Merge branch 'x86/hyperv' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Topic branch for stable KVM clockource under Hyper-V.

Thanks to Christoffer Dall for resolving the ARM conflict.

12 files changed, 74 insertions, 31 deletions

diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 59dd46a..afb0f08 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -208,7 +208,8 @@ struct kvm_s390_sie_block {
 	__u16	ipa;			/* 0x0056 */
 	__u32	ipb;			/* 0x0058 */
 	__u32	scaoh;			/* 0x005c */
-	__u8	reserved60;		/* 0x0060 */
+#define FPF_BPBC 	0x20
+	__u8	fpf;			/* 0x0060 */
 #define ECB_GS		0x40
 #define ECB_TE		0x10
 #define ECB_SRSI	0x04
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 57d7bc9..0a6b028 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1264,12 +1264,6 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud;
 }
 
-#define pud_write pud_write
-static inline int pud_write(pud_t pud)
-{
-	return (pud_val(pud) & _REGION3_ENTRY_WRITE) != 0;
-}
-
 static inline pud_t pud_mkclean(pud_t pud)
 {
 	if (pud_large(pud)) {
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 0880a37..25d6ec3 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -42,8 +42,6 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 void arch_release_task_struct(struct task_struct *tsk);
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h
index 38535a57..4cdaa55 100644
--- a/arch/s390/include/uapi/asm/kvm.h
+++ b/arch/s390/include/uapi/asm/kvm.h
@@ -224,6 +224,7 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_RICCB  (1UL << 7)
 #define KVM_SYNC_FPRS   (1UL << 8)
 #define KVM_SYNC_GSCB   (1UL << 9)
+#define KVM_SYNC_BPBC   (1UL << 10)
 /* length and alignment of the sdnx as a power of two */
 #define SDNXC 8
 #define SDNXL (1UL << SDNXC)
@@ -247,7 +248,9 @@ struct kvm_sync_regs {
 	};
 	__u8  reserved[512];	/* for future vector expansion */
 	__u32 fpc;		/* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */
-	__u8 padding1[52];	/* riccb needs to be 64byte aligned */
+	__u8 bpbc : 1;		/* bp mode */
+	__u8 reserved2 : 7;
+	__u8 padding1[51];	/* riccb needs to be 64byte aligned */
 	__u8 riccb[64];		/* runtime instrumentation controls block */
 	__u8 padding2[192];	/* sdnx needs to be 256byte aligned */
 	union {
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index f04db37..59eea9c 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -263,6 +263,7 @@ COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplis
 		return retval;
 	}
 
+	groups_sort(group_info);
 	retval = set_current_groups(group_info);
 	put_group_info(group_info);
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 58bee42..ba4c709 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -434,6 +434,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_GS:
 		r = test_facility(133);
 		break;
+	case KVM_CAP_S390_BPB:
+		r = test_facility(82);
+		break;
 	default:
 		r = 0;
 	}
@@ -779,7 +782,7 @@ static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
 
 /*
  * Must be called with kvm->srcu held to avoid races on memslots, and with
- * kvm->lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
+ * kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
  */
 static int kvm_s390_vm_start_migration(struct kvm *kvm)
 {
@@ -805,11 +808,12 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 
 	if (kvm->arch.use_cmma) {
 		/*
-		 * Get the last slot. They should be sorted by base_gfn, so the
-		 * last slot is also the one at the end of the address space.
-		 * We have verified above that at least one slot is present.
+		 * Get the first slot. They are reverse sorted by base_gfn, so
+		 * the first slot is also the one at the end of the address
+		 * space. We have verified above that at least one slot is
+		 * present.
 		 */
-		ms = slots->memslots + slots->used_slots - 1;
+		ms = slots->memslots;
 		/* round up so we only use full longs */
 		ram_pages = roundup(ms->base_gfn + ms->npages, BITS_PER_LONG);
 		/* allocate enough bytes to store all the bits */
@@ -834,7 +838,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
 }
 
 /*
- * Must be called with kvm->lock to avoid races with ourselves and
+ * Must be called with kvm->slots_lock to avoid races with ourselves and
  * kvm_s390_vm_start_migration.
  */
 static int kvm_s390_vm_stop_migration(struct kvm *kvm)
@@ -849,6 +853,8 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 
 	if (kvm->arch.use_cmma) {
 		kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
+		/* We have to wait for the essa emulation to finish */
+		synchronize_srcu(&kvm->srcu);
 		vfree(mgs->pgste_bitmap);
 	}
 	kfree(mgs);
@@ -858,14 +864,12 @@ static int kvm_s390_vm_stop_migration(struct kvm *kvm)
 static int kvm_s390_vm_set_migration(struct kvm *kvm,
 				     struct kvm_device_attr *attr)
 {
-	int idx, res = -ENXIO;
+	int res = -ENXIO;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->slots_lock);
 	switch (attr->attr) {
 	case KVM_S390_VM_MIGRATION_START:
-		idx = srcu_read_lock(&kvm->srcu);
 		res = kvm_s390_vm_start_migration(kvm);
-		srcu_read_unlock(&kvm->srcu, idx);
 		break;
 	case KVM_S390_VM_MIGRATION_STOP:
 		res = kvm_s390_vm_stop_migration(kvm);
@@ -873,7 +877,7 @@ static int kvm_s390_vm_set_migration(struct kvm *kvm,
 	default:
 		break;
 	}
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return res;
 }
@@ -1775,7 +1779,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_get_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		if (!r) {
 			r = copy_to_user(argp, &args, sizeof(args));
 			if (r)
@@ -1789,7 +1795,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&args, argp, sizeof(args)))
 			break;
+		mutex_lock(&kvm->slots_lock);
 		r = kvm_s390_set_cmma_bits(kvm, &args);
+		mutex_unlock(&kvm->slots_lock);
 		break;
 	}
 	default:
@@ -2225,6 +2233,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, 0);
 	if (test_kvm_facility(vcpu->kvm, 64))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
+	if (test_kvm_facility(vcpu->kvm, 82))
+		vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC;
 	if (test_kvm_facility(vcpu->kvm, 133))
 		vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB;
 	/* fprs can be synchronized via vrs, even if the guest has no vx. With
@@ -2366,6 +2376,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	current->thread.fpu.fpc = 0;
 	vcpu->arch.sie_block->gbea = 1;
 	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
@@ -3371,6 +3382,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 		vcpu->arch.gs_enabled = 1;
 	}
+	if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) &&
+	    test_kvm_facility(vcpu->kvm, 82)) {
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
+	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	/* save host (userspace) fprs/vrs */
@@ -3417,6 +3433,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 	/* Save guest register state */
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 125a7ff..c4c4e15 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -1030,7 +1030,7 @@ static inline int do_essa(struct kvm_vcpu *vcpu, const int orc)
 		cbrlo[entries] = gfn << PAGE_SHIFT;
 	}
 
