Merge tag 'kvm-3.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "KVM updates for the 3.9 merge window, including x86 real mode
  emulation fixes, stronger memory slot interface restrictions, mmu_lock
  spinlock hold time reduction, improved handling of large page faults
  on shadow, initial APICv HW acceleration support, s390 channel IO
  based virtio, amongst others"

* tag 'kvm-3.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (143 commits)
  Revert "KVM: MMU: lazily drop large spte"
  x86: pvclock kvm: align allocation size to page size
  KVM: nVMX: Remove redundant get_vmcs12 from nested_vmx_exit_handled_msr
  x86 emulator: fix parity calculation for AAD instruction
  KVM: PPC: BookE: Handle alignment interrupts
  booke: Added DBCR4 SPR number
  KVM: PPC: booke: Allow multiple exception types
  KVM: PPC: booke: use vcpu reference from thread_struct
  KVM: Remove user_alloc from struct kvm_memory_slot
  KVM: VMX: disable apicv by default
  KVM: s390: Fix handling of iscs.
  KVM: MMU: cleanup __direct_map
  KVM: MMU: remove pt_access in mmu_set_spte
  KVM: MMU: cleanup mapping-level
  KVM: MMU: lazily drop large spte
  KVM: VMX: cleanup vmx_set_cr0().
  KVM: VMX: add missing exit names to VMX_EXIT_REASONS array
  KVM: VMX: disable SMEP feature when guest is in non-paging mode
  KVM: Remove duplicate text in api.txt
  Revert "KVM: MMU: split kvm_mmu_free_page"
  ...

Documentation/virtual/kvm/api.txt

@@ -219,19 +219,6 @@ allocation of vcpu ids.  For example, if userspace wants
 single-threaded guest vcpus, it should make all vcpu ids be a multiple
 of the number of vcpus per vcore.
 
-On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
-threads in one or more virtual CPU cores.  (This is because the
-hardware requires all the hardware threads in a CPU core to be in the
-same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
-of vcpus per virtual core (vcore).  The vcore id is obtained by
-dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
-given vcore will always be in the same physical core as each other
-(though that might be a different physical core from time to time).
-Userspace can control the threading (SMT) mode of the guest by its
-allocation of vcpu ids.  For example, if userspace wants
-single-threaded guest vcpus, it should make all vcpu ids be a multiple
-of the number of vcpus per vcore.
-
 For virtual cpus that have been created with S390 user controlled virtual
 machines, the resulting vcpu fd can be memory mapped at page offset
 KVM_S390_SIE_PAGE_OFFSET in order to obtain a memory map of the virtual
@@ -345,7 +332,7 @@ struct kvm_sregs {
 	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
 };
 
-/* ppc -- see arch/powerpc/include/asm/kvm.h */
+/* ppc -- see arch/powerpc/include/uapi/asm/kvm.h */
 
 interrupt_bitmap is a bitmap of pending external interrupts.  At most
 one bit may be set.  This interrupt has been acknowledged by the APIC
@@ -892,12 +879,12 @@ It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
 be identical.  This allows large pages in the guest to be backed by large
 pages in the host.
 
-The flags field supports two flag, KVM_MEM_LOG_DIRTY_PAGES, which instructs
-kvm to keep track of writes to memory within the slot.  See KVM_GET_DIRTY_LOG
-ioctl.  The KVM_CAP_READONLY_MEM capability indicates the availability of the
-KVM_MEM_READONLY flag.  When this flag is set for a memory region, KVM only
-allows read accesses.  Writes will be posted to userspace as KVM_EXIT_MMIO
-exits.
+The flags field supports two flags: KVM_MEM_LOG_DIRTY_PAGES and
+KVM_MEM_READONLY.  The former can be set to instruct KVM to keep track of
+writes to memory within the slot.  See KVM_GET_DIRTY_LOG ioctl to know how to
+use it.  The latter can be set, if KVM_CAP_READONLY_MEM capability allows it,
+to make a new slot read-only.  In this case, writes to this memory will be
+posted to userspace as KVM_EXIT_MMIO exits.
 
 When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
 the memory region are automatically reflected into the guest.  For example, an
@@ -931,7 +918,7 @@ documentation when it pops into existence).
 4.37 KVM_ENABLE_CAP
 
 Capability: KVM_CAP_ENABLE_CAP
-Architectures: ppc
+Architectures: ppc, s390
 Type: vcpu ioctl
 Parameters: struct kvm_enable_cap (in)
 Returns: 0 on success; -1 on error
@@ -1792,6 +1779,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_VPA_SLB   | 128
   PPC   | KVM_REG_PPC_VPA_DTL   | 128
   PPC   | KVM_REG_PPC_EPCR	| 32
+  PPC   | KVM_REG_PPC_EPR	| 32
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
@@ -2108,6 +2096,14 @@ KVM_S390_INT_VIRTIO (vm) - virtio external interrupt; external interrupt
 KVM_S390_INT_SERVICE (vm) - sclp external interrupt; sclp parameter in parm
 KVM_S390_INT_EMERGENCY (vcpu) - sigp emergency; source cpu in parm
 KVM_S390_INT_EXTERNAL_CALL (vcpu) - sigp external call; source cpu in parm
+KVM_S390_INT_IO(ai,cssid,ssid,schid) (vm) - compound value to indicate an
+    I/O interrupt (ai - adapter interrupt; cssid,ssid,schid - subchannel);
+    I/O interruption parameters in parm (subchannel) and parm64 (intparm,
+    interruption subclass)
+KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
+                           machine check interrupt code in parm64 (note that
+                           machine checks needing further payload are not
+                           supported by this ioctl)
 
 Note that the vcpu ioctl is asynchronous to vcpu execution.
 
@@ -2359,8 +2355,8 @@ executed a memory-mapped I/O instruction which could not be satisfied
 by kvm.  The 'data' member contains the written data if 'is_write' is
 true, and should be filled by application code otherwise.
 
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR
-      and KVM_EXIT_PAPR the corresponding
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR,
+      KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding
 operations are complete (and guest state is consistent) only after userspace
 has re-entered the kernel with KVM_RUN.  The kernel side will first finish
 incomplete operations and then check for pending signals.  Userspace
@@ -2463,6 +2459,41 @@ The possible hypercalls are defined in the Power Architecture Platform
 Requirements (PAPR) document available from www.power.org (free
 developer registration required to access it).
 
+		/* KVM_EXIT_S390_TSCH */
+		struct {
+			__u16 subchannel_id;
+			__u16 subchannel_nr;
+			__u32 io_int_parm;
+			__u32 io_int_word;
+			__u32 ipb;
+			__u8 dequeued;
+		} s390_tsch;
+
+s390 specific. This exit occurs when KVM_CAP_S390_CSS_SUPPORT has been enabled
+and TEST SUBCHANNEL was intercepted. If dequeued is set, a pending I/O
+interrupt for the target subchannel has been dequeued and subchannel_id,
+subchannel_nr, io_int_parm and io_int_word contain the parameters for that
+interrupt. ipb is needed for instruction parameter decoding.
+
+		/* KVM_EXIT_EPR */
+		struct {
+			__u32 epr;
+		} epr;
+
+On FSL BookE PowerPC chips, the interrupt controller has a fast patch
+interrupt acknowledge path to the core. When the core successfully
+delivers an interrupt, it automatically populates the EPR register with
+the interrupt vector number and acknowledges the interrupt inside
+the interrupt controller.
+
+In case the interrupt controller lives in user space, we need to do
+the interrupt acknowledge cycle through it to fetch the next to be
+delivered interrupt vector using this exit.
+
+It gets triggered whenever both KVM_CAP_PPC_EPR are enabled and an
+external interrupt has just been delivered into the guest. User space
+should put the acknowledged interrupt vector into the 'epr' field.
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -2584,3 +2615,34 @@ For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
    where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
  - The tsize field of mas1 shall be set to 4K on TLB0, even though the
    hardware ignores this value for TLB0.
+
+6.4 KVM_CAP_S390_CSS_SUPPORT
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success; -1 on error
+
+This capability enables support for handling of channel I/O instructions.
+
+TEST PENDING INTERRUPTION and the interrupt portion of TEST SUBCHANNEL are
+handled in-kernel, while the other I/O instructions are passed to userspace.
+
+When this capability is enabled, KVM_EXIT_S390_TSCH will occur on TEST
+SUBCHANNEL intercepts.
+
+6.5 KVM_CAP_PPC_EPR
+
+Architectures: ppc
+Parameters: args[0] defines whether the proxy facility is active
+Returns: 0 on success; -1 on error
+
+This capability enables or disables the delivery of interrupts through the
+external proxy facility.
+
+When enabled (args[0] != 0), every time the guest gets an external interrupt
+delivered, it automatically exits into user space with a KVM_EXIT_EPR exit
+to receive the topmost interrupt vector.
+
+When disabled (args[0] == 0), behavior is as if this facility is unsupported.
+
+When this capability is enabled, KVM_EXIT_EPR can occur.

Documentation/virtual/kvm/mmu.txt

@@ -187,13 +187,6 @@ Shadow pages contain the following information:
     perform a reverse map from a pte to a gfn. When role.direct is set, any
     element of this array can be calculated from the gfn field when used, in
     this case, the array of gfns is not allocated. See role.direct and gfn.
-  slot_bitmap:
-    A bitmap containing one bit per memory slot.  If the page contains a pte
-    mapping a page from memory slot n, then bit n of slot_bitmap will be set
-    (if a page is aliased among several slots, then it is not guaranteed that
-    all slots will be marked).
-    Used during dirty logging to avoid scanning a shadow page if none if its
-    pages need tracking.
   root_count:
     A counter keeping track of how many hardware registers (guest cr3 or
     pdptrs) are now pointing at the page.  While this counter is nonzero, the

arch/ia64/include/asm/kvm_host.h

@@ -23,9 +23,7 @@
 #ifndef __ASM_KVM_HOST_H
 #define __ASM_KVM_HOST_H
 
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 32
 
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 

arch/ia64/kvm/kvm-ia64.c

@@ -955,7 +955,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 					kvm_mem.guest_phys_addr;
 		kvm_userspace_mem.memory_size = kvm_mem.memory_size;
 		r = kvm_vm_ioctl_set_memory_region(kvm,
-					&kvm_userspace_mem, 0);
+					&kvm_userspace_mem, false);
 		if (r)
 			goto out;
 		break;
@@ -1580,7 +1580,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
 		struct kvm_userspace_memory_region *mem,
-		int user_alloc)
+		bool user_alloc)
 {
 	unsigned long i;
 	unsigned long pfn;
@@ -1611,7 +1611,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 		struct kvm_userspace_memory_region *mem,
 		struct kvm_memory_slot old,
-		int user_alloc)
+		bool user_alloc)
 {
 	return;
 }
@@ -1834,7 +1834,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);

arch/ia64/kvm/lapic.h

@@ -27,4 +27,10 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
 #define kvm_apic_present(x) (true)
 #define kvm_lapic_enabled(x) (true)
 
+static inline bool kvm_apic_vid_enabled(void)
+{
+	/* IA64 has no apicv supporting, do nothing here */
+	return false;
+}
+
 #endif

arch/powerpc/include/asm/kvm_host.h

@@ -37,10 +37,8 @@
 
 #define KVM_MAX_VCPUS		NR_CPUS
 #define KVM_MAX_VCORES		NR_CPUS
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS 32
+#define KVM_MEM_SLOTS_NUM KVM_USER_MEM_SLOTS
 
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
@@ -523,6 +521,8 @@ struct kvm_vcpu_arch {
 	u8 sane;
 	u8 cpu_type;
 	u8 hcall_needed;
+	u8 epr_enabled;
+	u8 epr_needed;
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 

arch/powerpc/include/asm/kvm_ppc.h

@@ -44,12 +44,11 @@ enum emulation_result {
 	EMULATE_DO_DCR,       /* kvm_run filled with DCR request */
 	EMULATE_FAIL,         /* can't emulate this instruction */
 	EMULATE_AGAIN,        /* something went wrong. go again */
+	EMULATE_DO_PAPR,      /* kvm_run filled with PAPR request */
 };
 
 extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
-extern char kvmppc_handlers_start[];
-extern unsigned long kvmppc_handler_len;
 extern void kvmppc_handler_highmem(void);
 
 extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu);
@@ -263,6 +262,15 @@ static inline void kvm_linear_init(void)
 {}
 #endif
 
+static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GEPR, epr);
+#elif defined(CONFIG_BOOKE)
+	vcpu->arch.epr = epr;
+#endif
+}
+
 int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
 			      struct kvm_config_tlb *cfg);
 int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,

arch/powerpc/include/asm/reg.h

@@ -956,8 +956,6 @@
 #define SPRN_SPRG_RSCRATCH_DBG	SPRN_SPRG9
 #define SPRN_SPRG_WSCRATCH_DBG	SPRN_SPRG9
 #endif
-#define SPRN_SPRG_RVCPU		SPRN_SPRG1
-#define SPRN_SPRG_WVCPU		SPRN_SPRG1
 #endif
 
 #ifdef CONFIG_8xx

arch/powerpc/include/asm/reg_booke.h

@@ -56,6 +56,7 @@
 #define SPRN_SPRG7W	0x117	/* Special Purpose Register General 7 Write */
 #define SPRN_EPCR	0x133	/* Embedded Processor Control Register */
 #define SPRN_DBCR2	0x136	/* Debug Control Register 2 */
+#define SPRN_DBCR4	0x233	/* Debug Control Register 4 */
 #define SPRN_MSRP	0x137	/* MSR Protect Register */
 #define SPRN_IAC3	0x13A	/* Instruction Address Compare 3 */
 #define SPRN_IAC4	0x13B	/* Instruction Address Compare 4 */

arch/powerpc/include/uapi/asm/kvm.h

@@ -114,7 +114,10 @@ struct kvm_regs {
 /* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
 #define KVM_SREGS_E_SPE			(1 << 9)
 
-/* External Proxy (EXP) -- EPR */
+/*
+ * DEPRECATED! USE ONE_REG FOR THIS ONE!
+ * External Proxy (EXP) -- EPR
+ */
 #define KVM_SREGS_EXP			(1 << 10)
 
 /* External PID (E.PD) -- EPSC/EPLC */
@@ -412,5 +415,6 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_VPA_DTL	(KVM_REG_PPC | KVM_REG_SIZE_U128 | 0x84)
 
 #define KVM_REG_PPC_EPCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x85)
+#define KVM_REG_PPC_EPR		(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x86)
 
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kernel/asm-offsets.c

@@ -118,7 +118,7 @@ int main(void)
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
 #endif
-#ifdef CONFIG_KVM_BOOKE_HV
+#if defined(CONFIG_KVM) && defined(CONFIG_BOOKE)
 	DEFINE(THREAD_KVM_VCPU, offsetof(struct thread_struct, kvm_vcpu));
 #endif
 

arch/powerpc/kvm/Makefile

@@ -10,7 +10,8 @@ common-objs-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o \
 						eventfd.o)
 
 CFLAGS_44x_tlb.o  := -I.
-CFLAGS_e500_tlb.o := -I.
+CFLAGS_e500_mmu.o := -I.
+CFLAGS_e500_mmu_host.o := -I.
 CFLAGS_emulate.o  := -I.
 
 common-objs-y += powerpc.o emulate.o
@@ -35,7 +36,8 @@ kvm-e500-objs := \
 	booke_emulate.o \
 	booke_interrupts.o \
 	e500.o \
-	e500_tlb.o \
+	e500_mmu.o \
+	e500_mmu_host.o \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500V2) := $(kvm-e500-objs)
 
@@ -45,7 +47,8 @@ kvm-e500mc-objs := \
 	booke_emulate.o \
 	bookehv_interrupts.o \
 	e500mc.o \
-	e500_tlb.o \
+	e500_mmu.o \
+	e500_mmu_host.o \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500MC) := $(kvm-e500mc-objs)
 

arch/powerpc/kvm/book3s_emulate.c

@@ -34,6 +34,8 @@
 #define OP_31_XOP_MTSRIN	242
 #define OP_31_XOP_TLBIEL	274
 #define OP_31_XOP_TLBIE		306
+/* Opcode is officially reserved, reuse it as sc 1 when sc 1 doesn't trap */
+#define OP_31_XOP_FAKE_SC1	308
 #define OP_31_XOP_SLBMTE	402
 #define OP_31_XOP_SLBIE		434
 #define OP_31_XOP_SLBIA		498
@@ -170,6 +172,32 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
+#ifdef CONFIG_KVM_BOOK3S_64_PR
+		case OP_31_XOP_FAKE_SC1:
+		{
+			/* SC 1 papr hypercalls */
+			ulong cmd = kvmppc_get_gpr(vcpu, 3);
+			int i;
+
+		        if ((vcpu->arch.shared->msr & MSR_PR) ||
+			    !vcpu->arch.papr_enabled) {
+				emulated = EMULATE_FAIL;
+				break;
+			}
+
+			if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE)
+				break;
+
+			run->papr_hcall.nr = cmd;
+			for (i = 0; i < 9; ++i) {
+				ulong gpr = kvmppc_get_gpr(vcpu, 4 + i);
+				run->papr_hcall.args[i] = gpr;
+			}
+
+			emulated = EMULATE_DO_PAPR;
+			break;
+		}
+#endif
 		case OP_31_XOP_EIOIO:
 			break;
 		case OP_31_XOP_SLBMTE:
@@ -427,6 +455,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
+	case SPRN_MSSSR0:
 		break;
 unprivileged:
 	default:
@@ -523,6 +552,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_PMC3_GEKKO:
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
+	case SPRN_MSSSR0:
 		*spr_val = 0;
 		break;
 	default:

arch/powerpc/kvm/book3s_hv.c

@@ -1549,7 +1549,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);

arch/powerpc/kvm/book3s_pr.c

@@ -762,6 +762,11 @@ program_interrupt:
 			run->exit_reason = KVM_EXIT_MMIO;
 			r = RESUME_HOST_NV;
 			break;
+		case EMULATE_DO_PAPR:
+			run->exit_reason = KVM_EXIT_PAPR_HCALL;
+			vcpu->arch.hcall_needed = 1;
+			r = RESUME_HOST_NV;
+			break;
 		default:
 			BUG();
 		}

arch/powerpc/kvm/booke.c

@@ -182,6 +182,14 @@ static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu,
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
 }
 
+static void kvmppc_core_queue_alignment(struct kvm_vcpu *vcpu, ulong dear_flags,
+					ulong esr_flags)
+{
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALIGNMENT);
+}
+
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
 {
 	vcpu->arch.queued_esr = esr_flags;
@@ -300,13 +308,22 @@ static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
 #endif
 }
 
+static unsigned long get_guest_epr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GEPR);
+#else
+	return vcpu->arch.epr;
+#endif
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
 {
 	int allowed = 0;
 	ulong msr_mask = 0;
-	bool update_esr = false, update_dear = false;
+	bool update_esr = false, update_dear = false, update_epr = false;
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
@@ -330,9 +347,13 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		keep_irq = true;
 	}
 
+	if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled)
+		update_epr = true;
+
 	switch (priority) {
 	case BOOKE_IRQPRIO_DTLB_MISS:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
+	case BOOKE_IRQPRIO_ALIGNMENT:
 		update_dear = true;
 		/* fall through */
 	case BOOKE_IRQPRIO_INST_STORAGE:
@@ -346,7 +367,6 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_SPE_FP_DATA:
 	case BOOKE_IRQPRIO_SPE_FP_ROUND:
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
-	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
 		msr_mask = MSR_CE | MSR_ME | MSR_DE;
 		int_class = INT_CLASS_NONCRIT;
@@ -408,6 +428,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
 			set_guest_dear(vcpu, vcpu->arch.queued_dear);
+		if (update_epr == true)
+			kvm_make_request(KVM_REQ_EPR_EXIT, vcpu);
 
 		new_msr &= msr_mask;
 #if defined(CONFIG_64BIT)
@@ -581,6 +603,11 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 
 	kvmppc_core_check_exceptions(vcpu);
 
+	if (vcpu->requests) {
+		/* Exception delivery raised request; start over */
+		return 1;
+	}
+
 	if (vcpu->arch.shared->msr & MSR_WE) {
 		local_irq_enable();
 		kvm_vcpu_block(vcpu);
@@ -610,6 +637,13 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu)
 		r = 0;
 	}
 
+	if (kvm_check_request(KVM_REQ_EPR_EXIT, vcpu)) {
+		vcpu->run->epr.epr = 0;
+		vcpu->arch.epr_needed = true;
+		vcpu->run->exit_reason = KVM_EXIT_EPR;
+		r = 0;
+	}
+
 	return r;
 }
 
@@ -945,6 +979,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_ALIGNMENT:
+		kvmppc_core_queue_alignment(vcpu, vcpu->arch.fault_dear,
+		                            vcpu->arch.fault_esr);
+		r = RESUME_GUEST;
+		break;
+
 #ifdef CONFIG_KVM_BOOKE_HV
 	case BOOKE_INTERRUPT_HV_SYSCALL:
 		if (!(vcpu->arch.shared->msr & MSR_PR)) {
@@ -1388,6 +1428,11 @@ int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				 &vcpu->arch.dbg_reg.dac[dac], sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 epr = get_guest_epr(vcpu);
+		r = put_user(epr, (u32 __user *)(long)reg->addr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR:
 		r = put_user(vcpu->arch.epcr, (u32 __user *)(long)reg->addr);
@@ -1420,6 +1465,13 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 			     (u64 __user *)(long)reg->addr, sizeof(u64));
 		break;
 	}
+	case KVM_REG_PPC_EPR: {
+		u32 new_epr;
+		r = get_user(new_epr, (u32 __user *)(long)reg->addr);
+		if (!r)
+			kvmppc_set_epr(vcpu, new_epr);
+		break;
+	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR: {
 		u32 new_epcr;
@@ -1556,7 +1608,9 @@ int __init kvmppc_booke_init(void)
 {
 #ifndef CONFIG_KVM_BOOKE_HV
 	unsigned long ivor[16];
+	unsigned long *handler = kvmppc_booke_handler_addr;
 	unsigned long max_ivor = 0;
+	unsigned long handler_len;
 	int i;
 
 	/* We install our own exception handlers by hijacking IVPR. IVPR must
@@ -1589,14 +1643,16 @@ int __init kvmppc_booke_init(void)
 
 	for (i = 0; i < 16; i++) {
 		if (ivor[i] > max_ivor)
-			max_ivor = ivor[i];
+			max_ivor = i;
 
+		handler_len = handler[i + 1] - handler[i];
 		memcpy((void *)kvmppc_booke_handlers + ivor[i],
-		       kvmppc_handlers_start + i * kvmppc_handler_len,
-		       kvmppc_handler_len);
+		       (void *)handler[i], handler_len);
 	}
-	flush_icache_range(kvmppc_booke_handlers,
-	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+
+	handler_len = handler[max_ivor + 1] - handler[max_ivor];
+	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
+			   ivor[max_ivor] + handler_len);
 #endif /* !BOOKE_HV */
 	return 0;
 }

arch/powerpc/kvm/booke.h

@@ -65,6 +65,7 @@
 			  (1 << BOOKE_IRQPRIO_CRITICAL))
 
 extern unsigned long kvmppc_booke_handlers;
+extern unsigned long kvmppc_booke_handler_addr[];
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr);
 void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr);

arch/powerpc/kvm/booke_emulate.c

@@ -269,6 +269,9 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_ESR:
 		*spr_val = vcpu->arch.shared->esr;
 		break;
+	case SPRN_EPR:
+		*spr_val = vcpu->arch.epr;
+		break;
 	case SPRN_CSRR0:
 		*spr_val = vcpu->arch.csrr0;
 		break;

arch/powerpc/kvm/booke_interrupts.S

@@ -45,18 +45,21 @@
                         (1<<BOOKE_INTERRUPT_DEBUG))
 
 #define NEED_DEAR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
-                        (1<<BOOKE_INTERRUPT_DTLB_MISS))
+                        (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                        (1<<BOOKE_INTERRUPT_ALIGNMENT))
 
 #define NEED_ESR_MASK ((1<<BOOKE_INTERRUPT_DATA_STORAGE) | \
                        (1<<BOOKE_INTERRUPT_INST_STORAGE) | \
                        (1<<BOOKE_INTERRUPT_PROGRAM) | \
-                       (1<<BOOKE_INTERRUPT_DTLB_MISS))
+                       (1<<BOOKE_INTERRUPT_DTLB_MISS) | \
+                       (1<<BOOKE_INTERRUPT_ALIGNMENT))
 
