diff mbox series

[GIT,PULL,v1,14/20] KVM: s390: stop using page->index for non-shadow gmaps

Message ID 20250130095113.166876-15-imbrenda@linux.ibm.com (mailing list archive)
State New
Headers show
Series [GIT,PULL,v1,01/20] KVM: s390: vsie: fix some corner-cases when grabbing vsie pages | expand

Commit Message

Claudio Imbrenda Jan. 30, 2025, 9:51 a.m. UTC 
The host_to_guest radix tree will now map userspace addresses to guest
addresses, instead of userspace addresses to segment tables.

When segment tables and page tables are needed, they are found using an
additional gmap_table_walk().

This gets rid of all usage of page->index for non-shadow gmaps.

Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Christoph Schlameuss <schlameuss@linux.ibm.com>
Link: https://lore.kernel.org/r/20250123144627.312456-11-imbrenda@linux.ibm.com
Signed-off-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
Message-ID: <20250123144627.312456-11-imbrenda@linux.ibm.com>
---
 arch/s390/mm/gmap.c | 105 +++++++++++++++++++++++---------------------
 1 file changed, 54 insertions(+), 51 deletions(-)
diff mbox series

Patch

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index ae71b401312b..1f83262a5a55 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -24,8 +24,20 @@ 
 #include <asm/page.h>
 #include <asm/tlb.h>
 
+/*
+ * The address is saved in a radix tree directly; NULL would be ambiguous,
+ * since 0 is a valid address, and NULL is returned when nothing was found.
+ * The lower bits are ignored by all users of the macro, so it can be used
+ * to distinguish a valid address 0 from a NULL.
+ */
+#define VALID_GADDR_FLAG 1
+#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG)
+#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG)
+
 #define GMAP_SHADOW_FAKE_TABLE 1ULL
 
+static inline unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
+
 static struct page *gmap_alloc_crst(void)
 {
 	struct page *page;
@@ -82,7 +94,6 @@  struct gmap *gmap_alloc(unsigned long limit)
 	page = gmap_alloc_crst();
 	if (!page)
 		goto out_free;
-	page->index = 0;
 	list_add(&page->lru, &gmap->crst_list);
 	table = page_to_virt(page);
 	crst_table_init(table, etype);
@@ -303,7 +314,6 @@  static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 		list_add(&page->lru, &gmap->crst_list);
 		*table = __pa(new) | _REGION_ENTRY_LENGTH |
 			(*table & _REGION_ENTRY_TYPE_MASK);
-		page->index = gaddr;
 		page = NULL;
 	}
 	spin_unlock(&gmap->guest_table_lock);
@@ -312,21 +322,23 @@  static int gmap_alloc_table(struct gmap *gmap, unsigned long *table,
 	return 0;
 }
 
-/**
- * __gmap_segment_gaddr - find virtual address from segment pointer
- * @entry: pointer to a segment table entry in the guest address space
- *
- * Returns the virtual address in the guest address space for the segment
- */
-static unsigned long __gmap_segment_gaddr(unsigned long *entry)
+static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr)
 {
-	struct page *page;
-	unsigned long offset;
+	return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
 
-	offset = (unsigned long) entry / sizeof(unsigned long);
-	offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE;
-	page = pmd_pgtable_page((pmd_t *) entry);
-	return page->index + offset;
+static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr)
+{
+	return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
+}
+
+static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr,
+				       unsigned long *gaddr)
+{
+	*gaddr = host_to_guest_delete(gmap, vmaddr);
+	if (IS_GADDR_VALID(*gaddr))
+		return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1);
+	return NULL;
 }
 
 /**
@@ -338,16 +350,19 @@  static unsigned long __gmap_segment_gaddr(unsigned long *entry)
  */
 static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr)
 {
-	unsigned long *entry;
+	unsigned long gaddr;
 	int flush = 0;
+	pmd_t *pmdp;
 
