Merge branch 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (84 commits)
  KVM: VMX: Fix comparison of guest efer with stale host value
  KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c
  KVM: Drop user return notifier when disabling virtualization on a cpu
  KVM: VMX: Disable unrestricted guest when EPT disabled
  KVM: x86 emulator: limit instructions to 15 bytes
  KVM: s390: Make psw available on all exits, not just a subset
  KVM: x86: Add KVM_GET/SET_VCPU_EVENTS
  KVM: VMX: Report unexpected simultaneous exceptions as internal errors
  KVM: Allow internal errors reported to userspace to carry extra data
  KVM: Reorder IOCTLs in main kvm.h
  KVM: x86: Polish exception injection via KVM_SET_GUEST_DEBUG
  KVM: only clear irq_source_id if irqchip is present
  KVM: x86: disallow KVM_{SET,GET}_LAPIC without allocated in-kernel lapic
  KVM: x86: disallow multiple KVM_CREATE_IRQCHIP
  KVM: VMX: Remove vmx->msr_offset_efer
  KVM: MMU: update invlpg handler comment
  KVM: VMX: move CR3/PDPTR update to vmx_set_cr3
  KVM: remove duplicated task_switch check
  KVM: powerpc: Fix BUILD_BUG_ON condition
  KVM: VMX: Use shared msr infrastructure
  ...

Trivial conflicts due to new Kconfig options in arch/Kconfig and kernel/Makefile

Documentation/kvm/api.txt

@@ -593,6 +593,115 @@ struct kvm_irqchip {
 	} chip;
 };
 
+4.27 KVM_XEN_HVM_CONFIG
+
+Capability: KVM_CAP_XEN_HVM
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_xen_hvm_config (in)
+Returns: 0 on success, -1 on error
+
+Sets the MSR that the Xen HVM guest uses to initialize its hypercall
+page, and provides the starting address and size of the hypercall
+blobs in userspace.  When the guest writes the MSR, kvm copies one
+page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
+memory.
+
+struct kvm_xen_hvm_config {
+	__u32 flags;
+	__u32 msr;
+	__u64 blob_addr_32;
+	__u64 blob_addr_64;
+	__u8 blob_size_32;
+	__u8 blob_size_64;
+	__u8 pad2[30];
+};
+
+4.27 KVM_GET_CLOCK
+
+Capability: KVM_CAP_ADJUST_CLOCK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_clock_data (out)
+Returns: 0 on success, -1 on error
+
+Gets the current timestamp of kvmclock as seen by the current guest. In
+conjunction with KVM_SET_CLOCK, it is used to ensure monotonicity on scenarios
+such as migration.
+
+struct kvm_clock_data {
+	__u64 clock;  /* kvmclock current value */
+	__u32 flags;
+	__u32 pad[9];
+};
+
+4.28 KVM_SET_CLOCK
+
+Capability: KVM_CAP_ADJUST_CLOCK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_clock_data (in)
+Returns: 0 on success, -1 on error
+
+Sets the current timestamp of kvmclock to the valued specific in its parameter.
+In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios
+such as migration.
+
+struct kvm_clock_data {
+	__u64 clock;  /* kvmclock current value */
+	__u32 flags;
+	__u32 pad[9];
+};
+
+4.29 KVM_GET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_vcpu_event (out)
+Returns: 0 on success, -1 on error
+
+Gets currently pending exceptions, interrupts, and NMIs as well as related
+states of the vcpu.
+
+struct kvm_vcpu_events {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 pad;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+	__u32 flags;   /* must be zero */
+};
+
+4.30 KVM_SET_VCPU_EVENTS
+
+Capability: KVM_CAP_VCPU_EVENTS
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_vcpu_event (in)
+Returns: 0 on success, -1 on error
+
+Set pending exceptions, interrupts, and NMIs as well as related states of the
+vcpu.
+
+See KVM_GET_VCPU_EVENTS for the data structure.
+
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

arch/Kconfig

@@ -83,6 +83,13 @@ config KRETPROBES
 	def_bool y
 	depends on KPROBES && HAVE_KRETPROBES
 
+config USER_RETURN_NOTIFIER
+	bool
+	depends on HAVE_USER_RETURN_NOTIFIER
+	help
+	  Provide a kernel-internal notification when a cpu is about to
+	  switch to user mode.
+
 config HAVE_IOREMAP_PROT
 	bool
 
@@ -132,5 +139,7 @@ config HAVE_HW_BREAKPOINT
 	select ANON_INODES
 	select PERF_EVENTS
 
+config HAVE_USER_RETURN_NOTIFIER
+	bool
 
 source "kernel/gcov/Kconfig"

arch/ia64/include/asm/kvm.h

@@ -60,6 +60,7 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_PIC_MASTER   0
 #define KVM_IRQCHIP_PIC_SLAVE    1
 #define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
 