 .macro KVM_HANDLER ivor_nr scratch srr0
 _GLOBAL(kvmppc_handler_\ivor_nr)
 	/* Get pointer to vcpu and record exit number. */
 	mtspr	\scratch , r4
-	mfspr	r4, SPRN_SPRG_RVCPU
+	mfspr   r4, SPRN_SPRG_THREAD
+	lwz     r4, THREAD_KVM_VCPU(r4)
 	stw	r3, VCPU_GPR(R3)(r4)
 	stw	r5, VCPU_GPR(R5)(r4)
 	stw	r6, VCPU_GPR(R6)(r4)
@@ -73,6 +76,14 @@ _GLOBAL(kvmppc_handler_\ivor_nr)
 	bctr
 .endm
 
+.macro KVM_HANDLER_ADDR ivor_nr
+	.long	kvmppc_handler_\ivor_nr
+.endm
+
+.macro KVM_HANDLER_END
+	.long	kvmppc_handlers_end
+.endm
+
 _GLOBAL(kvmppc_handlers_start)
 KVM_HANDLER BOOKE_INTERRUPT_CRITICAL SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_MACHINE_CHECK  SPRN_SPRG_RSCRATCH_MC SPRN_MCSRR0
@@ -93,9 +104,7 @@ KVM_HANDLER BOOKE_INTERRUPT_DEBUG SPRN_SPRG_RSCRATCH_CRIT SPRN_CSRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_UNAVAIL SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_DATA SPRN_SPRG_RSCRATCH0 SPRN_SRR0
 KVM_HANDLER BOOKE_INTERRUPT_SPE_FP_ROUND SPRN_SPRG_RSCRATCH0 SPRN_SRR0
-
-_GLOBAL(kvmppc_handler_len)
-	.long kvmppc_handler_1 - kvmppc_handler_0
+_GLOBAL(kvmppc_handlers_end)
 
 /* Registers:
  *  SPRG_SCRATCH0: guest r4
@@ -402,9 +411,6 @@ lightweight_exit:
 	lwz	r8, kvmppc_booke_handlers@l(r8)
 	mtspr	SPRN_IVPR, r8
 
-	/* Save vcpu pointer for the exception handlers. */
-	mtspr	SPRN_SPRG_WVCPU, r4
-
 	lwz	r5, VCPU_SHARED(r4)
 
 	/* Can't switch the stack pointer until after IVPR is switched,
@@ -463,6 +469,31 @@ lightweight_exit:
 	lwz	r4, VCPU_GPR(R4)(r4)
 	rfi
 
+	.data
+	.align	4
+	.globl	kvmppc_booke_handler_addr
+kvmppc_booke_handler_addr:
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_CRITICAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_MACHINE_CHECK
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DATA_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_INST_STORAGE
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_EXTERNAL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ALIGNMENT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_PROGRAM
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SYSCALL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_AP_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DECREMENTER
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_FIT
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_WATCHDOG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DTLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_ITLB_MISS
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_DEBUG
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_UNAVAIL
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_DATA
+KVM_HANDLER_ADDR BOOKE_INTERRUPT_SPE_FP_ROUND
+KVM_HANDLER_END /*Always keep this in end*/
+
 #ifdef CONFIG_SPE
 _GLOBAL(kvmppc_save_guest_spe)
 	cmpi	0,r3,0

arch/powerpc/kvm/e500.c

@@ -491,6 +491,9 @@ static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];
+	/* Process remaining handlers above the generic first 16 */
+	unsigned long *handler = &kvmppc_booke_handler_addr[16];
+	unsigned long handler_len;
 	unsigned long max_ivor = 0;
 
 	r = kvmppc_core_check_processor_compat();
@@ -506,15 +509,16 @@ static int __init kvmppc_e500_init(void)
 	ivor[1] = mfspr(SPRN_IVOR33);
 	ivor[2] = mfspr(SPRN_IVOR34);
 	for (i = 0; i < 3; i++) {
-		if (ivor[i] > max_ivor)
-			max_ivor = ivor[i];
+		if (ivor[i] > ivor[max_ivor])
+			max_ivor = i;
 
+		handler_len = handler[i + 1] - handler[i];
 		memcpy((void *)kvmppc_booke_handlers + ivor[i],
-		       kvmppc_handlers_start + (i + 16) * kvmppc_handler_len,
-		       kvmppc_handler_len);
+		       (void *)handler[i], handler_len);
 	}
-	flush_icache_range(kvmppc_booke_handlers,
-			kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
+	handler_len = handler[max_ivor + 1] - handler[max_ivor];
+	flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers +
+			   ivor[max_ivor] + handler_len);
 
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
 }

arch/powerpc/kvm/e500.h

@@ -28,6 +28,7 @@
 
 #define E500_TLB_VALID 1
 #define E500_TLB_BITMAP 2
+#define E500_TLB_TLB0		(1 << 2)
 
 struct tlbe_ref {
 	pfn_t pfn;

arch/powerpc/kvm/e500_tlb.c → arch/powerpc/kvm/e500_mmu.c

@@ -1,10 +1,11 @@
 /*
- * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, yu.liu@freescale.com
  *         Scott Wood, scottwood@freescale.com
  *         Ashish Kalra, ashish.kalra@freescale.com
  *         Varun Sethi, varun.sethi@freescale.com
+ *         Alexander Graf, agraf@suse.de
  *
  * Description:
  * This file is based on arch/powerpc/kvm/44x_tlb.c,
@@ -33,10 +34,7 @@
 #include "e500.h"
 #include "trace.h"
 #include "timing.h"
-
-#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
-
-static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+#include "e500_mmu_host.h"
 
 static inline unsigned int gtlb0_get_next_victim(
 		struct kvmppc_vcpu_e500 *vcpu_e500)
@@ -50,174 +48,6 @@ static inline unsigned int gtlb0_get_next_victim(
 	return victim;
 }
 
-static inline unsigned int tlb1_max_shadow_size(void)
-{
-	/* reserve one entry for magic page */
-	return host_tlb_params[1].entries - tlbcam_index - 1;
-}
-
-static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
-{
-	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
-}
-
-static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
-{
-	/* Mask off reserved bits. */
-	mas3 &= MAS3_ATTRIB_MASK;
-
-#ifndef CONFIG_KVM_BOOKE_HV
-	if (!usermode) {
-		/* Guest is in supervisor mode,
-		 * so we need to translate guest
-		 * supervisor permissions into user permissions. */
-		mas3 &= ~E500_TLB_USER_PERM_MASK;
-		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
-	}
-	mas3 |= E500_TLB_SUPER_PERM_MASK;
-#endif
-	return mas3;
-}
-
-static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
-{
-#ifdef CONFIG_SMP
-	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
-#else
-	return mas2 & MAS2_ATTRIB_MASK;
-#endif
-}
-
-/*
- * writing shadow tlb entry to host TLB
- */
-static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
-				     uint32_t mas0)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	mtspr(SPRN_MAS0, mas0);
-	mtspr(SPRN_MAS1, stlbe->mas1);
-	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
-	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
-	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
-#ifdef CONFIG_KVM_BOOKE_HV
-	mtspr(SPRN_MAS8, stlbe->mas8);
-#endif
-	asm volatile("isync; tlbwe" : : : "memory");
-
-#ifdef CONFIG_KVM_BOOKE_HV
-	/* Must clear mas8 for other host tlbwe's */
-	mtspr(SPRN_MAS8, 0);
-	isync();
-#endif
-	local_irq_restore(flags);
-
-	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
-	                              stlbe->mas2, stlbe->mas7_3);
-}
-
-/*
- * Acquire a mas0 with victim hint, as if we just took a TLB miss.
- *
- * We don't care about the address we're searching for, other than that it's
- * in the right set and is not present in the TLB.  Using a zero PID and a
- * userspace address means we don't have to set and then restore MAS5, or
- * calculate a proper MAS6 value.
- */
-static u32 get_host_mas0(unsigned long eaddr)
-{
-	unsigned long flags;
-	u32 mas0;
-
-	local_irq_save(flags);
-	mtspr(SPRN_MAS6, 0);
-	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
-	mas0 = mfspr(SPRN_MAS0);
-	local_irq_restore(flags);
-
-	return mas0;
-}
-
-/* sesel is for tlb1 only */
-static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	u32 mas0;
-
-	if (tlbsel == 0) {
-		mas0 = get_host_mas0(stlbe->mas2);
-		__write_host_tlbe(stlbe, mas0);
-	} else {
-		__write_host_tlbe(stlbe,
-				  MAS0_TLBSEL(1) |
-				  MAS0_ESEL(to_htlb1_esel(sesel)));
-	}
-}
-
-#ifdef CONFIG_KVM_E500V2
-void kvmppc_map_magic(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry magic;
-	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
-	unsigned int stid;
-	pfn_t pfn;
-
-	pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT;
-	get_page(pfn_to_page(pfn));
-
-	preempt_disable();
-	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);
-
-	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
-		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
-	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
-		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
-	magic.mas8 = 0;
-
-	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
-	preempt_enable();
-}
-#endif
-
-static void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500,
-				int tlbsel, int esel)
-{
-	struct kvm_book3e_206_tlb_entry *gtlbe =
-		get_entry(vcpu_e500, tlbsel, esel);
-
-	if (tlbsel == 1 &&
-	    vcpu_e500->gtlb_priv[1][esel].ref.flags & E500_TLB_BITMAP) {
-		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
-		int hw_tlb_indx;
-		unsigned long flags;
-
-		local_irq_save(flags);
-		while (tmp) {
-			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
-			mtspr(SPRN_MAS0,
-			      MAS0_TLBSEL(1) |
-			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
-			mtspr(SPRN_MAS1, 0);
-			asm volatile("tlbwe");
-			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
-			tmp &= tmp - 1;
-		}
-		mb();
-		vcpu_e500->g2h_tlb1_map[esel] = 0;
-		vcpu_e500->gtlb_priv[1][esel].ref.flags &= ~E500_TLB_BITMAP;
-		local_irq_restore(flags);
-
-		return;
-	}
-
-	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
-	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
-}
-
 static int tlb0_set_base(gva_t addr, int sets, int ways)
 {
 	int set_base;
@@ -296,70 +126,6 @@ static int kvmppc_e500_tlb_index(struct kvmppc_vcpu_e500 *vcpu_e500,
 	return -1;
 }
 
-static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
-					 struct kvm_book3e_206_tlb_entry *gtlbe,
-					 pfn_t pfn)
-{
-	ref->pfn = pfn;
-	ref->flags = E500_TLB_VALID;
-
-	if (tlbe_is_writable(gtlbe))
-		kvm_set_pfn_dirty(pfn);
-}
-
-static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
-{
-	if (ref->flags & E500_TLB_VALID) {
-		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
-		ref->flags = 0;
-	}
-}
-
-static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	if (vcpu_e500->g2h_tlb1_map)
-		memset(vcpu_e500->g2h_tlb1_map, 0,
-		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
-	if (vcpu_e500->h2g_tlb1_rmap)
-		memset(vcpu_e500->h2g_tlb1_rmap, 0,
-		       sizeof(unsigned int) * host_tlb_params[1].entries);
-}
-
-static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int tlbsel = 0;
-	int i;
-
-	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
-		kvmppc_e500_ref_release(ref);
-	}
-}
-
-static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
-{
-	int stlbsel = 1;
-	int i;
-
-	kvmppc_e500_tlbil_all(vcpu_e500);
-
-	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
-		struct tlbe_ref *ref =
-			&vcpu_e500->tlb_refs[stlbsel][i];
-		kvmppc_e500_ref_release(ref);
-	}
-
-	clear_tlb_privs(vcpu_e500);
-}
-
-void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	clear_tlb_refs(vcpu_e500);
-	clear_tlb1_bitmap(vcpu_e500);
-}
-
 static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		unsigned int eaddr, int as)
 {
@@ -385,216 +151,6 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 		| (as ? MAS6_SAS : 0);
 }
 
-/* TID must be supplied by the caller */
-static inline void kvmppc_e500_setup_stlbe(
-	struct kvm_vcpu *vcpu,
-	struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tsize, struct tlbe_ref *ref, u64 gvaddr,
-	struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	pfn_t pfn = ref->pfn;
-	u32 pr = vcpu->arch.shared->msr & MSR_PR;
-
-	BUG_ON(!(ref->flags & E500_TLB_VALID));
-
-	/* Force IPROT=0 for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
-	stlbe->mas2 = (gvaddr & MAS2_EPN) |
-		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
-	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
-			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
-
-#ifdef CONFIG_KVM_BOOKE_HV
-	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
-#endif
-}
-
-static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
-	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
-	struct tlbe_ref *ref)
-{
-	struct kvm_memory_slot *slot;
-	unsigned long pfn = 0; /* silence GCC warning */
-	unsigned long hva;
-	int pfnmap = 0;
-	int tsize = BOOK3E_PAGESZ_4K;
-
-	/*
-	 * Translate guest physical to true physical, acquiring
-	 * a page reference if it is normal, non-reserved memory.
-	 *
-	 * gfn_to_memslot() must succeed because otherwise we wouldn't
-	 * have gotten this far.  Eventually we should just pass the slot
-	 * pointer through from the first lookup.
-	 */
-	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
-	hva = gfn_to_hva_memslot(slot, gfn);
-
-	if (tlbsel == 1) {
-		struct vm_area_struct *vma;
-		down_read(&current->mm->mmap_sem);
-
-		vma = find_vma(current->mm, hva);
-		if (vma && hva >= vma->vm_start &&
-		    (vma->vm_flags & VM_PFNMAP)) {
-			/*
-			 * This VMA is a physically contiguous region (e.g.
-			 * /dev/mem) that bypasses normal Linux page
-			 * management.  Find the overlap between the
-			 * vma and the memslot.
-			 */
-
-			unsigned long start, end;
-			unsigned long slot_start, slot_end;
-
-			pfnmap = 1;
-
-			start = vma->vm_pgoff;
-			end = start +
-			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);
-
-			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
-
-			slot_start = pfn - (gfn - slot->base_gfn);
-			slot_end = slot_start + slot->npages;
-
-			if (start < slot_start)
-				start = slot_start;
-			if (end > slot_end)
-				end = slot_end;
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-
-			/*
-			 * Now find the largest tsize (up to what the guest
-			 * requested) that will cover gfn, stay within the
-			 * range, and for which gfn and pfn are mutually
-			 * aligned.
-			 */
-
-			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
-				unsigned long gfn_start, gfn_end, tsize_pages;
-				tsize_pages = 1 << (tsize - 2);
-
-				gfn_start = gfn & ~(tsize_pages - 1);
-				gfn_end = gfn_start + tsize_pages;
-
-				if (gfn_start + pfn - gfn < start)
-					continue;
-				if (gfn_end + pfn - gfn > end)
-					continue;
-				if ((gfn & (tsize_pages - 1)) !=
-				    (pfn & (tsize_pages - 1)))
-					continue;
-
-				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
-				pfn &= ~(tsize_pages - 1);
-				break;
-			}
-		} else if (vma && hva >= vma->vm_start &&
-			   (vma->vm_flags & VM_HUGETLB)) {
-			unsigned long psize = vma_kernel_pagesize(vma);
-
-			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
-				MAS1_TSIZE_SHIFT;
-
-			/*
-			 * Take the largest page size that satisfies both host
-			 * and guest mapping
-			 */
-			tsize = min(__ilog2(psize) - 10, tsize);
-
-			/*
-			 * e500 doesn't implement the lowest tsize bit,
-			 * or 1K pages.
-			 */
-			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
-		}
-
-		up_read(&current->mm->mmap_sem);
-	}
-
-	if (likely(!pfnmap)) {
-		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
-		pfn = gfn_to_pfn_memslot(slot, gfn);
-		if (is_error_noslot_pfn(pfn)) {
-			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
-					(long)gfn);
-			return;
-		}
-
-		/* Align guest and physical address to page map boundaries */
-		pfn &= ~(tsize_pages - 1);
-		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
-	}
-
-	/* Drop old ref and setup new one. */
-	kvmppc_e500_ref_release(ref);
-	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
-
-	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
-				ref, gvaddr, stlbe);
-
-	/* Clear i-cache for new pages */
-	kvmppc_mmu_flush_icache(pfn);
-
-	/* Drop refcount on page, so that mmu notifiers can clear it */
-	kvm_release_pfn_clean(pfn);
-}
-
-/* XXX only map the one-one case, for now use TLB0 */
-static void kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-				 int esel,
-				 struct kvm_book3e_206_tlb_entry *stlbe)
-{
-	struct kvm_book3e_206_tlb_entry *gtlbe;
-	struct tlbe_ref *ref;
-
-	gtlbe = get_entry(vcpu_e500, 0, esel);
-	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
-
-	kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
-			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
-			gtlbe, 0, stlbe, ref);
-}
-
-/* Caller must ensure that the specified guest TLB entry is safe to insert into
- * the shadow TLB. */
-/* XXX for both one-one and one-to-many , for now use TLB1 */
-static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
-		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
-		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
-{
-	struct tlbe_ref *ref;
-	unsigned int victim;
-
-	victim = vcpu_e500->host_tlb1_nv++;
-
-	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
-		vcpu_e500->host_tlb1_nv = 0;
-
-	ref = &vcpu_e500->tlb_refs[1][victim];
-	kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe, ref);
-
-	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << victim;
-	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
-	if (vcpu_e500->h2g_tlb1_rmap[victim]) {
-		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[victim];
-		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << victim);
-	}
-	vcpu_e500->h2g_tlb1_rmap[victim] = esel;
-
-	return victim;
-}
-
 static void kvmppc_recalc_tlb1map_range(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int size = vcpu_e500->gtlb_params[1].entries;
@@ -683,8 +239,8 @@ int kvmppc_e500_emul_mt_mmucsr0(struct kvmppc_vcpu_e500 *vcpu_e500, ulong value)
 		for (esel = 0; esel < vcpu_e500->gtlb_params[1].entries; esel++)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, 1, esel);
 
-	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_tlbil_all(vcpu_e500);
+	/* Invalidate all host shadow mappings */
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 
 	return EMULATE_DONE;
 }
@@ -713,8 +269,8 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, gva_t ea)
 			kvmppc_e500_gtlbe_invalidate(vcpu_e500, tlbsel, esel);
 	}
 
-	/* Invalidate all vcpu id mappings */
-	kvmppc_e500_tlbil_all(vcpu_e500);
+	/* Invalidate all host shadow mappings */
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 
 	return EMULATE_DONE;
 }
@@ -834,27 +390,11 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, gva_t ea)
 	return EMULATE_DONE;
 }
 
-/* sesel is for tlb1 only */
-static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
-			struct kvm_book3e_206_tlb_entry *gtlbe,
-			struct kvm_book3e_206_tlb_entry *stlbe,
-			int stlbsel, int sesel)
-{
-	int stid;
-
-	preempt_disable();
-	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
-
-	stlbe->mas1 |= MAS1_TID(stid);
-	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
-	preempt_enable();
-}
-
 int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
-	int tlbsel, esel, stlbsel, sesel;
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	int tlbsel, esel;
 	int recal = 0;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
@@ -892,40 +432,16 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
-		u64 eaddr;
-		u64 raddr;
+		u64 eaddr = get_tlb_eaddr(gtlbe);
+		u64 raddr = get_tlb_raddr(gtlbe);
 
-		switch (tlbsel) {
-		case 0:
-			/* TLB0 */
+		if (tlbsel == 0) {
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
 			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
-
-			stlbsel = 0;
-			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
-			sesel = 0; /* unused */
-
-			break;
-
-		case 1:
-			/* TLB1 */
-			eaddr = get_tlb_eaddr(gtlbe);
-			raddr = get_tlb_raddr(gtlbe);
-
-			/* Create a 4KB mapping on the host.
-			 * If the guest wanted a large page,
-			 * only the first 4KB is mapped here and the rest
-			 * are mapped on the fly. */
-			stlbsel = 1;
-			sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr,
-				    raddr >> PAGE_SHIFT, gtlbe, &stlbe, esel);
-			break;
-
-		default:
-			BUG();
 		}
 
-		write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
+		/* Premap the faulting page */
+		kvmppc_mmu_map(vcpu, eaddr, raddr, index_of(tlbsel, esel));
 	}
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
@@ -1019,100 +535,14 @@ void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
-			unsigned int index)
-{
-	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
-	struct tlbe_priv *priv;
-	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
-	int tlbsel = tlbsel_of(index);
-	int esel = esel_of(index);
-	int stlbsel, sesel;
-
-	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
-
-	switch (tlbsel) {
-	case 0:
-		stlbsel = 0;
-		sesel = 0; /* unused */
-		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
-
-		/* Only triggers after clear_tlb_refs */
-		if (unlikely(!(priv->ref.flags & E500_TLB_VALID)))
-			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
-		else
-			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
-						&priv->ref, eaddr, &stlbe);
-		break;
-
-	case 1: {
-		gfn_t gfn = gpaddr >> PAGE_SHIFT;
-
-		stlbsel = 1;
-		sesel = kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn,
-					     gtlbe, &stlbe, esel);
-		break;
-	}
-
-	default:
-		BUG();
-		break;
-	}
-
-	write_stlbe(vcpu_e500, gtlbe, &stlbe, stlbsel, sesel);
-}
-
-/************* MMU Notifiers *************/
-
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
-{
-	trace_kvm_unmap_hva(hva);
-
-	/*
-	 * Flush all shadow tlb entries everywhere. This is slow, but
-	 * we are 100% sure that we catch the to be unmapped page
-	 */
-	kvm_flush_remote_tlbs(kvm);
-
-	return 0;
-}
-
-int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
-{
-	/* kvm_unmap_hva flushes everything anyways */
-	kvm_unmap_hva(kvm, start);
-
-	return 0;
-}
-
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	/* XXX could be more clever ;) */
-	return 0;
-}
-
-int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
-{
-	/* XXX could be more clever ;) */
-	return 0;
-}
-
-void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
-{
-	/* The page will get remapped properly on its next fault */
-	kvm_unmap_hva(kvm, hva);
-}
-
 /*****************************************/
 
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	int i;
 
-	clear_tlb1_bitmap(vcpu_e500);
+	kvmppc_core_flush_tlb(&vcpu_e500->vcpu);
 	kfree(vcpu_e500->g2h_tlb1_map);
-
-	clear_tlb_refs(vcpu_e500);
 	kfree(vcpu_e500->gtlb_priv[0]);
 	kfree(vcpu_e500->gtlb_priv[1]);
 
@@ -1303,7 +733,7 @@ int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	kvmppc_recalc_tlb1map_range(vcpu_e500);
-	clear_tlb_refs(vcpu_e500);
+	kvmppc_core_flush_tlb(vcpu);
 	return 0;
 }
 
@@ -1313,37 +743,8 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	int entry_size = sizeof(struct kvm_book3e_206_tlb_entry);
 	int entries = KVM_E500_TLB0_SIZE + KVM_E500_TLB1_SIZE;
 
-	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
-	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
-
-	/*
-	 * This should never happen on real e500 hardware, but is
-	 * architecturally possible -- e.g. in some weird nested
-	 * virtualization case.
-	 */
-	if (host_tlb_params[0].entries == 0 ||
-	    host_tlb_params[1].entries == 0) {
-		pr_err("%s: need to know host tlb size\n", __func__);
-		return -ENODEV;
-	}
-
-	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
-				  TLBnCFG_ASSOC_SHIFT;
-	host_tlb_params[1].ways = host_tlb_params[1].entries;
-
-	if (!is_power_of_2(host_tlb_params[0].entries) ||
-	    !is_power_of_2(host_tlb_params[0].ways) ||
-	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
-	    host_tlb_params[0].ways == 0) {
-		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
-		       __func__, host_tlb_params[0].entries,
-		       host_tlb_params[0].ways);
-		return -ENODEV;
-	}
-
-	host_tlb_params[0].sets =
-		host_tlb_params[0].entries / host_tlb_params[0].ways;
-	host_tlb_params[1].sets = 1;
+	if (e500_mmu_host_init(vcpu_e500))
+		goto err;
 
 	vcpu_e500->gtlb_params[0].entries = KVM_E500_TLB0_SIZE;
 	vcpu_e500->gtlb_params[1].entries = KVM_E500_TLB1_SIZE;
@@ -1362,18 +763,6 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	vcpu_e500->gtlb_offset[0] = 0;
 	vcpu_e500->gtlb_offset[1] = KVM_E500_TLB0_SIZE;
 
