[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <64f071a5-3454-4dd2-9228-da9b394a3d07@intel.com>
Date: Wed, 18 Jun 2025 07:47:18 -0700
From: Dave Hansen <dave.hansen@...el.com>
To: "Liang, Kan" <kan.liang@...ux.intel.com>,
Peter Zijlstra <peterz@...radead.org>
Cc: Mark Rutland <mark.rutland@....com>,
"Mi, Dapeng" <dapeng1.mi@...ux.intel.com>, mingo@...hat.com,
acme@...nel.org, namhyung@...nel.org, tglx@...utronix.de,
dave.hansen@...ux.intel.com, irogers@...gle.com, adrian.hunter@...el.com,
jolsa@...nel.org, alexander.shishkin@...ux.intel.com,
linux-kernel@...r.kernel.org, ak@...ux.intel.com, zide.chen@...el.com,
broonie@...nel.org
Subject: Re: [RFC PATCH 06/12] perf: Support extension of sample_regs
On 6/18/25 07:30, Dave Hansen wrote:
> If software is going to munge the XSAVE format, then you don't have to
> worry about alignment because you'd save it to some probably per-cpu
> 64-byte-aligned buffer and then munge it into the unaligned
> PERF_SAMPLE_SIMD_REGS above.
BTW, Peter just mentioned that you're just going to munge both the XSAVE
and PEBS formats before letting userspace see them. Big ack from me on
that, fwiw.
Powered by blists - more mailing lists