 #define KVM_CONTEXT_SIZE	8*1024
 

arch/ia64/include/asm/kvm_host.h

@@ -475,7 +475,6 @@ struct kvm_arch {
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
 	int iommu_flags;
-	struct hlist_head irq_ack_notifier_list;
 
 	unsigned long irq_sources_bitmap;
 	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];

arch/ia64/kvm/Makefile

@@ -49,7 +49,7 @@ EXTRA_CFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 EXTRA_AFLAGS += -Ivirt/kvm -Iarch/ia64/kvm/
 
 common-objs = $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
-		coalesced_mmio.o irq_comm.o)
+		coalesced_mmio.o irq_comm.o assigned-dev.o)
 
 ifeq ($(CONFIG_IOMMU_API),y)
 common-objs += $(addprefix ../../../virt/kvm/, iommu.o)

arch/ia64/kvm/kvm-ia64.c

@@ -124,7 +124,7 @@ long ia64_pal_vp_create(u64 *vpd, u64 *host_iva, u64 *opt_handler)
 
 static  DEFINE_SPINLOCK(vp_lock);
 
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
 	long  status;
 	long  tmp_base;
@@ -137,7 +137,7 @@ void kvm_arch_hardware_enable(void *garbage)
 	slot = ia64_itr_entry(0x3, KVM_VMM_BASE, pte, KVM_VMM_SHIFT);
 	local_irq_restore(saved_psr);
 	if (slot < 0)
-		return;
+		return -EINVAL;
 
 	spin_lock(&vp_lock);
 	status = ia64_pal_vp_init_env(kvm_vsa_base ?
@@ -145,7 +145,7 @@ void kvm_arch_hardware_enable(void *garbage)
 			__pa(kvm_vm_buffer), KVM_VM_BUFFER_BASE, &tmp_base);
 	if (status != 0) {
 		printk(KERN_WARNING"kvm: Failed to Enable VT Support!!!!\n");
-		return ;
+		return -EINVAL;
 	}
 
 	if (!kvm_vsa_base) {
@@ -154,6 +154,8 @@ void kvm_arch_hardware_enable(void *garbage)
 	}
 	spin_unlock(&vp_lock);
 	ia64_ptr_entry(0x3, slot);
+
+	return 0;
 }
 
 void kvm_arch_hardware_disable(void *garbage)
@@ -851,8 +853,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm,
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_IOAPIC:
-		memcpy(&chip->chip.ioapic, ioapic_irqchip(kvm),
-				sizeof(struct kvm_ioapic_state));
+		r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -868,9 +869,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_IOAPIC:
-		memcpy(ioapic_irqchip(kvm),
-				&chip->chip.ioapic,
-				sizeof(struct kvm_ioapic_state));
+		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -944,7 +943,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 {
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
-	int r = -EINVAL;
+	int r = -ENOTTY;
 
 	switch (ioctl) {
 	case KVM_SET_MEMORY_REGION: {
@@ -985,10 +984,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,

arch/powerpc/kvm/powerpc.c

@@ -78,8 +78,9 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	return r;
 }
 
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
+	return 0;
 }
 
 void kvm_arch_hardware_disable(void *garbage)
@@ -421,7 +422,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	default:
-		r = -EINVAL;
+		r = -ENOTTY;
 	}
 
 	return r;

arch/powerpc/kvm/timing.h

@@ -51,7 +51,7 @@ static inline void kvmppc_account_exit_stat(struct kvm_vcpu *vcpu, int type)
 
 	/* The BUILD_BUG_ON below breaks in funny ways, commented out
 	 * for now ... -BenH
-	BUILD_BUG_ON(__builtin_constant_p(type));
+	BUILD_BUG_ON(!__builtin_constant_p(type));
 	*/
 	switch (type) {
 	case EXT_INTR_EXITS:

arch/s390/include/asm/kvm.h

 #ifndef __LINUX_KVM_S390_H
 #define __LINUX_KVM_S390_H
-
 /*
  * asm-s390/kvm.h - KVM s390 specific structures and definitions
  *
@@ -15,6 +14,8 @@
  */
 #include <linux/types.h>
 
+#define __KVM_S390
+
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
 	/* general purpose regs for s390 */

arch/s390/kvm/kvm-s390.c

@@ -74,9 +74,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 static unsigned long long *facilities;
 
 /* Section: not file related */
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
 	/* every s390 is virtualization enabled ;-) */
+	return 0;
 }
 
 void kvm_arch_hardware_disable(void *garbage)
@@ -116,10 +117,16 @@ long kvm_arch_dev_ioctl(struct file *filp,
 
 int kvm_dev_ioctl_check_extension(long ext)
 {
+	int r;
+
 	switch (ext) {
+	case KVM_CAP_S390_PSW:
+		r = 1;
+		break;
 	default:
-		return 0;
+		r = 0;
 	}
+	return r;
 }
 
 /* Section: vm related */
@@ -150,7 +157,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		break;
 	}
 	default:
-		r = -EINVAL;
+		r = -ENOTTY;
 	}
 
 	return r;
@@ -419,8 +426,10 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 	vcpu_load(vcpu);
 	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
 		rc = -EBUSY;
-	else
-		vcpu->arch.sie_block->gpsw = psw;
+	else {
+		vcpu->run->psw_mask = psw.mask;
+		vcpu->run->psw_addr = psw.addr;
+	}
 	vcpu_put(vcpu);
 	return rc;
 }
@@ -508,9 +517,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:
-		vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask;
-		vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
-		break;
 	case KVM_EXIT_UNKNOWN:
 	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
@@ -519,6 +525,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		BUG();
 	}
 
