KVM: arm64: Reschedule as needed when destroying the stage-2 page-tables

When a large VM, specifically one that holds a significant number of PTEs,
gets abruptly destroyed, the following warning is seen during the
page-table walk:

 sched: CPU 0 need_resched set for > 100018840 ns (100 ticks) without schedule
 CPU: 0 UID: 0 PID: 9617 Comm: kvm_page_table_ Tainted: G O 6.16.0-smp-DEV #3 NONE
 Tainted: [O]=OOT_MODULE
 Call trace:
  show_stack+0x20/0x38 (C)
  dump_stack_lvl+0x3c/0xb8
  dump_stack+0x18/0x30
  resched_latency_warn+0x7c/0x88
  sched_tick+0x1c4/0x268
  update_process_times+0xa8/0xd8
  tick_nohz_handler+0xc8/0x168
  __hrtimer_run_queues+0x11c/0x338
  hrtimer_interrupt+0x104/0x308
  arch_timer_handler_phys+0x40/0x58
  handle_percpu_devid_irq+0x8c/0x1b0
  generic_handle_domain_irq+0x48/0x78
  gic_handle_irq+0x1b8/0x408
  call_on_irq_stack+0x24/0x30
  do_interrupt_handler+0x54/0x78
  el1_interrupt+0x44/0x88
  el1h_64_irq_handler+0x18/0x28
  el1h_64_irq+0x84/0x88
  stage2_free_walker+0x30/0xa0 (P)
  __kvm_pgtable_walk+0x11c/0x258
  __kvm_pgtable_walk+0x180/0x258
  __kvm_pgtable_walk+0x180/0x258
  __kvm_pgtable_walk+0x180/0x258
  kvm_pgtable_walk+0xc4/0x140
  kvm_pgtable_stage2_destroy+0x5c/0xf0
  kvm_free_stage2_pgd+0x6c/0xe8
  kvm_uninit_stage2_mmu+0x24/0x48
  kvm_arch_flush_shadow_all+0x80/0xa0
  kvm_mmu_notifier_release+0x38/0x78
  __mmu_notifier_release+0x15c/0x250
  exit_mmap+0x68/0x400
  __mmput+0x38/0x1c8
  mmput+0x30/0x68
  exit_mm+0xd4/0x198
  do_exit+0x1a4/0xb00
  do_group_exit+0x8c/0x120
  get_signal+0x6d4/0x778
  do_signal+0x90/0x718
  do_notify_resume+0x70/0x170
  el0_svc+0x74/0xd8
  el0t_64_sync_handler+0x60/0xc8
  el0t_64_sync+0x1b0/0x1b8

The warning is seen majorly on the host kernels that are configured
not to force-preempt, such as CONFIG_PREEMPT_NONE=y. To avoid this,
instead of walking the entire page-table in one go, split it into
smaller ranges, by checking for cond_resched() between each range.
Since the path is executed during VM destruction, after the
page-table structure is unlinked from the KVM MMU, relying on
cond_resched_rwlock_write() isn't necessary.

Signed-off-by: Raghavendra Rao Ananta <rananta@google.com>
Suggested-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250820162242.2624752-3-rananta@google.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>

diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 6330a02c8418667aa9fcb8fd78df0e52311da7d9..86f3d80daf37aff30e41ee0f244b0499acae3d2d 100644 (file)
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -904,11 +904,35 @@ static int kvm_init_ipa_range(struct kvm_s2_mmu *mmu, unsigned long type)
        return 0;
 }
 
+/*
+ * Assume that @pgt is valid and unlinked from the KVM MMU to free the
+ * page-table without taking the kvm_mmu_lock and without performing any
+ * TLB invalidations.
+ *
+ * Also, the range of addresses can be large enough to cause need_resched
+ * warnings, for instance on CONFIG_PREEMPT_NONE kernels. Hence, invoke
+ * cond_resched() periodically to prevent hogging the CPU for a long time
+ * and schedule something else, if required.
+ */
+static void stage2_destroy_range(struct kvm_pgtable *pgt, phys_addr_t addr,
+                                  phys_addr_t end)
+{
+       u64 next;
+
+       do {
+               next = stage2_range_addr_end(addr, end);
+               KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, addr,
+                                                               next - addr);
+               if (next != end)
+                       cond_resched();
+       } while (addr = next, addr != end);
+}
+
 static void kvm_stage2_destroy(struct kvm_pgtable *pgt)
 {
        unsigned int ia_bits = VTCR_EL2_IPA(pgt->mmu->vtcr);
 
-       KVM_PGT_FN(kvm_pgtable_stage2_destroy_range)(pgt, 0, BIT(ia_bits));
+       stage2_destroy_range(pgt, 0, BIT(ia_bits));
        KVM_PGT_FN(kvm_pgtable_stage2_destroy_pgd)(pgt);
 }