Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - GICv4.1 support

   - 32bit host removal

  PPC:
   - secure (encrypted) using under the Protected Execution Framework
     ultravisor

  s390:
   - allow disabling GISA (hardware interrupt injection) and protected
     VMs/ultravisor support.

  x86:
   - New dirty bitmap flag that sets all bits in the bitmap when dirty
     page logging is enabled; this is faster because it doesn't require
     bulk modification of the page tables.

   - Initial work on making nested SVM event injection more similar to
     VMX, and less buggy.

   - Various cleanups to MMU code (though the big ones and related
     optimizations were delayed to 5.8). Instead of using cr3 in
     function names which occasionally means eptp, KVM too has
     standardized on "pgd".

   - A large refactoring of CPUID features, which now use an array that
     parallels the core x86_features.

   - Some removal of pointer chasing from kvm_x86_ops, which will also
     be switched to static calls as soon as they are available.

   - New Tigerlake CPUID features.

   - More bugfixes, optimizations and cleanups.

  Generic:
   - selftests: cleanups, new MMU notifier stress test, steal-time test

   - CSV output for kvm_stat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
  x86/kvm: fix a missing-prototypes "vmread_error"
  KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
  KVM: VMX: Add a trampoline to fix VMREAD error handling
  KVM: SVM: Annotate svm_x86_ops as __initdata
  KVM: VMX: Annotate vmx_x86_ops as __initdata
  KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
  KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
  KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
  KVM: VMX: Configure runtime hooks using vmx_x86_ops
  KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
  KVM: x86: Move init-only kvm_x86_ops to separate struct
  KVM: Pass kvm_init()'s opaque param to additional arch funcs
  s390/gmap: return proper error code on ksm unsharing
  KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
  KVM: Fix out of range accesses to memslots
  KVM: X86: Micro-optimize IPI fastpath delay
  KVM: X86: Delay read msr data iff writes ICR MSR
  KVM: PPC: Book3S HV: Add a capability for enabling secure guests
  KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
  KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
  ...

2 files changed, 137 insertions, 13 deletions

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index aeccdb30899a..09bf7f2121ac 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -38,6 +38,7 @@
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/facility.h>
+#include <asm/uv.h>
 #include "../kernel/entry.h"
 
 #define __FAIL_ADDR_MASK -4096L
@@ -812,3 +813,80 @@ out_extint:
 early_initcall(pfault_irq_init);
 
 #endif /* CONFIG_PFAULT */
+
+#if IS_ENABLED(CONFIG_PGSTE)
+void do_secure_storage_access(struct pt_regs *regs)
+{
+	unsigned long addr = regs->int_parm_long & __FAIL_ADDR_MASK;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	struct page *page;
+	int rc;
+
+	switch (get_fault_type(regs)) {
+	case USER_FAULT:
+		mm = current->mm;
+		down_read(&mm->mmap_sem);
+		vma = find_vma(mm, addr);
+		if (!vma) {
+			up_read(&mm->mmap_sem);
+			do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+			break;
+		}
+		page = follow_page(vma, addr, FOLL_WRITE | FOLL_GET);
+		if (IS_ERR_OR_NULL(page)) {
+			up_read(&mm->mmap_sem);
+			break;
+		}
+		if (arch_make_page_accessible(page))
+			send_sig(SIGSEGV, current, 0);
+		put_page(page);
+		up_read(&mm->mmap_sem);
+		break;
+	case KERNEL_FAULT:
+		page = phys_to_page(addr);
+		if (unlikely(!try_get_page(page)))
+			break;
+		rc = arch_make_page_accessible(page);
+		put_page(page);
+		if (rc)
+			BUG();
+		break;
+	case VDSO_FAULT:
+		/* fallthrough */
+	case GMAP_FAULT:
+		/* fallthrough */
+	default:
+		do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+		WARN_ON_ONCE(1);
+	}
+}
+NOKPROBE_SYMBOL(do_secure_storage_access);
+
+void do_non_secure_storage_access(struct pt_regs *regs)
+{
+	unsigned long gaddr = regs->int_parm_long & __FAIL_ADDR_MASK;
+	struct gmap *gmap = (struct gmap *)S390_lowcore.gmap;
+
+	if (get_fault_type(regs) != GMAP_FAULT) {
+		do_fault_error(regs, VM_READ | VM_WRITE, VM_FAULT_BADMAP);
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+	if (gmap_convert_to_secure(gmap, gaddr) == -EINVAL)
+		send_sig(SIGSEGV, current, 0);
+}
+NOKPROBE_SYMBOL(do_non_secure_storage_access);
+
+#else
+void do_secure_storage_access(struct pt_regs *regs)
+{
+	default_trap_handler(regs);
+}
+
+void do_non_secure_storage_access(struct pt_regs *regs)
+{
+	default_trap_handler(regs);
+}
+#endif
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index edcdca97e85e..2fbece47ef6f 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -804,7 +804,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 		if (*table & _REGION_ENTRY_INVALID)
 			return NULL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-		/* Fallthrough */
+		fallthrough;
 	case _ASCE_TYPE_REGION2:
 		table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT;
 		if (level == 3)
@@ -812,7 +812,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 		if (*table & _REGION_ENTRY_INVALID)
 			return NULL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-		/* Fallthrough */
+		fallthrough;
 	case _ASCE_TYPE_REGION3:
 		table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT;
 		if (level == 2)
@@ -820,7 +820,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap,
 		if (*table & _REGION_ENTRY_INVALID)
 			return NULL;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
-		/* Fallthrough */
+		fallthrough;
 	case _ASCE_TYPE_SEGMENT:
 		table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT;
 		if (level == 1)
@@ -2548,6 +2548,23 @@ int s390_enable_sie(void)
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
 
