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
  ...

22 files changed, 1537 insertions, 167 deletions

diff --git a/arch/powerpc/include/asm/disassemble.h b/arch/powerpc/include/asm/disassemble.h
index 4852e849128b..c0a55050f70f 100644
--- a/arch/powerpc/include/asm/disassemble.h
+++ b/arch/powerpc/include/asm/disassemble.h
@@ -87,6 +87,11 @@ static inline unsigned int get_oc(u32 inst)
 	return (inst >> 11) & 0x7fff;
 }
 
+static inline unsigned int get_tx_or_sx(u32 inst)
+{
+	return (inst) & 0x1;
+}
+
 #define IS_XFORM(inst)	(get_op(inst)  == 31)
 #define IS_DSFORM(inst)	(get_op(inst) >= 56)
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index d96142572e6d..8a8ce220d7d0 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -296,11 +296,21 @@ static inline void iommu_restore(void)
 #endif
 
 /* The API to support IOMMU operations for VFIO */
-extern int iommu_tce_clear_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce_value,
-		unsigned long npages);
-extern int iommu_tce_put_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce);
+extern int iommu_tce_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages);
+extern int iommu_tce_check_gpa(unsigned long page_shift,
+		unsigned long gpa);
+
+#define iommu_tce_clear_param_check(tbl, ioba, tce_value, npages) \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), (npages)) || (tce_value))
+#define iommu_tce_put_param_check(tbl, ioba, gpa)                 \
+		(iommu_tce_check_ioba((tbl)->it_page_shift,       \
+				(tbl)->it_offset, (tbl)->it_size, \
+				(ioba), 1) ||                     \
+		iommu_tce_check_gpa((tbl)->it_page_shift, (gpa)))
 
 extern void iommu_flush_tce(struct iommu_table *tbl);
 extern int iommu_take_ownership(struct iommu_table *tbl);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 7bba8f415627..77c60826d145 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -45,9 +45,6 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#ifdef CONFIG_KVM_MMIO
-#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
-#endif
 #define KVM_HALT_POLL_NS_DEFAULT 10000	/* 10 us */
 
 /* These values are internal and can be increased later */
@@ -191,6 +188,13 @@ struct kvmppc_pginfo {
 	atomic_t refcnt;
 };
 
+struct kvmppc_spapr_tce_iommu_table {
+	struct rcu_head rcu;
+	struct list_head next;
+	struct iommu_table *tbl;
+	struct kref kref;
+};
+
 struct kvmppc_spapr_tce_table {
 	struct list_head list;
 	struct kvm *kvm;
@@ -199,6 +203,7 @@ struct kvmppc_spapr_tce_table {
 	u32 page_shift;
 	u64 offset;		/* in pages */
 	u64 size;		/* window size in pages */
+	struct list_head iommu_tables;
 	struct page *pages[0];
 };
 
@@ -345,6 +350,7 @@ struct kvmppc_pte {
 	bool may_read		: 1;
 	bool may_write		: 1;
 	bool may_execute	: 1;
+	unsigned long wimg;
 	u8 page_size;		/* MMU_PAGE_xxx */
 };
 
@@ -441,6 +447,11 @@ struct mmio_hpte_cache {
 	unsigned int index;
 };
 
+#define KVMPPC_VSX_COPY_NONE		0
+#define KVMPPC_VSX_COPY_WORD		1
+#define KVMPPC_VSX_COPY_DWORD		2
+#define KVMPPC_VSX_COPY_DWORD_LOAD_DUMP	3
+
 struct openpic;
 
 struct kvm_vcpu_arch {
@@ -644,6 +655,21 @@ struct kvm_vcpu_arch {
 	u8 io_gpr; /* GPR used as IO source/target */
 	u8 mmio_host_swabbed;
 	u8 mmio_sign_extend;
+	/* conversion between single and double precision */
+	u8 mmio_sp64_extend;
+	/*
+	 * Number of simulations for vsx.
+	 * If we use 2*8bytes to simulate 1*16bytes,
+	 * then the number should be 2 and
+	 * mmio_vsx_copy_type=KVMPPC_VSX_COPY_DWORD.
+	 * If we use 4*4bytes to simulate 1*16bytes,
+	 * the number should be 4 and
+	 * mmio_vsx_copy_type=KVMPPC_VSX_COPY_WORD.
+	 */
+	u8 mmio_vsx_copy_nums;
+	u8 mmio_vsx_offset;
+	u8 mmio_vsx_copy_type;
+	u8 mmio_vsx_tx_sx_enabled;
 	u8 osi_needed;
 	u8 osi_enabled;
 	u8 papr_enabled;
@@ -732,6 +758,8 @@ struct kvm_vcpu_arch {
 };
 
