggestions are welcomed.
As to hugetlb, guess due to smaller page table, and smaller active TLB
entries, I didn't see benefit via my benchmark, so no optimizing now.
My micro benchmark show in ideal scenarios, the performance improves 70
percent in reading. And in worst scenario, the reading/writing
performance is similar with unpatched 3.4-rc4 kernel.
Here is the reading data on my 2P * 4cores *HT NHM EP machine, with THP
'always':
multi thread testing, '-t' paramter is thread number:
with patch unpatched 3.4-rc4
./mprotect -t 1 14ns 24ns
./mprotect -t 2 13ns 22ns
./mprotect -t 4 12ns 19ns
./mprotect -t 8 14ns 16ns
./mprotect -t 16 28ns 26ns
./mprotect -t 32 54ns 51ns
./mprotect -t 128 200ns 199ns
Single process with sequencial flushing and memory accessing:
with patch unpatched 3.4-rc4
./mprotect 7ns 11ns
./mprotect -p 4096 -l 8 -n 10240
21ns 21ns
[ hpa: http://lkml.kernel.org/r/1B4B44D9196EFF41AE41FDA404FC0A100BFF94@SHSMSX101.ccr.corp.intel.com
has additional performance numbers. ]
Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-3-git-send-email-alex.shi@intel.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
There were paravirt_ops hooks for the full register set variant of
{rd,wr}msr_safe which are actually not used by anyone anymore. Remove
them to make the code cleaner and avoid silent breakages when the pvops
members were uninitialized. This has been boot-tested natively and under
Xen with PVOPS enabled and disabled on one machine.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Link: http://lkml.kernel.org/r/1338562358-28182-2-git-send-email-bp@amd64.org
Acked-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
GET_CR2_INTO_RCX is asinine: it is only used in one place, the actual
paravirt call returns the value in %rax, not %rcx; and the one place
that wants it wants the result in %r9. We actually generate as a
result of this call:
call ...
movq %rax, %rcx
xorq %rax, %rax /* this value isn't even used... */
movq %rcx, %r9
At least make the macro do what the paravirt call does, which is put
the value into %rax.
Nevermind the fact that the macro clobbers all the volatile registers.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1334794610-5546-4-git-send-email-hpa@zytor.com
Cc: Glauber de Oliveira Costa <glommer@parallels.com>
"[RFC - PATCH 0/7] consolidation of BUG support code."
https://lkml.org/lkml/2012/1/26/525
--
The changes shown here are to unify linux's BUG support under
the one <linux/bug.h> file. Due to historical reasons, we have
some BUG code in bug.h and some in kernel.h -- i.e. the support for
BUILD_BUG in linux/kernel.h predates the addition of linux/bug.h,
but old code in kernel.h wasn't moved to bug.h at that time. As
a band-aid, kernel.h was including <asm/bug.h> to pseudo link them.
This has caused confusion[1] and general yuck/WTF[2] reactions.
Here is an example that violates the principle of least surprise:
CC lib/string.o
lib/string.c: In function 'strlcat':
lib/string.c:225:2: error: implicit declaration of function 'BUILD_BUG_ON'
make[2]: *** [lib/string.o] Error 1
$
$ grep linux/bug.h lib/string.c
#include <linux/bug.h>
$
We've included <linux/bug.h> for the BUG infrastructure and yet we
still get a compile fail! [We've not kernel.h for BUILD_BUG_ON.]
Ugh - very confusing for someone who is new to kernel development.
With the above in mind, the goals of this changeset are:
1) find and fix any include/*.h files that were relying on the
implicit presence of BUG code.
2) find and fix any C files that were consuming kernel.h and
hence relying on implicitly getting some/all BUG code.
3) Move the BUG related code living in kernel.h to <linux/bug.h>
4) remove the asm/bug.h from kernel.h to finally break the chain.
During development, the order was more like 3-4, build-test, 1-2.
But to ensure that git history for bisect doesn't get needless
build failures introduced, the commits have been reorderd to fix
the problem areas in advance.