-	if (orc) {
+	if (orc && gfn < ms->bitmap_size) {
 		/* increment only if we are really flipping the bit to 1 */
 		if (!test_and_set_bit(gfn, ms->pgste_bitmap))
 			atomic64_inc(&ms->dirty_pages);
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 6d494ed5..ec77270 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -237,6 +237,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	memcpy(scb_o->gcr, scb_s->gcr, 128);
 	scb_o->pp = scb_s->pp;
 
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82)) {
+		scb_o->fpf &= ~FPF_BPBC;
+		scb_o->fpf |= scb_s->fpf & FPF_BPBC;
+	}
+
 	/* interrupt intercept */
 	switch (scb_s->icptcode) {
 	case ICPT_PROGI:
@@ -283,6 +289,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->ecb3 = 0;
 	scb_s->ecd = 0;
 	scb_s->fac = 0;
+	scb_s->fpf = 0;
 
 	rc = prepare_cpuflags(vcpu, vsie_page);
 	if (rc)
@@ -342,6 +349,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			prefix_unmapped(vsie_page);
 		scb_s->ecb |= ECB_TE;
 	}
+	/* branch prediction */
+	if (test_kvm_facility(vcpu->kvm, 82))
+		scb_s->fpf |= scb_o->fpf & FPF_BPBC;
 	/* SIMD */
 	if (test_kvm_facility(vcpu->kvm, 129)) {
 		scb_s->eca |= scb_o->eca & ECA_VX;
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index cae5a1e..c4f8039 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -89,11 +89,11 @@ EXPORT_SYMBOL(enable_sacf_uaccess);
 
 void disable_sacf_uaccess(mm_segment_t old_fs)
 {
+	current->thread.mm_segment = old_fs;
 	if (old_fs == USER_DS && test_facility(27)) {
 		__ctl_load(S390_lowcore.user_asce, 1, 1);
 		clear_cpu_flag(CIF_ASCE_PRIMARY);
 	}
-	current->thread.mm_segment = old_fs;
 }
 EXPORT_SYMBOL(disable_sacf_uaccess);
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index e81c168..9557d8b 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -55,8 +55,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_SKB_CHANGE	64	/* code changes skb data */
-#define SEEN_REG_AX	128	/* code uses constant blinding */
+#define SEEN_REG_AX	64	/* code uses constant blinding */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -448,12 +447,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB)
+	if (jit->seen & SEEN_SKB) {
 		emit_load_skb_data_hlen(jit);
-	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
+	}
 }
 
 /*
@@ -983,8 +982,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if (bpf_helper_changes_pkt_data((void *)func)) {
-			jit->seen |= SEEN_SKB_CHANGE;
+		if ((jit->seen & SEEN_SKB) &&
+		    bpf_helper_changes_pkt_data((void *)func)) {
 			/* lg %b1,ST_OFF_SKBP(%r15) */
 			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
 				      REG_15, STK_OFF_SKBP);
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index f7aa5a7..2d15d84 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -181,6 +181,9 @@ out_unlock:
 static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			   size_t size, int flags)
 {
+	unsigned long irqflags;
+	int ret;
+
 	/*
 	 * With zdev->tlb_refresh == 0, rpcit is not required to establish new
 	 * translations when previously invalid translation-table entries are
@@ -196,8 +199,22 @@ static int __dma_purge_tlb(struct zpci_dev *zdev, dma_addr_t dma_addr,
 			return 0;
 	}
 
-	return zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
-				  PAGE_ALIGN(size));
+	ret = zpci_refresh_trans((u64) zdev->fh << 32, dma_addr,
+				 PAGE_ALIGN(size));
+	if (ret == -ENOMEM && !s390_iommu_strict) {
+		/* enable the hypervisor to free some resources */
+		if (zpci_refresh_global(zdev))
+			goto out;
+
+		spin_lock_irqsave(&zdev->iommu_bitmap_lock, irqflags);
+		bitmap_andnot(zdev->iommu_bitmap, zdev->iommu_bitmap,
+			      zdev->lazy_bitmap, zdev->iommu_pages);
+		bitmap_zero(zdev->lazy_bitmap, zdev->iommu_pages);
+		spin_unlock_irqrestore(&zdev->iommu_bitmap_lock, irqflags);
+		ret = 0;
+	}
+out:
+	return ret;
 }
 
 static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa,
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index 19bcb3b..f069929 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -89,6 +89,9 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 	if (cc)
 		zpci_err_insn(cc, status, addr, range);
 
+	if (cc == 1 && (status == 4 || status == 16))
+		return -ENOMEM;
+
 	return (cc) ? -EIO : 0;
 }