-	vcpu_e500->tlb_refs[0] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[0])
-		goto err;
-
-	vcpu_e500->tlb_refs[1] =
-		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
-			GFP_KERNEL);
-	if (!vcpu_e500->tlb_refs[1])
-		goto err;
-
 	vcpu_e500->gtlb_priv[0] = kzalloc(sizeof(struct tlbe_ref) *
 					  vcpu_e500->gtlb_params[0].entries,
 					  GFP_KERNEL);
@@ -1392,12 +781,6 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (!vcpu_e500->g2h_tlb1_map)
 		goto err;
 
-	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
-					   host_tlb_params[1].entries,
-					   GFP_KERNEL);
-	if (!vcpu_e500->h2g_tlb1_rmap)
-		goto err;
-
 	/* Init TLB configuration register */
 	vcpu->arch.tlbcfg[0] = mfspr(SPRN_TLB0CFG) &
 			     ~(TLBnCFG_N_ENTRY | TLBnCFG_ASSOC);
@@ -1416,15 +799,11 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 err:
 	free_gtlb(vcpu_e500);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
 	return -1;
 }
 
 void kvmppc_e500_tlb_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	free_gtlb(vcpu_e500);
-	kfree(vcpu_e500->h2g_tlb1_rmap);
-	kfree(vcpu_e500->tlb_refs[0]);
-	kfree(vcpu_e500->tlb_refs[1]);
+	e500_mmu_host_uninit(vcpu_e500);
 }

arch/powerpc/kvm/e500_mmu_host.c

@@ -0,0 +1,699 @@
+/*
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Yu Liu, yu.liu@freescale.com
+ *         Scott Wood, scottwood@freescale.com
+ *         Ashish Kalra, ashish.kalra@freescale.com
+ *         Varun Sethi, varun.sethi@freescale.com
+ *         Alexander Graf, agraf@suse.de
+ *
+ * Description:
+ * This file is based on arch/powerpc/kvm/44x_tlb.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/log2.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/rwsem.h>
+#include <linux/vmalloc.h>
+#include <linux/hugetlb.h>
+#include <asm/kvm_ppc.h>
+
+#include "e500.h"
+#include "trace.h"
+#include "timing.h"
+#include "e500_mmu_host.h"
+
+#define to_htlb1_esel(esel) (host_tlb_params[1].entries - (esel) - 1)
+
+static struct kvmppc_e500_tlb_params host_tlb_params[E500_TLB_NUM];
+
+static inline unsigned int tlb1_max_shadow_size(void)
+{
+	/* reserve one entry for magic page */
+	return host_tlb_params[1].entries - tlbcam_index - 1;
+}
+
+static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
+{
+	/* Mask off reserved bits. */
+	mas3 &= MAS3_ATTRIB_MASK;
+
+#ifndef CONFIG_KVM_BOOKE_HV
+	if (!usermode) {
+		/* Guest is in supervisor mode,
+		 * so we need to translate guest
+		 * supervisor permissions into user permissions. */
+		mas3 &= ~E500_TLB_USER_PERM_MASK;
+		mas3 |= (mas3 & E500_TLB_SUPER_PERM_MASK) << 1;
+	}
+	mas3 |= E500_TLB_SUPER_PERM_MASK;
+#endif
+	return mas3;
+}
+
+static inline u32 e500_shadow_mas2_attrib(u32 mas2, int usermode)
+{
+#ifdef CONFIG_SMP
+	return (mas2 & MAS2_ATTRIB_MASK) | MAS2_M;
+#else
+	return mas2 & MAS2_ATTRIB_MASK;
+#endif
+}
+
+/*
+ * writing shadow tlb entry to host TLB
+ */
+static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
+				     uint32_t mas0)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS0, mas0);
+	mtspr(SPRN_MAS1, stlbe->mas1);
+	mtspr(SPRN_MAS2, (unsigned long)stlbe->mas2);
+	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
+	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_MAS8, stlbe->mas8);
+#endif
+	asm volatile("isync; tlbwe" : : : "memory");
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	/* Must clear mas8 for other host tlbwe's */
+	mtspr(SPRN_MAS8, 0);
+	isync();
+#endif
+	local_irq_restore(flags);
+
+	trace_kvm_booke206_stlb_write(mas0, stlbe->mas8, stlbe->mas1,
+	                              stlbe->mas2, stlbe->mas7_3);
+}
+
+/*
+ * Acquire a mas0 with victim hint, as if we just took a TLB miss.
+ *
+ * We don't care about the address we're searching for, other than that it's
+ * in the right set and is not present in the TLB.  Using a zero PID and a
+ * userspace address means we don't have to set and then restore MAS5, or
+ * calculate a proper MAS6 value.
+ */
+static u32 get_host_mas0(unsigned long eaddr)
+{
+	unsigned long flags;
+	u32 mas0;
+
+	local_irq_save(flags);
+	mtspr(SPRN_MAS6, 0);
+	asm volatile("tlbsx 0, %0" : : "b" (eaddr & ~CONFIG_PAGE_OFFSET));
+	mas0 = mfspr(SPRN_MAS0);
+	local_irq_restore(flags);
+
+	return mas0;
+}
+
+/* sesel is for tlb1 only */
+static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+		int tlbsel, int sesel, struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	u32 mas0;
+
+	if (tlbsel == 0) {
+		mas0 = get_host_mas0(stlbe->mas2);
+		__write_host_tlbe(stlbe, mas0);
+	} else {
+		__write_host_tlbe(stlbe,
+				  MAS0_TLBSEL(1) |
+				  MAS0_ESEL(to_htlb1_esel(sesel)));
+	}
+}
+
+/* sesel is for tlb1 only */
+static void write_stlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
+			struct kvm_book3e_206_tlb_entry *gtlbe,
+			struct kvm_book3e_206_tlb_entry *stlbe,
+			int stlbsel, int sesel)
+{
+	int stid;
+
+	preempt_disable();
+	stid = kvmppc_e500_get_tlb_stid(&vcpu_e500->vcpu, gtlbe);
+
+	stlbe->mas1 |= MAS1_TID(stid);
+	write_host_tlbe(vcpu_e500, stlbsel, sesel, stlbe);
+	preempt_enable();
+}
+
+#ifdef CONFIG_KVM_E500V2
+/* XXX should be a hook in the gva2hpa translation */
+void kvmppc_map_magic(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct kvm_book3e_206_tlb_entry magic;
+	ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
+	unsigned int stid;
+	pfn_t pfn;
+
+	pfn = (pfn_t)virt_to_phys((void *)shared_page) >> PAGE_SHIFT;
+	get_page(pfn_to_page(pfn));
+
+	preempt_disable();
+	stid = kvmppc_e500_get_sid(vcpu_e500, 0, 0, 0, 0);
+
+	magic.mas1 = MAS1_VALID | MAS1_TS | MAS1_TID(stid) |
+		     MAS1_TSIZE(BOOK3E_PAGESZ_4K);
+	magic.mas2 = vcpu->arch.magic_page_ea | MAS2_M;
+	magic.mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
+	magic.mas8 = 0;
+
+	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
+	preempt_enable();
+}
+#endif
+
+void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+			 int esel)
+{
+	struct kvm_book3e_206_tlb_entry *gtlbe =
+		get_entry(vcpu_e500, tlbsel, esel);
+	struct tlbe_ref *ref = &vcpu_e500->gtlb_priv[tlbsel][esel].ref;
+
+	/* Don't bother with unmapped entries */
+	if (!(ref->flags & E500_TLB_VALID))
+		return;
+
+	if (tlbsel == 1 && ref->flags & E500_TLB_BITMAP) {
+		u64 tmp = vcpu_e500->g2h_tlb1_map[esel];
+		int hw_tlb_indx;
+		unsigned long flags;
+
+		local_irq_save(flags);
+		while (tmp) {
+			hw_tlb_indx = __ilog2_u64(tmp & -tmp);
+			mtspr(SPRN_MAS0,
+			      MAS0_TLBSEL(1) |
+			      MAS0_ESEL(to_htlb1_esel(hw_tlb_indx)));
+			mtspr(SPRN_MAS1, 0);
+			asm volatile("tlbwe");
+			vcpu_e500->h2g_tlb1_rmap[hw_tlb_indx] = 0;
+			tmp &= tmp - 1;
+		}
+		mb();
+		vcpu_e500->g2h_tlb1_map[esel] = 0;
+		ref->flags &= ~(E500_TLB_BITMAP | E500_TLB_VALID);
+		local_irq_restore(flags);
+	}
+
+	if (tlbsel == 1 && ref->flags & E500_TLB_TLB0) {
+		/*
+		 * TLB1 entry is backed by 4k pages. This should happen
+		 * rarely and is not worth optimizing. Invalidate everything.
+		 */
+		kvmppc_e500_tlbil_all(vcpu_e500);
+		ref->flags &= ~(E500_TLB_TLB0 | E500_TLB_VALID);
+	}
+
+	/* Already invalidated in between */
+	if (!(ref->flags & E500_TLB_VALID))
+		return;
+
+	/* Guest tlbe is backed by at most one host tlbe per shadow pid. */
+	kvmppc_e500_tlbil_one(vcpu_e500, gtlbe);
+
+	/* Mark the TLB as not backed by the host anymore */
+	ref->flags &= ~E500_TLB_VALID;
+}
+
+static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe)
+{
+	return tlbe->mas7_3 & (MAS3_SW|MAS3_UW);
+}
+
+static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref,
+					 struct kvm_book3e_206_tlb_entry *gtlbe,
+					 pfn_t pfn)
+{
+	ref->pfn = pfn;
+	ref->flags = E500_TLB_VALID;
+
+	if (tlbe_is_writable(gtlbe))
+		kvm_set_pfn_dirty(pfn);
+}
+
+static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref)
+{
+	if (ref->flags & E500_TLB_VALID) {
+		trace_kvm_booke206_ref_release(ref->pfn, ref->flags);
+		ref->flags = 0;
+	}
+}
+
+static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	if (vcpu_e500->g2h_tlb1_map)
+		memset(vcpu_e500->g2h_tlb1_map, 0,
+		       sizeof(u64) * vcpu_e500->gtlb_params[1].entries);
+	if (vcpu_e500->h2g_tlb1_rmap)
+		memset(vcpu_e500->h2g_tlb1_rmap, 0,
+		       sizeof(unsigned int) * host_tlb_params[1].entries);
+}
+
+static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int tlbsel = 0;
+	int i;
+
+	for (i = 0; i < vcpu_e500->gtlb_params[tlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->gtlb_priv[tlbsel][i].ref;
+		kvmppc_e500_ref_release(ref);
+	}
+}
+
+static void clear_tlb_refs(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	int stlbsel = 1;
+	int i;
+
+	kvmppc_e500_tlbil_all(vcpu_e500);
+
+	for (i = 0; i < host_tlb_params[stlbsel].entries; i++) {
+		struct tlbe_ref *ref =
+			&vcpu_e500->tlb_refs[stlbsel][i];
+		kvmppc_e500_ref_release(ref);
+	}
+
+	clear_tlb_privs(vcpu_e500);
+}
+
+void kvmppc_core_flush_tlb(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	clear_tlb_refs(vcpu_e500);
+	clear_tlb1_bitmap(vcpu_e500);
+}
+
+/* TID must be supplied by the caller */
+static void kvmppc_e500_setup_stlbe(
+	struct kvm_vcpu *vcpu,
+	struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tsize, struct tlbe_ref *ref, u64 gvaddr,
+	struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	pfn_t pfn = ref->pfn;
+	u32 pr = vcpu->arch.shared->msr & MSR_PR;
+
+	BUG_ON(!(ref->flags & E500_TLB_VALID));
+
+	/* Force IPROT=0 for all guest mappings. */
+	stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID;
+	stlbe->mas2 = (gvaddr & MAS2_EPN) |
+		      e500_shadow_mas2_attrib(gtlbe->mas2, pr);
+	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
+			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
+
+#ifdef CONFIG_KVM_BOOKE_HV
+	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
+#endif
+}
+
+static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+	u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+	int tlbsel, struct kvm_book3e_206_tlb_entry *stlbe,
+	struct tlbe_ref *ref)
+{
+	struct kvm_memory_slot *slot;
+	unsigned long pfn = 0; /* silence GCC warning */
+	unsigned long hva;
+	int pfnmap = 0;
+	int tsize = BOOK3E_PAGESZ_4K;
+
+	/*
+	 * Translate guest physical to true physical, acquiring
+	 * a page reference if it is normal, non-reserved memory.
+	 *
+	 * gfn_to_memslot() must succeed because otherwise we wouldn't
+	 * have gotten this far.  Eventually we should just pass the slot
+	 * pointer through from the first lookup.
+	 */
+	slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn);
+	hva = gfn_to_hva_memslot(slot, gfn);
+
+	if (tlbsel == 1) {
+		struct vm_area_struct *vma;
+		down_read(&current->mm->mmap_sem);
+
+		vma = find_vma(current->mm, hva);
+		if (vma && hva >= vma->vm_start &&
+		    (vma->vm_flags & VM_PFNMAP)) {
+			/*
+			 * This VMA is a physically contiguous region (e.g.
+			 * /dev/mem) that bypasses normal Linux page
+			 * management.  Find the overlap between the
+			 * vma and the memslot.
+			 */
+
+			unsigned long start, end;
+			unsigned long slot_start, slot_end;
+
+			pfnmap = 1;
+
+			start = vma->vm_pgoff;
+			end = start +
+			      ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT);
+
+			pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT);
+
+			slot_start = pfn - (gfn - slot->base_gfn);
+			slot_end = slot_start + slot->npages;
+
+			if (start < slot_start)
+				start = slot_start;
+			if (end > slot_end)
+				end = slot_end;
+
+			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+				MAS1_TSIZE_SHIFT;
+
+			/*
+			 * e500 doesn't implement the lowest tsize bit,
+			 * or 1K pages.
+			 */
+			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+
+			/*
+			 * Now find the largest tsize (up to what the guest
+			 * requested) that will cover gfn, stay within the
+			 * range, and for which gfn and pfn are mutually
+			 * aligned.
+			 */
+
+			for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) {
+				unsigned long gfn_start, gfn_end, tsize_pages;
+				tsize_pages = 1 << (tsize - 2);
+
+				gfn_start = gfn & ~(tsize_pages - 1);
+				gfn_end = gfn_start + tsize_pages;
+
+				if (gfn_start + pfn - gfn < start)
+					continue;
+				if (gfn_end + pfn - gfn > end)
+					continue;
+				if ((gfn & (tsize_pages - 1)) !=
+				    (pfn & (tsize_pages - 1)))
+					continue;
+
+				gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+				pfn &= ~(tsize_pages - 1);
+				break;
+			}
+		} else if (vma && hva >= vma->vm_start &&
+			   (vma->vm_flags & VM_HUGETLB)) {
+			unsigned long psize = vma_kernel_pagesize(vma);
+
+			tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >>
+				MAS1_TSIZE_SHIFT;
+
+			/*
+			 * Take the largest page size that satisfies both host
+			 * and guest mapping
+			 */
+			tsize = min(__ilog2(psize) - 10, tsize);
+
+			/*
+			 * e500 doesn't implement the lowest tsize bit,
+			 * or 1K pages.
+			 */
+			tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1);
+		}
+
+		up_read(&current->mm->mmap_sem);
+	}
+
+	if (likely(!pfnmap)) {
+		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
+		pfn = gfn_to_pfn_memslot(slot, gfn);
+		if (is_error_noslot_pfn(pfn)) {
+			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
+					(long)gfn);
+			return -EINVAL;
+		}
+
+		/* Align guest and physical address to page map boundaries */
+		pfn &= ~(tsize_pages - 1);
+		gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1);
+	}
+
+	/* Drop old ref and setup new one. */
+	kvmppc_e500_ref_release(ref);
+	kvmppc_e500_ref_setup(ref, gtlbe, pfn);
+
+	kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize,
+				ref, gvaddr, stlbe);
+
+	/* Clear i-cache for new pages */
+	kvmppc_mmu_flush_icache(pfn);
+
+	/* Drop refcount on page, so that mmu notifiers can clear it */
+	kvm_release_pfn_clean(pfn);
+
+	return 0;
+}
+
+/* XXX only map the one-one case, for now use TLB0 */
+static int kvmppc_e500_tlb0_map(struct kvmppc_vcpu_e500 *vcpu_e500, int esel,
+				struct kvm_book3e_206_tlb_entry *stlbe)
+{
+	struct kvm_book3e_206_tlb_entry *gtlbe;
+	struct tlbe_ref *ref;
+	int stlbsel = 0;
+	int sesel = 0;
+	int r;
+
+	gtlbe = get_entry(vcpu_e500, 0, esel);
+	ref = &vcpu_e500->gtlb_priv[0][esel].ref;
+
+	r = kvmppc_e500_shadow_map(vcpu_e500, get_tlb_eaddr(gtlbe),
+			get_tlb_raddr(gtlbe) >> PAGE_SHIFT,
+			gtlbe, 0, stlbe, ref);
+	if (r)
+		return r;
+
+	write_stlbe(vcpu_e500, gtlbe, stlbe, stlbsel, sesel);
+
+	return 0;
+}
+
+static int kvmppc_e500_tlb1_map_tlb1(struct kvmppc_vcpu_e500 *vcpu_e500,
+				     struct tlbe_ref *ref,
+				     int esel)
+{
+	unsigned int sesel = vcpu_e500->host_tlb1_nv++;
+
+	if (unlikely(vcpu_e500->host_tlb1_nv >= tlb1_max_shadow_size()))
+		vcpu_e500->host_tlb1_nv = 0;
+
+	vcpu_e500->tlb_refs[1][sesel] = *ref;
+	vcpu_e500->g2h_tlb1_map[esel] |= (u64)1 << sesel;
+	vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_BITMAP;
+	if (vcpu_e500->h2g_tlb1_rmap[sesel]) {
+		unsigned int idx = vcpu_e500->h2g_tlb1_rmap[sesel];
+		vcpu_e500->g2h_tlb1_map[idx] &= ~(1ULL << sesel);
+	}
+	vcpu_e500->h2g_tlb1_rmap[sesel] = esel;
+
+	return sesel;
+}
+
+/* Caller must ensure that the specified guest TLB entry is safe to insert into
+ * the shadow TLB. */
+/* For both one-one and one-to-many */
+static int kvmppc_e500_tlb1_map(struct kvmppc_vcpu_e500 *vcpu_e500,
+		u64 gvaddr, gfn_t gfn, struct kvm_book3e_206_tlb_entry *gtlbe,
+		struct kvm_book3e_206_tlb_entry *stlbe, int esel)
+{
+	struct tlbe_ref ref;
+	int sesel;
+	int r;
+
+	ref.flags = 0;
+	r = kvmppc_e500_shadow_map(vcpu_e500, gvaddr, gfn, gtlbe, 1, stlbe,
+				   &ref);
+	if (r)
+		return r;
+
+	/* Use TLB0 when we can only map a page with 4k */
+	if (get_tlb_tsize(stlbe) == BOOK3E_PAGESZ_4K) {
+		vcpu_e500->gtlb_priv[1][esel].ref.flags |= E500_TLB_TLB0;
+		write_stlbe(vcpu_e500, gtlbe, stlbe, 0, 0);
+		return 0;
+	}
+
+	/* Otherwise map into TLB1 */
+	sesel = kvmppc_e500_tlb1_map_tlb1(vcpu_e500, &ref, esel);
+	write_stlbe(vcpu_e500, gtlbe, stlbe, 1, sesel);
+
+	return 0;
+}
+
+void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 eaddr, gpa_t gpaddr,
+		    unsigned int index)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+	struct tlbe_priv *priv;
+	struct kvm_book3e_206_tlb_entry *gtlbe, stlbe;
+	int tlbsel = tlbsel_of(index);
+	int esel = esel_of(index);
+
+	gtlbe = get_entry(vcpu_e500, tlbsel, esel);
+
+	switch (tlbsel) {
+	case 0:
+		priv = &vcpu_e500->gtlb_priv[tlbsel][esel];
+
+		/* Triggers after clear_tlb_refs or on initial mapping */
+		if (!(priv->ref.flags & E500_TLB_VALID)) {
+			kvmppc_e500_tlb0_map(vcpu_e500, esel, &stlbe);
+		} else {
+			kvmppc_e500_setup_stlbe(vcpu, gtlbe, BOOK3E_PAGESZ_4K,
+						&priv->ref, eaddr, &stlbe);
+			write_stlbe(vcpu_e500, gtlbe, &stlbe, 0, 0);
+		}
+		break;
+
+	case 1: {
+		gfn_t gfn = gpaddr >> PAGE_SHIFT;
+		kvmppc_e500_tlb1_map(vcpu_e500, eaddr, gfn, gtlbe, &stlbe,
+				     esel);
+		break;
+	}
+
+	default:
+		BUG();
+		break;
+	}
+}
+
+/************* MMU Notifiers *************/
+
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
+{
+	trace_kvm_unmap_hva(hva);
+
+	/*
+	 * Flush all shadow tlb entries everywhere. This is slow, but
+	 * we are 100% sure that we catch the to be unmapped page
+	 */
+	kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	/* kvm_unmap_hva flushes everything anyways */
+	kvm_unmap_hva(kvm, start);
+
+	return 0;
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	/* XXX could be more clever ;) */
+	return 0;
+}
+
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+	/* The page will get remapped properly on its next fault */
+	kvm_unmap_hva(kvm, hva);
+}
+
+/*****************************************/
+
+int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	host_tlb_params[0].entries = mfspr(SPRN_TLB0CFG) & TLBnCFG_N_ENTRY;
+	host_tlb_params[1].entries = mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY;
+
+	/*
+	 * This should never happen on real e500 hardware, but is
+	 * architecturally possible -- e.g. in some weird nested
+	 * virtualization case.
+	 */
+	if (host_tlb_params[0].entries == 0 ||
+	    host_tlb_params[1].entries == 0) {
+		pr_err("%s: need to know host tlb size\n", __func__);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].ways = (mfspr(SPRN_TLB0CFG) & TLBnCFG_ASSOC) >>
+				  TLBnCFG_ASSOC_SHIFT;
+	host_tlb_params[1].ways = host_tlb_params[1].entries;
+
+	if (!is_power_of_2(host_tlb_params[0].entries) ||
+	    !is_power_of_2(host_tlb_params[0].ways) ||
+	    host_tlb_params[0].entries < host_tlb_params[0].ways ||
+	    host_tlb_params[0].ways == 0) {
+		pr_err("%s: bad tlb0 host config: %u entries %u ways\n",
+		       __func__, host_tlb_params[0].entries,
+		       host_tlb_params[0].ways);
+		return -ENODEV;
+	}
+
+	host_tlb_params[0].sets =
+		host_tlb_params[0].entries / host_tlb_params[0].ways;
+	host_tlb_params[1].sets = 1;
+
+	vcpu_e500->tlb_refs[0] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[0].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[0])
+		goto err;
+
+	vcpu_e500->tlb_refs[1] =
+		kzalloc(sizeof(struct tlbe_ref) * host_tlb_params[1].entries,
+			GFP_KERNEL);
+	if (!vcpu_e500->tlb_refs[1])
+		goto err;
+
+	vcpu_e500->h2g_tlb1_rmap = kzalloc(sizeof(unsigned int) *
+					   host_tlb_params[1].entries,
+					   GFP_KERNEL);
+	if (!vcpu_e500->h2g_tlb1_rmap)
+		goto err;
+
+	return 0;
+
+err:
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
+	return -EINVAL;
+}
+
+void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500)
+{
+	kfree(vcpu_e500->h2g_tlb1_rmap);
+	kfree(vcpu_e500->tlb_refs[0]);
+	kfree(vcpu_e500->tlb_refs[1]);
+}

arch/powerpc/kvm/e500_mmu_host.h

@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2008-2013 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef KVM_E500_MMU_HOST_H
+#define KVM_E500_MMU_HOST_H
+
+void inval_gtlbe_on_host(struct kvmppc_vcpu_e500 *vcpu_e500, int tlbsel,
+			 int esel);
+
+int e500_mmu_host_init(struct kvmppc_vcpu_e500 *vcpu_e500);
+void e500_mmu_host_uninit(struct kvmppc_vcpu_e500 *vcpu_e500);
+
+#endif /* KVM_E500_MMU_HOST_H */

arch/powerpc/kvm/emulate.c

@@ -150,8 +150,6 @@ static int kvmppc_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_TBWL: break;
 	case SPRN_TBWU: break;
 
