Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-27 Thread Mark Rutland
On Thu, Feb 27, 2014 at 11:51:43AM +, Peter Zijlstra wrote: > On Thu, Feb 27, 2014 at 11:48:05AM +, Mark Rutland wrote: > > On Tue, Feb 25, 2014 at 11:31:00AM +, Peter Zijlstra wrote: > > > On Tue, Feb 11, 2014 at 05:56:51PM +, Mark Rutland wrote: > > > > Another option would be to

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-27 Thread Peter Zijlstra
On Thu, Feb 27, 2014 at 11:48:05AM +, Mark Rutland wrote: > On Tue, Feb 25, 2014 at 11:31:00AM +, Peter Zijlstra wrote: > > On Tue, Feb 11, 2014 at 05:56:51PM +, Mark Rutland wrote: > > > Another option would be to have a context per-pmu. Each context's pmu > > > pointer would be valid,

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-27 Thread Mark Rutland
On Tue, Feb 25, 2014 at 11:31:00AM +, Peter Zijlstra wrote: > On Tue, Feb 11, 2014 at 05:56:51PM +, Mark Rutland wrote: > > Another option would be to have a context per-pmu. Each context's pmu > > pointer would be valid, and (other than the case of software events) it > > doesn't make sens

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-25 Thread Peter Zijlstra
On Tue, Feb 11, 2014 at 05:56:51PM +, Mark Rutland wrote: > Another option would be to have a context per-pmu. Each context's pmu > pointer would be valid, and (other than the case of software events) it > doesn't make sense to place events from disparate PMUs into the same > group anyway. Then

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-12 Thread Dave Martin
On Tue, Feb 11, 2014 at 05:56:51PM +, Mark Rutland wrote: > On Mon, Feb 10, 2014 at 06:10:26PM +, Peter Zijlstra wrote: > > On Mon, Feb 10, 2014 at 05:44:24PM +, Mark Rutland wrote: > > > Currently portions of the perf subsystem assume that a > > > perf_event_context is associated with

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-11 Thread Mark Rutland
On Mon, Feb 10, 2014 at 06:10:26PM +, Peter Zijlstra wrote: > On Mon, Feb 10, 2014 at 05:44:24PM +, Mark Rutland wrote: > > Currently portions of the perf subsystem assume that a > > perf_event_context is associated with a single pmu while in reality a > > single perf_event_context may be s

Re: [PATCH 7/7] perf: kill perf_event_context::pmu

2014-02-10 Thread Peter Zijlstra
On Mon, Feb 10, 2014 at 05:44:24PM +, Mark Rutland wrote: > Currently portions of the perf subsystem assume that a > perf_event_context is associated with a single pmu while in reality a > single perf_event_context may be shared by a number of pmus, as commit > 443772776c69 (perf: Disable all p