 #define VCPU_FPR(vcpu, i)	(vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
+#define VCPU_VSX_FPR(vcpu, i, j)	((vcpu)->arch.fp.fpr[i][j])
+#define VCPU_VSX_VR(vcpu, i)		((vcpu)->arch.vr.vr[i])
 
 /* Values for vcpu->arch.state */
 #define KVMPPC_VCPU_NOTREADY		0
@@ -745,6 +773,7 @@ struct kvm_vcpu_arch {
 #define KVM_MMIO_REG_FPR	0x0020
 #define KVM_MMIO_REG_QPR	0x0040
 #define KVM_MMIO_REG_FQPR	0x0060
+#define KVM_MMIO_REG_VSX	0x0080
 
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c3877992eff9..76e940a3c145 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -78,9 +78,15 @@ extern int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
 extern int kvmppc_handle_loads(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                unsigned int rt, unsigned int bytes,
 			       int is_default_endian);
+extern int kvmppc_handle_vsx_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				unsigned int rt, unsigned int bytes,
+			int is_default_endian, int mmio_sign_extend);
 extern int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			       u64 val, unsigned int bytes,
 			       int is_default_endian);
+extern int kvmppc_handle_vsx_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				int rs, unsigned int bytes,
+				int is_default_endian);
 
 extern int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
 				 enum instruction_type type, u32 *inst);
@@ -132,6 +138,9 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
+extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_vsx_unavail(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
@@ -164,13 +173,19 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm_vcpu *vcpu,
 			struct kvm_memory_slot *memslot, unsigned long porder);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
+		struct iommu_group *grp);
+extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm,
+		struct iommu_group *grp);
 
 extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce_64 *args);
 extern struct kvmppc_spapr_tce_table *kvmppc_find_table(
-		struct kvm_vcpu *vcpu, unsigned long liobn);
-extern long kvmppc_ioba_validate(struct kvmppc_spapr_tce_table *stt,
-		unsigned long ioba, unsigned long npages);
+		struct kvm *kvm, unsigned long liobn);
+#define kvmppc_ioba_validate(stt, ioba, npages)                         \
+		(iommu_tce_check_ioba((stt)->page_shift, (stt)->offset, \
+				(stt)->size, (ioba), (npages)) ?        \
+				H_PARAMETER : H_SUCCESS)
 extern long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *tt,
 		unsigned long tce);
 extern long kvmppc_gpa_to_ua(struct kvm *kvm, unsigned long gpa,
@@ -240,6 +255,7 @@ union kvmppc_one_reg {
 	u64	dval;
 	vector128 vval;
 	u64	vsxval[2];
+	u32	vsx32val[4];
 	struct {
 		u64	addr;
 		u64	length;
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 142d78d645f4..3a8d278e7421 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -86,32 +86,79 @@
 #define OP_TRAP_64 2
 
