KVM: Fix an issue in non-preemptible kernel.

Add a cond_resched() to give the scheduler a chance to run madvise task to avoid endless loop here in non-preemptible kernel.

Otherwise, the kvm_mmu_notifier would have no chance to be descreased to 0 by madvise task -> syscall -> zap_page_range -> mmu_notifier_invalidate_range_end -> __mmu_notifier_invalidate_range_end -> invalidate_range_end -> kvm_mmu_notifier_invalidate_range_end, as the madvise task would be scheduled when running unmap_single_vma -> unmap_page_range -> zap_p4d_range -> zap_pud_range -> zap_pmd_range -> cond_resched which is called before mmu_notifier_invalidate_range_end in zap_page_range.

---
 arch/mips/kvm/mmu.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

index 97e538a8c1be..e52e63d225f4 100644
@@ -746,6 +746,22 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
 		 */
 		spin_unlock(&kvm->mmu_lock);
 		kvm_release_pfn_clean(pfn);
+		/*
+		 * Add a cond_resched() to give the scheduler a chance to run
+		 * madvise task to avoid endless loop here in non-preemptible
+		 * kernel.
+		 * Otherwise, the kvm_mmu_notifier would have no chance to be
+		 * descreased to 0 by madvise task -> syscall -> zap_page_range
+		 * -> mmu_notifier_invalidate_range_end ->
+		 * __mmu_notifier_invalidate_range_end -> invalidate_range_end
+		 * -> kvm_mmu_notifier_invalidate_range_end, as the madvise task
+		 * would be scheduled when running unmap_single_vma ->
+		 * unmap_page_range -> zap_p4d_range -> zap_pud_range ->
+		 * zap_pmd_range -> cond_resched which is called before
+		 * mmu_notifier_invalidate_range_end in zap_page_range.
+		 */
+		if (need_resched())
+			cond_resched();
 		goto retry;
 	}
 

2.17.1

Hi Gary,

Thanks for the patch!

s/descreased/decreased/
(and in the comment too)

I'm not entirely sure I follow - could you clarify whether the task invoking the madvise syscall is related to the task using KVM?

Hi Paul,

Thanks for your review.
Please see my comments below.

-----Original Message-----
From: Paul Burton <[email protected]>
Sent: Wednesday, September 4, 2019 10:03 PM
To: Gary Fu <[email protected]>
Cc: [email protected]; Paul Burton <[email protected]>; Archer Yan <[email protected]>; James Hogan <[email protected]>
Subject: Re: [PATCH] KVM: Fix an issue in non-preemptible kernel.

Hi Gary,

Thanks for the patch!

s/descreased/decreased/
(and in the comment too)

Thank you for your comments. I'll fix these typo errors.

I'm not entirely sure I follow - could you clarify whether the task invoking the madvise syscall is related to the task using KVM?

Yes, the QEMU application invokes the madvise syscall with behavior param MADV_DONTNEED.
When handling GPA faults by creating a new GPA mapping in kvm_mips_map_page, it will be retrying to get available page. In the low memory case, it is waiting for the memory resources freed by madvise syscall with MADV_DONTNEED (QEMU application -> madvise with MADV_DONTNEED -> syscall -> madvise_vma -> madvise_dontneed_free -> madvise_dontneed_single_vma -> zap_page_range). In zap_page_range, after the TLB of given address range is cleared by unmap_single_vma, it will call __mmu_notifier_invalidate_range_end which finally calls kvm_mmu_notifier_invalidate_range_end to decrease mmu_notifier_count to 0. The retrying loop in kvm_mips_map_page checks the mmu_notifier_count and if the value is 0 which indicates that some new page is available for mapping, it will jump out the retrying loop and set up PTE for a new GPA mapping. During the TLB clearing ( in unmap_single_vma in madvise syscall) mentioned above, it will call cond_resched() per PMD for avoiding occupying CPU for a long time (in case of huge page range zapping). When this happened in the non-preemptible kernel, the retrying loop in kvm_mips_map_page will be running endlessly as there is no chance to reschedule back to madvise syscall to run __mmu_notifier_invalidate_range_end to decrease mmu_notifier_count so that the value of mmu_notifier_count is always 1.
Adding a scheduling point before every retry in kvm_mips_map_page will give the madvise syscall (invoked by QEMU) a chance to be re-scheduled back to zap all the given pages and clear mmu_notifier_count value to let kvm_mips_map_page task jump out the loop.