-	case SPRN_MSSSR0: break;
-
 	case SPRN_DEC:
 		vcpu->arch.dec = spr_val;
 		kvmppc_emulate_dec(vcpu);
@@ -202,9 +200,6 @@ static int kvmppc_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_PIR:
 		spr_val = vcpu->vcpu_id;
 		break;
-	case SPRN_MSSSR0:
-		spr_val = 0;
-		break;
 
 	/* Note: mftb and TBRL/TBWL are user-accessible, so
 	 * the guest can always access the real TB anyways.

arch/powerpc/kvm/powerpc.c

@@ -237,7 +237,8 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		r = RESUME_HOST;
 		break;
 	default:
-		BUG();
+		WARN_ON(1);
+		r = RESUME_GUEST;
 	}
 
 	return r;
@@ -305,6 +306,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_SREGS:
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
+	case KVM_CAP_PPC_EPR:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_HIOR:
@@ -412,7 +414,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_memory_slot *memslot,
                                    struct kvm_memory_slot old,
                                    struct kvm_userspace_memory_region *mem,
-                                   int user_alloc)
+                                   bool user_alloc)
 {
 	return kvmppc_core_prepare_memory_region(kvm, memslot, mem);
 }
@@ -420,7 +422,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 void kvm_arch_commit_memory_region(struct kvm *kvm,
                struct kvm_userspace_memory_region *mem,
                struct kvm_memory_slot old,
-               int user_alloc)
+               bool user_alloc)
 {
 	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
@@ -720,6 +722,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		for (i = 0; i < 9; ++i)
 			kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
 		vcpu->arch.hcall_needed = 0;
+#ifdef CONFIG_BOOKE
+	} else if (vcpu->arch.epr_needed) {
+		kvmppc_set_epr(vcpu, run->epr.epr);
+		vcpu->arch.epr_needed = 0;
+#endif
 	}
 
 	r = kvmppc_vcpu_run(run, vcpu);
@@ -761,6 +768,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+	case KVM_CAP_PPC_EPR:
+		r = 0;
+		vcpu->arch.epr_enabled = cap->args[0];
+		break;
 #ifdef CONFIG_BOOKE
 	case KVM_CAP_PPC_BOOKE_WATCHDOG:
 		r = 0;

arch/s390/include/asm/irq.h

@@ -41,6 +41,7 @@ enum interruption_class {
 	IRQIO_CSC,
 	IRQIO_PCI,
 	IRQIO_MSI,
+	IRQIO_VIR,
 	NMI_NMI,
 	CPU_RST,
 	NR_ARCH_IRQS

arch/s390/include/asm/kvm_host.h

@@ -20,9 +20,7 @@
 #include <asm/cpu.h>
 
 #define KVM_MAX_VCPUS 64
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_USER_MEM_SLOTS 32
 
 struct sca_entry {
 	atomic_t scn;
@@ -76,8 +74,11 @@ struct kvm_s390_sie_block {
 	__u64	epoch;			/* 0x0038 */
 	__u8	reserved40[4];		/* 0x0040 */
 #define LCTL_CR0	0x8000
+#define LCTL_CR6	0x0200
+#define LCTL_CR14	0x0002
 	__u16   lctl;			/* 0x0044 */
 	__s16	icpua;			/* 0x0046 */
+#define ICTL_LPSW 0x00400000
 	__u32	ictl;			/* 0x0048 */
 	__u32	eca;			/* 0x004c */
 	__u8	icptcode;		/* 0x0050 */
@@ -127,6 +128,7 @@ struct kvm_vcpu_stat {
 	u32 deliver_prefix_signal;
 	u32 deliver_restart_signal;
 	u32 deliver_program_int;
+	u32 deliver_io_int;
 	u32 exit_wait_state;
 	u32 instruction_stidp;
 	u32 instruction_spx;
@@ -187,6 +189,11 @@ struct kvm_s390_emerg_info {
 	__u16 code;
 };
 
+struct kvm_s390_mchk_info {
+	__u64 cr14;
+	__u64 mcic;
+};
+
 struct kvm_s390_interrupt_info {
 	struct list_head list;
 	u64	type;
@@ -197,6 +204,7 @@ struct kvm_s390_interrupt_info {
 		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_extcall_info extcall;
 		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_mchk_info mchk;
 	};
 };
 
@@ -254,6 +262,7 @@ struct kvm_arch{
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;
 	struct gmap *gmap;
+	int css_support;
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);

arch/s390/kernel/irq.c

@@ -81,6 +81,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	[IRQIO_CSC]  = {.name = "CSC", .desc = "[I/O] CHSC Subchannel"},
 	[IRQIO_PCI]  = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
 	[IRQIO_MSI]  = {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
+	[IRQIO_VIR]  = {.name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
 	[NMI_NMI]    = {.name = "NMI", .desc = "[NMI] Machine Check"},
 	[CPU_RST]    = {.name = "RST", .desc = "[CPU] CPU Restart"},
 };

arch/s390/kvm/intercept.c

@@ -26,27 +26,20 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
-			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
 	u64 useraddr;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctlg++;
-	if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
-		return -EOPNOTSUPP;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
 
 	if (useraddr & 7)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
 	reg = reg1;
 
-	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
 
 	do {
@@ -68,23 +61,19 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 {
 	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	u32 val = 0;
 	int reg, rc;
 
 	vcpu->stat.instruction_lctl++;
 
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+	useraddr = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (useraddr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
 
-	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
-		   disp2);
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
 	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
 
 	reg = reg1;
@@ -104,14 +93,31 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static intercept_handler_t instruction_handlers[256] = {
+static const intercept_handler_t eb_handlers[256] = {
+	[0x2f] = handle_lctlg,
+	[0x8a] = kvm_s390_handle_priv_eb,
+};
+
+static int handle_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t instruction_handlers[256] = {
 	[0x01] = kvm_s390_handle_01,
+	[0x82] = kvm_s390_handle_lpsw,
 	[0x83] = kvm_s390_handle_diag,
 	[0xae] = kvm_s390_handle_sigp,
 	[0xb2] = kvm_s390_handle_b2,
 	[0xb7] = handle_lctl,
+	[0xb9] = kvm_s390_handle_b9,
 	[0xe5] = kvm_s390_handle_e5,
-	[0xeb] = handle_lctlg,
+	[0xeb] = handle_eb,
 };
 
 static int handle_noop(struct kvm_vcpu *vcpu)
@@ -258,6 +264,7 @@ static const intercept_handler_t intercept_funcs[] = {
 	[0x0C >> 2] = handle_instruction_and_prog,
 	[0x10 >> 2] = handle_noop,
 	[0x14 >> 2] = handle_noop,
+	[0x18 >> 2] = handle_noop,
 	[0x1C >> 2] = kvm_s390_handle_wait,
 	[0x20 >> 2] = handle_validity,
 	[0x28 >> 2] = handle_stop,

arch/s390/kvm/interrupt.c

@@ -21,11 +21,31 @@
 #include "gaccess.h"
 #include "trace-s390.h"
 
+#define IOINT_SCHID_MASK 0x0000ffff
+#define IOINT_SSID_MASK 0x00030000
+#define IOINT_CSSID_MASK 0x03fc0000
+#define IOINT_AI_MASK 0x04000000
+
+static int is_ioint(u64 type)
+{
+	return ((type & 0xfffe0000u) != 0xfffe0000u);
+}
+
 static int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
 	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
 }
 
+static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
+}
+
+static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
+}
+
 static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 {
 	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
@@ -35,6 +55,13 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static u64 int_word_to_isc_bits(u32 int_word)
+{
+	u8 isc = (int_word & 0x38000000) >> 27;
+
+	return (0x80 >> isc) << 24;
+}
+
 static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 				      struct kvm_s390_interrupt_info *inti)
 {
@@ -67,7 +94,22 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_SET_PREFIX:
 	case KVM_S390_RESTART:
 		return 1;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
+			return 1;
+		return 0;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[6] &
+		    int_word_to_isc_bits(inti->io.io_int_word))
+			return 1;
+		return 0;
 	default:
+		printk(KERN_WARNING "illegal interrupt type %llx\n",
+		       inti->type);
 		BUG();
 	}
 	return 0;
@@ -93,6 +135,7 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
 		&vcpu->arch.sie_block->cpuflags);
 	vcpu->arch.sie_block->lctl = 0x0000;
+	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
@@ -116,6 +159,18 @@ static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_STOP:
 		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
 		break;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR14;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR6;
+		break;
 	default:
 		BUG();
 	}
@@ -297,6 +352,73 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			exception = 1;
 		break;
 
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+			   inti->mchk.mcic);
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->mchk.cr14,
+						 inti->mchk.mcic);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_PREFIXED);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u64(vcpu, __LC_MCCK_CODE, inti->mchk.mcic);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
+				   &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				     __LC_MCK_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+	{
+		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
+			inti->io.subchannel_nr;
+		__u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
+			inti->io.io_int_word;
+		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
+		vcpu->stat.deliver_io_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 param0, param1);
+		rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_ID,
+				   inti->io.subchannel_id);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u16(vcpu, __LC_SUBCHANNEL_NR,
+				   inti->io.subchannel_nr);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_IO_INT_PARM,
+				   inti->io.io_int_parm);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = put_guest_u32(vcpu, __LC_IO_INT_WORD,
+				   inti->io.io_int_word);
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_to_guest(vcpu, __LC_IO_OLD_PSW,
+				   &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+
+		rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				     __LC_IO_NEW_PSW, sizeof(psw_t));
+		if (rc == -EFAULT)
+			exception = 1;
+		break;
+	}
 	default:
 		BUG();
 	}
@@ -518,6 +640,61 @@ void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 	}
 }
 
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -540,12 +717,50 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	return 0;
 }
 
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti, *iter;
+
+	if ((!schid && !cr6) || (schid && cr6))
+		return NULL;
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	inti = NULL;
+	list_for_each_entry(iter, &fi->list, list) {
+		if (!is_ioint(iter->type))
+			continue;
+		if (cr6 &&
+		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
+			continue;
+		if (schid) {
+			if (((schid & 0x00000000ffff0000) >> 16) !=
+			    iter->io.subchannel_id)
+				continue;
+			if ((schid & 0x000000000000ffff) !=
+			    iter->io.subchannel_nr)
+				continue;
+		}
+		inti = iter;
+		break;
+	}
+	if (inti)
+		list_del_init(&inti->list);
+	if (list_empty(&fi->list))
+		atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return inti;
+}
+
 int kvm_s390_inject_vm(struct kvm *kvm,
 		       struct kvm_s390_interrupt *s390int)
 {
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_float_interrupt *fi;
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt_info *inti, *iter;
 	int sigcpu;
 
 	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
@@ -569,6 +784,29 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	case KVM_S390_SIGP_STOP:
 	case KVM_S390_INT_EXTERNAL_CALL:
 	case KVM_S390_INT_EMERGENCY:
+		kfree(inti);
+		return -EINVAL;
+	case KVM_S390_MCHK:
+		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+			 s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
+		inti->mchk.mcic = s390int->parm64;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (s390int->type & IOINT_AI_MASK)
+			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
+		else
+			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
+				 s390int->type & IOINT_CSSID_MASK,
+				 s390int->type & IOINT_SSID_MASK,
+				 s390int->type & IOINT_SCHID_MASK);
+		inti->type = s390int->type;
+		inti->io.subchannel_id = s390int->parm >> 16;
+		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
+		inti->io.io_int_parm = s390int->parm64 >> 32;
+		inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull;
+		break;
 	default:
 		kfree(inti);
 		return -EINVAL;
@@ -579,7 +817,22 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
-	list_add_tail(&inti->list, &fi->list);
+	if (!is_ioint(inti->type))
+		list_add_tail(&inti->list, &fi->list);
+	else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+		/* Keep I/O interrupts sorted in isc order. */
+		list_for_each_entry(iter, &fi->list, list) {
+			if (!is_ioint(iter->type))
+				continue;
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
+				continue;
+			break;
+		}
+		list_add_tail(&inti->list, &iter->list);
+	}
 	atomic_set(&fi->active, 1);
 	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
 	if (sigcpu == KVM_MAX_VCPUS) {
@@ -651,8 +904,15 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		inti->type = s390int->type;
 		inti->emerg.code = s390int->parm;
 		break;
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+			   s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.mcic = s390int->parm64;
+		break;
 	case KVM_S390_INT_VIRTIO:
 	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 	default:
 		kfree(inti);
 		return -EINVAL;

arch/s390/kvm/kvm-s390.c

@@ -140,6 +140,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 #endif
 	case KVM_CAP_SYNC_REGS:
 	case KVM_CAP_ONE_REG:
+	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_S390_CSS_SUPPORT:
 		r = 1;
 		break;
 	case KVM_CAP_NR_VCPUS:
@@ -234,6 +236,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		if (!kvm->arch.gmap)
 			goto out_nogmap;
 	}
+
+	kvm->arch.css_support = 0;
+
 	return 0;
 out_nogmap:
 	debug_unregister(kvm->arch.dbf);
@@ -659,6 +664,7 @@ rerun_vcpu:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
 	case KVM_EXIT_S390_UCONTROL:
+	case KVM_EXIT_S390_TSCH:
 		break;
 	default:
 		BUG();
@@ -766,6 +772,14 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	} else
 		prefix = 0;
 
+	/*
+	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+	 * copying in vcpu load/put. Lets update our copies before we save
+	 * it into the save area
+	 */
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->run->s.regs.acrs);
+
 	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
 			vcpu->arch.guest_fpregs.fprs, 128, prefix))
 		return -EFAULT;
@@ -810,6 +824,29 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
 	return 0;
 }
 
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_S390_CSS_SUPPORT:
+		if (!vcpu->kvm->arch.css_support) {
+			vcpu->kvm->arch.css_support = 1;
+			trace_kvm_s390_enable_css(vcpu->kvm);
+		}
+		r = 0;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -896,6 +933,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = 0;
 		break;
 	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			break;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -930,7 +976,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_memory_slot old,
 				   struct kvm_userspace_memory_region *mem,
-				   int user_alloc)
+				   bool user_alloc)
 {
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
@@ -960,7 +1006,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
-				int user_alloc)
+				bool user_alloc)
 {
 	int rc;
 

arch/s390/kvm/kvm-s390.h

@@ -65,21 +65,67 @@ static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
 	vcpu->arch.sie_block->ihcpu  = 0xffff;
 }
 
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
+					      u64 *address1, u64 *address2)
+{
+	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	u32 base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	u32 disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+
+	*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+	*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+	/* The displacement is a 20bit _SIGNED_ value */
+	if (disp2 & 0x80000)
+		disp2+=0xfff00000;
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
 int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
 enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
 void kvm_s390_tasklet(unsigned long parm);
 void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
 int kvm_s390_inject_vm(struct kvm *kvm,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid);
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
 int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu);
 
 /* implemented in sigp.c */
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);

arch/s390/kvm/priv.c

@@ -18,23 +18,21 @@
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
+#include <asm/ptrace.h>
+#include <asm/compat.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
 #include "trace.h"
 
 static int handle_set_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address = 0;
 	u8 tmp;
 
 	vcpu->stat.instruction_spx++;
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -67,15 +65,12 @@ out:
 
 static int handle_store_prefix(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	u32 address;
 
 	vcpu->stat.instruction_stpx++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	/* must be word boundary */
 	if (operand2 & 3) {
@@ -100,15 +95,12 @@ out:
 
 static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 useraddr;
 	int rc;
 
 	vcpu->stat.instruction_stap++;
-	useraddr = disp2;
-	if (base2)
-		useraddr += vcpu->run->s.regs.gprs[base2];
+
+	useraddr = kvm_s390_get_base_disp_s(vcpu);
 
 	if (useraddr & 1) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -135,24 +127,96 @@ static int handle_skey(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static int handle_stsch(struct kvm_vcpu *vcpu)
+static int handle_tpi(struct kvm_vcpu *vcpu)
 {
-	vcpu->stat.instruction_stsch++;
-	VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
-	/* condition code 3 */
+	u64 addr;
+	struct kvm_s390_interrupt_info *inti;
+	int cc;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0);
+	if (inti) {
+		if (addr) {
+			/*
+			 * Store the two-word I/O interruption code into the
+			 * provided area.
+			 */
+			put_guest_u16(vcpu, addr, inti->io.subchannel_id);
+			put_guest_u16(vcpu, addr + 2, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, addr + 4, inti->io.io_int_parm);
+		} else {
+			/*
+			 * Store the three-word I/O interruption code into
+			 * the appropriate lowcore area.
+			 */
+			put_guest_u16(vcpu, 184, inti->io.subchannel_id);
+			put_guest_u16(vcpu, 186, inti->io.subchannel_nr);
+			put_guest_u32(vcpu, 188, inti->io.io_int_parm);
+			put_guest_u32(vcpu, 192, inti->io.io_int_word);
+		}
+		cc = 1;
+	} else
+		cc = 0;
+	kfree(inti);
+	/* Set condition code and we're done. */
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+	vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
 	return 0;
 }
 
-static int handle_chsc(struct kvm_vcpu *vcpu)
+static int handle_tsch(struct kvm_vcpu *vcpu)
 {
-	vcpu->stat.instruction_chsc++;
-	VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
-	/* condition code 3 */
-	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
-	vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
-	return 0;
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
+				   vcpu->run->s.regs.gprs[1]);
+
+	/*
+	 * Prepare exit to userspace.
+	 * We indicate whether we dequeued a pending I/O interrupt
+	 * so that userspace can re-inject it if the instruction gets
+	 * a program check. While this may re-order the pending I/O
+	 * interrupts, this is no problem since the priority is kept
+	 * intact.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_S390_TSCH;
+	vcpu->run->s390_tsch.dequeued = !!inti;
+	if (inti) {
+		vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id;
+		vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr;
+		vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm;
+		vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word;
+	}
+	vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb;
+	kfree(inti);
+	return -EREMOTE;
+}
+
+static int handle_io_inst(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
+
+	if (vcpu->kvm->arch.css_support) {
+		/*
+		 * Most I/O instructions will be handled by userspace.
+		 * Exceptions are tpi and the interrupt portion of tsch.
+		 */
+		if (vcpu->arch.sie_block->ipa == 0xb236)
+			return handle_tpi(vcpu);
+		if (vcpu->arch.sie_block->ipa == 0xb235)
+			return handle_tsch(vcpu);
+		/* Handle in userspace. */
+		return -EOPNOTSUPP;
+	} else {
+		/*
+		 * Set condition code 3 to stop the guest from issueing channel
+		 * I/O instructions.
+		 */
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+		return 0;
+	}
 }
 
 static int handle_stfl(struct kvm_vcpu *vcpu)
@@ -176,17 +240,107 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static void handle_new_psw(struct kvm_vcpu *vcpu)
+{
+	/* Check whether the new psw is enabled for machine checks. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK)
+		kvm_s390_deliver_pending_machine_checks(vcpu);
+}
+
+#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA)
+#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL
+#define PSW_ADDR_24 0x00000000000fffffUL
+#define PSW_ADDR_31 0x000000007fffffffUL
+
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_compat_t new_psw;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	if (!(new_psw.mask & PSW32_MASK_BASE)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask =
+		(new_psw.mask & ~PSW32_MASK_BASE) << 32;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
+static int handle_lpswe(struct kvm_vcpu *vcpu)
+{
+	u64 addr;
+	psw_t new_psw;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (addr & 7) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw))) {
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out;
+	}
+
+	vcpu->arch.sie_block->gpsw.mask = new_psw.mask;
+	vcpu->arch.sie_block->gpsw.addr = new_psw.addr;
+
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_UNASSIGNED) ||
+	    (((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	      PSW_MASK_BA) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_31)) ||
+	    (!(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) &&
+	     (vcpu->arch.sie_block->gpsw.addr & ~PSW_ADDR_24)) ||
+	    ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_ADDR_MODE) ==
+	     PSW_MASK_EA)) {
+		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+		goto out;
+	}
+
+	handle_new_psw(vcpu);
+out:
+	return 0;
+}
+
 static int handle_stidp(struct kvm_vcpu *vcpu)
 {
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	int rc;
 
 	vcpu->stat.instruction_stidp++;
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 7) {
 		kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -240,17 +394,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
 	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
 	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u64 operand2;
 	unsigned long mem;
 
 	vcpu->stat.instruction_stsi++;
 	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
 
-	operand2 = disp2;
-	if (base2)
-		operand2 += vcpu->run->s.regs.gprs[base2];
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
 
 	if (operand2 & 0xfff && fc > 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -297,7 +447,7 @@ out_fail:
 	return 0;
 }
 
-static intercept_handler_t priv_handlers[256] = {
+static const intercept_handler_t b2_handlers[256] = {
 	[0x02] = handle_stidp,
 	[0x10] = handle_set_prefix,
 	[0x11] = handle_store_prefix,
@@ -305,10 +455,25 @@ static intercept_handler_t priv_handlers[256] = {
 	[0x29] = handle_skey,
 	[0x2a] = handle_skey,
 	[0x2b] = handle_skey,
-	[0x34] = handle_stsch,
-	[0x5f] = handle_chsc,
+	[0x30] = handle_io_inst,
+	[0x31] = handle_io_inst,
+	[0x32] = handle_io_inst,
+	[0x33] = handle_io_inst,
+	[0x34] = handle_io_inst,
+	[0x35] = handle_io_inst,
+	[0x36] = handle_io_inst,
+	[0x37] = handle_io_inst,
+	[0x38] = handle_io_inst,
+	[0x39] = handle_io_inst,
+	[0x3a] = handle_io_inst,
+	[0x3b] = handle_io_inst,
+	[0x3c] = handle_io_inst,
+	[0x5f] = handle_io_inst,
+	[0x74] = handle_io_inst,
+	[0x76] = handle_io_inst,
 	[0x7d] = handle_stsi,
 	[0xb1] = handle_stfl,
+	[0xb2] = handle_lpswe,
 };
 
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
@@ -322,7 +487,7 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	 * state bit and (a) handle the instruction or (b) send a code 2
 	 * program check.
 	 * Anything else goes to userspace.*/
-	handler = priv_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
 	if (handler) {
 		if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 			return kvm_s390_inject_program_int(vcpu,
@@ -333,19 +498,74 @@ int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
 	return -EOPNOTSUPP;
 }
 
+static int handle_epsw(struct kvm_vcpu *vcpu)
+{
+	int reg1, reg2;
+
+	reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24;
+	reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
+
+	/* This basically extracts the mask half of the psw. */
+	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000;
+	vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32;
+	if (reg2) {
+		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000;
+		vcpu->run->s.regs.gprs[reg2] |=
+			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff;
+	}
+	return 0;
+}
+
+static const intercept_handler_t b9_handlers[256] = {
+	[0x8d] = handle_epsw,
+	[0x9c] = handle_io_inst,
+};
+
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* This is handled just as for the B2 instructions. */
+	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler) {
+		if ((handler != handle_epsw) &&
+		    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE))
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t eb_handlers[256] = {
+	[0x8a] = handle_io_inst,
+};
+
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* All eb instructions that end up here are privileged. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
 static int handle_tprot(struct kvm_vcpu *vcpu)
 {
-	int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
-	int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
-	int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
-	int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
-	u64 address1 = disp1 + base1 ? vcpu->run->s.regs.gprs[base1] : 0;
-	u64 address2 = disp2 + base2 ? vcpu->run->s.regs.gprs[base2] : 0;
+	u64 address1, address2;
 	struct vm_area_struct *vma;
 	unsigned long user_address;
 
 	vcpu->stat.instruction_tprot++;
 
