[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAP-5=fWvawhzhXx72L4iEPpNqeNW+oHQOTkAOy53z0r8UXnMSA@mail.gmail.com>
Date: Tue, 4 Nov 2025 08:04:17 -0800
From: Ian Rogers <irogers@...gle.com>
To: "jingxian.li" <jingxian.li@...pee.com>
Cc: stable@...r.kernel.org, peterz@...radead.org, mingo@...hat.com,
acme@...nel.org, mark.rutland@....com, alexander.shishkin@...ux.intel.com,
jolsa@...nel.org, namhyung@...nel.org, adrian.hunter@...el.com,
sashal@...nel.org, linux-perf-users@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH 6.6.y] Revert "perf dso: Add missed dso__put to dso__load_kcore"
On Tue, Nov 4, 2025 at 1:38 AM jingxian.li <jingxian.li@...pee.com> wrote:
>
> This reverts commit e5de9ea7796e79f3cd082624f788cc3442bff2a8.
>
> The patch introduced `map__zput(new_node->map)` in the kcore load
> path, causing a segmentation fault when running `perf c2c report`.
>
> The issue arises because `maps__merge_in` directly modifies and
> inserts the caller's `new_map`, causing it to be freed prematurely
> while still referenced by kmaps.
>
> Later branchs (6.12, 6.15, 6.16) are not affected because they use
> a different merge approach with a lazily sorted array, which avoids
> modifying the original `new_map`.
>
> Fixes: e5de9ea7796e ("perf dso: Add missed dso__put to dso__load_kcore")
>
> Signed-off-by: jingxian.li <jingxian.li@...pee.com>
Thanks for triaging this and the backport fix!
Acked-by: Ian Rogers <irogers@...gle.com>
> ---
> tools/perf/util/symbol.c | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
> index 4f0bbebcb6d6..ea24f21aafc3 100644
> --- a/tools/perf/util/symbol.c
> +++ b/tools/perf/util/symbol.c
> @@ -1366,7 +1366,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
> goto out_err;
> }
> }
> - map__zput(new_node->map);
> free(new_node);
> }
>
> --
> 2.43.0
>
>
Powered by blists - more mailing lists