 #define OP_31_XOP_TRAP      4
+#define OP_31_XOP_LDX       21
 #define OP_31_XOP_LWZX      23
+#define OP_31_XOP_LDUX      53
 #define OP_31_XOP_DCBST     54
 #define OP_31_XOP_LWZUX     55
 #define OP_31_XOP_TRAP_64   68
 #define OP_31_XOP_DCBF      86
 #define OP_31_XOP_LBZX      87
+#define OP_31_XOP_STDX      149
 #define OP_31_XOP_STWX      151
+#define OP_31_XOP_STDUX     181
+#define OP_31_XOP_STWUX     183
 #define OP_31_XOP_STBX      215
 #define OP_31_XOP_LBZUX     119
 #define OP_31_XOP_STBUX     247
 #define OP_31_XOP_LHZX      279
 #define OP_31_XOP_LHZUX     311
 #define OP_31_XOP_MFSPR     339
+#define OP_31_XOP_LWAX      341
 #define OP_31_XOP_LHAX      343
+#define OP_31_XOP_LWAUX     373
 #define OP_31_XOP_LHAUX     375
 #define OP_31_XOP_STHX      407
 #define OP_31_XOP_STHUX     439
 #define OP_31_XOP_MTSPR     467
 #define OP_31_XOP_DCBI      470
+#define OP_31_XOP_LDBRX     532
 #define OP_31_XOP_LWBRX     534
 #define OP_31_XOP_TLBSYNC   566
+#define OP_31_XOP_STDBRX    660
 #define OP_31_XOP_STWBRX    662
+#define OP_31_XOP_STFSX	    663
+#define OP_31_XOP_STFSUX    695
+#define OP_31_XOP_STFDX     727
+#define OP_31_XOP_STFDUX    759
 #define OP_31_XOP_LHBRX     790
+#define OP_31_XOP_LFIWAX    855
+#define OP_31_XOP_LFIWZX    887
 #define OP_31_XOP_STHBRX    918
+#define OP_31_XOP_STFIWX    983
+
+/* VSX Scalar Load Instructions */
+#define OP_31_XOP_LXSDX         588
+#define OP_31_XOP_LXSSPX        524
+#define OP_31_XOP_LXSIWAX       76
+#define OP_31_XOP_LXSIWZX       12
+
+/* VSX Scalar Store Instructions */
+#define OP_31_XOP_STXSDX        716
+#define OP_31_XOP_STXSSPX       652
+#define OP_31_XOP_STXSIWX       140
+
+/* VSX Vector Load Instructions */
+#define OP_31_XOP_LXVD2X        844
+#define OP_31_XOP_LXVW4X        780
+
+/* VSX Vector Load and Splat Instruction */
+#define OP_31_XOP_LXVDSX        332
+
+/* VSX Vector Store Instructions */
+#define OP_31_XOP_STXVD2X       972
+#define OP_31_XOP_STXVW4X       908
+
+#define OP_31_XOP_LFSX          535
+#define OP_31_XOP_LFSUX         567
+#define OP_31_XOP_LFDX          599
+#define OP_31_XOP_LFDUX		631
 
 #define OP_LWZ  32
+#define OP_STFS 52
+#define OP_STFSU 53
+#define OP_STFD 54
+#define OP_STFDU 55
 #define OP_LD   58
 #define OP_LWZU 33
 #define OP_LBZ  34
@@ -127,6 +174,17 @@
 #define OP_LHAU 43
 #define OP_STH  44
 #define OP_STHU 45
+#define OP_LMW  46
+#define OP_STMW 47
+#define OP_LFS  48
+#define OP_LFSU 49
+#define OP_LFD  50
+#define OP_LFDU 51
+#define OP_STFS 52
+#define OP_STFSU 53
+#define OP_STFD  54
+#define OP_STFDU 55
+#define OP_LQ    56
 
 /* sorted alphabetically */
 #define PPC_INST_BHRBE			0x7c00025c
diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h
index 4edbe4bb0e8b..07fbeb927834 100644
--- a/arch/powerpc/include/uapi/asm/kvm.h
+++ b/arch/powerpc/include/uapi/asm/kvm.h
@@ -29,6 +29,9 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_GUEST_DEBUG
 
+/* Not always available, but if it is, this is the correct offset.  */
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 struct kvm_regs {
 	__u64 pc;
 	__u64 cr;
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 5a3231fedf08..f2b724cd9e64 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -963,47 +963,36 @@ void iommu_flush_tce(struct iommu_table *tbl)
 }
 EXPORT_SYMBOL_GPL(iommu_flush_tce);
 
-int iommu_tce_clear_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce_value,
-		unsigned long npages)
+int iommu_tce_check_ioba(unsigned long page_shift,
+		unsigned long offset, unsigned long size,
+		unsigned long ioba, unsigned long npages)
 {
-	/* tbl->it_ops->clear() does not support any value but 0 */
-	if (tce_value)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
+	if (ioba & mask)
 		return -EINVAL;
 
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
+	ioba >>= page_shift;
+	if (ioba < offset)
 		return -EINVAL;
 
-	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+	if ((ioba + 1) > (offset + size))
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_ioba);
 
-int iommu_tce_put_param_check(struct iommu_table *tbl,
-		unsigned long ioba, unsigned long tce)
+int iommu_tce_check_gpa(unsigned long page_shift, unsigned long gpa)
 {
-	if (tce & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	if (ioba & ~IOMMU_PAGE_MASK(tbl))
-		return -EINVAL;
-
-	ioba >>= tbl->it_page_shift;
-	if (ioba < tbl->it_offset)
-		return -EINVAL;
+	unsigned long mask = (1UL << page_shift) - 1;
 
-	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+	if (gpa & mask)
 		return -EINVAL;
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+EXPORT_SYMBOL_GPL(iommu_tce_check_gpa);
 
 long iommu_tce_xchg(struct iommu_table *tbl, unsigned long entry,
 		unsigned long *hpa, enum dma_data_direction *direction)
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))