[1] https://lkml.org/lkml/2012/1/3/90
[2] https://lkml.org/lkml/2012/1/17/414
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)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=PYQT
-----END PGP SIGNATURE-----
Merge tag 'bug-for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux
Pull <linux/bug.h> cleanup from Paul Gortmaker:
"The changes shown here are to unify linux's BUG support under the one
<linux/bug.h> file. Due to historical reasons, we have some BUG code
in bug.h and some in kernel.h -- i.e. the support for BUILD_BUG in
linux/kernel.h predates the addition of linux/bug.h, but old code in
kernel.h wasn't moved to bug.h at that time. As a band-aid, kernel.h
was including <asm/bug.h> to pseudo link them.
This has caused confusion[1] and general yuck/WTF[2] reactions. Here
is an example that violates the principle of least surprise:
CC lib/string.o
lib/string.c: In function 'strlcat':
lib/string.c:225:2: error: implicit declaration of function 'BUILD_BUG_ON'
make[2]: *** [lib/string.o] Error 1
$
$ grep linux/bug.h lib/string.c
#include <linux/bug.h>
$
We've included <linux/bug.h> for the BUG infrastructure and yet we
still get a compile fail! [We've not kernel.h for BUILD_BUG_ON.] Ugh -
very confusing for someone who is new to kernel development.
With the above in mind, the goals of this changeset are:
1) find and fix any include/*.h files that were relying on the
implicit presence of BUG code.
2) find and fix any C files that were consuming kernel.h and hence
relying on implicitly getting some/all BUG code.
3) Move the BUG related code living in kernel.h to <linux/bug.h>
4) remove the asm/bug.h from kernel.h to finally break the chain.
During development, the order was more like 3-4, build-test, 1-2. But
to ensure that git history for bisect doesn't get needless build
failures introduced, the commits have been reorderd to fix the problem
areas in advance.
[1] https://lkml.org/lkml/2012/1/3/90
[2] https://lkml.org/lkml/2012/1/17/414"
Fix up conflicts (new radeon file, reiserfs header cleanups) as per Paul
and linux-next.
* tag 'bug-for-3.4' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux:
kernel.h: doesn't explicitly use bug.h, so don't include it.
bug: consolidate BUILD_BUG_ON with other bug code
BUG: headers with BUG/BUG_ON etc. need linux/bug.h
bug.h: add include of it to various implicit C users
lib: fix implicit users of kernel.h for TAINT_WARN
spinlock: macroize assert_spin_locked to avoid bug.h dependency
x86: relocate get/set debugreg fcns to include/asm/debugreg.
If a header file is making use of BUG, BUG_ON, BUILD_BUG_ON, or any
other BUG variant in a static inline (i.e. not in a #define) then
that header really should be including <linux/bug.h> and not just
expecting it to be implicitly present.
We can make this change risk-free, since if the files using these
headers didn't have exposure to linux/bug.h already, they would have
been causing compile failures/warnings.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
So here's a boot tested patch on top of Jason's series that does
all the cleanups I talked about and turns jump labels into a
more intuitive to use facility. It should also address the
various misconceptions and confusions that surround jump labels.
Typical usage scenarios:
#include <linux/static_key.h>
struct static_key key = STATIC_KEY_INIT_TRUE;
if (static_key_false(&key))
do unlikely code
else
do likely code
Or:
if (static_key_true(&key))
do likely code
else
do unlikely code
The static key is modified via:
static_key_slow_inc(&key);
...
static_key_slow_dec(&key);
The 'slow' prefix makes it abundantly clear that this is an
expensive operation.
I've updated all in-kernel code to use this everywhere. Note
that I (intentionally) have not pushed through the rename
blindly through to the lowest levels: the actual jump-label
patching arch facility should be named like that, so we want to
decouple jump labels from the static-key facility a bit.
On non-jump-label enabled architectures static keys default to
likely()/unlikely() branches.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jason Baron <jbaron@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: a.p.zijlstra@chello.nl
Cc: mathieu.desnoyers@efficios.com
Cc: davem@davemloft.net
Cc: ddaney.cavm@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds a function pointer in one of the many paravirt_ops
structs, to allow guests to register a steal time function. Besides
a steal time function, we also declare two jump_labels. They will be
used to allow the steal time code to be easily bypassed when not
in use.
