[PATCH AUTOSEL for 4.9 028/281] perf/callchain: Force USER_DS when invoking perf_callchain_user()

[Sasha Levin]

From: Will Deacon <will.deacon@xxxxxxx>

[ 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 <viro@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
Acked-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Sasha Levin <alexander.levin@xxxxxxxxxxxxx>
---
 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