+	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+
 	might_fault();
 
 	do {
@@ -538,8 +547,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		/* intercept cannot be handled in-kernel, prepare kvm-run */
 		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
 		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
-		kvm_run->s390_sieic.mask     = vcpu->arch.sie_block->gpsw.mask;
-		kvm_run->s390_sieic.addr     = vcpu->arch.sie_block->gpsw.addr;
 		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
 		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
 		rc = 0;
@@ -551,6 +558,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = 0;
 	}
 
+	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
+	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 

arch/s390/kvm/sigp.c

@@ -188,9 +188,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
-	if ((copy_from_guest(vcpu, &tmp,
-		(u64) (address + vcpu->arch.sie_block->gmsor) , 1)) ||
-	   (copy_from_guest(vcpu, &tmp, (u64) (address +
+	if ((copy_from_user(&tmp, (void __user *)
+		(address + vcpu->arch.sie_block->gmsor) , 1)) ||
+	   (copy_from_user(&tmp, (void __user *)(address +
 			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */

arch/x86/Kconfig

@@ -51,6 +51,7 @@ config X86
 	select HAVE_KERNEL_LZMA
 	select HAVE_HW_BREAKPOINT
 	select HAVE_ARCH_KMEMCHECK
+	select HAVE_USER_RETURN_NOTIFIER
 
 config OUTPUT_FORMAT
 	string

arch/x86/include/asm/kvm.h

@@ -19,6 +19,8 @@
 #define __KVM_HAVE_MSIX
 #define __KVM_HAVE_MCE
 #define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
+#define __KVM_HAVE_VCPU_EVENTS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -79,6 +81,7 @@ struct kvm_ioapic_state {
 #define KVM_IRQCHIP_PIC_MASTER   0
 #define KVM_IRQCHIP_PIC_SLAVE    1
 #define KVM_IRQCHIP_IOAPIC       2
+#define KVM_NR_IRQCHIPS          3
 
 /* for KVM_GET_REGS and KVM_SET_REGS */
 struct kvm_regs {
@@ -250,4 +253,31 @@ struct kvm_reinject_control {
 	__u8 pit_reinject;
 	__u8 reserved[31];
 };
+
+/* for KVM_GET/SET_VCPU_EVENTS */
+struct kvm_vcpu_events {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 pad;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+	__u32 flags;
+	__u32 reserved[10];
+};
+
 #endif /* _ASM_X86_KVM_H */

arch/x86/include/asm/kvm_emulate.h

@@ -129,7 +129,7 @@ struct decode_cache {
 	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
-	unsigned long eip;
+	unsigned long eip, eip_orig;
 	/* modrm */
 	u8 modrm;
 	u8 modrm_mod;

arch/x86/include/asm/kvm_host.h

@@ -354,7 +354,6 @@ struct kvm_vcpu_arch {
 	unsigned int time_offset;
 	struct page *time_page;
 
-	bool singlestep; /* guest is single stepped by KVM */
 	bool nmi_pending;
 	bool nmi_injected;
 
@@ -371,6 +370,10 @@ struct kvm_vcpu_arch {
 	u64 mcg_status;
 	u64 mcg_ctl;
 	u64 *mce_banks;
+
+	/* used for guest single stepping over the given code position */
+	u16 singlestep_cs;
+	unsigned long singlestep_rip;
 };
 
 struct kvm_mem_alias {
@@ -397,7 +400,6 @@ struct kvm_arch{
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
-	struct hlist_head irq_ack_notifier_list;
 	int vapics_in_nmi_mode;
 
 	unsigned int tss_addr;
@@ -410,8 +412,10 @@ struct kvm_arch{
 	gpa_t ept_identity_map_addr;
 
 	unsigned long irq_sources_bitmap;
-	unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
 	u64 vm_init_tsc;
+	s64 kvmclock_offset;
+
+	struct kvm_xen_hvm_config xen_hvm_config;
 };
 
 struct kvm_vm_stat {
@@ -461,7 +465,7 @@ struct descriptor_table {
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
-	void (*hardware_enable)(void *dummy);      /* __init */
+	int (*hardware_enable)(void *dummy);
 	void (*hardware_disable)(void *dummy);
 	void (*check_processor_compatibility)(void *rtn);
 	int (*hardware_setup)(void);               /* __init */
@@ -477,7 +481,7 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
-	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
+	void (*set_guest_debug)(struct kvm_vcpu *vcpu,
 				struct kvm_guest_debug *dbg);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
@@ -506,8 +510,8 @@ struct kvm_x86_ops {
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
 