+	kvm_s390_get_base_disp_sse(vcpu, &address1, &address2);
+
 	/* we only handle the Linux memory detection case:
 	 * access key == 0
 	 * guest DAT == off
@@ -405,7 +625,7 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static intercept_handler_t x01_handlers[256] = {
+static const intercept_handler_t x01_handlers[256] = {
 	[0x07] = handle_sckpf,
 };
 

arch/s390/kvm/sigp.c

@@ -137,8 +137,10 @@ static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
 	inti->type = KVM_S390_SIGP_STOP;
 
 	spin_lock_bh(&li->lock);
-	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED))
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+		kfree(inti);
 		goto out;
+	}
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
 	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
@@ -324,8 +326,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
 	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
-	int base2 = vcpu->arch.sie_block->ipb >> 28;
-	int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
 	u32 parameter;
 	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
 	u8 order_code;
@@ -336,9 +336,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		return kvm_s390_inject_program_int(vcpu,
 						   PGM_PRIVILEGED_OPERATION);
 
-	order_code = disp2;
-	if (base2)
-		order_code += vcpu->run->s.regs.gprs[base2];
+	order_code = kvm_s390_get_base_disp_rs(vcpu);
 
 	if (r1 % 2)
 		parameter = vcpu->run->s.regs.gprs[r1];

arch/s390/kvm/trace-s390.h

@@ -141,13 +141,13 @@ TRACE_EVENT(kvm_s390_inject_vcpu,
  * Trace point for the actual delivery of interrupts.
  */
 TRACE_EVENT(kvm_s390_deliver_interrupt,
-	    TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1),
+	    TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1),
 	    TP_ARGS(id, type, data0, data1),
 
 	    TP_STRUCT__entry(
 		    __field(int, id)
 		    __field(__u32, inttype)
-		    __field(__u32, data0)
+		    __field(__u64, data0)
 		    __field(__u64, data1)
 		    ),
 
@@ -159,7 +159,7 @@ TRACE_EVENT(kvm_s390_deliver_interrupt,
 		    ),
 
 	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
-		      "data:%08x %016llx",
+		      "data:%08llx %016llx",
 		      __entry->id, __entry->inttype,
 		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
 		      __entry->data0, __entry->data1)
@@ -204,6 +204,26 @@ TRACE_EVENT(kvm_s390_stop_request,
 	);
 
 
+/*
+ * Trace point for enabling channel I/O instruction support.
+ */
+TRACE_EVENT(kvm_s390_enable_css,
+	    TP_PROTO(void *kvm),
+	    TP_ARGS(kvm),
+
+	    TP_STRUCT__entry(
+		    __field(void *, kvm)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->kvm = kvm;
+		    ),
+
+	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+		      __entry->kvm)
+	);
+
+
 #endif /* _TRACE_KVMS390_H */
 
 /* This part must be outside protection */

arch/x86/include/asm/kvm_host.h

@@ -33,10 +33,10 @@
 
 #define KVM_MAX_VCPUS 254
 #define KVM_SOFT_MAX_VCPUS 160
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+#define KVM_USER_MEM_SLOTS 125
+/* memory slots that are not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 3
+#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
 #define KVM_MMIO_SIZE 16
 
@@ -219,11 +219,6 @@ struct kvm_mmu_page {
 	u64 *spt;
 	/* hold the gfn of each spte inside spt */
 	gfn_t *gfns;
-	/*
-	 * One bit set per slot which has memory
-	 * in this shadow page.
-	 */
-	DECLARE_BITMAP(slot_bitmap, KVM_MEM_SLOTS_NUM);
 	bool unsync;
 	int root_count;          /* Currently serving as active root */
 	unsigned int unsync_children;
@@ -502,6 +497,13 @@ struct kvm_vcpu_arch {
 		u64 msr_val;
 		struct gfn_to_hva_cache data;
 	} pv_eoi;
+
+	/*
+	 * Indicate whether the access faults on its page table in guest
+	 * which is set when fix page fault and used to detect unhandeable
+	 * instruction.
+	 */
+	bool write_fault_to_shadow_pgtable;
 };
 
 struct kvm_lpage_info {
@@ -697,6 +699,11 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
+	int (*vm_has_apicv)(struct kvm *kvm);
+	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
+	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
@@ -991,6 +998,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);

arch/x86/include/asm/kvm_para.h

@@ -27,7 +27,7 @@ static inline bool kvm_check_and_clear_guest_paused(void)
  *
  * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
  * The hypercall number should be placed in rax and the return value will be
- * placed in rax.  No other registers will be clobbered unless explicited
+ * placed in rax.  No other registers will be clobbered unless explicitly
  * noted by the particular hypercall.
  */
 

arch/x86/include/asm/vmx.h

@@ -57,9 +57,12 @@
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE   0x00000010
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT       0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY    0x00000200
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 
@@ -97,6 +100,7 @@ enum vmcs_field {
 	GUEST_GS_SELECTOR               = 0x0000080a,
 	GUEST_LDTR_SELECTOR             = 0x0000080c,
 	GUEST_TR_SELECTOR               = 0x0000080e,
+	GUEST_INTR_STATUS               = 0x00000810,
 	HOST_ES_SELECTOR                = 0x00000c00,
 	HOST_CS_SELECTOR                = 0x00000c02,
 	HOST_SS_SELECTOR                = 0x00000c04,
@@ -124,6 +128,14 @@ enum vmcs_field {
 	APIC_ACCESS_ADDR_HIGH		= 0x00002015,
 	EPT_POINTER                     = 0x0000201a,
 	EPT_POINTER_HIGH                = 0x0000201b,
+	EOI_EXIT_BITMAP0                = 0x0000201c,
+	EOI_EXIT_BITMAP0_HIGH           = 0x0000201d,
+	EOI_EXIT_BITMAP1                = 0x0000201e,
+	EOI_EXIT_BITMAP1_HIGH           = 0x0000201f,
+	EOI_EXIT_BITMAP2                = 0x00002020,
+	EOI_EXIT_BITMAP2_HIGH           = 0x00002021,
+	EOI_EXIT_BITMAP3                = 0x00002022,
+	EOI_EXIT_BITMAP3_HIGH           = 0x00002023,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
 	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
 	VMCS_LINK_POINTER               = 0x00002800,
@@ -346,9 +358,9 @@ enum vmcs_field {
 
 #define AR_RESERVD_MASK 0xfffe0f00
 
-#define TSS_PRIVATE_MEMSLOT			(KVM_MEMORY_SLOTS + 0)
-#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_MEMORY_SLOTS + 1)
-#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_MEMORY_SLOTS + 2)
+#define TSS_PRIVATE_MEMSLOT			(KVM_USER_MEM_SLOTS + 0)
+#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 1)
+#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT	(KVM_USER_MEM_SLOTS + 2)
 
 #define VMX_NR_VPIDS				(1 << 16)
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT		1

arch/x86/include/uapi/asm/vmx.h

@@ -62,10 +62,12 @@
 #define EXIT_REASON_MCE_DURING_VMENTRY  41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
+#define EXIT_REASON_EOI_INDUCED         45
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD              54
 #define EXIT_REASON_XSETBV              55
+#define EXIT_REASON_APIC_WRITE          56
 #define EXIT_REASON_INVPCID             58
 
 #define VMX_EXIT_REASONS \
@@ -103,7 +105,12 @@
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
-	{ EXIT_REASON_WBINVD,                "WBINVD" }
+	{ EXIT_REASON_WBINVD,                "WBINVD" }, \
+	{ EXIT_REASON_APIC_WRITE,            "APIC_WRITE" }, \
+	{ EXIT_REASON_EOI_INDUCED,           "EOI_INDUCED" }, \
+	{ EXIT_REASON_INVALID_STATE,         "INVALID_STATE" }, \
+	{ EXIT_REASON_INVD,                  "INVD" }, \
+	{ EXIT_REASON_INVPCID,               "INVPCID" }
 
 
 #endif /* _UAPIVMX_H */

arch/x86/kernel/kvmclock.c

@@ -218,6 +218,9 @@ static void kvm_shutdown(void)
 void __init kvmclock_init(void)
 {
 	unsigned long mem;
+	int size;
+
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
 	if (!kvm_para_available())
 		return;
@@ -231,16 +234,14 @@ void __init kvmclock_init(void)
 	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
-	mem = memblock_alloc(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS,
-			     PAGE_SIZE);
+	mem = memblock_alloc(size, PAGE_SIZE);
 	if (!mem)
 		return;
 	hv_clock = __va(mem);
 
 	if (kvm_register_clock("boot clock")) {
 		hv_clock = NULL;
-		memblock_free(mem,
-			sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
+		memblock_free(mem, size);
 		return;
 	}
 	pv_time_ops.sched_clock = kvm_clock_read;
@@ -275,7 +276,7 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 	struct pvclock_vcpu_time_info *vcpu_time;
 	unsigned int size;
 
-	size = sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS;
+	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
 
 	preempt_disable();
 	cpu = smp_processor_id();

arch/x86/kvm/i8254.c

@@ -122,7 +122,6 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	 */
 	remaining = hrtimer_get_remaining(&ps->timer);
 	elapsed = ps->period - ktime_to_ns(remaining);
-	elapsed = mod_64(elapsed, ps->period);
 
 	return elapsed;
 }

arch/x86/kvm/i8259.c

@@ -241,6 +241,8 @@ int kvm_pic_read_irq(struct kvm *kvm)
 	int irq, irq2, intno;
 	struct kvm_pic *s = pic_irqchip(kvm);
 
+	s->output = 0;
+
 	pic_lock(s);
 	irq = pic_get_irq(&s->pics[0]);
 	if (irq >= 0) {

arch/x86/kvm/irq.c

@@ -37,50 +37,82 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
+/*
+ * check if there is pending interrupt from
+ * non-APIC source without intack.
+ */
+static int kvm_cpu_has_extint(struct kvm_vcpu *v)
+{
+	if (kvm_apic_accept_pic_intr(v))
+		return pic_irqchip(v->kvm)->output;	/* PIC */
+	else
+		return 0;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
+	if (!irqchip_in_kernel(v->kvm))
+		return v->arch.interrupt.pending;
+
+	if (kvm_cpu_has_extint(v))
+		return 1;
+
+	if (kvm_apic_vid_enabled(v->kvm))
+		return 0;
+
+	return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
+}
+
 /*
  * check if there is pending interrupt without
  * intack.
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	struct kvm_pic *s;
-
 	if (!irqchip_in_kernel(v->kvm))
 		return v->arch.interrupt.pending;
 
-	if (kvm_apic_has_interrupt(v) == -1) {	/* LAPIC */
-		if (kvm_apic_accept_pic_intr(v)) {
-			s = pic_irqchip(v->kvm);	/* PIC */
-			return s->output;
-		} else
-			return 0;
-	}
-	return 1;
+	if (kvm_cpu_has_extint(v))
+		return 1;
+
+	return kvm_apic_has_interrupt(v) != -1;	/* LAPIC */
 }
 EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
 
+/*
+ * Read pending interrupt(from non-APIC source)
+ * vector and intack.
+ */
+static int kvm_cpu_get_extint(struct kvm_vcpu *v)
+{
+	if (kvm_cpu_has_extint(v))
+		return kvm_pic_read_irq(v->kvm); /* PIC */
+	return -1;
+}
+
 /*
  * Read pending interrupt vector and intack.
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	struct kvm_pic *s;
 	int vector;
 
 	if (!irqchip_in_kernel(v->kvm))
 		return v->arch.interrupt.nr;
 
-	vector = kvm_get_apic_interrupt(v);	/* APIC */
-	if (vector == -1) {
-		if (kvm_apic_accept_pic_intr(v)) {
-			s = pic_irqchip(v->kvm);
-			s->output = 0;		/* PIC */
-			vector = kvm_pic_read_irq(v->kvm);
-		}
-	}
-	return vector;
+	vector = kvm_cpu_get_extint(v);
+
+	if (kvm_apic_vid_enabled(v->kvm) || vector != -1)
+		return vector;			/* PIC */
+
+	return kvm_get_apic_interrupt(v);	/* APIC */
 }
-EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt);
 
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 {

arch/x86/kvm/lapic.c

@@ -140,31 +140,56 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline int apic_x2apic_mode(struct kvm_lapic *apic)
-{
-	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
-}
-
 static inline int kvm_apic_id(struct kvm_lapic *apic)
 {
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
-static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+				struct kvm_lapic_irq *irq,
+				u64 *eoi_exit_bitmap)
 {
-	u16 cid;
-	ldr >>= 32 - map->ldr_bits;
-	cid = (ldr >> map->cid_shift) & map->cid_mask;
+	struct kvm_lapic **dst;
+	struct kvm_apic_map *map;
+	unsigned long bitmap = 1;
+	int i;
 
-	BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+	rcu_read_lock();
+	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
-	return cid;
-}
+	if (unlikely(!map)) {
+		__set_bit(irq->vector, (unsigned long *)eoi_exit_bitmap);
+		goto out;
+	}
 
-static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
-{
-	ldr >>= (32 - map->ldr_bits);
-	return ldr & map->lid_mask;
+	if (irq->dest_mode == 0) { /* physical mode */
+		if (irq->delivery_mode == APIC_DM_LOWEST ||
+				irq->dest_id == 0xff) {
+			__set_bit(irq->vector,
+				  (unsigned long *)eoi_exit_bitmap);
+			goto out;
+		}
+		dst = &map->phys_map[irq->dest_id & 0xff];
+	} else {
+		u32 mda = irq->dest_id << (32 - map->ldr_bits);
+
+		dst = map->logical_map[apic_cluster_id(map, mda)];
+
+		bitmap = apic_logical_id(map, mda);
+	}
+
+	for_each_set_bit(i, &bitmap, 16) {
+		if (!dst[i])
+			continue;
+		if (dst[i]->vcpu == vcpu) {
+			__set_bit(irq->vector,
+				  (unsigned long *)eoi_exit_bitmap);
+			break;
+		}
+	}
+
+out:
+	rcu_read_unlock();
 }
 
 static void recalculate_apic_map(struct kvm *kvm)
@@ -230,6 +255,8 @@ out:
 
 	if (old)
 		kfree_rcu(old, rcu);
+
+	kvm_ioapic_make_eoibitmap_request(kvm);
 }
 
 static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
@@ -345,6 +372,10 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 {
 	int result;
 
+	/*
+	 * Note that irr_pending is just a hint. It will be always
+	 * true with virtual interrupt delivery enabled.
+	 */
 	if (!apic->irr_pending)
 		return -1;
 
@@ -461,6 +492,8 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
 static inline int apic_find_highest_isr(struct kvm_lapic *apic)
 {
 	int result;
+
+	/* Note that isr_count is always 1 with vid enabled */
 	if (!apic->isr_count)
 		return -1;
 	if (likely(apic->highest_isr_cache != -1))
@@ -740,6 +773,19 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
 }
 
+static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
+{
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+		int trigger_mode;
+		if (apic_test_vector(vector, apic->regs + APIC_TMR))
+			trigger_mode = IOAPIC_LEVEL_TRIG;
+		else
+			trigger_mode = IOAPIC_EDGE_TRIG;
+		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+	}
+}
+
 static int apic_set_eoi(struct kvm_lapic *apic)
 {
 	int vector = apic_find_highest_isr(apic);
@@ -756,19 +802,26 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
-		int trigger_mode;
-		if (apic_test_vector(vector, apic->regs + APIC_TMR))
-			trigger_mode = IOAPIC_LEVEL_TRIG;
-		else
-			trigger_mode = IOAPIC_EDGE_TRIG;
-		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
-	}
+	kvm_ioapic_send_eoi(apic, vector);
 	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
 	return vector;
 }
 
+/*
+ * this interface assumes a trap-like exit, which has already finished
+ * desired side effect including vISR and vPPR update.
+ */
+void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector)
+{
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	trace_kvm_eoi(apic, vector);
+
+	kvm_ioapic_send_eoi(apic, vector);
+	kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_set_eoi_accelerated);
+
 static void apic_send_ipi(struct kvm_lapic *apic)
 {
 	u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
@@ -1212,6 +1265,21 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
+/* emulate APIC access in a trap manner */
+void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
+{
+	u32 val = 0;
+
+	/* hw has done the conditional check and inst decode */
+	offset &= 0xff0;
+
+	apic_reg_read(vcpu->arch.apic, offset, 4, &val);
+
+	/* TODO: optimize to just emulate side effect w/o one more write */
+	apic_reg_write(vcpu->arch.apic, offset, val);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode);
+
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -1288,6 +1356,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
+	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	if (!apic) {
@@ -1309,11 +1378,16 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		value &= ~MSR_IA32_APICBASE_BSP;
 
 	vcpu->arch.apic_base = value;
-	if (apic_x2apic_mode(apic)) {
-		u32 id = kvm_apic_id(apic);
-		u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
-		kvm_apic_set_ldr(apic, ldr);
+	if ((old_value ^ value) & X2APIC_ENABLE) {
+		if (value & X2APIC_ENABLE) {
+			u32 id = kvm_apic_id(apic);
+			u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+			kvm_apic_set_ldr(apic, ldr);
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true);
+		} else
+			kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false);
 	}
+
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
 
@@ -1359,8 +1433,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
-	apic->irr_pending = false;
-	apic->isr_count = 0;
+	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
@@ -1575,8 +1649,10 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
-	apic->isr_count = count_vectors(apic->regs + APIC_ISR);
+	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
+	kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic));
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 

arch/x86/kvm/lapic.h

@@ -64,6 +64,9 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 
+void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
+void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
+
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
@@ -124,4 +127,35 @@ static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
 	return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
 }
 
+static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+{
+	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
+}
+
+static inline bool kvm_apic_vid_enabled(struct kvm *kvm)
+{
+	return kvm_x86_ops->vm_has_apicv(kvm);
+}
+
+static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+{
+	u16 cid;
+	ldr >>= 32 - map->ldr_bits;
+	cid = (ldr >> map->cid_shift) & map->cid_mask;
+
+	BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+
+	return cid;
+}
+
+static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
+{
+	ldr >>= (32 - map->ldr_bits);
+	return ldr & map->lid_mask;
+}
+
+void kvm_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+				struct kvm_lapic_irq *irq,
+				u64 *eoi_bitmap);
+
 #endif

arch/x86/kvm/mmu.c

@@ -448,7 +448,8 @@ static bool __check_direct_spte_mmio_pf(u64 spte)
 
 static bool spte_is_locklessly_modifiable(u64 spte)
 {
-	return !(~spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE));
+	return (spte & (SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE)) ==
+		(SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE);
 }
 
 static bool spte_has_volatile_bits(u64 spte)
@@ -831,8 +832,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
 
-	max_level = kvm_x86_ops->get_lpage_level() < host_level ?
-		kvm_x86_ops->get_lpage_level() : host_level;
+	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
 		if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
@@ -1142,7 +1142,7 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
-				 int level, bool pt_protect)
+				 bool pt_protect)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1180,7 +1180,7 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	while (mask) {
 		rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
 				      PT_PAGE_TABLE_LEVEL, slot);
-		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false);
+		__rmap_write_protect(kvm, rmapp, false);
 
 		/* clear the first set bit */
 		mask &= mask - 1;
@@ -1199,7 +1199,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 	for (i = PT_PAGE_TABLE_LEVEL;
 	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
 		rmapp = __gfn_to_rmap(gfn, i, slot);
-		write_protected |= __rmap_write_protect(kvm, rmapp, i, true);
+		write_protected |= __rmap_write_protect(kvm, rmapp, true);
 	}
 
 	return write_protected;
@@ -1460,28 +1460,14 @@ static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
 }
 
-/*
- * Remove the sp from shadow page cache, after call it,
- * we can not find this sp from the cache, and the shadow
- * page table is still valid.
- * It should be under the protection of mmu lock.
- */
-static void kvm_mmu_isolate_page(struct kvm_mmu_page *sp)
+static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
 {
 	ASSERT(is_empty_shadow_page(sp->spt));
 	hlist_del(&sp->hash_link);
-	if (!sp->role.direct)
-		free_page((unsigned long)sp->gfns);
-}
-
-/*
- * Free the shadow page table and the sp, we can do it
- * out of the protection of mmu lock.
- */
-static void kvm_mmu_free_page(struct kvm_mmu_page *sp)
-{
 	list_del(&sp->link);
 	free_page((unsigned long)sp->spt);
+	if (!sp->role.direct)
+		free_page((unsigned long)sp->gfns);
 	kmem_cache_free(mmu_page_header_cache, sp);
 }
 
@@ -1522,7 +1508,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
 		sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
 	set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
 	list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
-	bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM);
 	sp->parent_ptes = 0;
 	mmu_page_add_parent_pte(vcpu, sp, parent_pte);
 	kvm_mod_used_mmu_pages(vcpu->kvm, +1);
@@ -1973,9 +1958,9 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
 {
 	u64 spte;
 
-	spte = __pa(sp->spt)
-		| PT_PRESENT_MASK | PT_ACCESSED_MASK
-		| PT_WRITABLE_MASK | PT_USER_MASK;
+	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+
 	mmu_spte_set(sptep, spte);
 }
 
@@ -2126,7 +2111,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	do {
 		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
 		WARN_ON(!sp->role.invalid || sp->root_count);
-		kvm_mmu_isolate_page(sp);
 		kvm_mmu_free_page(sp);
 	} while (!list_empty(invalid_list));
 }
@@ -2144,6 +2128,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	 * change the value
 	 */
 
+	spin_lock(&kvm->mmu_lock);
+
 	if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) {
 		while (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages &&
 			!list_empty(&kvm->arch.active_mmu_pages)) {
@@ -2158,6 +2144,8 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 	}
 
 	kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages;
+
+	spin_unlock(&kvm->mmu_lock);
 }
 
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
@@ -2183,14 +2171,6 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page);
 
-static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn)
-{
-	int slot = memslot_id(kvm, gfn);
-	struct kvm_mmu_page *sp = page_header(__pa(pte));
-
-	__set_bit(slot, sp->slot_bitmap);
-}
-
 /*
  * The function is based on mtrr_type_lookup() in
  * arch/x86/kernel/cpu/mtrr/generic.c
@@ -2332,9 +2312,8 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 		if (s->role.level != PT_PAGE_TABLE_LEVEL)
 			return 1;
 
-		if (!need_unsync && !s->unsync) {
+		if (!s->unsync)
 			need_unsync = true;
-		}
 	}
 	if (need_unsync)
 		kvm_unsync_pages(vcpu, gfn);
@@ -2342,8 +2321,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 }
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-		    unsigned pte_access, int user_fault,
-		    int write_fault, int level,
+		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
@@ -2378,20 +2356,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 	spte |= (u64)pfn << PAGE_SHIFT;
 
-	if ((pte_access & ACC_WRITE_MASK)
-	    || (!vcpu->arch.mmu.direct_map && write_fault
-		&& !is_write_protection(vcpu) && !user_fault)) {
+	if (pte_access & ACC_WRITE_MASK) {
 
 		/*
-		 * There are two cases:
-		 * - the one is other vcpu creates new sp in the window
-		 *   between mapping_level() and acquiring mmu-lock.
-		 * - the another case is the new sp is created by itself
-		 *   (page-fault path) when guest uses the target gfn as
-		 *   its page table.
-		 * Both of these cases can be fixed by allowing guest to
-		 * retry the access, it will refault, then we can establish
-		 * the mapping by using small page.
+		 * Other vcpu creates new sp in the window between
+		 * mapping_level() and acquiring mmu-lock. We can
+		 * allow guest to retry the access, the mapping can
+		 * be fixed if guest refault.
 		 */
 		if (level > PT_PAGE_TABLE_LEVEL &&
 		    has_wrprotected_page(vcpu->kvm, gfn, level))
@@ -2399,19 +2370,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 		spte |= PT_WRITABLE_MASK | SPTE_MMU_WRITEABLE;
 
-		if (!vcpu->arch.mmu.direct_map
-		    && !(pte_access & ACC_WRITE_MASK)) {
-			spte &= ~PT_USER_MASK;
-			/*
-			 * If we converted a user page to a kernel page,
-			 * so that the kernel can write to it when cr0.wp=0,
-			 * then we should prevent the kernel from executing it
-			 * if SMEP is enabled.
-			 */
-			if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-				spte |= PT64_NX_MASK;
-		}
-
 		/*
 		 * Optimization: for pte sync, if spte was writable the hash
 		 * lookup is unnecessary (and expensive). Write protection
@@ -2441,19 +2399,15 @@ done:
 }
 
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-			 unsigned pt_access, unsigned pte_access,
-			 int user_fault, int write_fault,
-			 int *emulate, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative,
+			 unsigned pte_access, int write_fault, int *emulate,
+			 int level, gfn_t gfn, pfn_t pfn, bool speculative,
 			 bool host_writable)
 {
 	int was_rmapped = 0;
 	int rmap_count;
 
