Merge tag 'hlp_stage1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into features

Pull hlp_stage1 from Christian Borntraeger with the following changes:

KVM: s390: initial host large page support

- must be enabled via module parameter hpage=1
- cannot be used together with nested
- does support migration
- does support hugetlbfs
- no THP yet

Author: Martin Schwidefsky

Documentation/virtual/kvm/api.txt

@@ -4391,6 +4391,22 @@ all such vmexits.
 
 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+	 or cmma is enabled
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
 8. Other capabilities.
 ----------------------
 

arch/s390/include/asm/gmap.h

@@ -9,6 +9,14 @@
 #ifndef _ASM_S390_GMAP_H
 #define _ASM_S390_GMAP_H
 
+/* Generic bits for GMAP notification on DAT table entry changes. */
+#define GMAP_NOTIFY_SHADOW	0x2
+#define GMAP_NOTIFY_MPROT	0x1
+
+/* Status bits only for huge segment entries */
+#define _SEGMENT_ENTRY_GMAP_IN		0x8000	/* invalidation notify bit */
+#define _SEGMENT_ENTRY_GMAP_UC		0x4000	/* dirty (migration) */
+
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
@@ -132,4 +140,6 @@ void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
 int gmap_mprotect_notify(struct gmap *, unsigned long start,
 			 unsigned long len, int prot);
 
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr);
 #endif /* _ASM_S390_GMAP_H */

arch/s390/include/asm/hugetlb.h

@@ -37,7 +37,10 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define arch_clear_hugepage_flags(page)		do { } while (0)
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_arch_1, &page->flags);
+}
 
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)

arch/s390/include/asm/mmu.h

@@ -24,6 +24,8 @@ typedef struct {
 	unsigned int uses_skeys:1;
 	/* The mmu context uses CMM. */
 	unsigned int uses_cmm:1;
+	/* The gmaps associated with this context are allowed to use huge pages. */
+	unsigned int allow_gmap_hpage_1m:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \

arch/s390/include/asm/mmu_context.h

@@ -32,6 +32,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
+	mm->context.allow_gmap_hpage_1m = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case _REGION2_SIZE:

arch/s390/include/asm/pgtable.h

@@ -268,8 +268,10 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* page table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
@@ -1101,7 +1103,8 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 		    pte_t *sptep, pte_t *tptep, pte_t pte);
 void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
 
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address,
+			    pte_t *ptep);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
 int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
@@ -1116,6 +1119,10 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long addr,
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste);
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 
 /*
  * Certain architectures need to do special things when PTEs

arch/s390/kvm/kvm-s390.c

@@ -172,6 +172,10 @@ static int nested;
 module_param(nested, int, S_IRUGO);
 MODULE_PARM_DESC(nested, "Nested virtualization support");
 
+/* allow 1m huge page guest backing, if !nested */
+static int hpage;
+module_param(hpage, int, 0444);
+MODULE_PARM_DESC(hpage, "1m huge page backing support");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS_MIGRATION:
 		r = 1;
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		r = 0;
+		if (hpage)
+			r = 1;
+		break;
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
@@ -511,19 +520,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 }
 
 static void kvm_s390_sync_dirty_log(struct kvm *kvm,
-					struct kvm_memory_slot *memslot)
+				    struct kvm_memory_slot *memslot)
 {
+	int i;
 	gfn_t cur_gfn, last_gfn;
-	unsigned long address;
+	unsigned long gaddr, vmaddr;
 	struct gmap *gmap = kvm->arch.gmap;
+	DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
 
-	/* Loop over all guest pages */
+	/* Loop over all guest segments */
+	cur_gfn = memslot->base_gfn;
 	last_gfn = memslot->base_gfn + memslot->npages;
-	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
-		address = gfn_to_hva_memslot(memslot, cur_gfn);
+	for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
+		gaddr = gfn_to_gpa(cur_gfn);
+		vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
+		if (kvm_is_error_hva(vmaddr))
+			continue;
+
+		bitmap_zero(bitmap, _PAGE_ENTRIES);
+		gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
+		for (i = 0; i < _PAGE_ENTRIES; i++) {
+			if (test_bit(i, bitmap))
+				mark_page_dirty(kvm, cur_gfn + i);
+		}
 
-		if (test_and_clear_guest_dirty(gmap->mm, address))
-			mark_page_dirty(kvm, cur_gfn);
 		if (fatal_signal_pending(current))
 			return;
 		cond_resched();
@@ -667,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus)
+			r = -EBUSY;
+		else if (!hpage || kvm->arch.use_cmma)
+			r = -EINVAL;
+		else {
+			r = 0;
+			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			/*
+			 * We might have to create fake 4k page
+			 * tables. To avoid that the hardware works on
+			 * stale PGSTEs, we emulate these instructions.
+			 */
+			kvm->arch.use_skf = 0;
+			kvm->arch.use_pfmfi = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -714,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (!sclp.has_cmma)
 			break;
 
-		ret = -EBUSY;
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
-		if (!kvm->created_vcpus) {
+		if (kvm->created_vcpus)
+			ret = -EBUSY;
+		else if (kvm->mm->context.allow_gmap_hpage_1m)
+			ret = -EINVAL;
+		else {
 			kvm->arch.use_cmma = 1;
 			/* Not compatible with cmma. */
 			kvm->arch.use_pfmfi = 0;
@@ -1540,6 +1584,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	uint8_t *keys;
 	uint64_t hva;
 	int srcu_idx, i, r = 0;
+	bool unlocked;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1564,9 +1609,11 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (r)
 		goto out;
 
+	i = 0;
 	down_read(&current->mm->mmap_sem);
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < args->count; i++) {
+        while (i < args->count) {
+		unlocked = false;
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
@@ -1580,8 +1627,14 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		}
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
-		if (r)
-			break;
+		if (r) {
+			r = fixup_user_fault(current, current->mm, hva,
+					     FAULT_FLAG_WRITE, &unlocked);
+			if (r)
+				break;
+		}
+		if (!r)
+			i++;
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
@@ -4082,6 +4135,11 @@ static int __init kvm_s390_init(void)
 		return -ENODEV;
 	}
 
+	if (nested && hpage) {
+		pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < 16; i++)
 		kvm_s390_fac_base[i] |=
 			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);