Signed-off-by: Glauber Costa <glommer@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Tested-by: Eric B Munson <emunson@mgebm.net>
CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This fixes TRANSPARENT_HUGEPAGE=y with PARAVIRT=y and HIGHMEM64=n.
The #ifdef that this patch removes was erratically introduced to fix a
build error for noPAE (where pmd.pmd doesn't exist). So then the kernel
built but it failed at runtime because set_pmd_at was a noop. This will
correct it by enabling set_pmd_at for noPAE mode too.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: werner <w.landgraf@ru.ru>
Reported-by: Minchan Kim <minchan.kim@gmail.com>
Tested-by: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Paravirt ops pmd_update/pmd_update_defer/pmd_set_at. Not all might be
necessary (vmware needs pmd_update, Xen needs set_pmd_at, nobody needs
pmd_update_defer), but this is to keep full simmetry with pte paravirt
ops, which looks cleaner and simpler from a common code POV.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
halt() should use native_halt()
safe_halt() uses native_safe_halt()
If CONFIG_PARAVIRT=y, halt() is defined in arch/x86/include/asm/paravirt.h as
static inline void halt(void)
{
PVOP_VCALL0(pv_irq_ops.safe_halt);
}
Otherwise (no CONFIG_PARAVIRT) halt() in arch/x86/include/asm/irqflags.h is
static inline void halt(void)
{
native_halt();
}
So it looks to me like the CONFIG_PARAVIRT case of using native_safe_halt()
for a halt() is an oversight.
Am I missing something?
It probably hasn't shown up as a problem because the local apic is disabled
on a shutdown or restart. But if we disable interrupts and call halt()
we shouldn't expect that the halt() will re-enable interrupts.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
LKML-Reference: <E1PSBcz-0001g1-FM@eag09.americas.sgi.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
When running ktest.pl randconfig tests, I would sometimes trigger
a lockdep annotation bug (possible reason: unannotated irqs-on).
This triggering happened right after function tracer self test was
executed. After doing a config bisect I found that this was caused with
having function tracer, paravirt guest, prove locking, and rcu torture
all enabled.
The rcu torture just enhanced the likelyhood of triggering the bug.
Prove locking was needed, since it was the thing that was bugging.
Function tracer would trace and disable interrupts in all sorts
of funny places.
paravirt guest would turn arch_local_irq_* into functions that would
be traced.
Besides the fact that tracing arch_local_irq_* is just a bad idea,
this is what is happening.
The bug happened simply in the local_irq_restore() code:
if (raw_irqs_disabled_flags(flags)) { \
raw_local_irq_restore(flags); \
trace_hardirqs_off(); \
} else { \
trace_hardirqs_on(); \
raw_local_irq_restore(flags); \
} \
The raw_local_irq_restore() was defined as arch_local_irq_restore().
Now imagine, we are about to enable interrupts. We go into the else
case and call trace_hardirqs_on() which tells lockdep that we are enabling
interrupts, so it sets the current->hardirqs_enabled = 1.
Then we call raw_local_irq_restore() which calls arch_local_irq_restore()
which gets traced!
Now in the function tracer we disable interrupts with local_irq_save().
This is fine, but flags is stored that we have interrupts disabled.
When the function tracer calls local_irq_restore() it does it, but this
time with flags set as disabled, so we go into the if () path.
This keeps interrupts disabled and calls trace_hardirqs_off() which
sets current->hardirqs_enabled = 0.
When the tracer is finished and proceeds with the original code,
we enable interrupts but leave current->hardirqs_enabled as 0. Which
now breaks lockdeps internal processing.
