Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
On 03/25/2015 07:04 PM, Ingo Molnar wrote: >>> * Denys Vlasenko wrote: >>> SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Ingo Molnar
* Denys Vlasenko wrote: > On 03/25/2015 06:29 PM, Ingo Molnar wrote: > > > > * Denys Vlasenko wrote: > > > >> SYSRET code path has a small irq-off block. > >> On this code path, TRACE_IRQS_ON can't be called right before interrupts > >> are enabled for real, we can't clobber registers there.

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
On 03/25/2015 06:29 PM, Ingo Molnar wrote: > > * Denys Vlasenko wrote: > >> SYSRET code path has a small irq-off block. >> On this code path, TRACE_IRQS_ON can't be called right before interrupts >> are enabled for real, we can't clobber registers there. >> So current code does it earlier, in a

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Ingo Molnar
* Denys Vlasenko wrote: > SYSRET code path has a small irq-off block. > On this code path, TRACE_IRQS_ON can't be called right before interrupts > are enabled for real, we can't clobber registers there. > So current code does it earlier, in a safe place. > > But with this, TRACE_IRQS_OFF/ON

[PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it earlier, in a safe place. But with this, TRACE_IRQS_OFF/ON frames just two fast instructions, which

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Ingo Molnar
* Denys Vlasenko dvlas...@redhat.com wrote: On 03/25/2015 06:29 PM, Ingo Molnar wrote: * Denys Vlasenko dvlas...@redhat.com wrote: SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't

[PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it earlier, in a safe place. But with this, TRACE_IRQS_OFF/ON frames just two fast instructions, which

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
On 03/25/2015 06:29 PM, Ingo Molnar wrote: * Denys Vlasenko dvlas...@redhat.com wrote: SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Ingo Molnar
* Denys Vlasenko dvlas...@redhat.com wrote: SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it earlier, in a safe place. But with this,

Re: [PATCH 2/4] x86/asm/entry/64: do not TRACE_IRQS fast SYSRET64 path

2015-03-25 Thread Denys Vlasenko
On 03/25/2015 07:04 PM, Ingo Molnar wrote: * Denys Vlasenko dvlas...@redhat.com wrote: SYSRET code path has a small irq-off block. On this code path, TRACE_IRQS_ON can't be called right before interrupts are enabled for real, we can't clobber registers there. So current code does it earlier,