Re: [PATCH] powerpc/perf: Dereference bhrb entries safely
From: Balbir Singh
Date: Thu Dec 14 2017 - 07:24:18 EST
On Tue, Dec 12, 2017 at 11:29 PM, Ravi Bangoria
<ravi.bangoria@xxxxxxxxxxxxxxxxxx> wrote:
> It may very well happen that branch instructions recorded by
> bhrb entries already get unmapped before they get processed by
> the kernel. Hence, trying to dereference such memory location
> will endup in a crash. Ex,
>
> Unable to handle kernel paging request for data at address 0xc008000019c41764
> Faulting instruction address: 0xc000000000084a14
> NIP [c000000000084a14] branch_target+0x4/0x70
> LR [c0000000000eb828] record_and_restart+0x568/0x5c0
> Call Trace:
> [c0000000000eb3b4] record_and_restart+0xf4/0x5c0 (unreliable)
> [c0000000000ec378] perf_event_interrupt+0x298/0x460
> [c000000000027964] performance_monitor_exception+0x54/0x70
> [c000000000009ba4] performance_monitor_common+0x114/0x120
>
> Fix this by deferefencing them safely.
>
> Suggested-by: Naveen N. Rao <naveen.n.rao@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@xxxxxxxxxxxxxxxxxx>
> ---
> arch/powerpc/perf/core-book3s.c | 7 +++++--
> 1 file changed, 5 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
> index 9e3da168d54c..5a68d2effdf9 100644
> --- a/arch/powerpc/perf/core-book3s.c
> +++ b/arch/powerpc/perf/core-book3s.c
> @@ -410,8 +410,11 @@ static __u64 power_pmu_bhrb_to(u64 addr)
> int ret;
> __u64 target;
>
> - if (is_kernel_addr(addr))
> - return branch_target((unsigned int *)addr);
> + if (is_kernel_addr(addr)) {
I think __kernel_text_address() is more accurate right? In which case
you need to check for is_kernel_addr(addr) and if its not kernel_text_address()
then we have an interesting case of a branch from something not text.
It would be nice to catch such cases.
> + if (probe_kernel_address((void *)addr, instr))
> + return 0;
> + return branch_target(&instr);
> + }
>
> /* Userspace: need copy instruction here then translate it */
> pagefault_disable();
Otherwise,
Reviewed-by: Balbir Singh <bsingharora@xxxxxxxxx>