-	pgprintk("%s: spte %llx access %x write_fault %d"
-		 " user_fault %d gfn %llx\n",
-		 __func__, *sptep, pt_access,
-		 write_fault, user_fault, gfn);
+	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
+		 *sptep, write_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
 		/*
@@ -2477,9 +2431,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			was_rmapped = 1;
 	}
 
-	if (set_spte(vcpu, sptep, pte_access, user_fault, write_fault,
-		      level, gfn, pfn, speculative, true,
-		      host_writable)) {
+	if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative,
+	      true, host_writable)) {
 		if (write_fault)
 			*emulate = 1;
 		kvm_mmu_flush_tlb(vcpu);
@@ -2497,7 +2450,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		++vcpu->kvm->stat.lpages;
 
 	if (is_shadow_present_pte(*sptep)) {
-		page_header_update_slot(vcpu->kvm, sptep, gfn);
 		if (!was_rmapped) {
 			rmap_count = rmap_add(vcpu, sptep, gfn);
 			if (rmap_count > RMAP_RECYCLE_THRESHOLD)
@@ -2571,10 +2523,9 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 		return -1;
 
 	for (i = 0; i < ret; i++, gfn++, start++)
-		mmu_set_spte(vcpu, start, ACC_ALL,
-			     access, 0, 0, NULL,
-			     sp->role.level, gfn,
-			     page_to_pfn(pages[i]), true, true);
+		mmu_set_spte(vcpu, start, access, 0, NULL,
+			     sp->role.level, gfn, page_to_pfn(pages[i]),
+			     true, true);
 
 	return 0;
 }
@@ -2633,11 +2584,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 
 	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
 		if (iterator.level == level) {
-			unsigned pte_access = ACC_ALL;
-
-			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
-				     0, write, &emulate,
-				     level, gfn, pfn, prefault, map_writable);
+			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
+				     write, &emulate, level, gfn, pfn,
+				     prefault, map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
 			++vcpu->stat.pf_fixed;
 			break;
@@ -2652,11 +2601,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
 
-			mmu_spte_set(iterator.sptep,
-				     __pa(sp->spt)
-				     | PT_PRESENT_MASK | PT_WRITABLE_MASK
-				     | shadow_user_mask | shadow_x_mask
-				     | shadow_accessed_mask);
+			link_shadow_page(iterator.sptep, sp);
 		}
 	}
 	return emulate;
@@ -3719,6 +3664,7 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 	else
 		r = paging32_init_context(vcpu, context);
 
+	vcpu->arch.mmu.base_role.nxe = is_nx(vcpu);
 	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
 	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
 	vcpu->arch.mmu.base_role.smep_andnot_wp
@@ -3885,7 +3831,7 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
 		/* Handle a 32-bit guest writing two halves of a 64-bit gpte */
 		*gpa &= ~(gpa_t)7;
 		*bytes = 8;
-		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8));
+		r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, 8);
 		if (r)
 			gentry = 0;
 		new = (const u8 *)&gentry;
@@ -4039,7 +3985,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			      !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
 			      & mask.word) && rmap_can_add(vcpu))
 				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
-			if (!remote_flush && need_remote_flush(entry, *spte))
+			if (need_remote_flush(entry, *spte))
 				remote_flush = true;
 			++spte;
 		}
@@ -4198,26 +4144,36 @@ int kvm_mmu_setup(struct kvm_vcpu *vcpu)
 
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 {
-	struct kvm_mmu_page *sp;
-	bool flush = false;
+	struct kvm_memory_slot *memslot;
+	gfn_t last_gfn;
+	int i;
 
-	list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link) {
-		int i;
-		u64 *pt;
+	memslot = id_to_memslot(kvm->memslots, slot);
+	last_gfn = memslot->base_gfn + memslot->npages - 1;
 
-		if (!test_bit(slot, sp->slot_bitmap))
-			continue;
+	spin_lock(&kvm->mmu_lock);
 
-		pt = sp->spt;
-		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
-			if (!is_shadow_present_pte(pt[i]) ||
-			      !is_last_spte(pt[i], sp->role.level))
-				continue;
+	for (i = PT_PAGE_TABLE_LEVEL;
+	     i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+		unsigned long *rmapp;
+		unsigned long last_index, index;
 
-			spte_write_protect(kvm, &pt[i], &flush, false);
+		rmapp = memslot->arch.rmap[i - PT_PAGE_TABLE_LEVEL];
+		last_index = gfn_to_index(last_gfn, memslot->base_gfn, i);
+
+		for (index = 0; index <= last_index; ++index, ++rmapp) {
+			if (*rmapp)
+				__rmap_write_protect(kvm, rmapp, false);
+
+			if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+				kvm_flush_remote_tlbs(kvm);
+				cond_resched_lock(&kvm->mmu_lock);
+			}
 		}
 	}
+
 	kvm_flush_remote_tlbs(kvm);
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_mmu_zap_all(struct kvm *kvm)

arch/x86/kvm/mmutrace.h

@@ -195,12 +195,6 @@ DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_prepare_zap_page,
 	TP_ARGS(sp)
 );
 
-DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_delay_free_pages,
-	TP_PROTO(struct kvm_mmu_page *sp),
-
-	TP_ARGS(sp)
-);
-
 TRACE_EVENT(
 	mark_mmio_spte,
 	TP_PROTO(u64 *sptep, gfn_t gfn, unsigned access),

arch/x86/kvm/paging_tmpl.h

@@ -151,7 +151,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, pte_access, accessed_dirty, shift;
+	unsigned index, pt_access, pte_access, accessed_dirty;
 	gpa_t pte_gpa;
 	int offset;
 	const int write_fault = access & PFERR_WRITE_MASK;
@@ -249,16 +249,12 @@ retry_walk:
 
 	if (!write_fault)
 		protect_clean_gpte(&pte_access, pte);
-
-	/*
-	 * On a write fault, fold the dirty bit into accessed_dirty by shifting it one
-	 * place right.
-	 *
-	 * On a read fault, do nothing.
-	 */
-	shift = write_fault >> ilog2(PFERR_WRITE_MASK);
-	shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT;
-	accessed_dirty &= pte >> shift;
+	else
+		/*
+		 * On a write fault, fold the dirty bit into accessed_dirty by
+		 * shifting it one place right.
+		 */
+		accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
 		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -330,8 +326,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
-		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
+	mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL,
+		     gfn, pfn, true, true);
 
 	return true;
 }
@@ -405,7 +401,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  */
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
-			 int user_fault, int write_fault, int hlevel,
+			 int write_fault, int hlevel,
 			 pfn_t pfn, bool map_writable, bool prefault)
 {
 	struct kvm_mmu_page *sp = NULL;
@@ -413,9 +409,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	unsigned direct_access, access = gw->pt_access;
 	int top_level, emulate = 0;
 
-	if (!is_present_gpte(gw->ptes[gw->level - 1]))
-		return 0;
-
 	direct_access = gw->pte_access;
 
 	top_level = vcpu->arch.mmu.root_level;
@@ -477,9 +470,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
-	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
-		     user_fault, write_fault, &emulate, it.level,
-		     gw->gfn, pfn, prefault, map_writable);
+	mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate,
+		     it.level, gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
 	return emulate;
@@ -491,6 +483,46 @@ out_gpte_changed:
 	return 0;
 }
 
+ /*
+ * To see whether the mapped gfn can write its page table in the current
+ * mapping.
+ *
+ * It is the helper function of FNAME(page_fault). When guest uses large page
+ * size to map the writable gfn which is used as current page table, we should
+ * force kvm to use small page size to map it because new shadow page will be
+ * created when kvm establishes shadow page table that stop kvm using large
+ * page size. Do it early can avoid unnecessary #PF and emulation.
+ *
+ * @write_fault_to_shadow_pgtable will return true if the fault gfn is
+ * currently used as its page table.
+ *
+ * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok
+ * since the PDPT is always shadowed, that means, we can not use large page
+ * size to map the gfn which is used as PDPT.
+ */
+static bool
+FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
+			      struct guest_walker *walker, int user_fault,
+			      bool *write_fault_to_shadow_pgtable)
+{
+	int level;
+	gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1);
+	bool self_changed = false;
+
+	if (!(walker->pte_access & ACC_WRITE_MASK ||
+	      (!is_write_protection(vcpu) && !user_fault)))
+		return false;
+
+	for (level = walker->level; level <= walker->max_level; level++) {
+		gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1];
+
+		self_changed |= !(gfn & mask);
+		*write_fault_to_shadow_pgtable |= !gfn;
+	}
+
+	return self_changed;
+}
+
 /*
  * Page fault handler.  There are several causes for a page fault:
  *   - there is no shadow pte for the guest pte
@@ -516,7 +548,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int level = PT_PAGE_TABLE_LEVEL;
 	int force_pt_level;
 	unsigned long mmu_seq;
-	bool map_writable;
+	bool map_writable, is_self_change_mapping;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
 
@@ -544,8 +576,14 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 		return 0;
 	}
 
+	vcpu->arch.write_fault_to_shadow_pgtable = false;
+
+	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
+	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
+
 	if (walker.level >= PT_DIRECTORY_LEVEL)
-		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn);
+		force_pt_level = mapping_level_dirty_bitmap(vcpu, walker.gfn)
+		   || is_self_change_mapping;
 	else
 		force_pt_level = 1;
 	if (!force_pt_level) {
@@ -564,6 +602,26 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 				walker.gfn, pfn, walker.pte_access, &r))
 		return r;
 
+	/*
+	 * Do not change pte_access if the pfn is a mmio page, otherwise
+	 * we will cache the incorrect access into mmio spte.
+	 */
+	if (write_fault && !(walker.pte_access & ACC_WRITE_MASK) &&
+	     !is_write_protection(vcpu) && !user_fault &&
+	      !is_noslot_pfn(pfn)) {
+		walker.pte_access |= ACC_WRITE_MASK;
+		walker.pte_access &= ~ACC_USER_MASK;
+
+		/*
+		 * If we converted a user page to a kernel page,
+		 * so that the kernel can write to it when cr0.wp=0,
+		 * then we should prevent the kernel from executing it
+		 * if SMEP is enabled.
+		 */
+		if (kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
+			walker.pte_access &= ~ACC_EXEC_MASK;
+	}
+
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
 		goto out_unlock;
@@ -572,7 +630,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	kvm_mmu_free_some_pages(vcpu);
 	if (!force_pt_level)
 		transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level);
-	r = FNAME(fetch)(vcpu, addr, &walker, user_fault, write_fault,
+	r = FNAME(fetch)(vcpu, addr, &walker, write_fault,
 			 level, pfn, map_writable, prefault);
 	++vcpu->stat.pf_fixed;
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
@@ -747,7 +805,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		host_writable = sp->spt[i] & SPTE_HOST_WRITEABLE;
 
-		set_spte(vcpu, &sp->spt[i], pte_access, 0, 0,
+		set_spte(vcpu, &sp->spt[i], pte_access,
 			 PT_PAGE_TABLE_LEVEL, gfn,
 			 spte_to_pfn(sp->spt[i]), true, false,
 			 host_writable);

arch/x86/kvm/svm.c

@@ -3571,6 +3571,26 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
 }
 
+static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
+{
+	return;
+}
+
+static int svm_vm_has_apicv(struct kvm *kvm)
+{
+	return 0;
+}
+
+static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+	return;
+}
+
+static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
+{
+	return;
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4290,6 +4310,10 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
+	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
+	.vm_has_apicv = svm_vm_has_apicv,
+	.load_eoi_exitmap = svm_load_eoi_exitmap,
+	.hwapic_isr_update = svm_hwapic_isr_update,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,

arch/x86/kvm/x86.c

@@ -872,8 +872,6 @@ static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 	kvm_x86_ops->set_efer(vcpu, efer);
 
-	vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
-
 	/* Update reserved bits */
 	if ((efer ^ old_efer) & EFER_NX)
 		kvm_mmu_reset_context(vcpu);
@@ -2522,7 +2520,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_MEMORY_SLOTS;
+		r = KVM_USER_MEM_SLOTS;
 		break;
 	case KVM_CAP_PV_MMU:	/* obsolete */
 		r = 0;
@@ -3274,12 +3272,10 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 		return -EINVAL;
 
 	mutex_lock(&kvm->slots_lock);
-	spin_lock(&kvm->mmu_lock);
 
 	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
 	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
 
-	spin_unlock(&kvm->mmu_lock);
 	mutex_unlock(&kvm->slots_lock);
 	return 0;
 }
@@ -3439,7 +3435,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
@@ -4495,8 +4491,10 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 	kvm_get_segment(emul_to_vcpu(ctxt), &var, seg);
 	*selector = var.selector;
 
-	if (var.unusable)
+	if (var.unusable) {
+		memset(desc, 0, sizeof(*desc));
 		return false;
+	}
 
 	if (var.g)
 		var.limit >>= 12;
@@ -4757,26 +4755,26 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 	return r;
 }
 
-static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
+				  bool write_fault_to_shadow_pgtable)
 {
-	gpa_t gpa;
+	gpa_t gpa = cr2;
 	pfn_t pfn;
 
-	if (tdp_enabled)
-		return false;
-
-	/*
-	 * if emulation was due to access to shadowed page table
-	 * and it failed try to unshadow page and re-enter the
-	 * guest to let CPU execute the instruction.
-	 */
-	if (kvm_mmu_unprotect_page_virt(vcpu, gva))
-		return true;
-
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva, NULL);
+	if (!vcpu->arch.mmu.direct_map) {
+		/*
+		 * Write permission should be allowed since only
+		 * write access need to be emulated.
+		 */
+		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
 
-	if (gpa == UNMAPPED_GVA)
-		return true; /* let cpu generate fault */
+		/*
+		 * If the mapping is invalid in guest, let cpu retry
+		 * it to generate fault.
+		 */
+		if (gpa == UNMAPPED_GVA)
+			return true;
+	}
 
 	/*
 	 * Do not retry the unhandleable instruction if it faults on the
@@ -4785,12 +4783,43 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	 * instruction -> ...
 	 */
 	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
-	if (!is_error_noslot_pfn(pfn)) {
-		kvm_release_pfn_clean(pfn);
+
+	/*
+	 * If the instruction failed on the error pfn, it can not be fixed,
+	 * report the error to userspace.
+	 */
+	if (is_error_noslot_pfn(pfn))
+		return false;
+
+	kvm_release_pfn_clean(pfn);
+
+	/* The instructions are well-emulated on direct mmu. */
+	if (vcpu->arch.mmu.direct_map) {
+		unsigned int indirect_shadow_pages;
+
+		spin_lock(&vcpu->kvm->mmu_lock);
+		indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages;
+		spin_unlock(&vcpu->kvm->mmu_lock);
+
+		if (indirect_shadow_pages)
+			kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
+
 		return true;
 	}
 
-	return false;
+	/*
+	 * if emulation was due to access to shadowed page table
+	 * and it failed try to unshadow page and re-enter the
+	 * guest to let CPU execute the instruction.
+	 */
+	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
+
+	/*
+	 * If the access faults on its page table, it can not
+	 * be fixed by unprotecting shadow page and it should
+	 * be reported to userspace.
+	 */
+	return !write_fault_to_shadow_pgtable;
 }
 
 static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
@@ -4832,7 +4861,7 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	if (!vcpu->arch.mmu.direct_map)
 		gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
 
-	kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
 
 	return true;
 }
@@ -4849,7 +4878,13 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	int r;
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	bool writeback = true;
+	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	/*
+	 * Clear write_fault_to_shadow_pgtable here to ensure it is
+	 * never reused.
+	 */
+	vcpu->arch.write_fault_to_shadow_pgtable = false;
 	kvm_clear_exception_queue(vcpu);
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
@@ -4868,7 +4903,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		if (r != EMULATION_OK)  {
 			if (emulation_type & EMULTYPE_TRAP_UD)
 				return EMULATE_FAIL;
-			if (reexecute_instruction(vcpu, cr2))
+			if (reexecute_instruction(vcpu, cr2,
+						  write_fault_to_spt))
 				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
@@ -4898,7 +4934,7 @@ restart:
 		return EMULATE_DONE;
 
 	if (r == EMULATION_FAILED) {
-		if (reexecute_instruction(vcpu, cr2))
+		if (reexecute_instruction(vcpu, cr2, write_fault_to_spt))
 			return EMULATE_DONE;
 
 		return handle_emulation_failure(vcpu);
@@ -5541,7 +5577,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
 			vcpu->arch.nmi_injected = true;
 			kvm_x86_ops->set_nmi(vcpu);
 		}
-	} else if (kvm_cpu_has_interrupt(vcpu)) {
+	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);
@@ -5609,6 +5645,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 #endif
 }
 
+static void update_eoi_exitmap(struct kvm_vcpu *vcpu)
+{
+	u64 eoi_exit_bitmap[4];
+
+	memset(eoi_exit_bitmap, 0, 32);
+
+	kvm_ioapic_calculate_eoi_exitmap(vcpu, eoi_exit_bitmap);
+	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -5662,6 +5708,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_handle_pmu_event(vcpu);
 		if (kvm_check_request(KVM_REQ_PMI, vcpu))
 			kvm_deliver_pmi(vcpu);
+		if (kvm_check_request(KVM_REQ_EOIBITMAP, vcpu))
+			update_eoi_exitmap(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -5670,10 +5718,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		/* enable NMI/IRQ window open exits if needed */
 		if (vcpu->arch.nmi_pending)
 			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
+		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
 			kvm_x86_ops->enable_irq_window(vcpu);
 
 		if (kvm_lapic_enabled(vcpu)) {
+			/*
+			 * Update architecture specific hints for APIC
+			 * virtual interrupt delivery.
+			 */
+			if (kvm_x86_ops->hwapic_irr_update)
+				kvm_x86_ops->hwapic_irr_update(vcpu,
+					kvm_lapic_find_highest_irr(vcpu));
 			update_cr8_intercept(vcpu);
 			kvm_lapic_sync_to_vapic(vcpu);
 		}
@@ -6853,48 +6908,43 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
 				struct kvm_userspace_memory_region *mem,
-				int user_alloc)
+				bool user_alloc)
 {
 	int npages = memslot->npages;
-	int map_flags = MAP_PRIVATE | MAP_ANONYMOUS;
 
-	/* Prevent internal slot pages from being moved by fork()/COW. */
-	if (memslot->id >= KVM_MEMORY_SLOTS)
-		map_flags = MAP_SHARED | MAP_ANONYMOUS;
-
-	/*To keep backward compatibility with older userspace,
-	 *x86 needs to handle !user_alloc case.
+	/*
+	 * Only private memory slots need to be mapped here since
+	 * KVM_SET_MEMORY_REGION ioctl is no longer supported.
 	 */
-	if (!user_alloc) {
-		if (npages && !old.npages) {
-			unsigned long userspace_addr;
+	if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) {
+		unsigned long userspace_addr;
 
-			userspace_addr = vm_mmap(NULL, 0,
-						 npages * PAGE_SIZE,
-						 PROT_READ | PROT_WRITE,
-						 map_flags,
-						 0);
+		/*
+		 * MAP_SHARED to prevent internal slot pages from being moved
+		 * by fork()/COW.
+		 */
+		userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE,
+					 PROT_READ | PROT_WRITE,
+					 MAP_SHARED | MAP_ANONYMOUS, 0);
 
-			if (IS_ERR((void *)userspace_addr))
-				return PTR_ERR((void *)userspace_addr);
+		if (IS_ERR((void *)userspace_addr))
+			return PTR_ERR((void *)userspace_addr);
 
-			memslot->userspace_addr = userspace_addr;
-		}
+		memslot->userspace_addr = userspace_addr;
 	}
 
-
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
-				int user_alloc)
+				bool user_alloc)
 {
 
 	int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
 
-	if (!user_alloc && !old.user_alloc && old.npages && !npages) {
+	if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) {
 		int ret;
 
 		ret = vm_munmap(old.userspace_addr,
@@ -6908,11 +6958,15 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!kvm->arch.n_requested_mmu_pages)
 		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
 
-	spin_lock(&kvm->mmu_lock);
 	if (nr_mmu_pages)
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
-	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
-	spin_unlock(&kvm->mmu_lock);
+	/*
+	 * Write protect all pages for dirty logging.
+	 * Existing largepage mappings are destroyed here and new ones will
+	 * not be created until the end of the logging.
+	 */
+	if (npages && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
+		kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	/*
 	 * If memory slot is created, or moved, we need to clear all
 	 * mmio sptes.

drivers/s390/kvm/Makefile

@@ -6,4 +6,4 @@
 # it under the terms of the GNU General Public License (version 2 only)
 # as published by the Free Software Foundation.
 
-obj-$(CONFIG_S390_GUEST) += kvm_virtio.o
+obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o

drivers/s390/kvm/kvm_virtio.c

@@ -421,6 +421,26 @@ static void kvm_extint_handler(struct ext_code ext_code,
 	}
 }
 
+/*
+ * For s390-virtio, we expect a page above main storage containing
+ * the virtio configuration. Try to actually load from this area
+ * in order to figure out if the host provides this page.
+ */
+static int __init test_devices_support(unsigned long addr)
+{
+	int ret = -EIO;
+
+	asm volatile(
+		"0:	lura	0,%1\n"
+		"1:	xgr	%0,%0\n"
+		"2:\n"
+		EX_TABLE(0b,2b)
+		EX_TABLE(1b,2b)
+		: "+d" (ret)
+		: "a" (addr)
+		: "0", "cc");
+	return ret;
+}
 /*
  * Init function for virtio
  * devices are in a single page above top of "normal" mem
@@ -432,21 +452,23 @@ static int __init kvm_devices_init(void)
 	if (!MACHINE_IS_KVM)
 		return -ENODEV;
 
+	if (test_devices_support(real_memory_size) < 0)
+		return -ENODEV;
+
+	rc = vmem_add_mapping(real_memory_size, PAGE_SIZE);
+	if (rc)
+		return rc;
+
+	kvm_devices = (void *) real_memory_size;
+
 	kvm_root = root_device_register("kvm_s390");
 	if (IS_ERR(kvm_root)) {
 		rc = PTR_ERR(kvm_root);
 		printk(KERN_ERR "Could not register kvm_s390 root device");
+		vmem_remove_mapping(real_memory_size, PAGE_SIZE);
 		return rc;
 	}
 
