[PATCH 04/12] KVM: arm64: Support clear DBM bit for PTEs

[Keqian Zhu]

This supports clear DBM bit for PTEs, to realize dynamic enable
of hardware DBM.

Signed-off-by: Keqian Zhu <zhukeqian1@xxxxxxxxxx>
---
 arch/arm64/include/asm/kvm_host.h |   2 +
 arch/arm64/kvm/mmu.c              | 151 ++++++++++++++++++++++++++++++
 2 files changed, 153 insertions(+)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index c3e6fcc664b1..9ea2dcfd609c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -480,6 +480,8 @@ u64 __kvm_call_hyp(void *hypfn, ...);
 
 void force_vm_exit(const cpumask_t *mask);
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
+void kvm_mmu_clear_dbm(struct kvm *kvm, struct kvm_memory_slot *memslot);
+void kvm_mmu_clear_dbm_all(struct kvm *kvm);
 
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 27407153121b..f08b0fbca0a0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -2446,6 +2446,157 @@ int kvm_mmu_init(void)
 	return err;
 }
 
+#ifdef CONFIG_ARM64_HW_AFDBM
+/**
+ * stage2_clear_dbm_ptes() - clear DBM bit from PMD range
+ * @pmd:	pointer to pmd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_clear_dbm_ptes(pmd_t *pmd, phys_addr_t addr,
+				  phys_addr_t end)
+{
+	pte_t *pte;
+
+	pte = pte_offset_kernel(pmd, addr);
+	do {
+		if (!pte_none(*pte) && kvm_s2pte_dbm(pte))
+			kvm_clear_s2pte_dbm(pte);
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+}
+
+/**
+ * stage2_clear_dbm_pmds() - clear DBM bit from PUD range
+ * @kvm:	The KVM pointer
+ * @pud:	pointer to pud entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_clear_dbm_pmds(struct kvm *kvm, pud_t *pud,
+				  phys_addr_t addr, phys_addr_t end)
+{
+	pmd_t *pmd;
+	phys_addr_t next;
+
+	pmd = stage2_pmd_offset(kvm, pud, addr);
+	do {
+		next = stage2_pmd_addr_end(kvm, addr, end);
+		if (!pmd_none(*pmd) && !pmd_thp_or_huge(*pmd))
+			stage2_clear_dbm_ptes(pmd, addr, next);
+	} while (pmd++, addr = next, addr != end);
+}
+
+/**
+ * stage2_clear_dbm_puds() - clear DBM bit from P4D range
+ * @kvm:	The KVM pointer
+ * @pgd:	pointer to pgd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_clear_dbm_puds(struct kvm *kvm, p4d_t *p4d,
+				  phys_addr_t addr, phys_addr_t end)
+{
+	pud_t *pud;
+	phys_addr_t next;
+
+	pud = stage2_pud_offset(kvm, p4d, addr);
+	do {
+		next = stage2_pud_addr_end(kvm, addr, end);
+		if (!stage2_pud_none(kvm, *pud) && !stage2_pud_huge(kvm, *pud))
+			stage2_clear_dbm_pmds(kvm, pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+}
+
+/**
+ * stage2_clear_dbm_p4ds() - clear DBM bit from PGD range
+ * @kvm:	The KVM pointer
+ * @pgd:	pointer to pgd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
+static void stage2_clear_dbm_p4ds(struct kvm *kvm, pgd_t *pgd,
+				  phys_addr_t addr, phys_addr_t end)
+{
+	p4d_t *p4d;
+	phys_addr_t next;
+
+	p4d = stage2_p4d_offset(kvm, pgd, addr);
+	do {
+		next = stage2_p4d_addr_end(kvm, addr, end);
+		if (!stage2_p4d_none(kvm, *p4d))
+			stage2_clear_dbm_puds(kvm, p4d, addr, next);
+	} while (p4d++, addr = next, addr != end);
+}
+
+/**
+ * stage2_clear_dbm_range() - clear DBM bit from stage2 memory
+ * region range
+ * @kvm:	The KVM pointer
+ * @addr:	Start address of range
+ * @end:	End address of range
+ */
+static void stage2_clear_dbm_range(struct kvm *kvm, phys_addr_t addr,
+				   phys_addr_t end)
+{
+	pgd_t *pgd;
+	phys_addr_t next;
+
+	pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr);
+	do {
+		cond_resched_lock(&kvm->mmu_lock);
+		if (!READ_ONCE(kvm->arch.pgd))
+			break;
+		next = stage2_pgd_addr_end(kvm, addr, end);
+		if (stage2_pgd_present(kvm, *pgd))
+			stage2_clear_dbm_p4ds(kvm, pgd, addr, next);
+	} while (pgd++, addr = next, addr != end);
+}
+
+/**
+ * kvm_mmu_clear_dbm() - clear DBM bit from stage2 PTEs for memory slot
+ * @kvm:	The KVM pointer
+ * @slot:	The memory slot to clear DBM bit
+ *
+ * After this function returns, DBM bit of all block or page descriptors
+ * is cleared.
+ *
+ * Acquires kvm_mmu_lock. Called with kvm->slots_lock mutex acquired,
+ * serializing operations for VM memory regions.
+ */
+void kvm_mmu_clear_dbm(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	phys_addr_t start = memslot->base_gfn << PAGE_SHIFT;
+	phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT;
+
+	spin_lock(&kvm->mmu_lock);
+	stage2_clear_dbm_range(kvm, start, end);
+	spin_unlock(&kvm->mmu_lock);
+	kvm_flush_remote_tlbs(kvm);
+}
+
+/**
+ * kvm_mmu_clear_dbm_all() - clear DBM bit from stage2 PTEs for whole VM
+ * @kvm:	The KVM pointer
+ *
+ * Called with kvm->slots_lock mutex acquired.
+ */
+void kvm_mmu_clear_dbm_all(struct kvm *kvm)
+{
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *memslots = slots->memslots;
+	struct kvm_memory_slot *memslot;
+	int slot;
+
+	if (unlikely(!slots->used_slots))
+		return;
+
+	for (slot = 0; slot < slots->used_slots; slot++) {
+		memslot = &memslots[slot];
+		kvm_mmu_clear_dbm(kvm, memslot);
+	}
+}
+#endif /* CONFIG_ARM64_HW_AFDBM */
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_userspace_memory_region *mem,
 				   struct kvm_memory_slot *old,
-- 
2.19.1