[PATCH v2 11/20] KVM: s390: KVM page table management functions: storage keys

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

Add page table management functions to be used for KVM guest (gmap)
page tables.

This patch adds functions related to storage key handling.

Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 arch/s390/kvm/dat.c | 212 ++++++++++++++++++++++++++++++++++++++++++++
 arch/s390/kvm/dat.h |   6 ++
 2 files changed, 218 insertions(+)

diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c
index fe93e1c07158..f626e8c37770 100644
--- a/arch/s390/kvm/dat.c
+++ b/arch/s390/kvm/dat.c
@@ -560,3 +560,215 @@ long _dat_walk_gfn_range(gfn_t start, gfn_t end, union asce asce,
 
 	return dat_crste_walk_range(start, min(end, asce_end(asce)), table, &walk);
 }
+
+int dat_get_storage_key(union asce asce, gfn_t gfn, union skey *skey)
+{
+	union crste *crstep;
+	union pgste pgste;
+	union pte *ptep;
+	int rc;
+
+	skey->skey = 0;
+	rc = dat_entry_walk(gfn, asce, DAT_WALK_ANY, LEVEL_PTE, &crstep, &ptep);
+	if (rc)
+		return rc;
+
+	if (!ptep) {
+		union crste crste;
+
+		crste = READ_ONCE(*crstep);
+		if (!crste.h.fc || !crste.s.fc1.pr)
+			return 0;
+		skey->skey = page_get_storage_key(large_crste_to_phys(crste, gfn));
+		return 0;
+	}
+	pgste = pgste_get_lock(ptep);
+	if (ptep->h.i) {
+		skey->acc = pgste.acc;
+		skey->fp = pgste.fp;
+	} else {
+		skey->skey = page_get_storage_key(pte_origin(*ptep));
+	}
+	skey->r |= pgste.gr;
+	skey->c |= pgste.gc;
+	pgste_set_unlock(ptep, pgste);
+	return 0;
+}
+
+static void dat_update_ptep_sd(union pgste old, union pgste pgste, union pte *ptep)
+{
+	if (pgste.acc != old.acc || pgste.fp != old.fp || pgste.gr != old.gr || pgste.gc != old.gc)
+		__atomic64_or(_PAGE_SD, &ptep->val);
+}
+
+int dat_set_storage_key(union asce asce, gfn_t gfn, union skey skey, bool nq)
+{
+	union pgste pgste, old;
+	union crste *crstep;
+	union pte *ptep;
+	int rc;
+
+	rc = dat_entry_walk(gfn, asce, DAT_WALK_LEAF_ALLOC, LEVEL_PTE, &crstep, &ptep);
+	if (rc)
+		return rc;
+
+	if (!ptep) {
+		page_set_storage_key(large_crste_to_phys(*crstep, gfn), skey.skey, !nq);
+		return 0;
+	}
+
+	old = pgste_get_lock(ptep);
+	pgste = old;
+
+	pgste.acc = skey.acc;
+	pgste.fp = skey.fp;
+	pgste.gc = skey.c;
+	pgste.gr = skey.r;
+
+	if (!ptep->h.i) {
+		union skey old_skey;
+
+		old_skey.skey = page_get_storage_key(pte_origin(*ptep));
+		pgste.hc |= old_skey.c;
+		pgste.hr |= old_skey.r;
+		skey.r = 0;
+		skey.c = 0;
+		page_set_storage_key(pte_origin(*ptep), skey.skey, !nq);
+	}
+
+	dat_update_ptep_sd(old, pgste, ptep);
+	pgste_set_unlock(ptep, pgste);
+	return 0;
+}
+
+static bool page_cond_set_storage_key(phys_addr_t paddr, union skey skey, union skey *oldkey,
+				      bool nq, bool mr, bool mc)
+{
+	oldkey->skey = page_get_storage_key(paddr);
+	if (oldkey->acc == skey.acc && oldkey->fp == skey.fp &&
+	    (oldkey->r == skey.r || mr) && (oldkey->c == skey.c || mc))
+		return false;
+	page_set_storage_key(paddr, skey.skey, !nq);
+	return true;
+}
+
+int dat_cond_set_storage_key(union asce asce, gfn_t gfn, union skey skey, union skey *oldkey,
+			     bool nq, bool mr, bool mc)
+{
+	union pgste pgste, old;
+	union crste *crstep;
+	union pte *ptep;
+	int rc;
+
+	rc = dat_entry_walk(gfn, asce, DAT_WALK_LEAF_ALLOC, LEVEL_PTE, &crstep, &ptep);
+	if (rc)
+		return rc;
+
+	if (!ptep)
+		return page_cond_set_storage_key(large_crste_to_phys(*crstep, gfn), skey, oldkey,
