Merge tag 'kvm-s390-next-7.0-1' of https://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

- gmap rewrite: completely new memory management for kvm/s390
- vSIE improvement
- maintainership change for s390 vfio-pci
- small quality of life improvement for protected guests

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -6518,6 +6518,40 @@ the capability to be present.
 
 `flags` must currently be zero.
 
+4.144 KVM_S390_KEYOP
+--------------------
+
+:Capability: KVM_CAP_S390_KEYOP
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_keyop (in/out)
+:Returns: 0 in case of success, < 0 on error
+
+The specified key operation is performed on the given guest address. The
+previous storage key (or the relevant part thereof) will be returned in
+`key`.
+
+::
+
+  struct kvm_s390_keyop {
+	__u64 guest_addr;
+	__u8  key;
+	__u8  operation;
+  };
+
+Currently supported values for ``operation``:
+
+KVM_S390_KEYOP_ISKE
+  Returns the storage key for the guest address ``guest_addr`` in ``key``.
+
+KVM_S390_KEYOP_RRBE
+  Resets the reference bit for the guest address ``guest_addr``, returning the
+  R and C bits of the old storage key in ``key``; the remaining fields of
+  the storage key will be set to 0.
+
+KVM_S390_KEYOP_SSKE
+  Sets the storage key for the guest address ``guest_addr`` to the key
+  specified in ``key``, returning the previous value in ``key``.
 
 .. _kvm_run:
 
@@ -9384,6 +9418,14 @@ The presence of this capability indicates that KVM_RUN will update the
 KVM_RUN_X86_GUEST_MODE bit in kvm_run.flags to indicate whether the
 vCPU was executing nested guest code when it exited.
 
+8.46 KVM_CAP_S390_KEYOP
+-----------------------
+
+:Architectures: s390
+
+The presence of this capability indicates that the KVM_S390_KEYOP ioctl is
+available.
+
 KVM exits with the register state of either the L1 or L2 guest
 depending on which executed at the time of an exit. Userspace must
 take care to differentiate between these cases.

MAINTAINERS

@@ -13914,14 +13914,12 @@ L:	kvm@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
 F:	Documentation/virt/kvm/s390*
-F:	arch/s390/include/asm/gmap.h
 F:	arch/s390/include/asm/gmap_helpers.h
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/include/uapi/asm/kvm*
 F:	arch/s390/include/uapi/asm/uvdevice.h
 F:	arch/s390/kernel/uv.c
 F:	arch/s390/kvm/
-F:	arch/s390/mm/gmap.c
 F:	arch/s390/mm/gmap_helpers.c
 F:	drivers/s390/char/uvdevice.c
 F:	tools/testing/selftests/drivers/s390x/uvdevice/
@@ -23111,7 +23109,8 @@ F:	include/uapi/linux/vfio_ccw.h
 
 S390 VFIO-PCI DRIVER
 M:	Matthew Rosato <mjrosato@linux.ibm.com>
-M:	Eric Farman <farman@linux.ibm.com>
+M:	Farhan Ali <alifm@linux.ibm.com>
+R:	Eric Farman <farman@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
 S:	Supported

arch/s390/Kconfig

@@ -32,9 +32,6 @@ config GENERIC_BUG_RELATIVE_POINTERS
 config GENERIC_LOCKBREAK
 	def_bool y if PREEMPTION
 
-config PGSTE
-	def_bool y if KVM
-
 config AUDIT_ARCH
 	def_bool y
 

arch/s390/include/asm/dat-bits.h

@@ -9,6 +9,32 @@
 #ifndef _S390_DAT_BITS_H
 #define _S390_DAT_BITS_H
 
+/*
+ * vaddress union in order to easily decode a virtual address into its
+ * region first index, region second index etc. parts.
+ */
+union vaddress {
+	unsigned long addr;
+	struct {
+		unsigned long rfx : 11;
+		unsigned long rsx : 11;
+		unsigned long rtx : 11;
+		unsigned long sx  : 11;
+		unsigned long px  : 8;
+		unsigned long bx  : 12;
+	};
+	struct {
+		unsigned long rfx01 : 2;
+		unsigned long	    : 9;
+		unsigned long rsx01 : 2;
+		unsigned long	    : 9;
+		unsigned long rtx01 : 2;
+		unsigned long	    : 9;
+		unsigned long sx01  : 2;
+		unsigned long	    : 29;
+	};
+};
+
 union asce {
 	unsigned long val;
 	struct {
@@ -98,7 +124,8 @@ union region3_table_entry {
 	struct {
 		unsigned long	: 53;
 		unsigned long fc: 1; /* Format-Control */
-		unsigned long	: 4;
+		unsigned long p : 1; /* DAT-Protection Bit */
+		unsigned long	: 3;
 		unsigned long i : 1; /* Region-Invalid Bit */
 		unsigned long cr: 1; /* Common-Region Bit */
 		unsigned long tt: 2; /* Table-Type Bits */
@@ -140,7 +167,8 @@ union segment_table_entry {
 	struct {
 		unsigned long	: 53;
 		unsigned long fc: 1; /* Format-Control */
-		unsigned long	: 4;
+		unsigned long p : 1; /* DAT-Protection Bit */
+		unsigned long	: 3;
 		unsigned long i : 1; /* Segment-Invalid Bit */
 		unsigned long cs: 1; /* Common-Segment Bit */
 		unsigned long tt: 2; /* Table-Type Bits */

arch/s390/include/asm/gmap.h

@@ -11,5 +11,6 @@
 void gmap_helper_zap_one_page(struct mm_struct *mm, unsigned long vmaddr);
 void gmap_helper_discard(struct mm_struct *mm, unsigned long vmaddr, unsigned long end);
 int gmap_helper_disable_cow_sharing(void);
+void gmap_helper_try_set_pte_unused(struct mm_struct *mm, unsigned long vmaddr);
 
 #endif /* _ASM_S390_GMAP_HELPERS_H */

arch/s390/include/asm/gmap_helpers.h

@@ -37,12 +37,6 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return __huge_ptep_get_and_clear(mm, addr, ptep);
 }
 
-static inline void arch_clear_hugetlb_flags(struct folio *folio)
-{
-	clear_bit(PG_arch_1, &folio->flags.f);
-}
-#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
-
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)

arch/s390/include/asm/hugetlb.h

@@ -27,6 +27,7 @@
 #include <asm/isc.h>
 #include <asm/guarded_storage.h>
 
+#define KVM_HAVE_MMU_RWLOCK
 #define KVM_MAX_VCPUS 255
 
 #define KVM_INTERNAL_MEM_SLOTS 1
@@ -441,6 +442,7 @@ struct kvm_vcpu_arch {
 	bool acrs_loaded;
 	struct kvm_s390_pv_vcpu pv;
 	union diag318_info diag318_info;
+	struct kvm_s390_mmu_cache *mc;
 };
 
 struct kvm_vm_stat {
@@ -630,8 +632,12 @@ struct kvm_s390_pv {
 	void *set_aside;
 	struct list_head need_cleanup;
 	struct mmu_notifier mmu_notifier;
+	/* Protects against concurrent import-like operations */
+	struct mutex import_lock;
 };
 
+struct kvm_s390_mmu_cache;
+
 struct kvm_arch {
 	struct esca_block *sca;
 	debug_info_t *dbf;
@@ -671,6 +677,7 @@ struct kvm_arch {
 	struct kvm_s390_pv pv;
 	struct list_head kzdev_list;
 	spinlock_t kzdev_list_lock;
+	struct kvm_s390_mmu_cache *mc;
 };
 
 #define KVM_HVA_ERR_BAD		(-1UL)