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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - HYP mode stub supports kexec/kdump on 32-bit
   - improved PMU support
   - virtual interrupt controller performance improvements
   - support for userspace virtual interrupt controller (slower, but
     necessary for KVM on the weird Broadcom SoCs used by the Raspberry
     Pi 3)

  MIPS:
   - basic support for hardware virtualization (ImgTec P5600/P6600/I6400
     and Cavium Octeon III)

  PPC:
   - in-kernel acceleration for VFIO

  s390:
   - support for guests without storage keys
   - adapter interruption suppression

  x86:
   - usual range of nVMX improvements, notably nested EPT support for
     accessed and dirty bits
   - emulation of CPL3 CPUID faulting

  generic:
   - first part of VCPU thread request API
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  kvm: nVMX: Don't validate disabled secondary controls
  KVM: put back #ifndef CONFIG_S390 around kvm_vcpu_kick
  Revert "KVM: Support vCPU-based gfn->hva cache"
  tools/kvm: fix top level makefile
  KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING
  KVM: Documentation: remove VM mmap documentation
  kvm: nVMX: Remove superfluous VMX instruction fault checks
  KVM: x86: fix emulation of RSM and IRET instructions
  KVM: mark requests that need synchronization
  KVM: return if kvm_vcpu_wake_up() did wake up the VCPU
  KVM: add explicit barrier to kvm_vcpu_kick
  KVM: perform a wake_up in kvm_make_all_cpus_request
  KVM: mark requests that do not need a wakeup
  KVM: remove #ifndef CONFIG_S390 around kvm_vcpu_wake_up
  KVM: x86: always use kvm_make_request instead of set_bit
  KVM: add kvm_{test,clear}_request to replace {test,clear}_bit
  s390: kvm: Cpu model support for msa6, msa7 and msa8
  KVM: x86: remove irq disablement around KVM_SET_CLOCK/KVM_GET_CLOCK
  kvm: better MWAIT emulation for guests
  KVM: x86: virtualize cpuid faulting
  ...

15 files changed, 1392 insertions, 132 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 029be26b5a17..65a471de96de 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -67,6 +67,7 @@ config KVM_BOOK3S_64
 	select KVM_BOOK3S_64_HANDLER
 	select KVM
 	select KVM_BOOK3S_PR_POSSIBLE if !KVM_BOOK3S_HV_POSSIBLE
+	select SPAPR_TCE_IOMMU if IOMMU_SUPPORT
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index aedacefd961d..8c4d7e9d27d2 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -197,6 +197,24 @@ void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 }
 EXPORT_SYMBOL_GPL(kvmppc_core_queue_program);
 
+void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu)
+{
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, 0);
+}
+
+void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu)
+{
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_ALTIVEC, 0);
+}
+
+void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu)
+{
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_VSX, 0);
+}
+
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
 {
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 70153578131a..29ebe2fd5867 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -319,6 +319,7 @@ do_second:
 		gpte->may_execute = true;
 	gpte->may_read = false;
 	gpte->may_write = false;
+	gpte->wimg = r & HPTE_R_WIMG;
 
 	switch (pp) {
 	case 0:
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 74b0153780e3..9a4614cd0e53 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -145,6 +145,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte,
 	else
 		kvmppc_mmu_flush_icache(pfn);
 
+	rflags = (rflags & ~HPTE_R_WIMG) | orig_pte->wimg;
+
 	/*
 	 * Use 64K pages if possible; otherwise, on 64K page kernels,
 	 * we need to transfer 4 more bits from guest real to host real addr.
@@ -177,12 +179,15 @@ map_again:
 	ret = mmu_hash_ops.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
 				       hpsize, hpsize, MMU_SEGSIZE_256M);
 
