On 09/12/24 15:42, Petr Tesarik wrote:
> On Mon, 9 Dec 2024 13:12:49 +0100
> Peter Zijlstra wrote:
>
>> On Mon, Dec 09, 2024 at 01:04:43PM +0100, Valentin Schneider wrote:
>>
>> > > But I wonder what exactly was the original scenario encountered by
>
On 05/12/24 18:31, Petr Tesarik wrote:
> On Thu, 21 Nov 2024 16:30:16 +0100
> Peter Zijlstra wrote:
>
>> On Thu, Nov 21, 2024 at 07:07:44AM -0800, Dave Hansen wrote:
>> > On 11/21/24 03:12, Peter Zijlstra wrote:
>> > >> I see e.g. ds_clear_cea() clears PTEs that can have the _PAGE_GLOBAL
>> > >>
On 24/11/24 22:46, Frederic Weisbecker wrote:
> Le Fri, Nov 22, 2024 at 03:56:59PM +0100, Valentin Schneider a écrit :
>> On 20/11/24 18:30, Frederic Weisbecker wrote:
>> > Le Wed, Nov 20, 2024 at 06:10:43PM +0100, Valentin Schneider a écrit :
>> >> On 20/11/24 15
On 20/11/24 18:30, Frederic Weisbecker wrote:
> Le Wed, Nov 20, 2024 at 06:10:43PM +0100, Valentin Schneider a écrit :
>> On 20/11/24 15:23, Frederic Weisbecker wrote:
>>
>> > Ah but there is CT_STATE_GUEST and I see the last patch also applies that
>> > to
>
On 22/11/24 04:53, Paul E. McKenney wrote:
> On Tue, Nov 19, 2024 at 04:34:51PM +0100, Valentin Schneider wrote:
>> +config RCU_DYNTICKS_TORTURE
>> +bool "Minimize RCU dynticks counter size"
>> +depends on RCU_EXPERT
>> +default n
>> +he
On 21/11/24 12:21, Josh Poimboeuf wrote:
> On Thu, Nov 21, 2024 at 04:51:09PM +0100, Valentin Schneider wrote:
>> Okay so forcing the IPI for .noinstr patching lets us get rid of all the
>> force_ipi faff; however I would still want the special marking to tell
>> objtool &quo
On 21/11/24 12:00, Peter Zijlstra wrote:
> On Wed, Nov 20, 2024 at 08:55:15AM -0800, Josh Poimboeuf wrote:
>> On Wed, Nov 20, 2024 at 03:57:46PM +0100, Peter Zijlstra wrote:
>> > On Wed, Nov 20, 2024 at 03:56:49PM +0100, Peter Zijlstra wrote:
>> >
>> > > But I think we can make the fall-back safer,
On 20/11/24 16:32, Peter Zijlstra wrote:
> On Wed, Nov 20, 2024 at 04:22:16PM +0100, Peter Zijlstra wrote:
>> On Tue, Nov 19, 2024 at 04:35:00PM +0100, Valentin Schneider wrote:
>>
>> > +void noinstr __flush_tlb_all_noinstr(void)
>> > +{
>> > + /*
>&g
On 20/11/24 15:23, Frederic Weisbecker wrote:
> Ah but there is CT_STATE_GUEST and I see the last patch also applies that to
> CT_STATE_IDLE.
>
> So that could be:
>
> bool ct_set_cpu_work(unsigned int cpu, unsigned int work)
> {
> struct context_tracking *ct = per_cpu_ptr(&context_tracking,
On 20/11/24 15:59, Peter Zijlstra wrote:
> On Tue, Nov 19, 2024 at 04:34:55PM +0100, Valentin Schneider wrote:
>> Later commits will cause objtool to warn about non __ro_after_init static
>> keys being used in .noinstr sections in order to safely defer instruction
>> patc
On 19/11/24 15:39, Josh Poimboeuf wrote:
> On Tue, Nov 19, 2024 at 04:34:53PM +0100, Valentin Schneider wrote:
>> Later commits will cause objtool to warn about non __ro_after_init static
>> keys being used in .noinstr sections in order to safely defer instruction
>> patc
On 20/11/24 15:50, Peter Zijlstra wrote:
> On Tue, Nov 19, 2024 at 04:34:51PM +0100, Valentin Schneider wrote:
>> A later commit will reduce the size of the RCU watching counter to free up
>> some bits for another purpose. Paul suggested adding a config option to
>> test the e
On 19/11/24 11:45, Steven Rostedt wrote:
> On Tue, 19 Nov 2024 16:34:47 +0100
> Valentin Schneider wrote:
>
>> Context
>> ===
>>
>> We've observed within Red Hat that isolated, NOHZ_FULL CPUs running a
>> pure-userspace application get regularly i
). Suppressing the text_poke_sync() IPI has
little benefits for this key, as NOHZ_FULL is incompatible with an unstable
TSC anyway.
Mark it as forceful to let the kernel know to always send the
text_poke_sync() IPI for it, and to let objtool know not to warn about it.
Signed-off-by: Valentin Schneider
NOHZ_FULL interference, so add a jump type that will be
leveraged by both the kernel (to know not to defer the IPI) and objtool (to
know not to generate the aforementioned warning).
Signed-off-by: Valentin Schneider
---
include/linux/jump_label.h | 26 +++---
1 file changed, 19
/performance), but the backing
mechanism is identical.