-	rc = vmem_add_mapping(real_memory_size, PAGE_SIZE);
-	if (rc) {
-		root_device_unregister(kvm_root);
-		return rc;
-	}
-
-	kvm_devices = (void *) real_memory_size;
-
 	INIT_WORK(&hotplug_work, hotplug_devices);
 
 	service_subclass_irq_register();

drivers/s390/kvm/virtio_ccw.c

@@ -0,0 +1,926 @@
+/*
+ * ccw based virtio transport
+ *
+ * Copyright IBM Corp. 2012
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/err.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio_ring.h>
+#include <linux/pfn.h>
+#include <linux/async.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/kvm_para.h>
+#include <asm/setup.h>
+#include <asm/irq.h>
+#include <asm/cio.h>
+#include <asm/ccwdev.h>
+
+/*
+ * virtio related functions
+ */
+
+struct vq_config_block {
+	__u16 index;
+	__u16 num;
+} __packed;
+
+#define VIRTIO_CCW_CONFIG_SIZE 0x100
+/* same as PCI config space size, should be enough for all drivers */
+
+struct virtio_ccw_device {
+	struct virtio_device vdev;
+	__u8 *status;
+	__u8 config[VIRTIO_CCW_CONFIG_SIZE];
+	struct ccw_device *cdev;
+	__u32 curr_io;
+	int err;
+	wait_queue_head_t wait_q;
+	spinlock_t lock;
+	struct list_head virtqueues;
+	unsigned long indicators;
+	unsigned long indicators2;
+	struct vq_config_block *config_block;
+};
+
+struct vq_info_block {
+	__u64 queue;
+	__u32 align;
+	__u16 index;
+	__u16 num;
+} __packed;
+
+struct virtio_feature_desc {
+	__u32 features;
+	__u8 index;
+} __packed;
+
+struct virtio_ccw_vq_info {
+	struct virtqueue *vq;
+	int num;
+	void *queue;
+	struct vq_info_block *info_block;
+	struct list_head node;
+};
+
+#define KVM_VIRTIO_CCW_RING_ALIGN 4096
+
+#define KVM_S390_VIRTIO_CCW_NOTIFY 3
+
+#define CCW_CMD_SET_VQ 0x13
+#define CCW_CMD_VDEV_RESET 0x33
+#define CCW_CMD_SET_IND 0x43
+#define CCW_CMD_SET_CONF_IND 0x53
+#define CCW_CMD_READ_FEAT 0x12
+#define CCW_CMD_WRITE_FEAT 0x11
+#define CCW_CMD_READ_CONF 0x22
+#define CCW_CMD_WRITE_CONF 0x21
+#define CCW_CMD_WRITE_STATUS 0x31
+#define CCW_CMD_READ_VQ_CONF 0x32
+
+#define VIRTIO_CCW_DOING_SET_VQ 0x00010000
+#define VIRTIO_CCW_DOING_RESET 0x00040000
+#define VIRTIO_CCW_DOING_READ_FEAT 0x00080000
+#define VIRTIO_CCW_DOING_WRITE_FEAT 0x00100000
+#define VIRTIO_CCW_DOING_READ_CONFIG 0x00200000
+#define VIRTIO_CCW_DOING_WRITE_CONFIG 0x00400000
+#define VIRTIO_CCW_DOING_WRITE_STATUS 0x00800000
+#define VIRTIO_CCW_DOING_SET_IND 0x01000000
+#define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000
+#define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000
+#define VIRTIO_CCW_INTPARM_MASK 0xffff0000
+
+static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
+{
+	return container_of(vdev, struct virtio_ccw_device, vdev);
+}
+
+static int doing_io(struct virtio_ccw_device *vcdev, __u32 flag)
+{
+	unsigned long flags;
+	__u32 ret;
+
+	spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags);
+	if (vcdev->err)
+		ret = 0;
+	else
+		ret = vcdev->curr_io & flag;
+	spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags);
+	return ret;
+}
+
+static int ccw_io_helper(struct virtio_ccw_device *vcdev,
+			 struct ccw1 *ccw, __u32 intparm)
+{
+	int ret;
+	unsigned long flags;
+	int flag = intparm & VIRTIO_CCW_INTPARM_MASK;
+
+	do {
+		spin_lock_irqsave(get_ccwdev_lock(vcdev->cdev), flags);
+		ret = ccw_device_start(vcdev->cdev, ccw, intparm, 0, 0);
+		if (!ret)
+			vcdev->curr_io |= flag;
+		spin_unlock_irqrestore(get_ccwdev_lock(vcdev->cdev), flags);
+		cpu_relax();
+	} while (ret == -EBUSY);
+	wait_event(vcdev->wait_q, doing_io(vcdev, flag) == 0);
+	return ret ? ret : vcdev->err;
+}
+
+static inline long do_kvm_notify(struct subchannel_id schid,
+				 unsigned long queue_index)
+{
+	register unsigned long __nr asm("1") = KVM_S390_VIRTIO_CCW_NOTIFY;
+	register struct subchannel_id __schid asm("2") = schid;
+	register unsigned long __index asm("3") = queue_index;
+	register long __rc asm("2");
+
+	asm volatile ("diag 2,4,0x500\n"
+		      : "=d" (__rc) : "d" (__nr), "d" (__schid), "d" (__index)
+		      : "memory", "cc");
+	return __rc;
+}
+
+static void virtio_ccw_kvm_notify(struct virtqueue *vq)
+{
+	struct virtio_ccw_vq_info *info = vq->priv;
+	struct virtio_ccw_device *vcdev;
+	struct subchannel_id schid;
+
+	vcdev = to_vc_device(info->vq->vdev);
+	ccw_device_get_schid(vcdev->cdev, &schid);
+	do_kvm_notify(schid, virtqueue_get_queue_index(vq));
+}
+
+static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev,
+				   struct ccw1 *ccw, int index)
+{
+	vcdev->config_block->index = index;
+	ccw->cmd_code = CCW_CMD_READ_VQ_CONF;
+	ccw->flags = 0;
+	ccw->count = sizeof(struct vq_config_block);
+	ccw->cda = (__u32)(unsigned long)(vcdev->config_block);
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF);
+	return vcdev->config_block->num;
+}
+
+static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vq->vdev);
+	struct virtio_ccw_vq_info *info = vq->priv;
+	unsigned long flags;
+	unsigned long size;
+	int ret;
+	unsigned int index = virtqueue_get_queue_index(vq);
+
+	/* Remove from our list. */
+	spin_lock_irqsave(&vcdev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vcdev->lock, flags);
+
+	/* Release from host. */
+	info->info_block->queue = 0;
+	info->info_block->align = 0;
+	info->info_block->index = index;
+	info->info_block->num = 0;
+	ccw->cmd_code = CCW_CMD_SET_VQ;
+	ccw->flags = 0;
+	ccw->count = sizeof(*info->info_block);
+	ccw->cda = (__u32)(unsigned long)(info->info_block);
+	ret = ccw_io_helper(vcdev, ccw,
+			    VIRTIO_CCW_DOING_SET_VQ | index);
+	/*
+	 * -ENODEV isn't considered an error: The device is gone anyway.
+	 * This may happen on device detach.
+	 */
+	if (ret && (ret != -ENODEV))
+		dev_warn(&vq->vdev->dev, "Error %d while deleting queue %d",
+			 ret, index);
+
+	vring_del_virtqueue(vq);
+	size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN));
+	free_pages_exact(info->queue, size);
+	kfree(info->info_block);
+	kfree(info);
+}
+
+static void virtio_ccw_del_vqs(struct virtio_device *vdev)
+{
+	struct virtqueue *vq, *n;
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		virtio_ccw_del_vq(vq, ccw);
+
+	kfree(ccw);
+}
+
+static struct virtqueue *virtio_ccw_setup_vq(struct virtio_device *vdev,
+					     int i, vq_callback_t *callback,
+					     const char *name,
+					     struct ccw1 *ccw)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	int err;
+	struct virtqueue *vq = NULL;
+	struct virtio_ccw_vq_info *info;
+	unsigned long size = 0; /* silence the compiler */
+	unsigned long flags;
+
+	/* Allocate queue. */
+	info = kzalloc(sizeof(struct virtio_ccw_vq_info), GFP_KERNEL);
+	if (!info) {
+		dev_warn(&vcdev->cdev->dev, "no info\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+	info->info_block = kzalloc(sizeof(*info->info_block),
+				   GFP_DMA | GFP_KERNEL);
+	if (!info->info_block) {
+		dev_warn(&vcdev->cdev->dev, "no info block\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+	info->num = virtio_ccw_read_vq_conf(vcdev, ccw, i);
+	size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN));
+	info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
+	if (info->queue == NULL) {
+		dev_warn(&vcdev->cdev->dev, "no queue\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	vq = vring_new_virtqueue(i, info->num, KVM_VIRTIO_CCW_RING_ALIGN, vdev,
+				 true, info->queue, virtio_ccw_kvm_notify,
+				 callback, name);
+	if (!vq) {
+		/* For now, we fail if we can't get the requested size. */
+		dev_warn(&vcdev->cdev->dev, "no vq\n");
+		err = -ENOMEM;
+		goto out_err;
+	}
+
+	/* Register it with the host. */
+	info->info_block->queue = (__u64)info->queue;
+	info->info_block->align = KVM_VIRTIO_CCW_RING_ALIGN;
+	info->info_block->index = i;
+	info->info_block->num = info->num;
+	ccw->cmd_code = CCW_CMD_SET_VQ;
+	ccw->flags = 0;
+	ccw->count = sizeof(*info->info_block);
+	ccw->cda = (__u32)(unsigned long)(info->info_block);
+	err = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_VQ | i);
+	if (err) {
+		dev_warn(&vcdev->cdev->dev, "SET_VQ failed\n");
+		goto out_err;
+	}
+
+	info->vq = vq;
+	vq->priv = info;
+
+	/* Save it to our list. */
+	spin_lock_irqsave(&vcdev->lock, flags);
+	list_add(&info->node, &vcdev->virtqueues);
+	spin_unlock_irqrestore(&vcdev->lock, flags);
+
+	return vq;
+
+out_err:
+	if (vq)
+		vring_del_virtqueue(vq);
+	if (info) {
+		if (info->queue)
+			free_pages_exact(info->queue, size);
+		kfree(info->info_block);
+	}
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			       struct virtqueue *vqs[],
+			       vq_callback_t *callbacks[],
+			       const char *names[])
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	unsigned long *indicatorp = NULL;
+	int ret, i;
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return -ENOMEM;
+
+	for (i = 0; i < nvqs; ++i) {
+		vqs[i] = virtio_ccw_setup_vq(vdev, i, callbacks[i], names[i],
+					     ccw);
+		if (IS_ERR(vqs[i])) {
+			ret = PTR_ERR(vqs[i]);
+			vqs[i] = NULL;
+			goto out;
+		}
+	}
+	ret = -ENOMEM;
+	/* We need a data area under 2G to communicate. */
+	indicatorp = kmalloc(sizeof(&vcdev->indicators), GFP_DMA | GFP_KERNEL);
+	if (!indicatorp)
+		goto out;
+	*indicatorp = (unsigned long) &vcdev->indicators;
+	/* Register queue indicators with host. */
+	vcdev->indicators = 0;
+	ccw->cmd_code = CCW_CMD_SET_IND;
+	ccw->flags = 0;
+	ccw->count = sizeof(vcdev->indicators);
+	ccw->cda = (__u32)(unsigned long) indicatorp;
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND);
+	if (ret)
+		goto out;
+	/* Register indicators2 with host for config changes */
+	*indicatorp = (unsigned long) &vcdev->indicators2;
+	vcdev->indicators2 = 0;
+	ccw->cmd_code = CCW_CMD_SET_CONF_IND;
+	ccw->flags = 0;
+	ccw->count = sizeof(vcdev->indicators2);
+	ccw->cda = (__u32)(unsigned long) indicatorp;
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_CONF_IND);
+	if (ret)
+		goto out;
+
+	kfree(indicatorp);
+	kfree(ccw);
+	return 0;
+out:
+	kfree(indicatorp);
+	kfree(ccw);
+	virtio_ccw_del_vqs(vdev);
+	return ret;
+}
+
+static void virtio_ccw_reset(struct virtio_device *vdev)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	/* Zero status bits. */
+	*vcdev->status = 0;
+
+	/* Send a reset ccw on device. */
+	ccw->cmd_code = CCW_CMD_VDEV_RESET;
+	ccw->flags = 0;
+	ccw->count = 0;
+	ccw->cda = 0;
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_RESET);
+	kfree(ccw);
+}
+
+static u32 virtio_ccw_get_features(struct virtio_device *vdev)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	struct virtio_feature_desc *features;
+	int ret, rc;
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return 0;
+
+	features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL);
+	if (!features) {
+		rc = 0;
+		goto out_free;
+	}
+	/* Read the feature bits from the host. */
+	/* TODO: Features > 32 bits */
+	features->index = 0;
+	ccw->cmd_code = CCW_CMD_READ_FEAT;
+	ccw->flags = 0;
+	ccw->count = sizeof(*features);
+	ccw->cda = (__u32)(unsigned long)features;
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_FEAT);
+	if (ret) {
+		rc = 0;
+		goto out_free;
+	}
+
+	rc = le32_to_cpu(features->features);
+
+out_free:
+	kfree(features);
+	kfree(ccw);
+	return rc;
+}
+
+static void virtio_ccw_finalize_features(struct virtio_device *vdev)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	struct virtio_feature_desc *features;
+	int i;
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	features = kzalloc(sizeof(*features), GFP_DMA | GFP_KERNEL);
+	if (!features)
+		goto out_free;
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	for (i = 0; i < sizeof(*vdev->features) / sizeof(features->features);
+	     i++) {
+		int highbits = i % 2 ? 32 : 0;
+		features->index = i;
+		features->features = cpu_to_le32(vdev->features[i / 2]
+						 >> highbits);
+		/* Write the feature bits to the host. */
+		ccw->cmd_code = CCW_CMD_WRITE_FEAT;
+		ccw->flags = 0;
+		ccw->count = sizeof(*features);
+		ccw->cda = (__u32)(unsigned long)features;
+		ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_FEAT);
+	}
+out_free:
+	kfree(features);
+	kfree(ccw);
+}
+
+static void virtio_ccw_get_config(struct virtio_device *vdev,
+				  unsigned int offset, void *buf, unsigned len)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	int ret;
+	struct ccw1 *ccw;
+	void *config_area;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL);
+	if (!config_area)
+		goto out_free;
+
+	/* Read the config area from the host. */
+	ccw->cmd_code = CCW_CMD_READ_CONF;
+	ccw->flags = 0;
+	ccw->count = offset + len;
+	ccw->cda = (__u32)(unsigned long)config_area;
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_CONFIG);
+	if (ret)
+		goto out_free;
+
+	memcpy(vcdev->config, config_area, sizeof(vcdev->config));
+	memcpy(buf, &vcdev->config[offset], len);
+
+out_free:
+	kfree(config_area);
+	kfree(ccw);
+}
+
+static void virtio_ccw_set_config(struct virtio_device *vdev,
+				  unsigned int offset, const void *buf,
+				  unsigned len)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	struct ccw1 *ccw;
+	void *config_area;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	config_area = kzalloc(VIRTIO_CCW_CONFIG_SIZE, GFP_DMA | GFP_KERNEL);
+	if (!config_area)
+		goto out_free;
+
+	memcpy(&vcdev->config[offset], buf, len);
+	/* Write the config area to the host. */
+	memcpy(config_area, vcdev->config, sizeof(vcdev->config));
+	ccw->cmd_code = CCW_CMD_WRITE_CONF;
+	ccw->flags = 0;
+	ccw->count = offset + len;
+	ccw->cda = (__u32)(unsigned long)config_area;
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_CONFIG);
+
+out_free:
+	kfree(config_area);
+	kfree(ccw);
+}
+
+static u8 virtio_ccw_get_status(struct virtio_device *vdev)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+
+	return *vcdev->status;
+}
+
+static void virtio_ccw_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
+	struct ccw1 *ccw;
+
+	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
+	if (!ccw)
+		return;
+
+	/* Write the status to the host. */
+	*vcdev->status = status;
+	ccw->cmd_code = CCW_CMD_WRITE_STATUS;
+	ccw->flags = 0;
+	ccw->count = sizeof(status);
+	ccw->cda = (__u32)(unsigned long)vcdev->status;
+	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_WRITE_STATUS);
+	kfree(ccw);
+}
+
+static struct virtio_config_ops virtio_ccw_config_ops = {
+	.get_features = virtio_ccw_get_features,
+	.finalize_features = virtio_ccw_finalize_features,
+	.get = virtio_ccw_get_config,
+	.set = virtio_ccw_set_config,
+	.get_status = virtio_ccw_get_status,
+	.set_status = virtio_ccw_set_status,
+	.reset = virtio_ccw_reset,
+	.find_vqs = virtio_ccw_find_vqs,
+	.del_vqs = virtio_ccw_del_vqs,
+};
+
+
+/*
+ * ccw bus driver related functions
+ */
+
+static void virtio_ccw_release_dev(struct device *_d)
+{
+	struct virtio_device *dev = container_of(_d, struct virtio_device,
+						 dev);
+	struct virtio_ccw_device *vcdev = to_vc_device(dev);
+
+	kfree(vcdev->status);
+	kfree(vcdev->config_block);
+	kfree(vcdev);
+}
+
+static int irb_is_error(struct irb *irb)
+{
+	if (scsw_cstat(&irb->scsw) != 0)
+		return 1;
+	if (scsw_dstat(&irb->scsw) & ~(DEV_STAT_CHN_END | DEV_STAT_DEV_END))
+		return 1;
+	if (scsw_cc(&irb->scsw) != 0)
+		return 1;
+	return 0;
+}
+
+static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev,
+					      int index)
+{
+	struct virtio_ccw_vq_info *info;
+	unsigned long flags;
+	struct virtqueue *vq;
+
+	vq = NULL;
+	spin_lock_irqsave(&vcdev->lock, flags);
+	list_for_each_entry(info, &vcdev->virtqueues, node) {
+		if (virtqueue_get_queue_index(info->vq) == index) {
+			vq = info->vq;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&vcdev->lock, flags);
+	return vq;
+}
+
+static void virtio_ccw_int_handler(struct ccw_device *cdev,
+				   unsigned long intparm,
+				   struct irb *irb)
+{
+	__u32 activity = intparm & VIRTIO_CCW_INTPARM_MASK;
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+	int i;
+	struct virtqueue *vq;
+	struct virtio_driver *drv;
+
+	/* Check if it's a notification from the host. */
+	if ((intparm == 0) &&
+	    (scsw_stctl(&irb->scsw) ==
+	     (SCSW_STCTL_ALERT_STATUS | SCSW_STCTL_STATUS_PEND))) {
+		/* OK */
+	}
+	if (irb_is_error(irb))
+		vcdev->err = -EIO; /* XXX - use real error */
+	if (vcdev->curr_io & activity) {
+		switch (activity) {
+		case VIRTIO_CCW_DOING_READ_FEAT:
+		case VIRTIO_CCW_DOING_WRITE_FEAT:
+		case VIRTIO_CCW_DOING_READ_CONFIG:
+		case VIRTIO_CCW_DOING_WRITE_CONFIG:
+		case VIRTIO_CCW_DOING_WRITE_STATUS:
+		case VIRTIO_CCW_DOING_SET_VQ:
+		case VIRTIO_CCW_DOING_SET_IND:
+		case VIRTIO_CCW_DOING_SET_CONF_IND:
+		case VIRTIO_CCW_DOING_RESET:
+		case VIRTIO_CCW_DOING_READ_VQ_CONF:
+			vcdev->curr_io &= ~activity;
+			wake_up(&vcdev->wait_q);
+			break;
+		default:
+			/* don't know what to do... */
+			dev_warn(&cdev->dev, "Suspicious activity '%08x'\n",
+				 activity);
+			WARN_ON(1);
+			break;
+		}
+	}
+	for_each_set_bit(i, &vcdev->indicators,
+			 sizeof(vcdev->indicators) * BITS_PER_BYTE) {
+		/* The bit clear must happen before the vring kick. */
+		clear_bit(i, &vcdev->indicators);
+		barrier();
+		vq = virtio_ccw_vq_by_ind(vcdev, i);
+		vring_interrupt(0, vq);
+	}
+	if (test_bit(0, &vcdev->indicators2)) {
+		drv = container_of(vcdev->vdev.dev.driver,
+				   struct virtio_driver, driver);
+
+		if (drv && drv->config_changed)
+			drv->config_changed(&vcdev->vdev);
+		clear_bit(0, &vcdev->indicators2);
+	}
+}
+
+/*
+ * We usually want to autoonline all devices, but give the admin
+ * a way to exempt devices from this.
+ */
+#define __DEV_WORDS ((__MAX_SUBCHANNEL + (8*sizeof(long) - 1)) / \
+		     (8*sizeof(long)))
+static unsigned long devs_no_auto[__MAX_SSID + 1][__DEV_WORDS];
+
+static char *no_auto = "";
+
+module_param(no_auto, charp, 0444);
+MODULE_PARM_DESC(no_auto, "list of ccw bus id ranges not to be auto-onlined");
+
+static int virtio_ccw_check_autoonline(struct ccw_device *cdev)
+{
+	struct ccw_dev_id id;
+
+	ccw_device_get_id(cdev, &id);
+	if (test_bit(id.devno, devs_no_auto[id.ssid]))
+		return 0;
+	return 1;
+}
+
+static void virtio_ccw_auto_online(void *data, async_cookie_t cookie)
+{
+	struct ccw_device *cdev = data;
+	int ret;
+
+	ret = ccw_device_set_online(cdev);
+	if (ret)
+		dev_warn(&cdev->dev, "Failed to set online: %d\n", ret);
+}
+
+static int virtio_ccw_probe(struct ccw_device *cdev)
+{
+	cdev->handler = virtio_ccw_int_handler;
+
+	if (virtio_ccw_check_autoonline(cdev))
+		async_schedule(virtio_ccw_auto_online, cdev);
+	return 0;
+}
+
+static void virtio_ccw_remove(struct ccw_device *cdev)
+{
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+
+	if (cdev->online) {
+		unregister_virtio_device(&vcdev->vdev);
+		dev_set_drvdata(&cdev->dev, NULL);
+	}
+	cdev->handler = NULL;
+}
+
+static int virtio_ccw_offline(struct ccw_device *cdev)
+{
+	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+
+	unregister_virtio_device(&vcdev->vdev);
+	dev_set_drvdata(&cdev->dev, NULL);
+	return 0;
+}
+
+
+static int virtio_ccw_online(struct ccw_device *cdev)
+{
+	int ret;
+	struct virtio_ccw_device *vcdev;
+
+	vcdev = kzalloc(sizeof(*vcdev), GFP_KERNEL);
+	if (!vcdev) {
+		dev_warn(&cdev->dev, "Could not get memory for virtio\n");
+		ret = -ENOMEM;
+		goto out_free;
+	}
+	vcdev->config_block = kzalloc(sizeof(*vcdev->config_block),
+				   GFP_DMA | GFP_KERNEL);
+	if (!vcdev->config_block) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+	vcdev->status = kzalloc(sizeof(*vcdev->status), GFP_DMA | GFP_KERNEL);
+	if (!vcdev->status) {
+		ret = -ENOMEM;
+		goto out_free;
+	}
+
+	vcdev->vdev.dev.parent = &cdev->dev;
+	vcdev->vdev.dev.release = virtio_ccw_release_dev;
+	vcdev->vdev.config = &virtio_ccw_config_ops;
+	vcdev->cdev = cdev;
+	init_waitqueue_head(&vcdev->wait_q);
+	INIT_LIST_HEAD(&vcdev->virtqueues);
+	spin_lock_init(&vcdev->lock);
+
+	dev_set_drvdata(&cdev->dev, vcdev);
+	vcdev->vdev.id.vendor = cdev->id.cu_type;
+	vcdev->vdev.id.device = cdev->id.cu_model;
+	ret = register_virtio_device(&vcdev->vdev);
+	if (ret) {
+		dev_warn(&cdev->dev, "Failed to register virtio device: %d\n",
+			 ret);
+		goto out_put;
+	}
+	return 0;
+out_put:
+	dev_set_drvdata(&cdev->dev, NULL);
+	put_device(&vcdev->vdev.dev);
+	return ret;
+out_free:
+	if (vcdev) {
+		kfree(vcdev->status);
+		kfree(vcdev->config_block);
+	}
+	kfree(vcdev);
+	return ret;
+}
+
+static int virtio_ccw_cio_notify(struct ccw_device *cdev, int event)
+{
+	/* TODO: Check whether we need special handling here. */
+	return 0;
+}
+
+static struct ccw_device_id virtio_ids[] = {
+	{ CCW_DEVICE(0x3832, 0) },
+	{},
+};
+MODULE_DEVICE_TABLE(ccw, virtio_ids);
+
+static struct ccw_driver virtio_ccw_driver = {
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "virtio_ccw",
+	},
+	.ids = virtio_ids,
+	.probe = virtio_ccw_probe,
+	.remove = virtio_ccw_remove,
+	.set_offline = virtio_ccw_offline,
+	.set_online = virtio_ccw_online,
+	.notify = virtio_ccw_cio_notify,
+	.int_class = IRQIO_VIR,
+};
+
+static int __init pure_hex(char **cp, unsigned int *val, int min_digit,
+			   int max_digit, int max_val)
+{
+	int diff;
+
+	diff = 0;
+	*val = 0;
+
+	while (diff <= max_digit) {
+		int value = hex_to_bin(**cp);
+
+		if (value < 0)
+			break;
+		*val = *val * 16 + value;
+		(*cp)++;
+		diff++;
+	}
+
+	if ((diff < min_digit) || (diff > max_digit) || (*val > max_val))
+		return 1;
+
+	return 0;
+}
+
+static int __init parse_busid(char *str, unsigned int *cssid,
+			      unsigned int *ssid, unsigned int *devno)
+{
+	char *str_work;
+	int rc, ret;
+
+	rc = 1;
+
+	if (*str == '\0')
+		goto out;
+
+	str_work = str;
+	ret = pure_hex(&str_work, cssid, 1, 2, __MAX_CSSID);
+	if (ret || (str_work[0] != '.'))
+		goto out;
+	str_work++;
+	ret = pure_hex(&str_work, ssid, 1, 1, __MAX_SSID);
+	if (ret || (str_work[0] != '.'))
+		goto out;
+	str_work++;
+	ret = pure_hex(&str_work, devno, 4, 4, __MAX_SUBCHANNEL);
+	if (ret || (str_work[0] != '\0'))
+		goto out;
+
+	rc = 0;
+out:
+	return rc;
+}
+
+static void __init no_auto_parse(void)
+{
+	unsigned int from_cssid, to_cssid, from_ssid, to_ssid, from, to;
+	char *parm, *str;
+	int rc;
+
+	str = no_auto;
+	while ((parm = strsep(&str, ","))) {
+		rc = parse_busid(strsep(&parm, "-"), &from_cssid,
+				 &from_ssid, &from);
+		if (rc)
+			continue;
+		if (parm != NULL) {
+			rc = parse_busid(parm, &to_cssid,
+					 &to_ssid, &to);
+			if ((from_ssid > to_ssid) ||
+			    ((from_ssid == to_ssid) && (from > to)))
+				rc = -EINVAL;
+		} else {
+			to_cssid = from_cssid;
+			to_ssid = from_ssid;
+			to = from;
+		}
+		if (rc)
+			continue;
+		while ((from_ssid < to_ssid) ||
+		       ((from_ssid == to_ssid) && (from <= to))) {
+			set_bit(from, devs_no_auto[from_ssid]);
+			from++;
+			if (from > __MAX_SUBCHANNEL) {
+				from_ssid++;
+				from = 0;
+			}
+		}
+	}
+}
+
+static int __init virtio_ccw_init(void)
+{
+	/* parse no_auto string before we do anything further */
+	no_auto_parse();
+	return ccw_driver_register(&virtio_ccw_driver);
+}
+module_init(virtio_ccw_init);
+
+static void __exit virtio_ccw_exit(void)
+{
+	ccw_driver_unregister(&virtio_ccw_driver);
+}
+module_exit(virtio_ccw_exit);

include/linux/kvm_host.h

@@ -123,6 +123,8 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_WATCHDOG          18
 #define KVM_REQ_MASTERCLOCK_UPDATE 19
 #define KVM_REQ_MCLOCK_INPROGRESS 20
+#define KVM_REQ_EPR_EXIT          21
+#define KVM_REQ_EOIBITMAP         22
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
@@ -267,12 +269,11 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
 struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
-	unsigned long flags;
 	unsigned long *dirty_bitmap;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
-	int user_alloc;
-	int id;
+	u32 flags;
+	short id;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
@@ -314,8 +315,12 @@ struct kvm_irq_routing_table {};
 
