Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-12 Thread Roger Pau Monné
On Thu, Jan 11, 2024 at 05:47:30PM +, David Woodhouse wrote: > On Wed, 2024-01-10 at 11:26 +0100, Jan Beulich wrote: > > On 10.01.2024 10:53, Roger Pau Monne wrote: > > > The HVM pirq feature allows routing interrupts from both physical and > > > emulated > > > devices over event channels, thi

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-11 Thread David Woodhouse
On Wed, 2024-01-10 at 11:26 +0100, Jan Beulich wrote: > On 10.01.2024 10:53, Roger Pau Monne wrote: > > The HVM pirq feature allows routing interrupts from both physical and > > emulated > > devices over event channels, this was done a performance improvement.  > > However > > its usage is fully

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-11 Thread Xenia Ragiadakou
Hi Roger, On 10/1/24 17:21, Roger Pau Monné wrote: On Wed, Jan 10, 2024 at 03:47:12PM +0200, Xenia Ragiadakou wrote: On 10/1/24 12:26, Jan Beulich wrote: On 10.01.2024 10:53, Roger Pau Monne wrote: The HVM pirq feature allows routing interrupts from both physical and emulated devices over e

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Roger Pau Monné
On Wed, Jan 10, 2024 at 03:47:12PM +0200, Xenia Ragiadakou wrote: > > > On 10/1/24 12:26, Jan Beulich wrote: > > On 10.01.2024 10:53, Roger Pau Monne wrote: > > > The HVM pirq feature allows routing interrupts from both physical and > > > emulated > > > devices over event channels, this was done

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Andrew Cooper
On 10/01/2024 10:26 am, Jan Beulich wrote: > On 10.01.2024 10:53, Roger Pau Monne wrote: >> The HVM pirq feature allows routing interrupts from both physical and >> emulated >> devices over event channels, this was done a performance improvement. >> However >> its usage is fully undocumented, an

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Xenia Ragiadakou
On 10/1/24 12:26, Jan Beulich wrote: On 10.01.2024 10:53, Roger Pau Monne wrote: The HVM pirq feature allows routing interrupts from both physical and emulated devices over event channels, this was done a performance improvement. However its usage is fully undocumented, and the only referenc

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Roger Pau Monné
On Wed, Jan 10, 2024 at 11:26:02AM +0100, Jan Beulich wrote: > On 10.01.2024 10:53, Roger Pau Monne wrote: > > The HVM pirq feature allows routing interrupts from both physical and > > emulated > > devices over event channels, this was done a performance improvement. > > However > > its usage is

Re: [PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Jan Beulich
On 10.01.2024 10:53, Roger Pau Monne wrote: > The HVM pirq feature allows routing interrupts from both physical and emulated > devices over event channels, this was done a performance improvement. However > its usage is fully undocumented, and the only reference implementation is in > Linux. It d

[PATCH] x86/hvm: don't expose XENFEAT_hvm_pirqs by default

2024-01-10 Thread Roger Pau Monne
The HVM pirq feature allows routing interrupts from both physical and emulated devices over event channels, this was done a performance improvement. However its usage is fully undocumented, and the only reference implementation is in Linux. It defeats the purpose of local APIC hardware virtualiza