-	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
-	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	void (*run)(struct kvm_vcpu *vcpu);
+	int (*handle_exit)(struct kvm_vcpu *vcpu);
 	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
 	void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
 	u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
@@ -519,6 +523,8 @@ struct kvm_x86_ops {
 				bool has_error_code, u32 error_code);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
+	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
 	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);
@@ -568,7 +574,7 @@ enum emulation_result {
 #define EMULTYPE_NO_DECODE	    (1 << 0)
 #define EMULTYPE_TRAP_UD	    (1 << 1)
 #define EMULTYPE_SKIP		    (1 << 2)
-int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
+int emulate_instruction(struct kvm_vcpu *vcpu,
 			unsigned long cr2, u16 error_code, int emulation_type);
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
@@ -585,9 +591,9 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
 struct x86_emulate_ctxt;
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
 		     int size, unsigned port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 			   int size, unsigned long count, int down,
 			    gva_t address, int rep, unsigned port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
@@ -616,6 +622,9 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 
+unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
+
 void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
@@ -802,4 +811,7 @@ 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);
 
+void kvm_define_shared_msr(unsigned index, u32 msr);
+void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+
 #endif /* _ASM_X86_KVM_HOST_H */

arch/x86/include/asm/svm.h

@@ -57,7 +57,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u16 intercept_dr_write;
 	u32 intercept_exceptions;
 	u64 intercept;
-	u8 reserved_1[44];
+	u8 reserved_1[42];
+	u16 pause_filter_count;
 	u64 iopm_base_pa;
 	u64 msrpm_base_pa;
 	u64 tsc_offset;

arch/x86/include/asm/thread_info.h

@@ -83,6 +83,7 @@ struct thread_info {
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* 32bit process */
 #define TIF_FORK		18	/* ret_from_fork */
@@ -107,6 +108,7 @@ struct thread_info {
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
+#define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
 #define _TIF_FORK		(1 << TIF_FORK)
@@ -142,13 +144,14 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
+	 _TIF_USER_RETURN_NOTIFY)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
 	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
 
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
 
 #define PREEMPT_ACTIVE		0x10000000

arch/x86/include/asm/vmx.h

@@ -56,6 +56,7 @@
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -144,6 +145,8 @@ enum vmcs_field {
 	VM_ENTRY_INSTRUCTION_LEN        = 0x0000401a,
 	TPR_THRESHOLD                   = 0x0000401c,
 	SECONDARY_VM_EXEC_CONTROL       = 0x0000401e,
+	PLE_GAP                         = 0x00004020,
+	PLE_WINDOW                      = 0x00004022,
 	VM_INSTRUCTION_ERROR            = 0x00004400,
 	VM_EXIT_REASON                  = 0x00004402,
 	VM_EXIT_INTR_INFO               = 0x00004404,
@@ -248,6 +251,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44

arch/x86/kernel/process.c

@@ -9,6 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <linux/random.h>
+#include <linux/user-return-notifier.h>
 #include <trace/events/power.h>
 #include <linux/hw_breakpoint.h>
 #include <asm/system.h>
@@ -209,6 +210,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		 */
 		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
 	}
+	propagate_user_return_notify(prev_p, next_p);
 }
 
 int sys_fork(struct pt_regs *regs)

arch/x86/kernel/signal.c

@@ -19,6 +19,7 @@
 #include <linux/stddef.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
@@ -863,6 +864,8 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 		if (current->replacement_session_keyring)
 			key_replace_session_keyring();
 	}
+	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
+		fire_user_return_notifiers();
 
 #ifdef CONFIG_X86_32
 	clear_thread_flag(TIF_IRET);

arch/x86/kvm/Kconfig

@@ -28,6 +28,7 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
+	select USER_RETURN_NOTIFIER
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/Makefile

@@ -6,7 +6,8 @@ CFLAGS_svm.o := -I.
 CFLAGS_vmx.o := -I.
 
 kvm-y			+= $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
-				coalesced_mmio.o irq_comm.o eventfd.o)
+				coalesced_mmio.o irq_comm.o eventfd.o \
+				assigned-dev.o)
 kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \

arch/x86/kvm/i8254.c

@@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
-	mutex_unlock(&kvm->irq_lock);
 
 	/*
 	 * Provides NMI watchdog support via Virtual Wire mode.

arch/x86/kvm/i8259.c

@@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 	s->isr_ack |= (1 << irq);
 	if (s != &s->pics_state->pics[0])
 		irq += 8;
+	/*
+	 * We are dropping lock while calling ack notifiers since ack
+	 * notifier callbacks for assigned devices call into PIC recursively.
+	 * Other interrupt may be delivered to PIC while lock is dropped but
+	 * it should be safe since PIC state is already updated at this stage.
+	 */
+	spin_unlock(&s->pics_state->lock);
 	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
+	spin_lock(&s->pics_state->lock);
 }
 