-	if (ret < 0) {
+	if (ret == -1) {
 		/* If we couldn't map a primary PTE, try a secondary */
 		hash = ~hash;
 		vflags ^= HPTE_V_SECONDARY;
 		attempt++;
 		goto map_again;
+	} else if (ret < 0) {
+		r = -EIO;
+		goto out_unlock;
 	} else {
 		trace_kvm_book3s_64_mmu_map(rflags, hpteg,
 					    vpn, hpaddr, orig_pte);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 3e26cd4979f9..a160c14304eb 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -28,6 +28,8 @@
 #include <linux/hugetlb.h>
 #include <linux/list.h>
 #include <linux/anon_inodes.h>
+#include <linux/iommu.h>
+#include <linux/file.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -40,6 +42,7 @@
 #include <asm/udbg.h>
 #include <asm/iommu.h>
 #include <asm/tce.h>
+#include <asm/mmu_context.h>
 
 static unsigned long kvmppc_tce_pages(unsigned long iommu_pages)
 {
@@ -91,6 +94,137 @@ static long kvmppc_account_memlimit(unsigned long stt_pages, bool inc)
 	return ret;
 }
 
+static void kvm_spapr_tce_iommu_table_free(struct rcu_head *head)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(head,
+			struct kvmppc_spapr_tce_iommu_table, rcu);
+
+	iommu_tce_table_put(stit->tbl);
+
+	kfree(stit);
+}
+
+static void kvm_spapr_tce_liobn_put(struct kref *kref)
+{
+	struct kvmppc_spapr_tce_iommu_table *stit = container_of(kref,
+			struct kvmppc_spapr_tce_iommu_table, kref);
+
+	list_del_rcu(&stit->next);
+
+	call_rcu(&stit->rcu, kvm_spapr_tce_iommu_table_free);
+}
+
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp)
+{
+	int i;
+	struct kvmppc_spapr_tce_table *stt;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
+	struct iommu_table_group *table_group = NULL;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+
+		table_group = iommu_group_get_iommudata(grp);
+		if (WARN_ON(!table_group))
+			continue;
+
+		list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+			for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+				if (table_group->tables[i] != stit->tbl)
+					continue;
+
+				kref_put(&stit->kref, kvm_spapr_tce_liobn_put);
+				return;
+			}
+		}
+	}
+}
+
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp)
+{
+	struct kvmppc_spapr_tce_table *stt = NULL;
+	bool found = false;
+	struct iommu_table *tbl = NULL;
+	struct iommu_table_group *table_group;
+	long i;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	struct fd f;
+
+	f = fdget(tablefd);
+	if (!f.file)
+		return -EBADF;
+
+	list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt == f.file->private_data) {
+			found = true;
+			break;
+		}
+	}
+
+	fdput(f);
+
+	if (!found)
+		return -EINVAL;
+
+	table_group = iommu_group_get_iommudata(grp);
+	if (WARN_ON(!table_group))
+		return -EFAULT;
+
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbltmp = table_group->tables[i];
+
+		if (!tbltmp)
+			continue;
+		/*
+		 * Make sure hardware table parameters are exactly the same;
+		 * this is used in the TCE handlers where boundary checks
+		 * use only the first attached table.
+		 */
+		if ((tbltmp->it_page_shift == stt->page_shift) &&
+				(tbltmp->it_offset == stt->offset) &&
+				(tbltmp->it_size == stt->size)) {
+			/*
+			 * Reference the table to avoid races with
+			 * add/remove DMA windows.
+			 */
+			tbl = iommu_tce_table_get(tbltmp);
+			break;
+		}
+	}
+	if (!tbl)
+		return -EINVAL;
+
+	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
+		if (tbl != stit->tbl)
+			continue;
+
+		if (!kref_get_unless_zero(&stit->kref)) {
+			/* stit is being destroyed */
+			iommu_tce_table_put(tbl);
+			return -ENOTTY;
+		}
+		/*
+		 * The table is already known to this KVM, we just increased
+		 * its KVM reference counter and can return.
+		 */
+		return 0;
+	}
+
+	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
+	if (!stit) {
+		iommu_tce_table_put(tbl);
+		return -ENOMEM;
+	}
+
+	stit->tbl = tbl;
+	kref_init(&stit->kref);
+
+	list_add_rcu(&stit->next, &stt->iommu_tables);
+
+	return 0;
+}
+
 static void release_spapr_tce_table(struct rcu_head *head)
 {
 	struct kvmppc_spapr_tce_table *stt = container_of(head,
@@ -130,9 +264,18 @@ static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
 static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 {
 	struct kvmppc_spapr_tce_table *stt = filp->private_data;
+	struct kvmppc_spapr_tce_iommu_table *stit, *tmp;
 
 	list_del_rcu(&stt->list);
 