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-2.6-irqflags:
Fix IRQ flag handling naming
MIPS: Add missing #inclusions of <linux/irq.h>
smc91x: Add missing #inclusion of <linux/irq.h>
Drop a couple of unnecessary asm/system.h inclusions
SH: Add missing consts to sys_execve() declaration
Blackfin: Rename IRQ flags handling functions
Blackfin: Add missing dep to asm/irqflags.h
Blackfin: Rename DES PC2() symbol to avoid collision
Blackfin: Split the BF532 BFIN_*_FIO_FLAG() functions to their own header
Blackfin: Split PLL code from mach-specific cdef headers
Fix the IRQ flag handling naming. In linux/irqflags.h under one configuration,
it maps:
local_irq_enable() -> raw_local_irq_enable()
local_irq_disable() -> raw_local_irq_disable()
local_irq_save() -> raw_local_irq_save()
...
and under the other configuration, it maps:
raw_local_irq_enable() -> local_irq_enable()
raw_local_irq_disable() -> local_irq_disable()
raw_local_irq_save() -> local_irq_save()
...
This is quite confusing. There should be one set of names expected of the
arch, and this should be wrapped to give another set of names that are expected
by users of this facility.
Change this to have the arch provide:
flags = arch_local_save_flags()
flags = arch_local_irq_save()
arch_local_irq_restore(flags)
arch_local_irq_disable()
arch_local_irq_enable()
arch_irqs_disabled_flags(flags)
arch_irqs_disabled()
arch_safe_halt()
Then linux/irqflags.h wraps these to provide:
raw_local_save_flags(flags)
raw_local_irq_save(flags)
raw_local_irq_restore(flags)
raw_local_irq_disable()
raw_local_irq_enable()
raw_irqs_disabled_flags(flags)
raw_irqs_disabled()
raw_safe_halt()
with type checking on the flags 'arguments', and then wraps those to provide:
local_save_flags(flags)
local_irq_save(flags)
local_irq_restore(flags)
local_irq_disable()
local_irq_enable()
irqs_disabled_flags(flags)
irqs_disabled()
safe_halt()
with tracing included if enabled.
The arch functions can now all be inline functions rather than some of them
having to be macros.
Signed-off-by: David Howells <dhowells@redhat.com> [X86, FRV, MN10300]
Signed-off-by: Chris Metcalf <cmetcalf@tilera.com> [Tile]
Signed-off-by: Michal Simek <monstr@monstr.eu> [Microblaze]
Tested-by: Catalin Marinas <catalin.marinas@arm.com> [ARM]
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> [AVR]
Acked-by: Tony Luck <tony.luck@intel.com> [IA-64]
Acked-by: Hirokazu Takata <takata@linux-m32r.org> [M32R]
Acked-by: Greg Ungerer <gerg@uclinux.org> [M68K/M68KNOMMU]
Acked-by: Ralf Baechle <ralf@linux-mips.org> [MIPS]
Acked-by: Kyle McMartin <kyle@mcmartin.ca> [PA-RISC]
Acked-by: Paul Mackerras <paulus@samba.org> [PowerPC]
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [S390]
Acked-by: Chen Liqin <liqin.chen@sunplusct.com> [Score]
Acked-by: Matt Fleming <matt@console-pimps.org> [SH]
Acked-by: David S. Miller <davem@davemloft.net> [Sparc]
Acked-by: Chris Zankel <chris@zankel.net> [Xtensa]
Reviewed-by: Richard Henderson <rth@twiddle.net> [Alpha]
Reviewed-by: Yoshinori Sato <ysato@users.sourceforge.jp> [H8300]
Cc: starvik@axis.com [CRIS]
Cc: jesper.nilsson@axis.com [CRIS]
Cc: linux-cris-kernel@axis.com
VMI was the only user of the alloc_pmd_clone hook, given that VMI
is now removed we can also remove this hook.
Signed-off-by: Alok N Kataria <akataria@vmware.com>
LKML-Reference: <1282608357.19396.36.camel@ank32.eng.vmware.com>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Now that both Xen and VMI disable allocations of PTE pages from high
memory this paravirt op serves no further purpose.
This effectively reverts ce6234b5 "add kmap_atomic_pte for mapping
highpte pages".
