2018-08-23 23:01:38

by Yabin Cui

Subject: [PATCH] perf: Force USER_DS when recording user stack data.

Perf can record user stack data in response to a synchronous request, such
as a tracepoint firing. If this happens under set_fs(KERNEL_DS), then we
end up reading user stack data using __copy_from_user_inatomic() under
set_fs(KERNEL_DS). I think this conflicts with the intention of using
set_fs(KERNEL_DS). And it is explicitly forbidden by hardware on ARM64
when both CONFIG_ARM64_UAO and CONFIG_ARM64_PAN are used.

So fix this by forcing USER_DS when recording user stack data.

Signed-off-by: Yabin Cui <[email protected]>
---
kernel/events/core.c | 4 ++++
1 file changed, 4 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2a62b96600ad..9bc047421e75 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5948,6 +5948,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
unsigned long sp;
unsigned int rem;
u64 dyn_size;
+ mm_segment_t fs;

/*
* We dump:
@@ -5965,7 +5966,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,

/* Data. */
sp = perf_user_stack_pointer(regs);
+ fs = get_fs();
+ set_fs(USER_DS);
rem = __output_copy_user(handle, (void *) sp, dump_size);
+ set_fs(fs);
dyn_size = dump_size - rem;

perf_output_skip(handle, rem);
--
2.19.0.rc0.228.g281dcd1b4d0-goog

2018-08-24 09:03:11

by Peter Zijlstra

Subject: Re: [PATCH] perf: Force USER_DS when recording user stack data.

On Thu, Aug 23, 2018 at 03:59:35PM -0700, Yabin Cui wrote:
> Perf can record user stack data in response to a synchronous request, such
> as a tracepoint firing. If this happens under set_fs(KERNEL_DS), then we
> end up reading user stack data using __copy_from_user_inatomic() under
> set_fs(KERNEL_DS). I think this conflicts with the intention of using
> set_fs(KERNEL_DS). And it is explicitly forbidden by hardware on ARM64
> when both CONFIG_ARM64_UAO and CONFIG_ARM64_PAN are used.
>
> So fix this by forcing USER_DS when recording user stack data.
>
> Signed-off-by: Yabin Cui <[email protected]>

Ingo, I think this wants a stable tag too; seems to be a corrolary of:

88b0193d9418 ("perf/callchain: Force USER_DS when invoking perf_callchain_user()")

Acked-by: Peter Zijlstra (Intel) <[email protected]>

> ---
> kernel/events/core.c | 4 ++++
> 1 file changed, 4 insertions(+)
>
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 2a62b96600ad..9bc047421e75 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -5948,6 +5948,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
> unsigned long sp;
> unsigned int rem;
> u64 dyn_size;
> + mm_segment_t fs;
>
> /*
> * We dump:
> @@ -5965,7 +5966,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
>
> /* Data. */
> sp = perf_user_stack_pointer(regs);
> + fs = get_fs();
> + set_fs(USER_DS);
> rem = __output_copy_user(handle, (void *) sp, dump_size);
> + set_fs(fs);
> dyn_size = dump_size - rem;
>
> perf_output_skip(handle, rem);
> --
> 2.19.0.rc0.228.g281dcd1b4d0-goog
>

2018-09-10 12:41:50

by tip-bot for Vasyl Gomonovych

Subject: [tip:perf/urgent] perf/core: Force USER_DS when recording user stack data

Commit-ID: 02e184476eff848273826c1d6617bb37e5bcc7ad
Gitweb: https://git.kernel.org/tip/02e184476eff848273826c1d6617bb37e5bcc7ad
Author: Yabin Cui <[email protected]>
AuthorDate: Thu, 23 Aug 2018 15:59:35 -0700
Committer: Ingo Molnar <[email protected]>
CommitDate: Mon, 10 Sep 2018 14:01:46 +0200

perf/core: Force USER_DS when recording user stack data

Perf can record user stack data in response to a synchronous request, such
as a tracepoint firing. If this happens under set_fs(KERNEL_DS), then we
end up reading user stack data using __copy_from_user_inatomic() under
set_fs(KERNEL_DS). I think this conflicts with the intention of using
set_fs(KERNEL_DS). And it is explicitly forbidden by hardware on ARM64
when both CONFIG_ARM64_UAO and CONFIG_ARM64_PAN are used.

So fix this by forcing USER_DS when recording user stack data.

Signed-off-by: Yabin Cui <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Cc: <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Arnaldo Carvalho de Melo <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Fixes: 88b0193d9418 ("perf/callchain: Force USER_DS when invoking perf_callchain_user()")
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
---
kernel/events/core.c | 4 ++++
1 file changed, 4 insertions(+)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index abaed4f8bb7f..c80549bf82c6 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5943,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,
unsigned long sp;
unsigned int rem;
u64 dyn_size;
+ mm_segment_t fs;

/*
* We dump:
@@ -5960,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size,

/* Data. */
sp = perf_user_stack_pointer(regs);
+ fs = get_fs();
+ set_fs(USER_DS);
rem = __output_copy_user(handle, (void *) sp, dump_size);
+ set_fs(fs);
dyn_size = dump_size - rem;

perf_output_skip(handle, rem);