[<prev] [next>] [day] [month] [year] [list]
Message-ID: <87msimt5j4.fsf@ubik.fi.intel.com>
Date: Wed, 30 Oct 2024 09:26:55 +0200
From: Alexander Shishkin <alexander.shishkin@...ux.intel.com>
To: Li RongQing <lirongqing@...du.com>, peterz@...radead.org,
mingo@...hat.com, acme@...nel.org, namhyung@...nel.org,
mark.rutland@....com, jolsa@...nel.org, irogers@...gle.com,
adrian.hunter@...el.com, kan.liang@...ux.intel.com, tglx@...utronix.de,
bp@...en8.de, dave.hansen@...ux.intel.com, x86@...nel.org, hpa@...or.com,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
zhiquan1.li@...el.com, alexander.shishkin@...ux.intel.com
Cc: Li RongQing <lirongqing@...du.com>
Subject: Re: [PATCH] perf/x86/intel/bts: allocate bts_ctx only if necessary
Li RongQing <lirongqing@...du.com> writes:
> Avoid unnecessary per-CPU memory allocation on unsupported CPUs,
> this can save 12K memory for every CPU
Looks reasonable, but have you tested it? This driver is in serious
danger of bitrot ever since KPTI. It might save even more if we simply
remove the whole thing.
Regards,
--
Alex
Powered by blists - more mailing lists