 	BUG_ON(gmap_is_shadow(gmap));
 	spin_lock(&gmap->guest_table_lock);
-	entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT);
-	if (entry) {
-		flush = (*entry != _SEGMENT_ENTRY_EMPTY);
-		*entry = _SEGMENT_ENTRY_EMPTY;
+
+	pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+	if (pmdp) {
+		flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY);
+		*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 	}
+
 	spin_unlock(&gmap->guest_table_lock);
 	return flush;
 }
@@ -564,7 +579,8 @@  int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	spin_lock(&gmap->guest_table_lock);
 	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
-				       vmaddr >> PMD_SHIFT, table);
+				       vmaddr >> PMD_SHIFT,
+				       (void *)MAKE_VALID_GADDR(gaddr));
 		if (!rc) {
 			if (pmd_leaf(*pmd)) {
 				*table = (pmd_val(*pmd) &
@@ -1995,7 +2011,6 @@  void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 		 pte_t *pte, unsigned long bits)
 {
 	unsigned long offset, gaddr = 0;
-	unsigned long *table;
 	struct gmap *gmap, *sg, *next;
 
 	offset = ((unsigned long) pte) & (255 * sizeof(pte_t));
@@ -2003,12 +2018,9 @@  void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		table = radix_tree_lookup(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (table)
-			gaddr = __gmap_segment_gaddr(table) + offset;
+		gaddr = host_to_guest_lookup(gmap, vmaddr) + offset;
 		spin_unlock(&gmap->guest_table_lock);
-		if (!table)
+		if (!IS_GADDR_VALID(gaddr))
 			continue;
 
 		if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) {
@@ -2068,10 +2080,8 @@  static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
-						  vmaddr >> PMD_SHIFT);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
 		if (pmdp) {
-			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
 			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
 						   _SEGMENT_ENTRY_GMAP_UC |
@@ -2115,28 +2125,25 @@  EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
  */
 void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *entry, gaddr;
+	unsigned long gaddr;
 	struct gmap *gmap;
 	pmd_t *pmdp;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		entry = radix_tree_delete(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (entry) {
-			pmdp = (pmd_t *)entry;
-			gaddr = __gmap_segment_gaddr(entry);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+		if (pmdp) {
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
-					   _SEGMENT_ENTRY_GMAP_UC |
-					   _SEGMENT_ENTRY));
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC |
+						   _SEGMENT_ENTRY));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_LOCAL);
 			else if (MACHINE_HAS_IDTE)
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
-			*entry = _SEGMENT_ENTRY_EMPTY;
+			*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		}
 		spin_unlock(&gmap->guest_table_lock);
 	}
@@ -2151,22 +2158,19 @@  EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
  */
 void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 {
-	unsigned long *entry, gaddr;
+	unsigned long gaddr;
 	struct gmap *gmap;
 	pmd_t *pmdp;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
 		spin_lock(&gmap->guest_table_lock);
-		entry = radix_tree_delete(&gmap->host_to_guest,
-					  vmaddr >> PMD_SHIFT);
-		if (entry) {
-			pmdp = (pmd_t *)entry;
-			gaddr = __gmap_segment_gaddr(entry);
+		pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr);
+		if (pmdp) {
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
-					   _SEGMENT_ENTRY_GMAP_UC |
-					   _SEGMENT_ENTRY));
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC |
+						   _SEGMENT_ENTRY));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_GLOBAL);
@@ -2174,7 +2178,7 @@  void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
 			else
 				__pmdp_csp(pmdp);
-			*entry = _SEGMENT_ENTRY_EMPTY;
+			*pmdp = __pmd(_SEGMENT_ENTRY_EMPTY);
 		}
 		spin_unlock(&gmap->guest_table_lock);
 	}
@@ -2690,7 +2694,6 @@  int s390_replace_asce(struct gmap *gmap)
 	page = gmap_alloc_crst();
 	if (!page)
 		return -ENOMEM;
-	page->index = 0;
 	table = page_to_virt(page);
 	memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT));