Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-04 Thread Andrew Cooper
On 04/07/2025 8:52 am, Roger Pau Monné wrote: > On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: >> diff --git a/xen/arch/x86/include/asm/softirq.h >> b/xen/arch/x86/include/asm/softirq.h >> index e4b194f069fb..069e5716a68d 100644 >> --- a/xen/arch/x86/include/asm/softirq.h >> +++ b/

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-04 Thread Andrew Cooper
On 04/07/2025 8:24 am, Roger Pau Monné wrote: > On Thu, Jul 03, 2025 at 06:48:23PM +0100, Andrew Cooper wrote: >> On 03/07/2025 5:36 pm, Roger Pau Monné wrote: >>> On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: In order elide IPIs, we must be able to identify whether a target C

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-04 Thread Roger Pau Monné
On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: > diff --git a/xen/arch/x86/include/asm/softirq.h > b/xen/arch/x86/include/asm/softirq.h > index e4b194f069fb..069e5716a68d 100644 > --- a/xen/arch/x86/include/asm/softirq.h > +++ b/xen/arch/x86/include/asm/softirq.h > @@ -1,6 +1,8 @@

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-04 Thread Roger Pau Monné
On Thu, Jul 03, 2025 at 06:48:23PM +0100, Andrew Cooper wrote: > On 03/07/2025 5:36 pm, Roger Pau Monné wrote: > > On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: > >> In order elide IPIs, we must be able to identify whether a target CPU is in > >> MWAIT at the point it is woken up.

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Andrew Cooper
On 03/07/2025 5:36 pm, Roger Pau Monné wrote: > On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: >> In order elide IPIs, we must be able to identify whether a target CPU is in >> MWAIT at the point it is woken up. i.e. the store to wake it up must also >> identify the state. >> >> Cr

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Andrew Cooper
On 03/07/2025 3:07 pm, Jan Beulich wrote: > On 03.07.2025 13:59, Andrew Cooper wrote: >> On 03/07/2025 10:01 am, Jan Beulich wrote: >>> On 02.07.2025 16:41, Andrew Cooper wrote: @@ -452,6 +466,10 @@ void mwait_idle_with_hints(unsigned int eax, unsigned int ecx) mwait(eax, e

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Roger Pau Monné
On Wed, Jul 02, 2025 at 03:41:19PM +0100, Andrew Cooper wrote: > In order elide IPIs, we must be able to identify whether a target CPU is in > MWAIT at the point it is woken up. i.e. the store to wake it up must also > identify the state. > > Create a new in_mwait variable beside __softirq_pendin

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Jan Beulich
On 03.07.2025 13:59, Andrew Cooper wrote: > On 03/07/2025 10:01 am, Jan Beulich wrote: >> On 02.07.2025 16:41, Andrew Cooper wrote: >>> @@ -452,6 +466,10 @@ void mwait_idle_with_hints(unsigned int eax, unsigned >>> int ecx) >>> mwait(eax, ecx); >>> spec_ctrl_exit_idle(info); >>>

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Andrew Cooper
On 03/07/2025 10:01 am, Jan Beulich wrote: > On 02.07.2025 16:41, Andrew Cooper wrote: >> In order elide IPIs, we must be able to identify whether a target CPU is in >> MWAIT at the point it is woken up. i.e. the store to wake it up must also >> identify the state. >> >> Create a new in_mwait vari

Re: [PATCH 4/6] x86/idle: Implement a new MWAIT IPI-elision algorithm

2025-07-03 Thread Jan Beulich
On 02.07.2025 16:41, Andrew Cooper wrote: > In order elide IPIs, we must be able to identify whether a target CPU is in > MWAIT at the point it is woken up. i.e. the store to wake it up must also > identify the state. > > Create a new in_mwait variable beside __softirq_pending, so we can use a >