Add a default-no option to enable IPI deferral with NO_HZ_IDLE.
Signed-off-by: Valentin Schneider
---
kernel/time/Kconfig | 16 +++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/kernel/time/Kconfig b/kernel/time
including user mappings), this only happens when reaching a
invalidation range threshold where it is cheaper to do a full flush than to
individually invalidate each page in the range via INVLPG. IOW, it doesn't
*require* invalidating user mappings, and thus remains safe to defer until
a later
d these be instead new operations made
available through pv_ops.mmu.*? x86_64_start_kernel() uses
__native_tlb_flush_global() regardless of paravirt, so I'm thinking the
paravirt variants are more optimizations than hard requirements?
Signed-off-by: Valentin Schneider
--
ge the new context_tracking infrastructure to defer sync_core() IPIs
to a target CPU's next kernel entry.
Signed-off-by: Peter Zijlstra (Intel)
Signed-off-by: Nicolas Saenz Julienne
Signed-off-by: Valentin Schneider
---
arch/x86/include/asm/context_tracking_work.h | 6 ++--
arch/x86/include/asm/
CT_STATE_KERNEL in the ct_state prevents queuing deferred work.
Later commits introduce the bit:callback mappings.
Link: https://lore.kernel.org/all/20210929151723.162004...@infradead.org/
Signed-off-by: Nicolas Saenz Julienne
Signed-off-by: Valentin Schneider
uch can be (ab)used to store this information at the start
of text_poke_bp_batch().
Signed-off-by: Valentin Schneider
---
arch/x86/include/asm/text-patching.h | 12 ++--
arch/x86/kernel/alternative.c| 16 ++--
arch/x86/kernel/jump_label.c | 7 ---
3 fi
would be the result of a code change that
will need looking at.
Suggested-by: Josh Poimboeuf
Signed-off-by: Valentin Schneider
---
offset_of(static_key.type) and JUMP_TYPE_FORCEFUL would need to be shoved
into a somewhat standalone header file that could be included by objtool
itself.
---
tools
and to let objtool know not to warn about it.
Signed-off-by: Valentin Schneider
---
arch/x86/kernel/cpu/bugs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 47a01d4028f60..dcc4d5d6e3b95 100644
--- a/arch/x86/kernel/
es (Steven)
o Fixed __ro_after_init keys used in modules (Peter)
o Dropped the extra context_tracking atomic, squashed the new bits in the
existing .state field (Peter, Frederic)
o Added an RCU_EXPERT config for the RCU dynticks counter size, and added an
rcutorture case for a low-size
-laptop
Suggested-by: Paul E. McKenney
Signed-off-by: Valentin Schneider
---
tools/testing/selftests/rcutorture/configs/rcu/TREE04 | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
RCU_EXPERT. While at it, add a comment to
explain the layout of context_tracking->state.
Link:
http://lore.kernel.org/r/4c2cb573-168f-4806-b1d9-164e8276e66a@paulmck-laptop
Suggested-by: Paul E. McKenney
Signed-off-by: Valentin Schneider
---
include/linux/context_tracking_state.h |
sched_clock_running is only ever enabled in the __init functions
sched_clock_init() and sched_clock_init_late(), and is never disabled. Mark
it __ro_after_init.
Signed-off-by: Valentin Schneider
---
kernel/sched/clock.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel
I had to look into objtool itself to understand what this warning was
about; make it more explicit.
Signed-off-by: Valentin Schneider
---
tools/objtool/check.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5f1d0f95fc04b
: Valentin Schneider
---
tools/objtool/check.c | 15 +--
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 6604f5d038aad..5f1d0f95fc04b 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -3448,7 +3448,7
On 18/06/2019 16:31, Jonathan Corbet wrote:
> On Tue, 18 Jun 2019 15:56:05 +0100
> Valentin Schneider wrote:
>
>> The asterisks prepended to the quoted text currently get translated to
>> bullet points, which gets increasingly confusing the smaller your
>> screen
The asterisks prepended to the quoted text currently get translated to
bullet points, which gets increasingly confusing the smaller your
screen is (when viewing the sphinx output, that is).
Convert the whole quote to a literal block.
Signed-off-by: Valentin Schneider
---
Documentation/vm
On 01/02/2019 08:45, Julien Thierry wrote:
[...]
>> +Kernel preemption
>> +=
>> +When returning from interrupt context, you should call either of
>> +preempt_schedule() or preempt_schedule_irq() if preemption is enabled
>> +and need_resched() is true.
>> +
>
> I don't think preempt
Since there are a few archs out there that call preempt_schedule_irq()
within a need_resched() loop, point out that it's not needed.
Signed-off-by: Valentin Schneider
Cc: Jonathan Corbet
Cc: Ingo Molnar
Cc: Peter Zijlstra
Cc: Thomas Gleixner
Cc: Julien Thierry
Cc: linux-doc@vger.kerne
kml/cc989920-a13b-d53b-db83-1584a7f53...@arm.com/
Valentin Schneider (3):
arm64: entry: Remove unneeded need_resched() loop
ARM: entry: Remove unneeded need_resched() loop
sched/Documentation: Point out use of preempt_schedule_irq()
Documentation/scheduler/sched-arch.txt | 10 +++
34 matches
Mail list logo