+	list_for_each_entry_safe(stit, tmp, &stt->iommu_tables, next) {
+		WARN_ON(!kref_read(&stit->kref));
+		while (1) {
+			if (kref_put(&stit->kref, kvm_spapr_tce_liobn_put))
+				break;
+		}
+	}
+
 	kvm_put_kvm(stt->kvm);
 
 	kvmppc_account_memlimit(
@@ -164,7 +307,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 			return -EBUSY;
 	}
 
-	size = args->size;
+	size = _ALIGN_UP(args->size, PAGE_SIZE >> 3);
 	npages = kvmppc_tce_pages(size);
 	ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true);
 	if (ret) {
@@ -183,6 +326,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
 	for (i = 0; i < npages; i++) {
 		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
@@ -211,15 +355,106 @@ fail:
 	return ret;
 }
 
+static void kvmppc_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (WARN_ON_ONCE(iommu_tce_xchg(tbl, entry, &hpa, &dir)))
+		return H_HARDWARE;
+
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret != H_SUCCESS)
+		iommu_tce_xchg(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+long kvmppc_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa, *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	if (mm_iommu_mapped_inc(mem))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg(tbl, entry, &hpa, &dir);
+	if (WARN_ON_ONCE(ret)) {
+		mm_iommu_mapped_dec(mem);
+		return H_HARDWARE;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
-	long ret;
+	struct kvmppc_spapr_tce_table *stt;
+	long ret, idx;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -231,7 +466,35 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir == DMA_NONE) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		} else {
+			idx = srcu_read_lock(&vcpu->kvm->srcu);
+			ret = kvmppc_tce_iommu_map(vcpu->kvm, stit->tbl,
+					entry, ua, dir);
+			srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		}
+
+		if (ret == H_SUCCESS)
+			continue;
+
+		if (ret == H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE(1);
+		kvmppc_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -246,8 +509,9 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	unsigned long entry, ua = 0;
 	u64 __user *tces;
 	u64 tce;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -284,6 +548,26 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
@@ -300,8 +584,9 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -313,6 +598,24 @@ long kvmppc_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE(1);
+			kvmppc_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index e4c4ea973e57..eda0a8f6fae8 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -40,6 +40,31 @@
 #include <asm/iommu.h>
 #include <asm/tce.h>
 
+#ifdef CONFIG_BUG
+
+#define WARN_ON_ONCE_RM(condition)	({			\
+	static bool __section(.data.unlikely) __warned;		\
+	int __ret_warn_once = !!(condition);			\
+								\
+	if (unlikely(__ret_warn_once && !__warned)) {		\
+		__warned = true;				\
+		pr_err("WARN_ON_ONCE_RM: (%s) at %s:%u\n",	\
+				__stringify(condition),		\
+				__func__, __LINE__);		\
+		dump_stack();					\
+	}							\
+	unlikely(__ret_warn_once);				\
+})
+
+#else
+
+#define WARN_ON_ONCE_RM(condition) ({				\
+	int __ret_warn_on = !!(condition);			\
+	unlikely(__ret_warn_on);				\
+})
+
+#endif
+
 #define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
 