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
LKML-Reference: <1267204562-11844-3-git-send-email-ian.campbell@citrix.com>
Acked-by: Alok Kataria <akataria@vmware.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Name space cleanup. No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
The raw_spin* namespace was taken by lockdep for the architecture
specific implementations. raw_spin_* would be the ideal name space for
the spinlocks which are not converted to sleeping locks in preempt-rt.
Linus suggested to convert the raw_ to arch_ locks and cleanup the
name space instead of using an artifical name like core_spin,
atomic_spin or whatever
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: linux-arch@vger.kernel.org
Bastian Blank reported a boot crash with stackprotector enabled,
and debugged it back to edx register corruption.
For historical reasons irq enable/disable/save/restore had special
calling sequences to make them more efficient. With the more
recent introduction of higher-level and more general optimisations
this is no longer necessary so we can just use the normal PVOP_
macros.
This fixes some residual bugs in the old implementations which left
edx liable to inadvertent clobbering. Also, fix some bugs in
__PVOP_VCALLEESAVE which were revealed by actual use.
Reported-by: Bastian Blank <bastian@waldi.eu.org>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Stable Kernel <stable@kernel.org>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4AD3BC9B.7040501@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (38 commits)
x86: Move get/set_wallclock to x86_platform_ops
x86: platform: Fix section annotations
x86: apic namespace cleanup
x86: Distangle ioapic and i8259
x86: Add Moorestown early detection
x86: Add hardware_subarch ID for Moorestown
x86: Add early platform detection
x86: Move tsc_init to late_time_init
x86: Move tsc_calibration to x86_init_ops
x86: Replace the now identical time_32/64.c by time.c
x86: time_32/64.c unify profile_pc
x86: Move calibrate_cpu to tsc.c
x86: Make timer setup and global variables the same in time_32/64.c
x86: Remove mca bus ifdef from timer interrupt
x86: Simplify timer_ack magic in time_32.c
x86: Prepare unification of time_32/64.c
x86: Remove do_timer hook
x86: Add timer_init to x86_init_ops
x86: Move percpu clockevents setup to x86_init_ops
x86: Move xen_post_allocator_init into xen_pagetable_setup_done
...
Fix up conflicts in arch/x86/include/asm/io_apic.h
get/set_wallclock() have already a set of platform dependent
implementations (default, EFI, paravirt). MRST will add another
variant.
Moving them to platform ops simplifies the existing code and minimizes
the effort to integrate new variants.
Signed-off-by: Feng Tang <feng.tang@intel.com>
LKML-Reference: <new-submission>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Switch them to native_{rd,wr}msr_safe_regs and remove
pv_cpu_ops.read_msr_amd.
Signed-off-by: Borislav Petkov <petkovbb@gmail.com>
LKML-Reference: <1251705011-18636-2-git-send-email-petkovbb@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
native_{rdmsr,wrmsr}_safe_regs are two new interfaces which allow
presetting of a subset of eight x86 GPRs before executing the rd/wrmsr
instructions. This is needed at least on AMD K8 for accessing an erratum
workaround MSR.
Originally based on an idea by H. Peter Anvin.
Signed-off-by: Borislav Petkov <petkovbb@gmail.com>
LKML-Reference: <1251705011-18636-1-git-send-email-petkovbb@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
TSC calibration is modified by the vmware hypervisor and paravirt by
separate means. Moorestown wants to add its own calibration routine as
well. So make calibrate_tsc a proper x86_init_ops function and
override it by paravirt or by the early setup of the vmware
hypervisor.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The timer init code is convoluted with several quirks and the paravirt
timer chooser. Figuring out which code path is actually taken is not
for the faint hearted.
Move the numaq TSC quirk to tsc_pre_init x86_init_ops function and
replace the paravirt time chooser and the remaining x86 quirk with a
simple x86_init_ops function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
paravirt overrides the setup of the default apic timers as per cpu
timers. Moorestown needs to override that as well.
