[PATCH 2/2] KVM: arm64: Only reschedule if MMU_NOTIFIER_RANGE_BLOCKABLE is not set

[Will Deacon]

When an MMU notifier call results in unmapping a range that spans multiple
PGDs, we end up calling into cond_resched_lock() when crossing a PGD boundary,
since this avoids running into RCU stalls during VM teardown. Unfortunately,
if the VM is destroyed as a result of OOM, then blocking is not permitted
and the call to the scheduler triggers the following BUG():

 | BUG: sleeping function called from invalid context at arch/arm64/kvm/mmu.c:394
 | in_atomic(): 1, irqs_disabled(): 0, non_block: 1, pid: 36, name: oom_reaper
 | INFO: lockdep is turned off.
 | CPU: 3 PID: 36 Comm: oom_reaper Not tainted 5.8.0 #1
 | Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
 | Call trace:
 |  dump_backtrace+0x0/0x284
 |  show_stack+0x1c/0x28
 |  dump_stack+0xf0/0x1a4
 |  ___might_sleep+0x2bc/0x2cc
 |  unmap_stage2_range+0x160/0x1ac
 |  kvm_unmap_hva_range+0x1a0/0x1c8
 |  kvm_mmu_notifier_invalidate_range_start+0x8c/0xf8
 |  __mmu_notifier_invalidate_range_start+0x218/0x31c
 |  mmu_notifier_invalidate_range_start_nonblock+0x78/0xb0
 |  __oom_reap_task_mm+0x128/0x268
 |  oom_reap_task+0xac/0x298
 |  oom_reaper+0x178/0x17c
 |  kthread+0x1e4/0x1fc
 |  ret_from_fork+0x10/0x30

Use the new 'flags' argument to kvm_unmap_hva_range() to ensure that we
only reschedule if MMU_NOTIFIER_RANGE_BLOCKABLE is set in the notifier
flags.

Cc: <stable@xxxxxxxxxxxxxxx>
Fixes: 8b3405e345b5 ("kvm: arm/arm64: Fix locking for kvm_free_stage2_pgd")
Cc: Marc Zyngier <maz@xxxxxxxxxx>
Cc: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
Cc: James Morse <james.morse@xxxxxxx>
Signed-off-by: Will Deacon <will@xxxxxxxxxx>
---
 arch/arm64/kvm/mmu.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 5f6b35c33618..bd47f06739d6 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -365,7 +365,8 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd,
  * destroying the VM), otherwise another faulting VCPU may come in and mess
  * with things behind our backs.
  */
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void __unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size,
+				 bool may_block)
 {
 	pgd_t *pgd;
 	phys_addr_t addr = start, end = start + size;
@@ -390,11 +391,16 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 		 * If the range is too large, release the kvm->mmu_lock
 		 * to prevent starvation and lockup detector warnings.
 		 */
-		if (next != end)
+		if (may_block && next != end)
 			cond_resched_lock(&kvm->mmu_lock);
 	} while (pgd++, addr = next, addr != end);
 }
 
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+{
+	__unmap_stage2_range(kvm, start, size, true);
+}
+
 static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
 			      phys_addr_t addr, phys_addr_t end)
 {
@@ -2198,7 +2204,10 @@ static int handle_hva_to_gpa(struct kvm *kvm,
 
 static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
 {
-	unmap_stage2_range(kvm, gpa, size);
+	unsigned flags = *(unsigned *)data;
+	bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE;
+
+	__unmap_stage2_range(kvm, gpa, size, may_block);
 	return 0;
 }
 
@@ -2209,7 +2218,7 @@ int kvm_unmap_hva_range(struct kvm *kvm,
 		return 0;
 
 	trace_kvm_unmap_hva_range(start, end);
-	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+	handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags);
 	return 0;
 }
 
-- 
2.28.0.236.gb10cc79966-goog