search for: progressm

...out of the slow >> paths, and then there are a few parameters to tune. > Can you clarify? The slow path is already in use on ARM64 which is weak, > so I doubt there's superfluous serialization present. And Will spend a > fair amount of time on making that thing guarantee forward progressm, so > there just isn't too much room to play. > >> We don't have a good alternate patching for function calls yet, but >> that would be something to do for native vs pv. > Going by your jump_label implementation, support for static_call should > be fairly straight fo...

...out of the slow >> paths, and then there are a few parameters to tune. > Can you clarify? The slow path is already in use on ARM64 which is weak, > so I doubt there's superfluous serialization present. And Will spend a > fair amount of time on making that thing guarantee forward progressm, so > there just isn't too much room to play. > >> We don't have a good alternate patching for function calls yet, but >> that would be something to do for native vs pv. > Going by your jump_label implementation, support for static_call should > be fairly straight fo...

Excerpts from Waiman Long's message of July 7, 2020 4:39 am: > On 7/6/20 12:35 AM, Nicholas Piggin wrote: >> v3 is updated to use __pv_queued_spin_unlock, noticed by Waiman (thank you). >> >> Thanks, >> Nick >> >> Nicholas Piggin (6): >> powerpc/powernv: must include hvcall.h to get PAPR defines >> powerpc/pseries: move some PAPR

Excerpts from Waiman Long's message of July 7, 2020 4:39 am: > On 7/6/20 12:35 AM, Nicholas Piggin wrote: >> v3 is updated to use __pv_queued_spin_unlock, noticed by Waiman (thank you). >> >> Thanks, >> Nick >> >> Nicholas Piggin (6): >> powerpc/powernv: must include hvcall.h to get PAPR defines >> powerpc/pseries: move some PAPR

...t more performance out of the slow > paths, and then there are a few parameters to tune. Can you clarify? The slow path is already in use on ARM64 which is weak, so I doubt there's superfluous serialization present. And Will spend a fair amount of time on making that thing guarantee forward progressm, so there just isn't too much room to play. > We don't have a good alternate patching for function calls yet, but > that would be something to do for native vs pv. Going by your jump_label implementation, support for static_call should be fairly straight forward too, no? https://...

...> > paths, and then there are a few parameters to tune. > > Can you clarify? The slow path is already in use on ARM64 which is weak, > > so I doubt there's superfluous serialization present. And Will spend a > > fair amount of time on making that thing guarantee forward progressm, so > > there just isn't too much room to play. > > > > > We don't have a good alternate patching for function calls yet, but > > > that would be something to do for native vs pv. > > Going by your jump_label implementation, support for static_call shoul...

...gt; Sorry for the delay, got bogged down and distracted by other things :( > Can you clarify? The slow path is already in use on ARM64 which is weak, > so I doubt there's superfluous serialization present. And Will spend a > fair amount of time on making that thing guarantee forward progressm, so > there just isn't too much room to play. Sure, the way the pending not-queued slowpath (which I guess is the medium-path) is implemented is just poorly structured for LL/SC. It has one more atomic than necessary (queued_fetch_set_pending_acquire), and a lot of branches in suboptimal or...

...gt; Sorry for the delay, got bogged down and distracted by other things :( > Can you clarify? The slow path is already in use on ARM64 which is weak, > so I doubt there's superfluous serialization present. And Will spend a > fair amount of time on making that thing guarantee forward progressm, so > there just isn't too much room to play. Sure, the way the pending not-queued slowpath (which I guess is the medium-path) is implemented is just poorly structured for LL/SC. It has one more atomic than necessary (queued_fetch_set_pending_acquire), and a lot of branches in suboptimal or...