 /*
@@ -48,10 +73,9 @@
  * WARNING: This will be called in real or virtual mode on HV KVM and virtual
  *          mode on PR KVM
  */
-struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
+struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 		unsigned long liobn)
 {
-	struct kvm *kvm = vcpu->kvm;
 	struct kvmppc_spapr_tce_table *stt;
 
 	list_for_each_entry_lockless(stt, &kvm->arch.spapr_tce_tables, list)
@@ -63,27 +87,6 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm_vcpu *vcpu,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 /*
- * Validates IO address.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
- */
-long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages)
-{
-	unsigned long mask = (1ULL << stt->page_shift) - 1;
-	unsigned long idx = ioba >> stt->page_shift;
-
-	if ((ioba & mask) || (idx < stt->offset) ||
-			(idx - stt->offset + npages > stt->size) ||
-			(idx + npages < idx))
-		return H_PARAMETER;
-
-	return H_SUCCESS;
-}
-EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
-
-/*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
  * As the host kernel does not access those addresses (just puts them
@@ -96,10 +99,14 @@ EXPORT_SYMBOL_GPL(kvmppc_ioba_validate);
  */
 long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, unsigned long tce)
 {
-	unsigned long page_mask = ~((1ULL << stt->page_shift) - 1);
-	unsigned long mask = ~(page_mask | TCE_PCI_WRITE | TCE_PCI_READ);
+	unsigned long gpa = tce & ~(TCE_PCI_READ | TCE_PCI_WRITE);
+	enum dma_data_direction dir = iommu_tce_direction(tce);
+
+	/* Allow userspace to poison TCE table */
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
 
-	if (tce & mask)
+	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
 	return H_SUCCESS;
@@ -179,15 +186,122 @@ long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
 EXPORT_SYMBOL_GPL(kvmppc_gpa_to_ua);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static void kvmppc_rm_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long hpa = 0;
+	enum dma_data_direction dir = DMA_NONE;
+
+	iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+}
+
+static long kvmppc_rm_tce_iommu_mapped_dec(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	struct mm_iommu_table_group_mem_t *mem = NULL;
+	const unsigned long pgsize = 1ULL << tbl->it_page_shift;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, *pua, pgsize);
+	if (!mem)
+		return H_TOO_HARD;
+
+	mm_iommu_mapped_dec(mem);
+
+	*pua = 0;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_rm_tce_iommu_unmap(struct kvm *kvm,
+		struct iommu_table *tbl, unsigned long entry)
+{
+	enum dma_data_direction dir = DMA_NONE;
+	unsigned long hpa = 0;
+	long ret;
+
+	if (iommu_tce_xchg_rm(tbl, entry, &hpa, &dir))
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+
+	if (dir == DMA_NONE)
+		return H_SUCCESS;
+
+	ret = kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+	if (ret)
+		iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+
+	return ret;
+}
+
+static long kvmppc_rm_tce_iommu_map(struct kvm *kvm, struct iommu_table *tbl,
+		unsigned long entry, unsigned long ua,
+		enum dma_data_direction dir)
+{
+	long ret;
+	unsigned long hpa = 0;
+	unsigned long *pua = IOMMU_TABLE_USERSPACE_ENTRY(tbl, entry);
+	struct mm_iommu_table_group_mem_t *mem;
+
+	if (!pua)
+		/* it_userspace allocation might be delayed */
+		return H_TOO_HARD;
+
+	mem = mm_iommu_lookup_rm(kvm->mm, ua, 1ULL << tbl->it_page_shift);
+	if (!mem)
+		return H_TOO_HARD;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+		return H_HARDWARE;
+
+	pua = (void *) vmalloc_to_phys(pua);
+	if (WARN_ON_ONCE_RM(!pua))
+		return H_HARDWARE;
+
+	if (WARN_ON_ONCE_RM(mm_iommu_mapped_inc(mem)))
+		return H_CLOSED;
+
+	ret = iommu_tce_xchg_rm(tbl, entry, &hpa, &dir);
+	if (ret) {
+		mm_iommu_mapped_dec(mem);
+		/*
+		 * real mode xchg can fail if struct page crosses
+		 * a page boundary
+		 */
+		return H_TOO_HARD;
+	}
+
+	if (dir != DMA_NONE)
+		kvmppc_rm_tce_iommu_mapped_dec(kvm, tbl, entry);
+
+	*pua = ua;
+
+	return 0;
+}
+
 long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		unsigned long ioba, unsigned long tce)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
+	unsigned long entry, ua = 0;
+	enum dma_data_direction dir;
 
