[PATCH v5 4/7] KVM: s390: Improve unmapping of large ranges

[Claudio Imbrenda <imbrenda@linux.ibm.com>]

When unmapping guest ranges, each individual leaf DAT entry is
invalidated. When unmapping large ranges, this results in a very large
amount of invalidations, which is time consuming. Moreover, since the
unmap callback is called by KVM while holding a spinlock, this also
leads to stall warnings.

Improve the situation by invalidating DAT entries higher in the tree,
instead of each leaf individually.

For small invalidations (up to 1 segment = 1M of guest memory), and
special cases (like protected VMs) regardless of the size, the old and
slow invalidation is performed; all leaf entries are invalidated one by
one.

For large invalidations (larger than 1M of guest memory), the new
strategy is used:
 - Invalidate prefixes on the whole range, extending start and end to
   1M granularity
 - Iterate through the page table pointed to by each pmd and unshadow
   entries as needed
 - Detach (invalidate) the pmd
 - Save storage keys as needed
 - Invalidate each (now detached) pte by simply overwriting it
 - Reattach the old pmd to point to the updated page table

Fixes: a2c17f9270cc ("KVM: s390: New gmap code")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: stable@vger.kernel.org # 7.0+
---
 arch/s390/kvm/gmap/gmap.c | 136 +++++++++++++++++++++++++++++++++++---
 1 file changed, 125 insertions(+), 11 deletions(-)

diff --git a/arch/s390/kvm/gmap/gmap.c b/arch/s390/kvm/gmap/gmap.c
index 225fdae3d57c..b9d92bef5459 100644
--- a/arch/s390/kvm/gmap/gmap.c
+++ b/arch/s390/kvm/gmap/gmap.c
@@ -434,17 +434,8 @@ static long _gmap_unmap_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct
 	return 0;
 }
 
-/**
- * gmap_unmap_gfn_range() - Unmap a range of guest addresses.
- * @gmap: The gmap to act on.
- * @slot: The memslot in which the range is located.
- * @start: The first gfn to unmap.
- * @end: The gfn after the last one to unmap.
- *
- * Context: Called with the kvm mmu write lock held.
- * Return: false
- */
-bool gmap_unmap_gfn_range(struct gmap *gmap, struct kvm_memory_slot *slot, gfn_t start, gfn_t end)
+static bool gmap_unmap_gfn_range_slow(struct gmap *gmap, struct kvm_memory_slot *slot,
+				      gfn_t start, gfn_t end)
 {
 	const struct dat_walk_ops ops = {
 		.pte_entry = _gmap_unmap_pte,
@@ -462,6 +453,129 @@ bool gmap_unmap_gfn_range(struct gmap *gmap, struct kvm_memory_slot *slot, gfn_t
 	return false;
 }
 