+int gmap_mark_unmergeable(void)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int ret;
+
+	for (vma = mm->mmap; vma; vma = vma->vm_next) {
+		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+				  MADV_UNMERGEABLE, &vma->vm_flags);
+		if (ret)
+			return ret;
+	}
+	mm->def_flags &= ~VM_MERGEABLE;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(gmap_mark_unmergeable);
+
 /*
  * Enable storage key handling from now on and initialize the storage
  * keys with the default key.
@@ -2593,7 +2610,6 @@ static const struct mm_walk_ops enable_skey_walk_ops = {
 int s390_enable_skey(void)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
 	int rc = 0;
 
 	down_write(&mm->mmap_sem);
@@ -2601,16 +2617,11 @@ int s390_enable_skey(void)
 		goto out_up;
 
 	mm->context.uses_skeys = 1;
-	for (vma = mm->mmap; vma; vma = vma->vm_next) {
-		if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
-				MADV_UNMERGEABLE, &vma->vm_flags)) {
-			mm->context.uses_skeys = 0;
-			rc = -ENOMEM;
-			goto out_up;
-		}
+	rc = gmap_mark_unmergeable();
+	if (rc) {
+		mm->context.uses_skeys = 0;
+		goto out_up;
 	}
-	mm->def_flags &= ~VM_MERGEABLE;
-
 	walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL);
 
 out_up:
@@ -2640,3 +2651,38 @@ void s390_reset_cmma(struct mm_struct *mm)
 	up_write(&mm->mmap_sem);
 }
 EXPORT_SYMBOL_GPL(s390_reset_cmma);
+
+/*
+ * make inaccessible pages accessible again
+ */
+static int __s390_reset_acc(pte_t *ptep, unsigned long addr,
+			    unsigned long next, struct mm_walk *walk)
+{
+	pte_t pte = READ_ONCE(*ptep);
+
+	if (pte_present(pte))
+		WARN_ON_ONCE(uv_convert_from_secure(pte_val(pte) & PAGE_MASK));
+	return 0;
+}
+
+static const struct mm_walk_ops reset_acc_walk_ops = {
+	.pte_entry		= __s390_reset_acc,
+};
+
+#include <linux/sched/mm.h>
+void s390_reset_acc(struct mm_struct *mm)
+{
+	/*
+	 * we might be called during
+	 * reset:                             we walk the pages and clear
+	 * close of all kvm file descriptors: we walk the pages and clear
+	 * exit of process on fd closure:     vma already gone, do nothing
+	 */
+	if (!mmget_not_zero(mm))
+		return;
+	down_read(&mm->mmap_sem);
+	walk_page_range(mm, 0, TASK_SIZE, &reset_acc_walk_ops, NULL);
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+}
+EXPORT_SYMBOL_GPL(s390_reset_acc);