Move it to x86_init_ops setup and create a separate x86_cpuinit struct
which holds the function for the secondary evtl. hotplugabble CPUs.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
We really do not need two paravirt/x86_init_ops functions which are
called in two consecutive source lines. Move the only user of
post_allocator_init into the already existing pagetable_setup_done
function.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Replace another obscure paravirt magic and move it to
x86_init_ops. Such a hook is also useful for embedded and special
hardware.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
ARCH_SETUP is a horrible leftover from the old arch/i386 mach support
code. It still has a lonely user in xen. Move it to x86_init_ops.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Split the monolithic asm/paravirt.h into separate paravirt.h (inlines and other
"active" definitions), and paravirt_types.h (types, constants and other "passive"
definitions). This makes it easier to use the type/constant definitions without
pulling in everything else and causing circular dependency problems.
[ Impact: cleanup ]
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
* 'x86-xen-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (42 commits)
xen: cache cr0 value to avoid trap'n'emulate for read_cr0
xen/x86-64: clean up warnings about IST-using traps
xen/x86-64: fix breakpoints and hardware watchpoints
xen: reserve Xen start_info rather than e820 reserving
xen: add FIX_TEXT_POKE to fixmap
lguest: update lazy mmu changes to match lguest's use of kvm hypercalls
xen: honour VCPU availability on boot
xen: add "capabilities" file
xen: drop kexec bits from /sys/hypervisor since kexec isn't implemented yet
xen/sys/hypervisor: change writable_pt to features
xen: add /sys/hypervisor support
xen/xenbus: export xenbus_dev_changed
xen: use device model for suspending xenbus devices
xen: remove suspend_cancel hook
xen/dev-evtchn: clean up locking in evtchn
xen: export ioctl headers to userspace
xen: add /dev/xen/evtchn driver
xen: add irq_from_evtchn
xen: clean up gate trap/interrupt constants
xen: set _PAGE_NX in __supported_pte_mask before pagetable construction
...
Xiaohui Xin and some other folks at Intel have been looking into what's
behind the performance hit of paravirt_ops when running native.
It appears that the hit is entirely due to the paravirtualized
spinlocks introduced by:
| commit 8efcbab674
| Date: Mon Jul 7 12:07:51 2008 -0700
|
| paravirt: introduce a "lock-byte" spinlock implementation
The extra call/return in the spinlock path is somehow
causing an increase in the cycles/instruction of somewhere around 2-7%
(seems to vary quite a lot from test to test). The working theory is
that the CPU's pipeline is getting upset about the
call->call->locked-op->return->return, and seems to be failing to
speculate (though I haven't seen anything definitive about the precise
reasons). This doesn't entirely make sense, because the performance
hit is also visible on unlock and other operations which don't involve
locked instructions. But spinlock operations clearly swamp all the
other pvops operations, even though I can't imagine that they're
nearly as common (there's only a .05% increase in instructions
executed).
If I disable just the pv-spinlock calls, my tests show that pvops is
identical to non-pvops performance on native (my measurements show that
it is actually about .1% faster, but Xiaohui shows a .05% slowdown).
Summary of results, averaging 10 runs of the "mmperf" test, using a
no-pvops build as baseline:
nopv Pv-nospin Pv-spin
CPU cycles 100.00% 99.89% 102.18%
instructions 100.00% 100.10% 100.15%
CPI 100.00% 99.79% 102.03%
cache ref 100.00% 100.84% 100.28%
cache miss 100.00% 90.47% 88.56%
cache miss rate 100.00% 89.72% 88.31%
branches 100.00% 99.93% 100.04%
branch miss 100.00% 103.66% 107.72%
branch miss rt 100.00% 103.73% 107.67%
wallclock 100.00% 99.90% 102.20%
The clear effect here is that the 2% increase in CPI is
directly reflected in the final wallclock time.
(The other interesting effect is that the more ops are
out of line calls via pvops, the lower the cache access
and miss rates. Not too surprising, but it suggests that
the non-pvops kernel is over-inlined. On the flipside,
the branch misses go up correspondingly...)
So, what's the fix?