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
@@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
 static inline void pic_intack(struct kvm_kpic_state *s, int irq)
 {
 	s->isr |= 1 << irq;
-	if (s->auto_eoi) {
-		if (s->rotate_on_auto_eoi)
-			s->priority_add = (irq + 1) & 7;
-		pic_clear_isr(s, irq);
-	}
 	/*
 	 * We don't clear a level sensitive interrupt here
 	 */
 	if (!(s->elcr & (1 << irq)))
 		s->irr &= ~(1 << irq);
+
+	if (s->auto_eoi) {
+		if (s->rotate_on_auto_eoi)
+			s->priority_add = (irq + 1) & 7;
+		pic_clear_isr(s, irq);
+	}
+
 }
 
 int kvm_pic_read_irq(struct kvm *kvm)
@@ -225,22 +235,11 @@ int kvm_pic_read_irq(struct kvm *kvm)
 
 void kvm_pic_reset(struct kvm_kpic_state *s)
 {
-	int irq, irqbase, n;
+	int irq;
 	struct kvm *kvm = s->pics_state->irq_request_opaque;
 	struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu;
+	u8 irr = s->irr, isr = s->imr;
 
-	if (s == &s->pics_state->pics[0])
-		irqbase = 0;
-	else
-		irqbase = 8;
-
-	for (irq = 0; irq < PIC_NUM_PINS/2; irq++) {
-		if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
-			if (s->irr & (1 << irq) || s->isr & (1 << irq)) {
-				n = irq + irqbase;
-				kvm_notify_acked_irq(kvm, SELECT_PIC(n), n);
-			}
-	}
 	s->last_irr = 0;
 	s->irr = 0;
 	s->imr = 0;
@@ -256,6 +255,13 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 	s->rotate_on_auto_eoi = 0;
 	s->special_fully_nested_mode = 0;
 	s->init4 = 0;
+
+	for (irq = 0; irq < PIC_NUM_PINS/2; irq++) {
+		if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
+			if (irr & (1 << irq) || isr & (1 << irq)) {
+				pic_clear_isr(s, irq);
+			}
+	}
 }
 
 static void pic_ioport_write(void *opaque, u32 addr, u32 val)
@@ -298,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 				priority = get_priority(s, s->isr);
 				if (priority != 8) {
 					irq = (priority + s->priority_add) & 7;
-					pic_clear_isr(s, irq);
 					if (cmd == 5)
 						s->priority_add = (irq + 1) & 7;
+					pic_clear_isr(s, irq);
 					pic_update_irq(s->pics_state);
 				}
 				break;

arch/x86/kvm/irq.h

@@ -71,6 +71,7 @@ struct kvm_pic {
 	int output;		/* intr from master PIC */
 	struct kvm_io_device dev;
 	void (*ack_notifier)(void *opaque, int irq);
+	unsigned long irq_states[16];
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
@@ -85,7 +86,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
-	return pic_irqchip(kvm) != NULL;
+	int ret;
+
+	ret = (pic_irqchip(kvm) != NULL);
+	smp_rmb();
+	return ret;
 }
 
 void kvm_pic_reset(struct kvm_kpic_state *s);

arch/x86/kvm/lapic.c

@@ -32,7 +32,6 @@
 #include <asm/current.h>
 #include <asm/apicdef.h>
 #include <asm/atomic.h>
-#include <asm/apicdef.h>
 #include "kvm_cache_regs.h"
 #include "irq.h"
 #include "trace.h"
@@ -471,11 +470,8 @@ static void apic_set_eoi(struct kvm_lapic *apic)
 		trigger_mode = IOAPIC_LEVEL_TRIG;
 	else
 		trigger_mode = IOAPIC_EDGE_TRIG;
-	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) {
-		mutex_lock(&apic->vcpu->kvm->irq_lock);
+	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
 		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
-		mutex_unlock(&apic->vcpu->kvm->irq_lock);
-	}
 }
 
 static void apic_send_ipi(struct kvm_lapic *apic)
@@ -504,9 +500,7 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
 		   irq.vector);
 
-	mutex_lock(&apic->vcpu->kvm->irq_lock);
 	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
-	mutex_unlock(&apic->vcpu->kvm->irq_lock);
 }
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)

arch/x86/kvm/mmu.c

@@ -2789,7 +2789,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 	if (r)
 		goto out;
 
-	er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0);
+	er = emulate_instruction(vcpu, cr2, error_code, 0);
 
 	switch (er) {
 	case EMULATE_DONE:
@@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 	case EMULATE_FAIL:
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
 	default:
 		BUG();

arch/x86/kvm/paging_tmpl.h

@@ -467,7 +467,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		level = iterator.level;
 		sptep = iterator.sptep;
 
-		/* FIXME: properly handle invlpg on large guest pages */
 		if (level == PT_PAGE_TABLE_LEVEL  ||
 		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
 		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {

arch/x86/kvm/trace.h

@@ -349,6 +349,171 @@ TRACE_EVENT(kvm_apic_accept_irq,
 		  __entry->coalesced ? " (coalesced)" : "")
 );
 