+static long _gmap_unmap_pud_fast(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *w)
+{
+	union crste old = *crstep;
+
+	/* We only care about large puds */
+	if (!old.h.fc)
+		return 0;
+	/*
+	 * The caller did not unmap prefixes outside the original range, which
+	 * does not necessarily cover the whole pud.
+	 * Since all prefixes are below 2G, the first pud covers them all;
+	 * make sure all prefixes are unmapped whenever the first pud is being
+	 * unmapped.
+	 */
+	if (!gfn)
+		gmap_unmap_prefix(w->priv, 0, next);
+	if (old.s.fc1.vsie_notif)
+		gmap_handle_vsie_unshadow_event(w->priv, gfn);
+
+	if (machine_has_tlb_guest())
+		idte_crste(crstep, gfn, IDTE_GUEST_ASCE, w->asce, 0);
+	else
+		idte_crste(crstep, gfn, 0, w->asce, 0);
+	*crstep = _CRSTE_EMPTY(old.h.tt);
+
+	return 0;
+}
+
+static long _gmap_unmap_pmd_fast(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *w)
+{
+	union crste old = *crstep;
+	struct page_table *pt;
+	gfn_t first, last;
+	unsigned int i;
+
+	if (old.h.fc) {
+		if (old.s.fc1.vsie_notif)
+			gmap_handle_vsie_unshadow_event(w->priv, gfn);
+
+		if (machine_has_tlb_guest())
+			idte_crste(crstep, gfn, IDTE_GUEST_ASCE, w->asce, 0);
+		else
+			idte_crste(crstep, gfn, 0, w->asce, 0);
+		WRITE_ONCE(*crstep, _CRSTE_EMPTY(old.h.tt));
+
+		return 0;
+	}
+
+	if (old.h.i)
+		return 0;
+
+	pt = dereference_pmd(old.pmd);
+	first = max(gfn, w->start) & (PTRS_PER_PTE - 1);
+	last = (min(next, w->end) - 1) & (PTRS_PER_PTE - 1);
+
+	for (i = first; i <= last; i++)
+		if (pte_needs_unshadow(pt->ptes[i], _PTE_EMPTY, pt->pgstes[i]))
+			gmap_handle_vsie_unshadow_event(w->priv, gfn + i);
+
+	/* Detach the page table */
+	if (machine_has_tlb_guest())
+		idte_crste(crstep, gfn, IDTE_GUEST_ASCE, w->asce, 0);
+	else
+		idte_crste(crstep, gfn, 0, w->asce, 0);
+
+	for (i = first; i <= last; i++) {
+		if (pte_hole(pt->ptes[i]))
+			continue;
+		if (!pt->ptes[i].h.i && uses_skeys(w->priv))
+			pt->pgstes[i] = dat_save_storage_key_into_pgste(pt->ptes[i], pt->pgstes[i]);
+		pt->ptes[i] = _PTE_EMPTY;
+		pt->pgstes[i].vsie_notif = 0;
+		pt->pgstes[i].vsie_gmem = 0;
+		pt->pgstes[i].zero = 0;
+		pt->pgstes[i].prefix_notif = 0;
+	}
+
+	barrier();
+	/* Reattach the modified page table */
+	WRITE_ONCE(*crstep, old);
+
+	return 0;
+}
+
+static bool gmap_unmap_gfn_range_fast(struct gmap *gmap, gfn_t start, gfn_t end)
+{
+	const struct dat_walk_ops ops = {
+		.pud_entry = _gmap_unmap_pud_fast,
+		.pmd_entry = _gmap_unmap_pmd_fast,
+	};
+	gfn_t aligned_start = ALIGN_DOWN(start, _PAGE_ENTRIES);
+	gfn_t aligned_end = ALIGN(end, _PAGE_ENTRIES);
+	bool failed;
+
+	lockdep_assert_held_write(&gmap->kvm->mmu_lock);
+
+	/* Prefixes are below 2G; if the start is above 2G, nothing to do */
+	if (aligned_start < _PAGES_PER_REGION3)
+		gmap_unmap_prefix(gmap, aligned_start, aligned_end);
+
+	failed = _dat_walk_gfn_range(start, end, gmap->asce, &ops, DAT_WALK_IGN_HOLES, gmap);
+	KVM_BUG_ON(failed, gmap->kvm);
+	return false;
+}
+
+/**
+ * gmap_unmap_gfn_range() - Unmap a range of guest addresses.
+ * @gmap: The gmap to act on.
+ * @slot: The memslot in which the range is located.
+ * @start: The first gfn to unmap.
+ * @end: The gfn after the last one to unmap.
+ *
+ * Context: Called with the kvm mmu write lock held.
+ * Return: false
+ */
+bool gmap_unmap_gfn_range(struct gmap *gmap, struct kvm_memory_slot *slot, gfn_t start, gfn_t end)
+{
+	if ((end - start <= _PAGES_PER_SEGMENT) ||
+	    test_bit(GMAP_FLAG_EXPORT_ON_UNMAP, &gmap->flags) || is_ucontrol(gmap))
+		return gmap_unmap_gfn_range_slow(gmap, slot, start, end);
+	return gmap_unmap_gfn_range_fast(gmap, start, end);
+}
+
 static union pgste __pte_test_and_clear_softdirty(union pte *ptep, union pgste pgste, gfn_t gfn,
 						  struct gmap *gmap)
 {
-- 
2.56.0