KVM: s390: cmma: Fix dirty tracking when removing memslot

When a memslot is removed, all ptes that mapped the slot are cleared or
even deallocated. If this happens while the system is in migration
mode, and if cmma-dirty pages are removed, the cmma-dirty counter will
not reflect reality.

Fix by appropriately decrementing the cmma-dirty counter when removing
a memslot.

Opportunistically improve kvm_arch_commit_memory_region() to use
__free() for the struct kvm_s390_mmu_cache.

Fixes: e38c884df921 ("KVM: s390: Switch to new gmap")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20260803124040.126471-9-imbrenda@linux.ibm.com>

2 files changed, 29 insertions, 3 deletions

diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index 171b61959908..3f2d6e8902d7 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -850,6 +850,7 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal
 	struct slot_priv *p = walk->priv;
 	union crste dummy = { .val = p->token };
 	union pte new_pte, pte = READ_ONCE(*ptep);
+	union pgste pgste;
 
 	new_pte = _PTE_TOK(dummy.tok.type, dummy.tok.par);
 
@@ -857,7 +858,11 @@ static long _dat_slot_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_wal
 	if (pte.val == new_pte.val)
 		return 0;
 
-	dat_ptep_xchg(ptep, new_pte, gfn, walk->asce, false);
+	pgste = pgste_get_lock(ptep);
+	pgste = __dat_ptep_xchg(ptep, pgste, new_pte, gfn, walk->asce, false);
+	pgste.cmma_d = 0;
+	pgste_set_unlock(ptep, pgste);
+
 	return 0;
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e5c5e9f61cb2..ba811f0673d1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -5812,14 +5812,30 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+static long cmma_d_count_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
+{
+	union pgste pgste;
+
+	pgste = pgste_get_lock(ptep);
+	if (pgste.cmma_d) {
+		pgste.cmma_d = 0;
+		atomic64_dec(walk->priv);
+	}
+	pgste_set_unlock(ptep, pgste);
+	return 0;
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	struct kvm_s390_mmu_cache *mc = NULL;
+	const struct dat_walk_ops ops = { .pte_entry = cmma_d_count_pte, };
+	struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL;
 	int rc = 0;
 
+	guard(mutex)(&kvm->slots_arch_lock);
+
 	if (change == KVM_MR_FLAGS_ONLY)
 		return;
 
@@ -5830,6 +5846,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	}
 
 	scoped_guard(write_lock, &kvm->mmu_lock) {
+		if (kvm->arch.migration_mode && kvm->arch.use_cmma && old) {
+			_dat_walk_gfn_range(old->base_gfn, old->base_gfn + old->npages,
+					    kvm->arch.gmap->asce, &ops, DAT_WALK_IGN_HOLES,
+					    &kvm->arch.cmma_dirty_pages);
+		}
+
 		switch (change) {
 		case KVM_MR_DELETE:
 			rc = dat_delete_slot(mc, kvm->arch.gmap->asce, old->base_gfn, old->npages);
@@ -5851,7 +5873,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 out:
 	if (rc)
 		pr_warn("failed to commit memory region\n");
-	kvm_s390_free_mmu_cache(mc);
 	return;
 }