On 2017/6/19 23:05, Andy Lutomirski wrote:
> On Mon, Jun 19, 2017 at 6:33 AM, zhong jiang <zhongji...@huawei.com> wrote:
>> On 2017/6/19 12:48, Andy Lutomirski wrote:
>>> It was historically possible to have two concurrent TLB flushes
>>> targeting the same CPU: one initiated locally and one initiated
>>> remotely. This can now cause an OOPS in leave_mm() at
>>> arch/x86/mm/tlb.c:47:
>>>
>>> if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
>>> BUG();
>>>
>>> with this call trace:
>>> flush_tlb_func_local arch/x86/mm/tlb.c:239 [inline]
>>> flush_tlb_mm_range+0x26d/0x370 arch/x86/mm/tlb.c:317
>>>
>>> Without reentrancy, this OOPS is impossible: leave_mm() is only
>>> called if we're not in TLBSTATE_OK, but then we're unexpectedly
>>> in TLBSTATE_OK in leave_mm().
>>>
>>> This can be caused by flush_tlb_func_remote() happening between
>>> the two checks and calling leave_mm(), resulting in two consecutive
>>> leave_mm() calls on the same CPU with no intervening switch_mm()
>>> calls.
>>>
>>> We never saw this OOPS before because the old leave_mm()
>>> implementation didn't put us back in TLBSTATE_OK, so the assertion
>>> didn't fire.
>> HI, Andy
>>
>> Today, I see same OOPS in linux 3.4 stable. It prove that it indeed has
>> fired.
>> but It is rarely to appear. I review the code. I found the a issue.
>> when current->mm is NULL, leave_mm will be called. but it maybe in
>> TLBSTATE_OK, eg: unuse_mm call after task->mm = NULL , but before
>> enter_lazy_tlb.
>>
>> therefore, it will fire. is it right?
> Is there a code path that does this?
eg:
cpu1 cpu2
flush_tlb_page unuse_mm
current->mm
= NULL
current->mm == NULL
leave_mm (cpu_tlbstate.state is TLBSATATE_OK)
enter_lazy_tlb
I am not sure the above race whether exist or not. Do you point out the
problem if it is not existence? please
Thanks
zhongjiang
>
> Also, the IPI handler on 3.4 looks like this:
>
> if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
> if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
> if (f->flush_va == TLB_FLUSH_ALL)
> local_flush_tlb();
> else
> __flush_tlb_one(f->flush_va);
> } else
> leave_mm(cpu);
> }
>
> but leave_mm() checks the same condition (cpu_tlbstate.state, not
> current->mm). How is the BUG triggering?
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majord...@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"d...@kvack.org";> em...@kvack.org </a>
>
>