+/*
+ * Tracepoint for nested VMRUN
+ */
+TRACE_EVENT(kvm_nested_vmrun,
+	    TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl,
+		     __u32 event_inj, bool npt),
+	    TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		rip		)
+		__field(	__u64,		vmcb		)
+		__field(	__u64,		nested_rip	)
+		__field(	__u32,		int_ctl		)
+		__field(	__u32,		event_inj	)
+		__field(	bool,		npt		)
+	),
+
+	TP_fast_assign(
+		__entry->rip		= rip;
+		__entry->vmcb		= vmcb;
+		__entry->nested_rip	= nested_rip;
+		__entry->int_ctl	= int_ctl;
+		__entry->event_inj	= event_inj;
+		__entry->npt		= npt;
+	),
+
+	TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x "
+		  "event_inj: 0x%08x npt: %s\n",
+		__entry->rip, __entry->vmcb, __entry->nested_rip,
+		__entry->int_ctl, __entry->event_inj,
+		__entry->npt ? "on" : "off")
+);
+
+/*
+ * Tracepoint for #VMEXIT while nested
+ */
+TRACE_EVENT(kvm_nested_vmexit,
+	    TP_PROTO(__u64 rip, __u32 exit_code,
+		     __u64 exit_info1, __u64 exit_info2,
+		     __u32 exit_int_info, __u32 exit_int_info_err),
+	    TP_ARGS(rip, exit_code, exit_info1, exit_info2,
+		    exit_int_info, exit_int_info_err),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		rip			)
+		__field(	__u32,		exit_code		)
+		__field(	__u64,		exit_info1		)
+		__field(	__u64,		exit_info2		)
+		__field(	__u32,		exit_int_info		)
+		__field(	__u32,		exit_int_info_err	)
+	),
+
+	TP_fast_assign(
+		__entry->rip			= rip;
+		__entry->exit_code		= exit_code;
+		__entry->exit_info1		= exit_info1;
+		__entry->exit_info2		= exit_info2;
+		__entry->exit_int_info		= exit_int_info;
+		__entry->exit_int_info_err	= exit_int_info_err;
+	),
+	TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx "
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  __entry->rip,
+		  ftrace_print_symbols_seq(p, __entry->exit_code,
+					   kvm_x86_ops->exit_reasons_str),
+		  __entry->exit_info1, __entry->exit_info2,
+		  __entry->exit_int_info, __entry->exit_int_info_err)
+);
+
+/*
+ * Tracepoint for #VMEXIT reinjected to the guest
+ */
+TRACE_EVENT(kvm_nested_vmexit_inject,
+	    TP_PROTO(__u32 exit_code,
+		     __u64 exit_info1, __u64 exit_info2,
+		     __u32 exit_int_info, __u32 exit_int_info_err),
+	    TP_ARGS(exit_code, exit_info1, exit_info2,
+		    exit_int_info, exit_int_info_err),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		exit_code		)
+		__field(	__u64,		exit_info1		)
+		__field(	__u64,		exit_info2		)
+		__field(	__u32,		exit_int_info		)
+		__field(	__u32,		exit_int_info_err	)
+	),
+
+	TP_fast_assign(
+		__entry->exit_code		= exit_code;
+		__entry->exit_info1		= exit_info1;
+		__entry->exit_info2		= exit_info2;
+		__entry->exit_int_info		= exit_int_info;
+		__entry->exit_int_info_err	= exit_int_info_err;
+	),
+
+	TP_printk("reason: %s ext_inf1: 0x%016llx "
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  ftrace_print_symbols_seq(p, __entry->exit_code,
+					   kvm_x86_ops->exit_reasons_str),
+		__entry->exit_info1, __entry->exit_info2,
+		__entry->exit_int_info, __entry->exit_int_info_err)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_nested_intr_vmexit,
+	    TP_PROTO(__u64 rip),
+	    TP_ARGS(rip),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+	),
+
+	TP_fast_assign(
+		__entry->rip	=	rip
+	),
+
+	TP_printk("rip: 0x%016llx\n", __entry->rip)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_invlpga,
+	    TP_PROTO(__u64 rip, int asid, u64 address),
+	    TP_ARGS(rip, asid, address),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+		__field(	int,	asid	)
+		__field(	__u64,	address	)
+	),
+
+	TP_fast_assign(
+		__entry->rip		=	rip;
+		__entry->asid		=	asid;
+		__entry->address	=	address;
+	),
+
+	TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n",
+		  __entry->rip, __entry->asid, __entry->address)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_skinit,
+	    TP_PROTO(__u64 rip, __u32 slb),
+	    TP_ARGS(rip, slb),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+		__field(	__u32,	slb	)
+	),
+
+	TP_fast_assign(
+		__entry->rip		=	rip;
+		__entry->slb		=	slb;
+	),
+
+	TP_printk("rip: 0x%016llx slb: 0x%08x\n",
+		  __entry->rip, __entry->slb)
+);
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */

include/linux/kvm_host.h

@@ -120,7 +120,7 @@ struct kvm_kernel_irq_routing_entry {
 	u32 gsi;
 	u32 type;
 	int (*set)(struct kvm_kernel_irq_routing_entry *e,
-		    struct kvm *kvm, int level);
+		   struct kvm *kvm, int irq_source_id, int level);
 	union {
 		struct {
 			unsigned irqchip;
@@ -128,9 +128,28 @@ struct kvm_kernel_irq_routing_entry {
 		} irqchip;
 		struct msi_msg msi;
 	};
-	struct list_head link;
+	struct hlist_node link;
+};
+
+#ifdef __KVM_HAVE_IOAPIC
+
+struct kvm_irq_routing_table {
+	int chip[KVM_NR_IRQCHIPS][KVM_IOAPIC_NUM_PINS];
+	struct kvm_kernel_irq_routing_entry *rt_entries;
+	u32 nr_rt_entries;
+	/*
+	 * Array indexed by gsi. Each entry contains list of irq chips
+	 * the gsi is connected to.
+	 */
+	struct hlist_head map[0];
 };
 
