2021-03-30 07:01:44

by Marco Elver

[permalink] [raw]
Subject: [PATCH mm] kfence, x86: fix preemptible warning on KPTI-enabled systems

On systems with KPTI enabled, we can currently observe the following warning:

BUG: using smp_processor_id() in preemptible
caller is invalidate_user_asid+0x13/0x50
CPU: 6 PID: 1075 Comm: dmesg Not tainted 5.12.0-rc4-gda4a2b1a5479-kfence_1+ #1
Hardware name: Hewlett-Packard HP Pro 3500 Series/2ABF, BIOS 8.11 10/24/2012
Call Trace:
dump_stack+0x7f/0xad
check_preemption_disabled+0xc8/0xd0
invalidate_user_asid+0x13/0x50
flush_tlb_one_kernel+0x5/0x20
kfence_protect+0x56/0x80
...

While it normally makes sense to require preemption to be off, so that
the expected CPU's TLB is flushed and not another, in our case it really
is best-effort (see comments in kfence_protect_page()).

Avoid the warning by disabling preemption around flush_tlb_one_kernel().

Link: https://lore.kernel.org/lkml/[email protected]/
Reported-by: Tomi Sarvela <[email protected]>
Signed-off-by: Marco Elver <[email protected]>
---
arch/x86/include/asm/kfence.h | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h
index 97bbb4a9083a..05b48b33baf0 100644
--- a/arch/x86/include/asm/kfence.h
+++ b/arch/x86/include/asm/kfence.h
@@ -56,8 +56,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
else
set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));

- /* Flush this CPU's TLB. */
+ /*
+ * Flush this CPU's TLB, assuming whoever did the allocation/free is
+ * likely to continue running on this CPU.
+ */
+ preempt_disable();
flush_tlb_one_kernel(addr);
+ preempt_enable();
return true;
}

--
2.31.0.291.g576ba9dcdaf-goog


2021-04-01 09:13:26

by Alexander Potapenko

[permalink] [raw]
Subject: Re: [PATCH mm] kfence, x86: fix preemptible warning on KPTI-enabled systems

On Tue, Mar 30, 2021 at 8:57 AM Marco Elver <[email protected]> wrote:
>
> On systems with KPTI enabled, we can currently observe the following warning:
>
> BUG: using smp_processor_id() in preemptible
> caller is invalidate_user_asid+0x13/0x50
> CPU: 6 PID: 1075 Comm: dmesg Not tainted 5.12.0-rc4-gda4a2b1a5479-kfence_1+ #1
> Hardware name: Hewlett-Packard HP Pro 3500 Series/2ABF, BIOS 8.11 10/24/2012
> Call Trace:
> dump_stack+0x7f/0xad
> check_preemption_disabled+0xc8/0xd0
> invalidate_user_asid+0x13/0x50
> flush_tlb_one_kernel+0x5/0x20
> kfence_protect+0x56/0x80
> ...
>
> While it normally makes sense to require preemption to be off, so that
> the expected CPU's TLB is flushed and not another, in our case it really
> is best-effort (see comments in kfence_protect_page()).
>
> Avoid the warning by disabling preemption around flush_tlb_one_kernel().
>
> Link: https://lore.kernel.org/lkml/[email protected]/
> Reported-by: Tomi Sarvela <[email protected]>
> Signed-off-by: Marco Elver <[email protected]>
Acked-by: Alexander Potapenko <[email protected]>