Merge tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "First batch of KVM changes for 4.15

  Common:
   - Python 3 support in kvm_stat
   - Accounting of slabs to kmemcg

  ARM:
   - Optimized arch timer handling for KVM/ARM
   - Improvements to the VGIC ITS code and introduction of an ITS reset
     ioctl
   - Unification of the 32-bit fault injection logic
   - More exact external abort matching logic

  PPC:
   - Support for running hashed page table (HPT) MMU mode on a host that
     is using the radix MMU mode; single threaded mode on POWER 9 is
     added as a pre-requisite
   - Resolution of merge conflicts with the last second 4.14 HPT fixes
   - Fixes and cleanups

  s390:
   - Some initial preparation patches for exitless interrupts and crypto
   - New capability for AIS migration
   - Fixes

  x86:
   - Improved emulation of LAPIC timer mode changes, MCi_STATUS MSRs,
     and after-reset state
   - Refined dependencies for VMX features
   - Fixes for nested SMI injection
   - A lot of cleanups"

* tag 'kvm-4.15-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (89 commits)
  KVM: s390: provide a capability for AIS state migration
  KVM: s390: clear_io_irq() requests are not expected for adapter interrupts
  KVM: s390: abstract conversion between isc and enum irq_types
  KVM: s390: vsie: use common code functions for pinning
  KVM: s390: SIE considerations for AP Queue virtualization
  KVM: s390: document memory ordering for kvm_s390_vcpu_wakeup
  KVM: PPC: Book3S HV: Cosmetic post-merge cleanups
  KVM: arm/arm64: fix the incompatible matching for external abort
  KVM: arm/arm64: Unify 32bit fault injection
  KVM: arm/arm64: vgic-its: Implement KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: Document KVM_DEV_ARM_ITS_CTRL_RESET
  KVM: arm/arm64: vgic-its: Free caches when GITS_BASER Valid bit is cleared
  KVM: arm/arm64: vgic-its: New helper functions to free the caches
  KVM: arm/arm64: vgic-its: Remove kvm_its_unmap_device
  arm/arm64: KVM: Load the timer state when enabling the timer
  KVM: arm/arm64: Rework kvm_timer_should_fire
  KVM: arm/arm64: Get rid of kvm_timer_flush_hwstate
  KVM: arm/arm64: Avoid phys timer emulation in vcpu entry/exit
  KVM: arm/arm64: Move phys_timer_emulate function
  KVM: arm/arm64: Use kvm_arm_timer_set/get_reg for guest register traps
  ...

4 files changed, 62 insertions, 40 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index fd006a272024..f3a9b5a445b6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -685,11 +685,28 @@ struct kvm_s390_crypto {
 	__u8 dea_kw;
 };
 
+#define APCB0_MASK_SIZE 1
+struct kvm_s390_apcb0 {
+	__u64 apm[APCB0_MASK_SIZE];		/* 0x0000 */
+	__u64 aqm[APCB0_MASK_SIZE];		/* 0x0008 */
+	__u64 adm[APCB0_MASK_SIZE];		/* 0x0010 */
+	__u64 reserved18;			/* 0x0018 */
+};
+
+#define APCB1_MASK_SIZE 4
+struct kvm_s390_apcb1 {
+	__u64 apm[APCB1_MASK_SIZE];		/* 0x0000 */
+	__u64 aqm[APCB1_MASK_SIZE];		/* 0x0020 */
+	__u64 adm[APCB1_MASK_SIZE];		/* 0x0040 */
+	__u64 reserved60[4];			/* 0x0060 */
+};
+
 struct kvm_s390_crypto_cb {
-	__u8    reserved00[72];                 /* 0x0000 */
-	__u8    dea_wrapping_key_mask[24];      /* 0x0048 */
-	__u8    aes_wrapping_key_mask[32];      /* 0x0060 */
-	__u8    reserved80[128];                /* 0x0080 */
+	struct kvm_s390_apcb0 apcb0;		/* 0x0000 */
+	__u8   reserved20[0x0048 - 0x0020];	/* 0x0020 */
+	__u8   dea_wrapping_key_mask[24];	/* 0x0048 */
+	__u8   aes_wrapping_key_mask[32];	/* 0x0060 */
+	struct kvm_s390_apcb1 apcb1;		/* 0x0080 */
 };
 
 /*
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 329b2843fee2..fa557372d600 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -213,6 +213,16 @@ static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
 	       vcpu->arch.local_int.pending_irqs;
 }
 
+static inline int isc_to_irq_type(unsigned long isc)
+{
+	return IRQ_PEND_IO_ISC_0 + isc;
+}
+
+static inline int irq_type_to_isc(unsigned long irq_type)
+{
+	return irq_type - IRQ_PEND_IO_ISC_0;
+}
+
 static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
 				   unsigned long active_mask)
 {
@@ -220,7 +230,7 @@ static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
 
 	for (i = 0; i <= MAX_ISC; i++)
 		if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i)))
-			active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i));
+			active_mask &= ~(1UL << (isc_to_irq_type(i)));
 
 	return active_mask;
 }
@@ -901,7 +911,7 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 	fi = &vcpu->kvm->arch.float_int;
 
