Merge: KVM: Fix two memory management related problems on s390x

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1128

JIRA: https://issues.redhat.com/browse/RHEL-92226

JIRA: https://issues.redhat.com/browse/RHEL-58218

Fix a call trace that can happen with the debug kernel on s390x when starting a nested guest, and fix a problem that occurs when backing the memory of a KVM guest with real files.

Note: I've included some selftest patches at the beginning of the series to be able to cherry-pick the other patches cleanly. These selftest patches at the beginning of the patch series show up as having conflicts in "revumatic", but that's only due to a rename of a subfolder from "s390x" to "s390", the changes themselves are clean.

Resolves: RHEL-92226

Resolves: RHEL-58218

Signed-off-by: Thomas Huth <thuth@redhat.com>

Approved-by: Rafael Aquini <raquini@redhat.com>
Approved-by: Cornelia Huck <cohuck@redhat.com>

Merged-by: Julio Faracco <jfaracco@redhat.com>

Author: jcfaracco

Documentation/virt/kvm/api.rst

@@ -1423,7 +1423,7 @@ fetch) is injected in the guest.
 S390:
 ^^^^^
 
-Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
+Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set.
 Returns -EINVAL if called on a protected VM.
 
 4.36 KVM_SET_TSS_ADDR

arch/s390/include/asm/gmap.h

@@ -23,7 +23,6 @@
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
- * @crst_list: list of all crst tables used in the guest address space
  * @mm: pointer to the parent mm_struct
  * @guest_to_host: radix tree with guest to host address translation
  * @host_to_guest: radix tree with pointer to segment table entries
@@ -35,7 +34,6 @@
  * @guest_handle: protected virtual machine handle for the ultravisor
  * @host_to_rmap: radix tree with gmap_rmap lists
  * @children: list of shadow gmap structures
- * @pt_list: list of all page tables used in the shadow guest address space
  * @shadow_lock: spinlock to protect the shadow gmap list
  * @parent: pointer to the parent gmap for shadow guest address spaces
  * @orig_asce: ASCE for which the shadow page table has been created
@@ -45,7 +43,6 @@
  */
 struct gmap {
 	struct list_head list;
-	struct list_head crst_list;
 	struct mm_struct *mm;
 	struct radix_tree_root guest_to_host;
 	struct radix_tree_root host_to_guest;
@@ -61,7 +58,6 @@ struct gmap {
 	/* Additional data for shadow guest address spaces */
 	struct radix_tree_root host_to_rmap;
 	struct list_head children;
-	struct list_head pt_list;
 	spinlock_t shadow_lock;
 	struct gmap *parent;
 	unsigned long orig_asce;
@@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit);
 void gmap_remove(struct gmap *gmap);
 struct gmap *gmap_get(struct gmap *gmap);
 void gmap_put(struct gmap *gmap);
+void gmap_free(struct gmap *gmap);
+struct gmap *gmap_alloc(unsigned long limit);
 
 int gmap_map_segment(struct gmap *gmap, unsigned long from,
 		     unsigned long to, unsigned long len);
 int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
 unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
-unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
 int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
-int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
 void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
 void __gmap_zap(struct gmap *, unsigned long gaddr);
 void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
 
 int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val);
 
-struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
-			 int edat_level);
-int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
+void gmap_unshadow(struct gmap *sg);
 int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
 		    int fake);
 int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
@@ -131,24 +125,21 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
 		    int fake);
 int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
 		    int fake);
-int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
-			   unsigned long *pgt, int *dat_protection, int *fake);
 int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
 
 void gmap_register_pte_notifier(struct gmap_notifier *);
 void gmap_unregister_pte_notifier(struct gmap_notifier *);
 
-int gmap_mprotect_notify(struct gmap *, unsigned long start,
-			 unsigned long len, int prot);
+int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits);
 
 void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
 			     unsigned long gaddr, unsigned long vmaddr);
 int s390_disable_cow_sharing(void);
-void s390_unlist_old_asce(struct gmap *gmap);
 int s390_replace_asce(struct gmap *gmap);
 void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
 int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
 			    unsigned long end, bool interruptible);
+unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
 
 /**
  * s390_uv_destroy_range - Destroy a range of pages in the given mm.

arch/s390/include/asm/kvm_host.h

@@ -30,6 +30,8 @@
 #define KVM_S390_ESCA_CPU_SLOTS 248
 #define KVM_MAX_VCPUS 255
 
+#define KVM_INTERNAL_MEM_SLOTS 1
+
 /*
  * These seem to be used for allocating ->chip in the routing table, which we
  * don't use. 1 is as small as we can get to reduce the needed memory. If we

arch/s390/include/asm/pgtable.h

@@ -419,9 +419,10 @@ static inline int is_module_addr(void *addr)
 #define PGSTE_HC_BIT	0x0020000000000000UL
 #define PGSTE_GR_BIT	0x0004000000000000UL
 #define PGSTE_GC_BIT	0x0002000000000000UL
-#define PGSTE_UC_BIT	0x0000800000000000UL	/* user dirty (migration) */
-#define PGSTE_IN_BIT	0x0000400000000000UL	/* IPTE notify bit */
-#define PGSTE_VSIE_BIT	0x0000200000000000UL	/* ref'd in a shadow table */
+#define PGSTE_ST2_MASK	0x0000ffff00000000UL
+#define PGSTE_UC_BIT	0x0000000000008000UL	/* user dirty (migration) */
+#define PGSTE_IN_BIT	0x0000000000004000UL	/* IPTE notify bit */
+#define PGSTE_VSIE_BIT	0x0000000000002000UL	/* ref'd in a shadow table */
 
 /* Guest Page State used for virtualization */
 #define _PGSTE_GPS_ZERO			0x0000000080000000UL
@@ -2011,4 +2012,18 @@ extern void s390_reset_cmma(struct mm_struct *mm);
 #define pmd_pgtable(pmd) \
 	((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE))
 
+static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt)
+{
+	unsigned long *pgstes, res;
+
+	pgstes = pgt + _PAGE_ENTRIES;
+
+	res = (pgstes[0] & PGSTE_ST2_MASK) << 16;
+	res |= pgstes[1] & PGSTE_ST2_MASK;
+	res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16;
+	res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32;
+
+	return res;
+}
+
 #endif /* _S390_PAGE_H */

arch/s390/include/asm/uv.h

@@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void)
 }
 
 int uv_pin_shared(unsigned long paddr);
-int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
-int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
 int uv_destroy_folio(struct folio *folio);
 int uv_destroy_pte(pte_t pte);
 int uv_convert_from_secure_pte(pte_t pte);
-int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
+int make_hva_secure(struct mm_struct *mm, unsigned long hva, struct uv_cb_header *uvcb);
+int uv_convert_from_secure(unsigned long paddr);
+int uv_convert_from_secure_folio(struct folio *folio);
 
 void setup_uv(void);