 	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
 	/* 	    liobn, ioba, tce); */
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -199,7 +313,32 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	kvmppc_tce_put(stt, ioba >> stt->page_shift, tce);
+	dir = iommu_tce_direction(tce);
+	if ((dir != DMA_NONE) && kvmppc_gpa_to_ua(vcpu->kvm,
+			tce & ~(TCE_PCI_READ | TCE_PCI_WRITE), &ua, NULL))
+		return H_PARAMETER;
+
+	entry = ioba >> stt->page_shift;
+
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		if (dir == DMA_NONE)
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry);
+		else
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry, ua, dir);
+
+		if (ret == H_SUCCESS)
+			continue;
+
+		if (ret == H_TOO_HARD)
+			return ret;
+
+		WARN_ON_ONCE_RM(1);
+		kvmppc_rm_clear_tce(stit->tbl, entry);
+	}
+
+	kvmppc_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -239,8 +378,10 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	long i, ret = H_SUCCESS;
 	unsigned long tces, entry, ua = 0;
 	unsigned long *rmap = NULL;
+	bool prereg = false;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -259,23 +400,49 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (ret != H_SUCCESS)
 		return ret;
 
-	if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
-		return H_TOO_HARD;
+	if (mm_iommu_preregistered(vcpu->kvm->mm)) {
+		/*
+		 * We get here if guest memory was pre-registered which
+		 * is normally VFIO case and gpa->hpa translation does not
+		 * depend on hpt.
+		 */
+		struct mm_iommu_table_group_mem_t *mem;
 
-	rmap = (void *) vmalloc_to_phys(rmap);
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+			return H_TOO_HARD;
 
-	/*
-	 * Synchronize with the MMU notifier callbacks in
-	 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
-	 * While we have the rmap lock, code running on other CPUs
-	 * cannot finish unmapping the host real page that backs
-	 * this guest real page, so we are OK to access the host
-	 * real page.
-	 */
-	lock_rmap(rmap);
-	if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
-		ret = H_TOO_HARD;
-		goto unlock_exit;
+		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
+		if (mem)
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+	}
+
+	if (!prereg) {
+		/*
+		 * This is usually a case of a guest with emulated devices only
+		 * when TCE list is not in preregistered memory.
+		 * We do not require memory to be preregistered in this case
+		 * so lock rmap and do __find_linux_pte_or_hugepte().
+		 */
+		if (kvmppc_gpa_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+			return H_TOO_HARD;
+
+		rmap = (void *) vmalloc_to_phys(rmap);
+		if (WARN_ON_ONCE_RM(!rmap))
+			return H_HARDWARE;
+
+		/*
+		 * Synchronize with the MMU notifier callbacks in
+		 * book3s_64_mmu_hv.c (kvm_unmap_hva_hv etc.).
+		 * While we have the rmap lock, code running on other CPUs
+		 * cannot finish unmapping the host real page that backs
+		 * this guest real page, so we are OK to access the host
+		 * real page.
+		 */
+		lock_rmap(rmap);
+		if (kvmppc_rm_ua_to_hpa(vcpu, ua, &tces)) {
+			ret = H_TOO_HARD;
+			goto unlock_exit;
+		}
 	}
 
 	for (i = 0; i < npages; ++i) {
@@ -285,11 +452,33 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		if (ret != H_SUCCESS)
 			goto unlock_exit;
 