Paravirt patching turns all the pvops calls into direct calls, so
_spin_lock etc do end up having direct calls. For example, the compiler
generated code for paravirtualized _spin_lock is:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq *0xffffffff805a5b30
<_spin_lock+22>: retq
The indirect call will get patched to:
<_spin_lock+0>: mov %gs:0xb4c8,%rax
<_spin_lock+9>: incl 0xffffffffffffe044(%rax)
<_spin_lock+15>: callq <__ticket_spin_lock>
<_spin_lock+20>: nop; nop /* or whatever 2-byte nop */
<_spin_lock+22>: retq
One possibility is to inline _spin_lock, etc, when building an
optimised kernel (ie, when there's no spinlock/preempt
instrumentation/debugging enabled). That will remove the outer
call/return pair, returning the instruction stream to a single
call/return, which will presumably execute the same as the non-pvops
case. The downsides arel 1) it will replicate the
preempt_disable/enable code at eack lock/unlock callsite; this code is
fairly small, but not nothing; and 2) the spinlock definitions are
already a very heavily tangled mass of #ifdefs and other preprocessor
magic, and making any changes will be non-trivial.
The other obvious answer is to disable pv-spinlocks. Making them a
separate config option is fairly easy, and it would be trivial to
enable them only when Xen is enabled (as the only non-default user).
But it doesn't really address the common case of a distro build which
is going to have Xen support enabled, and leaves the open question of
whether the native performance cost of pv-spinlocks is worth the
performance improvement on a loaded Xen system (10% saving of overall
system CPU when guests block rather than spin). Still it is a
reasonable short-term workaround.
[ Impact: fix pvops performance regression when running native ]
Analysed-by: "Xin Xiaohui" <xiaohui.xin@intel.com>
Analysed-by: "Li Xin" <xin.li@intel.com>
Analysed-by: "Nakajima Jun" <jun.nakajima@intel.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: H. Peter Anvin <hpa@zytor.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Xen-devel <xen-devel@lists.xensource.com>
LKML-Reference: <4A0B62F7.5030802@goop.org>
[ fixed the help text ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Conflicts:
arch/frv/include/asm/pgtable.h
arch/x86/include/asm/required-features.h
arch/x86/xen/mmu.c
Merge reason: x86/xen was on a .29 base still, move it to a fresher
branch and pick up Xen fixes as well, plus resolve
conflicts
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use phys_addr_t for receiving a physical address argument instead of
unsigned long. This allows fixmap to handle pages higher than 4GB on
x86-32.
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* commit 'origin/master': (4825 commits)
Fix build errors due to CONFIG_BRANCH_TRACER=y
parport: Use the PCI IRQ if offered
tty: jsm cleanups
Adjust path to gpio headers
KGDB_SERIAL_CONSOLE check for module
Change KCONFIG name
tty: Blackin CTS/RTS
Change hardware flow control from poll to interrupt driven
Add support for the MAX3100 SPI UART.
lanana: assign a device name and numbering for MAX3100
serqt: initial clean up pass for tty side
tty: Use the generic RS485 ioctl on CRIS
tty: Correct inline types for tty_driver_kref_get()
splice: fix deadlock in splicing to file
nilfs2: support nanosecond timestamp
nilfs2: introduce secondary super block
nilfs2: simplify handling of active state of segments
nilfs2: mark minor flag for checkpoint created by internal operation
nilfs2: clean up sketch file
nilfs2: super block operations fix endian bug
...
Conflicts:
arch/x86/include/asm/thread_info.h
arch/x86/lguest/boot.c
drivers/xen/manage.c
Impact: fix lazy context switch API
Pass the previous and next tasks into the context switch start
end calls, so that the called functions can properly access the
task state (esp in end_context_switch, in which the next task
is not yet completely current).
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Impact: allow preemption during lazy mmu updates
If we're in lazy mmu mode when context switching, leave
lazy mmu mode, but remember the task's state in
TIF_LAZY_MMU_UPDATES. When we resume the task, check this
flag and re-enter lazy mmu mode if its set.
This sets things up for allowing lazy mmu mode while preemptible,
though that won't actually be active until the next change.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Impact: simplification, prepare for later changes
Make lazy cpu mode more specific to context switching, so that
it makes sense to do more context-switch specific things in
the callbacks.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
