From: Will Deacon <will.dea...@arm.com>
[ Upstream commit 88b0193d9418c00340e45e0a913a0813bc6c8c96 ]
Perf can generate and record a user callchain in response to a synchronous
request, such as a tracepoint firing. If this happens under set_fs(KERNEL_DS),
then we can end up walking the user stack (and dereferencing/saving whatever we
find there) without the protections usually afforded by checks such as
access_ok.
Rather than play whack-a-mole with each architecture's stack unwinding
implementation, fix the root of the problem by ensuring that we force USER_DS
when invoking perf_callchain_user from the perf core.
Reported-by: Al Viro <v...@zeniv.linux.org.uk>
Signed-off-by: Will Deacon <will.dea...@arm.com>
Acked-by: Peter Zijlstra <pet...@infradead.org>
Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <a...@redhat.com>
Cc: Jiri Olsa <jo...@redhat.com>
Cc: Linus Torvalds <torva...@linux-foundation.org>
Cc: Thomas Gleixner <t...@linutronix.de>
Signed-off-by: Ingo Molnar <mi...@kernel.org>
Signed-off-by: Sasha Levin <alexander.le...@microsoft.com>
---
kernel/events/callchain.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index e9fdb5203de5..411226b26bca 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -227,12 +227,18 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr,
bool kernel, bool user,
}
if (regs) {
+ mm_segment_t fs;
+
if (crosstask)
goto exit_put;
if (add_mark)
perf_callchain_store_context(&ctx,
PERF_CONTEXT_USER);
+
+ fs = get_fs();
+ set_fs(USER_DS);
perf_callchain_user(&ctx, regs);
+ set_fs(fs);
}
}
--
2.14.1