+		ua = 0;
+		if (kvmppc_gpa_to_ua(vcpu->kvm,
+				tce & ~(TCE_PCI_READ | TCE_PCI_WRITE),
+				&ua, NULL))
+			return H_PARAMETER;
+
+		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+			ret = kvmppc_rm_tce_iommu_map(vcpu->kvm,
+					stit->tbl, entry + i, ua,
+					iommu_tce_direction(tce));
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				goto unlock_exit;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+
 		kvmppc_tce_put(stt, entry + i, tce);
 	}
 
 unlock_exit:
-	unlock_rmap(rmap);
+	if (rmap)
+		unlock_rmap(rmap);
 
 	return ret;
 }
@@ -300,8 +489,9 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_spapr_tce_table *stt;
 	long i, ret;
+	struct kvmppc_spapr_tce_iommu_table *stit;
 
-	stt = kvmppc_find_table(vcpu, liobn);
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
@@ -313,6 +503,24 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (tce_value & (TCE_PCI_WRITE | TCE_PCI_READ))
 		return H_PARAMETER;
 
+	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
+		unsigned long entry = ioba >> stit->tbl->it_page_shift;
+
+		for (i = 0; i < npages; ++i) {
+			ret = kvmppc_rm_tce_iommu_unmap(vcpu->kvm,
+					stit->tbl, entry + i);
+
+			if (ret == H_SUCCESS)
+				continue;
+
+			if (ret == H_TOO_HARD)
+				return ret;
+
+			WARN_ON_ONCE_RM(1);
+			kvmppc_rm_clear_tce(stit->tbl, entry);
+		}
+	}
+
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
 		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
@@ -322,12 +530,13 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		      unsigned long ioba)
 {
-	struct kvmppc_spapr_tce_table *stt = kvmppc_find_table(vcpu, liobn);
+	struct kvmppc_spapr_tce_table *stt;
 	long ret;
 	unsigned long idx;
 	struct page *page;
 	u64 *tbl;
 
+	stt = kvmppc_find_table(vcpu->kvm, liobn);
 	if (!stt)
 		return H_TOO_HARD;
 
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 8359752b3efc..68d68983948e 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -503,10 +503,18 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		break;
 unprivileged:
 	default:
-		printk(KERN_INFO "KVM: invalid SPR write: %d\n", sprn);
-#ifndef DEBUG_SPR
-		emulated = EMULATE_FAIL;
-#endif
+		pr_info_ratelimited("KVM: invalid SPR write: %d\n", sprn);
+		if (sprn & 0x10) {
+			if (kvmppc_get_msr(vcpu) & MSR_PR) {
+				kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+				emulated = EMULATE_AGAIN;
+			}
+		} else {
+			if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0) {
+				kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+				emulated = EMULATE_AGAIN;
+			}
+		}
 		break;
 	}
 
@@ -648,10 +656,20 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val
 		break;
 	default:
 unprivileged:
-		printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);
-#ifndef DEBUG_SPR
-		emulated = EMULATE_FAIL;
-#endif
+		pr_info_ratelimited("KVM: invalid SPR read: %d\n", sprn);
+		if (sprn & 0x10) {
+			if (kvmppc_get_msr(vcpu) & MSR_PR) {
+				kvmppc_core_queue_program(vcpu, SRR1_PROGPRIV);
+				emulated = EMULATE_AGAIN;
+			}
+		} else {
+			if ((kvmppc_get_msr(vcpu) & MSR_PR) || sprn == 0 ||
+			    sprn == 4 || sprn == 5 || sprn == 6) {
+				kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+				emulated = EMULATE_AGAIN;
+			}
+		}
+
 		break;
 	}
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index fadb75abfe37..549dd6070dee 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3624,11 +3624,9 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 		return -EIO;
 
 	mutex_lock(&kvm->lock);
+	if (!kvm->arch.pimap)
+		goto unlock;
 
-	if (kvm->arch.pimap == NULL) {
-		mutex_unlock(&kvm->lock);
-		return 0;
-	}
 	pimap = kvm->arch.pimap;
 
 	for (i = 0; i < pimap->n_mapped; i++) {
@@ -3650,7 +3648,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
 	 * We don't free this structure even when the count goes to
 	 * zero. The structure is freed when we destroy the VM.<