 	spin_lock(&fi->lock);
-	isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0];
+	isc_list = &fi->lists[irq_type_to_isc(irq_type)];
 	inti = list_first_entry_or_null(isc_list,
 					struct kvm_s390_interrupt_info,
 					list);
@@ -1074,6 +1084,12 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 	 * in kvm_vcpu_block without having the waitqueue set (polling)
 	 */
 	vcpu->valid_wakeup = true;
+	/*
+	 * This is mostly to document, that the read in swait_active could
+	 * be moved before other stores, leading to subtle races.
+	 * All current users do not store or use an atomic like update
+	 */
+	smp_mb__after_atomic();
 	if (swait_active(&vcpu->wq)) {
 		/*
 		 * The vcpu gave up the cpu voluntarily, mark it as a good
@@ -1395,7 +1411,7 @@ static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
 		list_del_init(&iter->list);
 		fi->counters[FIRQ_CNTR_IO] -= 1;
 		if (list_empty(isc_list))
-			clear_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
+			clear_bit(isc_to_irq_type(isc), &fi->pending_irqs);
 		spin_unlock(&fi->lock);
 		return iter;
 	}
@@ -1522,7 +1538,7 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	isc = int_word_to_isc(inti->io.io_int_word);
 	list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
 	list_add_tail(&inti->list, list);
-	set_bit(IRQ_PEND_IO_ISC_0 + isc, &fi->pending_irqs);
+	set_bit(isc_to_irq_type(isc), &fi->pending_irqs);
 	spin_unlock(&fi->lock);
 	return 0;
 }
@@ -2175,6 +2191,8 @@ static int clear_io_irq(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 	if (copy_from_user(&schid, (void __user *) attr->addr, sizeof(schid)))
 		return -EFAULT;
+	if (!schid)
+		return -EINVAL;
 	kfree(kvm_s390_get_io_int(kvm, isc_mask, schid));
 	/*
 	 * If userspace is conforming to the architecture, we can have at most
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4bc70afe0a10..98ad8b9e0360 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -395,6 +395,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_USER_INSTR0:
 	case KVM_CAP_S390_CMMA_MIGRATION:
 	case KVM_CAP_S390_AIS:
+	case KVM_CAP_S390_AIS_MIGRATION:
 		r = 1;
 		break;
 	case KVM_CAP_S390_MEM_OP:
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index b18b5652e5c5..a311938b63b3 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -443,22 +443,14 @@ static int map_prefix(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
  *
  * Returns: - 0 on success
  *          - -EINVAL if the gpa is not valid guest storage
- *          - -ENOMEM if out of memory
  */
 static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa)
 {
 	struct page *page;
-	hva_t hva;
-	int rc;
 
-	hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
-	if (kvm_is_error_hva(hva))
+	page = gfn_to_page(kvm, gpa_to_gfn(gpa));
+	if (is_error_page(page))
 		return -EINVAL;
-	rc = get_user_pages_fast(hva, 1, 1, &page);
-	if (rc < 0)
-		return rc;
-	else if (rc != 1)
-		return -ENOMEM;
 	*hpa = (hpa_t) page_to_virt(page) + (gpa & ~PAGE_MASK);
 	return 0;
 }
@@ -466,11 +458,7 @@ static int pin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t *hpa)
 /* Unpins a page previously pinned via pin_guest_page, marking it as dirty. */
 static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
 {
-	struct page *page;
-
-	page = virt_to_page(hpa);
-	set_page_dirty_lock(page);
-	put_page(page);
+	kvm_release_pfn_dirty(hpa >> PAGE_SHIFT);
 	/* mark the page always as dirty for migration */
 	mark_page_dirty(kvm, gpa_to_gfn(gpa));
 }
@@ -557,7 +545,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			rc = set_validity_icpt(scb_s, 0x003bU);
 		if (!rc) {
 			rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-			if (rc == -EINVAL)
+			if (rc)
 				rc = set_validity_icpt(scb_s, 0x0034U);
 		}
 		if (rc)
@@ -574,10 +562,10 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		}
 		/* 256 bytes cannot cross page boundaries */
 		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-		if (rc == -EINVAL)
+		if (rc) {
 			rc = set_validity_icpt(scb_s, 0x0080U);
-		if (rc)
 			goto unpin;
+		}
 		scb_s->itdba = hpa;
 	}
 
@@ -592,10 +580,10 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		 * if this block gets bigger, we have to shadow it.
 		 */
 		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-		if (rc == -EINVAL)
+		if (rc) {
 			rc = set_validity_icpt(scb_s, 0x1310U);
-		if (rc)
 			goto unpin;
+		}
 		scb_s->gvrd = hpa;
 	}
 
@@ -607,11 +595,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		}
 		/* 64 bytes cannot cross page boundaries */
 		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-		if (rc == -EINVAL)
+		if (rc) {
 			rc = set_validity_icpt(scb_s, 0x0043U);
-		/* Validity 0x0044 will be checked by SIE */
-		if (rc)
 			goto unpin;
+		}
+		/* Validity 0x0044 will be checked by SIE */
 		scb_s->riccbd = hpa;
 	}
 	if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
@@ -635,10 +623,10 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		 * cross page boundaries
 		 */
 		rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-		if (rc == -EINVAL)
+		if (rc) {
 			rc = set_validity_icpt(scb_s, 0x10b0U);
-		if (rc)
 			goto unpin;
+		}
 		scb_s->sdnxo = hpa | sdnxc;
 	}
 	return 0;
@@ -663,7 +651,6 @@ static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
  *
  * Returns: - 0 if the scb was pinned.
  *          - > 0 if control has to be given to guest 2
- *          - -ENOMEM if out of memory
  */
 static int pin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
 		   gpa_t gpa)
@@ -672,14 +659,13 @@ static int pin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page,
 	int rc;
 
 	rc = pin_guest_page(vcpu->kvm, gpa, &hpa);
-	if (rc == -EINVAL) {
+	if (rc) {
 		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		if (!rc)
-			rc = 1;
+		WARN_ON_ONCE(rc);
+		return 1;
 	}
-	if (!rc)
-		vsie_page->scb_o = (struct kvm_s390_sie_block *) hpa;
-	return rc;
+	vsie_page->scb_o = (struct kvm_s390_sie_block *) hpa;
+	return 0;
 }
 
 /*