+						 nq, mr, mc);
+
+	old = pgste_get_lock(ptep);
+	pgste = old;
+
+	rc = 1;
+	pgste.acc = skey.acc;
+	pgste.fp = skey.fp;
+	pgste.gc = skey.c;
+	pgste.gr = skey.r;
+
+	if (!ptep->h.i) {
+		union skey prev;
+
+		rc = page_cond_set_storage_key(pte_origin(*ptep), skey, &prev, nq, mr, mc);
+		pgste.hc |= prev.c;
+		pgste.hr |= prev.r;
+		if (oldkey)
+			*oldkey = prev;
+	}
+
+	dat_update_ptep_sd(old, pgste, ptep);
+	pgste_set_unlock(ptep, pgste);
+	return rc;
+}
+
+int dat_reset_reference_bit(union asce asce, gfn_t gfn)
+{
+	union pgste pgste, old;
+	union crste *crstep;
+	union pte *ptep;
+	int rc;
+
+	rc = dat_entry_walk(gfn, asce, DAT_WALK_ANY, LEVEL_PTE, &crstep, &ptep);
+	if (rc)
+		return rc;
+
+	if (!ptep) {
+		union crste crste = READ_ONCE(*crstep);
+
+		if (!crste.h.fc || !crste.s.fc1.pr)
+			return 0;
+		return page_reset_referenced(large_crste_to_phys(*crstep, gfn));
+	}
+	old = pgste_get_lock(ptep);
+	pgste = old;
+
+	if (!ptep->h.i) {
+		rc = page_reset_referenced(pte_origin(*ptep));
+		pgste.hr = rc >> 1;
+	}
+	rc |= (pgste.gr << 1) | pgste.gc;
+	pgste.gr = 0;
+
+	dat_update_ptep_sd(old, pgste, ptep);
+	pgste_set_unlock(ptep, pgste);
+	return rc;
+}
+
+static long dat_reset_skeys_pte(union pte *ptep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
+{
+	union pgste pgste;
+
+	pgste = pgste_get_lock(ptep);
+	pgste.acc = 0;
+	pgste.fp = 0;
+	pgste.gr = 0;
+	pgste.gc = 0;
+	if (ptep->s.pr)
+		page_set_storage_key(pte_origin(*ptep), PAGE_DEFAULT_KEY, 1);
+	pgste_set_unlock(ptep, pgste);
+
+	if (need_resched())
+		return next;
+	return 0;
+}
+
+static long dat_reset_skeys_crste(union crste *crstep, gfn_t gfn, gfn_t next, struct dat_walk *walk)
+{
+	phys_addr_t addr, end, origin = crste_origin_large(*crstep);
+
+	if (!crstep->h.fc || !crstep->s.fc1.pr)
+		return 0;
+
+	addr = ((max(gfn, walk->start) - gfn) << PAGE_SHIFT) + origin;
+	end = ((min(next, walk->end) - gfn) << PAGE_SHIFT) + origin;
+	while (ALIGN(addr + 1, _SEGMENT_SIZE) <= end)
+		addr = sske_frame(addr, PAGE_DEFAULT_KEY);
+	for ( ; addr < end; addr += PAGE_SIZE)
+		page_set_storage_key(addr, PAGE_DEFAULT_KEY, 1);
+
+	if (need_resched())
+		return next;
+	return 0;
+}
+
+long dat_reset_skeys(union asce asce, gfn_t start)
+{
+	const struct dat_walk_ops ops = {
+		.pte_entry = dat_reset_skeys_pte,
+		.pmd_entry = dat_reset_skeys_crste,
+		.pud_entry = dat_reset_skeys_crste,
+	};
+
+	return _dat_walk_gfn_range(start, asce_end(asce), asce, &ops, DAT_WALK_IGN_HOLES, NULL);
+}
diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h
index de4bd2298945..40f5c1371ef3 100644
--- a/arch/s390/kvm/dat.h
+++ b/arch/s390/kvm/dat.h
@@ -427,6 +427,12 @@ int dat_entry_walk(gfn_t gfn, union asce asce, int flags, int walk_level,
 void dat_free_level(struct crst_table *table, bool owns_ptes);
 struct page_table *dat_alloc_pt(unsigned long pte_bits, unsigned long pgste_bits);
 struct crst_table *dat_alloc_crst(unsigned long init);
+int dat_get_storage_key(union asce asce, gfn_t gfn, union skey *skey);
+int dat_set_storage_key(union asce asce, gfn_t gfn, union skey skey, bool nq);
+int dat_cond_set_storage_key(union asce asce, gfn_t gfn, union skey skey, union skey *oldkey,
+			     bool nq, bool mr, bool mc);
+int dat_reset_reference_bit(union asce asce, gfn_t gfn);
+long dat_reset_skeys(union asce asce, gfn_t start);
 
 static inline struct crst_table *crste_table_start(union crste *crstep)
 {
-- 
2.51.0