+#else
+
+struct kvm_irq_routing_table {};
+
+#endif
+
 struct kvm {
 	spinlock_t mmu_lock;
 	spinlock_t requests_lock;
@@ -166,8 +185,9 @@ struct kvm {
 
 	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-	struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */
+	struct kvm_irq_routing_table *irq_routing;
 	struct hlist_head mask_notifier_list;
+	struct hlist_head irq_ack_notifier_list;
 #endif
 
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
@@ -266,6 +286,7 @@ int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
@@ -325,7 +346,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu);
-void kvm_arch_hardware_enable(void *garbage);
+int kvm_arch_hardware_enable(void *garbage);
 void kvm_arch_hardware_disable(void *garbage);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
@@ -390,7 +411,12 @@ void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn);
 void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask);
 
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level);
+#ifdef __KVM_HAVE_IOAPIC
+void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
+				   union kvm_ioapic_redirect_entry *entry,
+				   unsigned long *deliver_bitmask);
+#endif
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 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);
@@ -552,4 +578,21 @@ static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
 }
 #endif
+
+#ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+				  unsigned long arg);
+
+#else
+
+static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+						unsigned long arg)
+{
+	return -ENOTTY;
+}
+
 #endif
+
+#endif
+

include/linux/user-return-notifier.h

+#ifndef _LINUX_USER_RETURN_NOTIFIER_H
+#define _LINUX_USER_RETURN_NOTIFIER_H
+
+#ifdef CONFIG_USER_RETURN_NOTIFIER
+
+#include <linux/list.h>
+#include <linux/sched.h>
+
+struct user_return_notifier {
+	void (*on_user_return)(struct user_return_notifier *urn);
+	struct hlist_node link;
+};
+
+
+void user_return_notifier_register(struct user_return_notifier *urn);
+void user_return_notifier_unregister(struct user_return_notifier *urn);
+
+static inline void propagate_user_return_notify(struct task_struct *prev,
+						struct task_struct *next)
+{
+	if (test_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY)) {
+		clear_tsk_thread_flag(prev, TIF_USER_RETURN_NOTIFY);
+		set_tsk_thread_flag(next, TIF_USER_RETURN_NOTIFY);
+	}
+}
+
+void fire_user_return_notifiers(void);
+
+static inline void clear_user_return_notifier(struct task_struct *p)
+{
+	clear_tsk_thread_flag(p, TIF_USER_RETURN_NOTIFY);
+}
+
+#else
+
+struct user_return_notifier {};
+
+static inline void propagate_user_return_notify(struct task_struct *prev,
+						struct task_struct *next)
+{
+}
+
+static inline void fire_user_return_notifiers(void) {}
+
+static inline void clear_user_return_notifier(struct task_struct *p) {}
+
+#endif
+
+#endif

kernel/Makefile

@@ -99,6 +99,7 @@ obj-$(CONFIG_SLOW_WORK) += slow-work.o
 obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
+obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/fork.c

@@ -64,6 +64,7 @@
 #include <linux/magic.h>
 #include <linux/perf_event.h>
 #include <linux/posix-timers.h>
+#include <linux/user-return-notifier.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -249,6 +250,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 		goto out;
 
 	setup_thread_stack(tsk, orig);
+	clear_user_return_notifier(tsk);
 	stackend = end_of_stack(tsk);
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 

kernel/user-return-notifier.c

+
+#include <linux/user-return-notifier.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+static DEFINE_PER_CPU(struct hlist_head, return_notifier_list);
+
+#define URN_LIST_HEAD per_cpu(return_notifier_list, raw_smp_processor_id())
+
+/*
+ * Request a notification when the current cpu returns to userspace.  Must be
+ * called in atomic context.  The notifier will also be called in atomic
+ * context.
+ */
+void user_return_notifier_register(struct user_return_notifier *urn)
+{
+	set_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+	hlist_add_head(&urn->link, &URN_LIST_HEAD);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_register);
+
+/*
+ * Removes a registered user return notifier.  Must be called from atomic
+ * context, and from the same cpu registration occured in.
+ */
+void user_return_notifier_unregister(struct user_return_notifier *urn)
+{
+	hlist_del(&urn->link);
+	if (hlist_empty(&URN_LIST_HEAD))
+		clear_tsk_thread_flag(current, TIF_USER_RETURN_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(user_return_notifier_unregister);
+
+/* Calls registered user return notifiers */
+void fire_user_return_notifiers(void)
+{
+	struct user_return_notifier *urn;
+	struct hlist_node *tmp1, *tmp2;
+	struct hlist_head *head;
+
+	head = &get_cpu_var(return_notifier_list);
+	hlist_for_each_entry_safe(urn, tmp1, tmp2, head, link)
+		urn->on_user_return(urn);
+	put_cpu_var(return_notifier_list);
+}

virt/kvm/eventfd.c

@@ -61,10 +61,8 @@ irqfd_inject(struct work_struct *work)
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
 	struct kvm *kvm = irqfd->kvm;
 