 #endif
 
+#ifndef KVM_PRIVATE_MEM_SLOTS
+#define KVM_PRIVATE_MEM_SLOTS 0
+#endif
+
 #ifndef KVM_MEM_SLOTS_NUM
-#define KVM_MEM_SLOTS_NUM (KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
+#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 #endif
 
 /*
@@ -327,7 +332,7 @@ struct kvm_memslots {
 	u64 generation;
 	struct kvm_memory_slot memslots[KVM_MEM_SLOTS_NUM];
 	/* The mapping table from slot id to the index in memslots[]. */
-	int id_to_index[KVM_MEM_SLOTS_NUM];
+	short id_to_index[KVM_MEM_SLOTS_NUM];
 };
 
 struct kvm {
@@ -425,7 +430,8 @@ void kvm_exit(void);
 
 void kvm_get_kvm(struct kvm *kvm);
 void kvm_put_kvm(struct kvm *kvm);
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new);
+void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new,
+		     u64 last_generation);
 
 static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)
 {
@@ -448,10 +454,10 @@ id_to_memslot(struct kvm_memslots *slots, int id)
 
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
-			  int user_alloc);
+			  bool user_alloc);
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
-			    int user_alloc);
+			    bool user_alloc);
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont);
 int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages);
@@ -459,11 +465,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
 				struct kvm_userspace_memory_region *mem,
-				int user_alloc);
+				bool user_alloc);
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
-				int user_alloc);
+				bool user_alloc);
 bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
 /* flush all memory translations */
@@ -533,6 +539,7 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
+void kvm_make_update_eoibitmap_request(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -550,7 +557,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 				   struct
 				   kvm_userspace_memory_region *mem,
-				   int user_alloc);
+				   bool user_alloc);
 int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg);
@@ -686,6 +693,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
 		int irq_source_id, int level);
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);

include/trace/events/kvm.h

@@ -14,7 +14,7 @@
 	ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR),	\
 	ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
-	ERSN(S390_UCONTROL)
+	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),

include/uapi/linux/kvm.h

@@ -169,6 +169,8 @@ struct kvm_pit_config {
 #define KVM_EXIT_PAPR_HCALL	  19
 #define KVM_EXIT_S390_UCONTROL	  20
 #define KVM_EXIT_WATCHDOG         21
+#define KVM_EXIT_S390_TSCH        22
+#define KVM_EXIT_EPR              23
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -286,6 +288,19 @@ struct kvm_run {
 			__u64 ret;
 			__u64 args[9];
 		} papr_hcall;
+		/* KVM_EXIT_S390_TSCH */
+		struct {
+			__u16 subchannel_id;
+			__u16 subchannel_nr;
+			__u32 io_int_parm;
+			__u32 io_int_word;
+			__u32 ipb;
+			__u8 dequeued;
+		} s390_tsch;
+		/* KVM_EXIT_EPR */
+		struct {
+			__u32 epr;
+		} epr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -398,10 +413,20 @@ struct kvm_s390_psw {
 #define KVM_S390_PROGRAM_INT		0xfffe0001u
 #define KVM_S390_SIGP_SET_PREFIX	0xfffe0002u
 #define KVM_S390_RESTART		0xfffe0003u
+#define KVM_S390_MCHK			0xfffe1000u
 #define KVM_S390_INT_VIRTIO		0xffff2603u
 #define KVM_S390_INT_SERVICE		0xffff2401u
 #define KVM_S390_INT_EMERGENCY		0xffff1201u
 #define KVM_S390_INT_EXTERNAL_CALL	0xffff1202u
+/* Anything below 0xfffe0000u is taken by INT_IO */
+#define KVM_S390_INT_IO(ai,cssid,ssid,schid)   \
+	(((schid)) |			       \
+	 ((ssid) << 16) |		       \
+	 ((cssid) << 18) |		       \
+	 ((ai) << 26))
+#define KVM_S390_INT_IO_MIN		0x00000000u
+#define KVM_S390_INT_IO_MAX		0xfffdffffu
+
 
 struct kvm_s390_interrupt {
 	__u32 type;
@@ -636,6 +661,8 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
+#define KVM_CAP_S390_CSS_SUPPORT 85
+#define KVM_CAP_PPC_EPR 86
 #define KVM_CAP_ARM_PSCI 87
 #define KVM_CAP_ARM_SET_DEVICE_ADDR 88
 

kernel/sched/core.c

@@ -4374,7 +4374,10 @@ EXPORT_SYMBOL(yield);
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
  *
- * Returns true if we indeed boosted the target task.
+ * Returns:
+ *	true (>0) if we indeed boosted the target task.
+ *	false (0) if we failed to boost the target.
+ *	-ESRCH if there's no task to yield to.
  */
 bool __sched yield_to(struct task_struct *p, bool preempt)
 {
@@ -4388,6 +4391,15 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
 
 again:
 	p_rq = task_rq(p);
+	/*
+	 * If we're the only runnable task on the rq and target rq also
+	 * has only one task, there's absolutely no point in yielding.
+	 */
+	if (rq->nr_running == 1 && p_rq->nr_running == 1) {
+		yielded = -ESRCH;
+		goto out_irq;
+	}
+
 	double_rq_lock(rq, p_rq);
 	while (task_rq(p) != p_rq) {
 		double_rq_unlock(rq, p_rq);
@@ -4395,13 +4407,13 @@ again:
 	}
 
 	if (!curr->sched_class->yield_to_task)
-		goto out;
+		goto out_unlock;
 
 	if (curr->sched_class != p->sched_class)
-		goto out;
+		goto out_unlock;
 
 	if (task_running(p_rq, p) || p->state)
-		goto out;
+		goto out_unlock;
 
 	yielded = curr->sched_class->yield_to_task(rq, p, preempt);
 	if (yielded) {
@@ -4414,11 +4426,12 @@ again:
 			resched_task(p_rq->curr);
 	}
 
-out:
+out_unlock:
 	double_rq_unlock(rq, p_rq);
+out_irq:
 	local_irq_restore(flags);
 
-	if (yielded)
+	if (yielded > 0)
 		schedule();
 
 	return yielded;

virt/kvm/ioapic.c

@@ -35,6 +35,7 @@
 #include <linux/hrtimer.h>
 #include <linux/io.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <asm/processor.h>
 #include <asm/page.h>
 #include <asm/current.h>
@@ -115,6 +116,42 @@ static void update_handled_vectors(struct kvm_ioapic *ioapic)
 	smp_wmb();
 }
 
+void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+					u64 *eoi_exit_bitmap)
+{
+	struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+	union kvm_ioapic_redirect_entry *e;
+	struct kvm_lapic_irq irqe;
+	int index;
+
+	spin_lock(&ioapic->lock);
+	/* traverse ioapic entry to set eoi exit bitmap*/
+	for (index = 0; index < IOAPIC_NUM_PINS; index++) {
+		e = &ioapic->redirtbl[index];
+		if (!e->fields.mask &&
+			(e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+			 kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC,
+				 index))) {
+			irqe.dest_id = e->fields.dest_id;
+			irqe.vector = e->fields.vector;
+			irqe.dest_mode = e->fields.dest_mode;
+			irqe.delivery_mode = e->fields.delivery_mode << 8;
+			kvm_calculate_eoi_exitmap(vcpu, &irqe, eoi_exit_bitmap);
+		}
+	}
+	spin_unlock(&ioapic->lock);
+}
+EXPORT_SYMBOL_GPL(kvm_ioapic_calculate_eoi_exitmap);
+
+void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm)
+{
+	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	if (!kvm_apic_vid_enabled(kvm) || !ioapic)
+		return;
+	kvm_make_update_eoibitmap_request(kvm);
+}
+
 static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
@@ -156,6 +193,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 		if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
 		    && ioapic->irr & (1 << index))
 			ioapic_service(ioapic, index);
+		kvm_ioapic_make_eoibitmap_request(ioapic->kvm);
 		break;
 	}
 }
@@ -179,15 +217,6 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 	irqe.level = 1;
 	irqe.shorthand = 0;
 
-#ifdef CONFIG_X86
-	/* Always delivery PIT interrupt to vcpu 0 */
-	if (irq == 0) {
-		irqe.dest_mode = 0; /* Physical mode. */
-		/* need to read apic_id from apic regiest since
-		 * it can be rewritten */
-		irqe.dest_id = ioapic->kvm->bsp_vcpu_id;
-	}
-#endif
 	return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 }
 
@@ -464,6 +493,7 @@ int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
 	spin_lock(&ioapic->lock);
 	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
 	update_handled_vectors(ioapic);
+	kvm_ioapic_make_eoibitmap_request(kvm);
 	spin_unlock(&ioapic->lock);
 	return 0;
 }

virt/kvm/ioapic.h

@@ -82,5 +82,9 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq);
 int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
 int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+void kvm_ioapic_make_eoibitmap_request(struct kvm *kvm);
+void kvm_ioapic_calculate_eoi_exitmap(struct kvm_vcpu *vcpu,
+					u64 *eoi_exit_bitmap);
+
 
 #endif

virt/kvm/iommu.c

@@ -76,7 +76,9 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 	gfn     = slot->base_gfn;
 	end_gfn = gfn + slot->npages;
 
-	flags = IOMMU_READ | IOMMU_WRITE;
+	flags = IOMMU_READ;
+	if (!(slot->flags & KVM_MEM_READONLY))
+		flags |= IOMMU_WRITE;
 	if (kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY)
 		flags |= IOMMU_CACHE;
 

virt/kvm/irq_comm.c

@@ -22,6 +22,7 @@
 
 #include <linux/kvm_host.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
@@ -237,6 +238,28 @@ int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	return ret;
 }
 
+bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+	struct kvm_irq_ack_notifier *kian;
+	struct hlist_node *n;
+	int gsi;
+
+	rcu_read_lock();
+	gsi = rcu_dereference(kvm->irq_routing)->chip[irqchip][pin];
+	if (gsi != -1)
+		hlist_for_each_entry_rcu(kian, n, &kvm->irq_ack_notifier_list,
+					 link)
+			if (kian->gsi == gsi) {
+				rcu_read_unlock();
+				return true;
+			}
+
+	rcu_read_unlock();
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);
+
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
@@ -261,6 +284,7 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 	mutex_lock(&kvm->irq_lock);
 	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
 	mutex_unlock(&kvm->irq_lock);
+	kvm_ioapic_make_eoibitmap_request(kvm);
 }
 
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
@@ -270,6 +294,7 @@ void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 	hlist_del_init_rcu(&kian->link);
 	mutex_unlock(&kvm->irq_lock);
 	synchronize_rcu();
+	kvm_ioapic_make_eoibitmap_request(kvm);
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)

virt/kvm/kvm_main.c

@@ -217,6 +217,11 @@ void kvm_make_mclock_inprogress_request(struct kvm *kvm)
 	make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS);
 }
 
+void kvm_make_update_eoibitmap_request(struct kvm *kvm)
+{
+	make_all_cpus_request(kvm, KVM_REQ_EOIBITMAP);
+}
+
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 {
 	struct page *page;
@@ -474,6 +479,8 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
+	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
+
 	r = -ENOMEM;
 	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
 	if (!kvm->memslots)
@@ -670,7 +677,8 @@ static void sort_memslots(struct kvm_memslots *slots)
 		slots->id_to_index[slots->memslots[i].id] = i;
 }
 
-void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
+void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new,
+		     u64 last_generation)
 {
 	if (new) {
 		int id = new->id;
@@ -682,7 +690,7 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
 			sort_memslots(slots);
 	}
 
-	slots->generation++;
+	slots->generation = last_generation + 1;
 }
 
 static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
@@ -699,6 +707,35 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
 	return 0;
 }
 
+static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
+		struct kvm_memslots *slots, struct kvm_memory_slot *new)
+{
+	struct kvm_memslots *old_memslots = kvm->memslots;
+
+	update_memslots(slots, new, kvm->memslots->generation);
+	rcu_assign_pointer(kvm->memslots, slots);
+	synchronize_srcu_expedited(&kvm->srcu);
+	return old_memslots; 
+}
+
+/*
+ * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
+ * - create a new memory slot
+ * - delete an existing memory slot
+ * - modify an existing memory slot
+ *   -- move it in the guest physical memory space
+ *   -- just change its flags
+ *
+ * Since flags can be changed by some of these operations, the following
+ * differentiation is the best we can do for __kvm_set_memory_region():
+ */
+enum kvm_mr_change {
+	KVM_MR_CREATE,
+	KVM_MR_DELETE,
+	KVM_MR_MOVE,
+	KVM_MR_FLAGS_ONLY,
+};
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -709,14 +746,15 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
  */
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
-			    int user_alloc)
+			    bool user_alloc)
 {
 	int r;
 	gfn_t base_gfn;
 	unsigned long npages;
-	struct kvm_memory_slot *memslot, *slot;
+	struct kvm_memory_slot *slot;
 	struct kvm_memory_slot old, new;
-	struct kvm_memslots *slots, *old_memslots;
+	struct kvm_memslots *slots = NULL, *old_memslots;
+	enum kvm_mr_change change;
 
 	r = check_memory_region_flags(mem);
 	if (r)
@@ -740,7 +778,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		goto out;
 
-	memslot = id_to_memslot(kvm->memslots, mem->slot);
+	slot = id_to_memslot(kvm->memslots, mem->slot);
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -751,26 +789,48 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!npages)
 		mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES;
 
-	new = old = *memslot;
+	new = old = *slot;
 
 	new.id = mem->slot;
 	new.base_gfn = base_gfn;
 	new.npages = npages;
 	new.flags = mem->flags;
 
-	/* Disallow changing a memory slot's size. */
 	r = -EINVAL;
-	if (npages && old.npages && npages != old.npages)
-		goto out_free;
+	if (npages) {
+		if (!old.npages)
+			change = KVM_MR_CREATE;
+		else { /* Modify an existing slot. */
+			if ((mem->userspace_addr != old.userspace_addr) ||
+			    (npages != old.npages) ||
+			    ((new.flags ^ old.flags) & KVM_MEM_READONLY))
+				goto out;
 
-	/* Check for overlaps */
-	r = -EEXIST;
-	kvm_for_each_memslot(slot, kvm->memslots) {
-		if (slot->id >= KVM_MEMORY_SLOTS || slot == memslot)
-			continue;
-		if (!((base_gfn + npages <= slot->base_gfn) ||
-		      (base_gfn >= slot->base_gfn + slot->npages)))
-			goto out_free;
+			if (base_gfn != old.base_gfn)
+				change = KVM_MR_MOVE;
+			else if (new.flags != old.flags)
+				change = KVM_MR_FLAGS_ONLY;
+			else { /* Nothing to change. */
+				r = 0;
+				goto out;
+			}
+		}
+	} else if (old.npages) {
+		change = KVM_MR_DELETE;
+	} else /* Modify a non-existent slot: disallowed. */
+		goto out;
+
+	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+		/* Check for overlaps */
+		r = -EEXIST;
+		kvm_for_each_memslot(slot, kvm->memslots) {
+			if ((slot->id >= KVM_USER_MEM_SLOTS) ||
+			    (slot->id == mem->slot))
+				continue;
+			if (!((base_gfn + npages <= slot->base_gfn) ||
+			      (base_gfn >= slot->base_gfn + slot->npages)))
+				goto out;
+		}
 	}
 
 	/* Free page dirty bitmap if unneeded */
@@ -778,10 +838,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		new.dirty_bitmap = NULL;
 
 	r = -ENOMEM;
-
-	/* Allocate if a slot is being created */
-	if (npages && !old.npages) {
-		new.user_alloc = user_alloc;
+	if (change == KVM_MR_CREATE) {
 		new.userspace_addr = mem->userspace_addr;
 
 		if (kvm_arch_create_memslot(&new, npages))
@@ -792,12 +849,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) {
 		if (kvm_create_dirty_bitmap(&new) < 0)
 			goto out_free;
-		/* destroy any largepage mappings for dirty tracking */
 	}
 
-	if (!npages || base_gfn != old.base_gfn) {
-		struct kvm_memory_slot *slot;
-
+	if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) {
 		r = -ENOMEM;
 		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
 				GFP_KERNEL);
@@ -806,11 +860,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		slot = id_to_memslot(slots, mem->slot);
 		slot->flags |= KVM_MEMSLOT_INVALID;
 
-		update_memslots(slots, NULL);
+		old_memslots = install_new_memslots(kvm, slots, NULL);
 
-		old_memslots = kvm->memslots;
-		rcu_assign_pointer(kvm->memslots, slots);
-		synchronize_srcu_expedited(&kvm->srcu);
+		/* slot was deleted or moved, clear iommu mapping */
+		kvm_iommu_unmap_pages(kvm, &old);
 		/* From this point no new shadow pages pointing to a deleted,
 		 * or moved, memslot will be created.
 		 *
@@ -819,37 +872,48 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		 * 	- kvm_is_visible_gfn (mmu_check_roots)
 		 */
 		kvm_arch_flush_shadow_memslot(kvm, slot);
-		kfree(old_memslots);
+		slots = old_memslots;
 	}
 
 	r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc);
 	if (r)
-		goto out_free;
+		goto out_slots;
 
-	/* map/unmap the pages in iommu page table */
-	if (npages) {
-		r = kvm_iommu_map_pages(kvm, &new);
-		if (r)
+	r = -ENOMEM;
+	/*
+	 * We can re-use the old_memslots from above, the only difference
+	 * from the currently installed memslots is the invalid flag.  This
+	 * will get overwritten by update_memslots anyway.
+	 */
+	if (!slots) {
+		slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
+				GFP_KERNEL);
+		if (!slots)
 			goto out_free;
-	} else
-		kvm_iommu_unmap_pages(kvm, &old);
+	}
 
-	r = -ENOMEM;
-	slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots),
-			GFP_KERNEL);
-	if (!slots)
-		goto out_free;
+	/*
+	 * IOMMU mapping:  New slots need to be mapped.  Old slots need to be
+	 * un-mapped and re-mapped if their base changes.  Since base change
+	 * unmapping is handled above with slot deletion, mapping alone is
+	 * needed here.  Anything else the iommu might care about for existing
+	 * slots (size changes, userspace addr changes and read-only flag
+	 * changes) is disallowed above, so any other attribute changes getting
+	 * here can be skipped.
+	 */
+	if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) {
+		r = kvm_iommu_map_pages(kvm, &new);
+		if (r)
+			goto out_slots;
+	}
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
-	if (!npages) {
+	if (change == KVM_MR_DELETE) {
 		new.dirty_bitmap = NULL;
 		memset(&new.arch, 0, sizeof(new.arch));
 	}
 
-	update_memslots(slots, &new);
-	old_memslots = kvm->memslots;
-	rcu_assign_pointer(kvm->memslots, slots);
-	synchronize_srcu_expedited(&kvm->srcu);
+	old_memslots = install_new_memslots(kvm, slots, &new);
 
 	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
 
@@ -858,17 +922,18 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	return 0;
 
+out_slots:
+	kfree(slots);
 out_free:
 	kvm_free_physmem_slot(&new, &old);
 out:
 	return r;
-
 }
 EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
 
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
-			  int user_alloc)
+			  bool user_alloc)
 {
 	int r;
 
@@ -882,9 +947,9 @@ EXPORT_SYMBOL_GPL(kvm_set_memory_region);
 int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 				   struct
 				   kvm_userspace_memory_region *mem,
-				   int user_alloc)
+				   bool user_alloc)
 {
-	if (mem->slot >= KVM_MEMORY_SLOTS)
+	if (mem->slot >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 	return kvm_set_memory_region(kvm, mem, user_alloc);
 }
@@ -898,7 +963,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 	unsigned long any = 0;
 
 	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
+	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
@@ -944,7 +1009,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
 
-	if (!memslot || memslot->id >= KVM_MEMORY_SLOTS ||
+	if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
 	      memslot->flags & KVM_MEMSLOT_INVALID)
 		return 0;
 
@@ -1641,6 +1706,7 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct pid *pid;
 	struct task_struct *task = NULL;
+	bool ret = false;
 
 	rcu_read_lock();
 	pid = rcu_dereference(target->pid);
@@ -1648,17 +1714,15 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 		task = get_pid_task(target->pid, PIDTYPE_PID);
 	rcu_read_unlock();
 	if (!task)
-		return false;
+		return ret;
 	if (task->flags & PF_VCPU) {
 		put_task_struct(task);
-		return false;
-	}
-	if (yield_to(task, 1)) {
-		put_task_struct(task);
-		return true;
+		return ret;
 	}
+	ret = yield_to(task, 1);
 	put_task_struct(task);
-	return false;
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
 
@@ -1699,12 +1763,14 @@ bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
 	return eligible;
 }
 #endif
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
 	struct kvm_vcpu *vcpu;
 	int last_boosted_vcpu = me->kvm->last_boosted_vcpu;
 	int yielded = 0;
+	int try = 3;
 	int pass;
 	int i;
 
@@ -1716,7 +1782,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	 * VCPU is holding the lock that we need and will release it.
 	 * We approximate round-robin by starting at the last boosted VCPU.
 	 */
-	for (pass = 0; pass < 2 && !yielded; pass++) {
+	for (pass = 0; pass < 2 && !yielded && try; pass++) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (!pass && i <= last_boosted_vcpu) {
 				i = last_boosted_vcpu;
@@ -1729,10 +1795,15 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
-			if (kvm_vcpu_yield_to(vcpu)) {
+
+			yielded = kvm_vcpu_yield_to(vcpu);
+			if (yielded > 0) {
 				kvm->last_boosted_vcpu = i;
-				yielded = 1;
 				break;
+			} else if (yielded < 0) {
+				try--;
+				if (!try)
+					break;
 			}
 		}
 	}
@@ -2127,7 +2198,7 @@ static long kvm_vm_ioctl(struct file *filp,
 						sizeof kvm_userspace_mem))
 			goto out;
 
-		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1);
+		r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, true);
 		break;
 	}
 	case KVM_GET_DIRTY_LOG: {