-	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
-	mutex_unlock(&kvm->irq_lock);
 }
 
 /*

virt/kvm/ioapic.c

@@ -182,6 +182,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 	union kvm_ioapic_redirect_entry entry;
 	int ret = 1;
 
+	mutex_lock(&ioapic->lock);
 	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
 		entry = ioapic->redirtbl[irq];
 		level ^= entry.fields.polarity;
@@ -198,34 +199,51 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
 		}
 		trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
 	}
+	mutex_unlock(&ioapic->lock);
+
 	return ret;
 }
 
-static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int pin,
+static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
 				     int trigger_mode)
 {
-	union kvm_ioapic_redirect_entry *ent;
+	int i;
+
+	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
 
-	ent = &ioapic->redirtbl[pin];
+		if (ent->fields.vector != vector)
+			continue;
+
+		/*
+		 * We are dropping lock while calling ack notifiers because ack
+		 * notifier callbacks for assigned devices call into IOAPIC
+		 * recursively. Since remote_irr is cleared only after call
+		 * to notifiers if the same vector will be delivered while lock
+		 * is dropped it will be put into irr and will be delivered
+		 * after ack notifier returns.
+		 */
+		mutex_unlock(&ioapic->lock);
+		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
+		mutex_lock(&ioapic->lock);
 
-	kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, pin);
+		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+			continue;
 
-	if (trigger_mode == IOAPIC_LEVEL_TRIG) {
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
 		ent->fields.remote_irr = 0;
-		if (!ent->fields.mask && (ioapic->irr & (1 << pin)))
-			ioapic_service(ioapic, pin);
+		if (!ent->fields.mask && (ioapic->irr & (1 << i)))
+			ioapic_service(ioapic, i);
 	}
 }
 
 void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-	int i;
 
-	for (i = 0; i < IOAPIC_NUM_PINS; i++)
-		if (ioapic->redirtbl[i].fields.vector == vector)
-			__kvm_ioapic_update_eoi(ioapic, i, trigger_mode);
+	mutex_lock(&ioapic->lock);
+	__kvm_ioapic_update_eoi(ioapic, vector, trigger_mode);
+	mutex_unlock(&ioapic->lock);
 }
 
 static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
@@ -250,8 +268,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
-	mutex_lock(&ioapic->kvm->irq_lock);
 	addr &= 0xff;
+	mutex_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		result = ioapic->ioregsel;
@@ -265,6 +283,8 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 		result = 0;
 		break;
 	}
+	mutex_unlock(&ioapic->lock);
+
 	switch (len) {
 	case 8:
 		*(u64 *) val = result;
@@ -277,7 +297,6 @@ static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
 	}
-	mutex_unlock(&ioapic->kvm->irq_lock);
 	return 0;
 }
 
@@ -293,15 +312,15 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
-	mutex_lock(&ioapic->kvm->irq_lock);
 	if (len == 4 || len == 8)
 		data = *(u32 *) val;
 	else {
 		printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
-		goto unlock;
+		return 0;
 	}
 
 	addr &= 0xff;
+	mutex_lock(&ioapic->lock);
 	switch (addr) {
 	case IOAPIC_REG_SELECT:
 		ioapic->ioregsel = data;
@@ -312,15 +331,14 @@ static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 		break;
 #ifdef	CONFIG_IA64
 	case IOAPIC_REG_EOI:
-		kvm_ioapic_update_eoi(ioapic->kvm, data, IOAPIC_LEVEL_TRIG);
+		__kvm_ioapic_update_eoi(ioapic, data, IOAPIC_LEVEL_TRIG);
 		break;
 #endif
 
 	default:
 		break;
 	}
-unlock:
-	mutex_unlock(&ioapic->kvm->irq_lock);
+	mutex_unlock(&ioapic->lock);
 	return 0;
 }
 
@@ -349,6 +367,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
 	if (!ioapic)
 		return -ENOMEM;
+	mutex_init(&ioapic->lock);
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
@@ -360,3 +379,26 @@ int kvm_ioapic_init(struct kvm *kvm)
 	return ret;
 }
 
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	mutex_lock(&ioapic->lock);
+	memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
+	mutex_unlock(&ioapic->lock);
+	return 0;
+}
+
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+	struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+	if (!ioapic)
+		return -EINVAL;
+
+	mutex_lock(&ioapic->lock);
+	memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
+	mutex_unlock(&ioapic->lock);
+	return 0;
+}

virt/kvm/ioapic.h

@@ -41,9 +41,11 @@ struct kvm_ioapic {
 	u32 irr;
 	u32 pad;
 	union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
+	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
 	void (*ack_notifier)(void *opaque, int irq);
+	struct mutex lock;
 };
 
 #ifdef DEBUG
@@ -73,4 +75,7 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 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);
+
 #endif