Merge remote-tracking branch 'qemu-kvm/uq/master' into stable-1.5

* qemu-kvm/uq/master:
  kvm-stub: fix compilation
  kvm: shorten the parameter list for get_real_device()
  kvm: i386: fix LAPIC TSC deadline timer save/restore
  kvm-all.c: max_cpus should not exceed KVM vcpu limit
  kvm: Simplify kvm_handle_io
  kvm: x86: fix setting IA32_FEATURE_CONTROL with nested VMX disabled
  kvm: add KVM_IRQFD_FLAG_RESAMPLE support
  kvm: migrate vPMU state
  target-i386: remove tabs from target-i386/cpu.h
  Initialize IA32_FEATURE_CONTROL MSR in reset and migration

Conflicts:
	target-i386/cpu.h
	target-i386/kvm.c

aliguori: fixup trivial conflicts due to whitespace and added cpu
          argument

Signed-off-by: Anthony Liguori <anthony@codemonkey.ws>

9 files changed, 333 insertions, 126 deletions

diff --git a/hw/i386/kvm/pci-assign.c b/hw/i386/kvm/pci-assign.c
index 5618173cc6..011764fbf6 100644
--- a/hw/i386/kvm/pci-assign.c
+++ b/hw/i386/kvm/pci-assign.c
@@ -568,8 +568,7 @@ static int get_real_device_id(const char *devpath, uint16_t *val)
     return get_real_id(devpath, "device", val);
 }
 
-static int get_real_device(AssignedDevice *pci_dev, uint16_t r_seg,
-                           uint8_t r_bus, uint8_t r_dev, uint8_t r_func)
+static int get_real_device(AssignedDevice *pci_dev)
 {
     char dir[128], name[128];
     int fd, r = 0, v;
@@ -582,7 +581,8 @@ static int get_real_device(AssignedDevice *pci_dev, uint16_t r_seg,
     dev->region_number = 0;
 
     snprintf(dir, sizeof(dir), "/sys/bus/pci/devices/%04x:%02x:%02x.%x/",
-             r_seg, r_bus, r_dev, r_func);
+             pci_dev->host.domain, pci_dev->host.bus,
+             pci_dev->host.slot, pci_dev->host.function);
 
     snprintf(name, sizeof(name), "%sconfig", dir);
 
@@ -1769,8 +1769,7 @@ static int assigned_initfn(struct PCIDevice *pci_dev)
     memcpy(dev->emulate_config_write, dev->emulate_config_read,
            sizeof(dev->emulate_config_read));
 
-    if (get_real_device(dev, dev->host.domain, dev->host.bus,
-                        dev->host.slot, dev->host.function)) {
+    if (get_real_device(dev)) {
         error_report("pci-assign: Error: Couldn't get real device (%s)!",
                      dev->dev.qdev.id);
         goto out;
diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c
index d215e29e46..a1c08fb74e 100644
--- a/hw/misc/vfio.c
+++ b/hw/misc/vfio.c
@@ -646,7 +646,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr,
     vector->virq = msg ? kvm_irqchip_add_msi_route(kvm_state, *msg) : -1;
     if (vector->virq < 0 ||
         kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
-                                       vector->virq) < 0) {
+                                       NULL, vector->virq) < 0) {
         if (vector->virq >= 0) {
             kvm_irqchip_release_virq(kvm_state, vector->virq);
             vector->virq = -1;
@@ -814,7 +814,7 @@ retry:
         vector->virq = kvm_irqchip_add_msi_route(kvm_state, msg);
         if (vector->virq < 0 ||
             kvm_irqchip_add_irqfd_notifier(kvm_state, &vector->interrupt,
-                                           vector->virq) < 0) {
+                                           NULL, vector->virq) < 0) {
             qemu_set_fd_handler(event_notifier_get_fd(&vector->interrupt),
                                 vfio_msi_interrupt, NULL, vector);
         }
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index d37037ef17..f2c489b66c 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -508,7 +508,7 @@ static int kvm_virtio_pci_irqfd_use(VirtIOPCIProxy *proxy,
     VirtQueue *vq = virtio_get_queue(proxy->vdev, queue_no);
     EventNotifier *n = virtio_queue_get_guest_notifier(vq);
     int ret;
-    ret = kvm_irqchip_add_irqfd_notifier(kvm_state, n, irqfd->virq);
+    ret = kvm_irqchip_add_irqfd_notifier(kvm_state, n, NULL, irqfd->virq);
     return ret;
 }
 
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index de74411f41..8e7668524b 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -309,7 +309,8 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg);
 int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg);
 void kvm_irqchip_release_virq(KVMState *s, int virq);
 
-int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, int virq);
+int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                   EventNotifier *rn, int virq);
 int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq);
 void kvm_pc_gsi_handler(void *opaque, int n, int level);
 void kvm_pc_setup_irq_routing(bool pci_enabled);
diff --git a/kvm-all.c b/kvm-all.c
index 716860f617..875e32ec87 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -1230,7 +1230,8 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
     return kvm_update_routing_entry(s, &kroute);
 }
 
-static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int virq, bool assign)
+static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int rfd, int virq,
+                                    bool assign)
 {
     struct kvm_irqfd irqfd = {
         .fd = fd,
@@ -1238,6 +1239,11 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int virq, bool assign)
         .flags = assign ? 0 : KVM_IRQFD_FLAG_DEASSIGN,
     };
 
+    if (rfd != -1) {
+        irqfd.flags |= KVM_IRQFD_FLAG_RESAMPLE;
+        irqfd.resamplefd = rfd;
+    }
+
     if (!kvm_irqfds_enabled()) {
         return -ENOSYS;
     }
@@ -1276,14 +1282,17 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
 }
 #endif /* !KVM_CAP_IRQ_ROUTING */
 
-int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
+int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                   EventNotifier *rn, int virq)
 {
-    return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n), virq, true);
+    return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n),
+           rn ? event_notifier_get_fd(rn) : -1, virq, true);
 }
 
 int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
 {
-    return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n), virq, false);
+    return kvm_irqchip_assign_irqfd(s, event_notifier_get_fd(n), -1, virq,
+           false);
 }
 
 static int kvm_irqchip_create(KVMState *s)
@@ -1391,6 +1400,13 @@ int kvm_init(void)
         goto err;
     }
 
+    if (max_cpus > max_vcpus) {
+        ret = -EINVAL;
+        fprintf(stderr, "Number of hotpluggable cpus requested (%d) exceeds max cpus "
+                "supported by KVM (%d)\n", max_cpus, max_vcpus);
+        goto err;
+    }
+
     s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0);
     if (s->vmfd < 0) {
 #ifdef TARGET_S390X
@@ -1499,32 +1515,8 @@ static void kvm_handle_io(uint16_t port, void *data, int direction, int size,
     uint8_t *ptr = data;
 
     for (i = 0; i < count; i++) {
-        if (direction == KVM_EXIT_IO_IN) {
-            switch (size) {
-            case 1:
-                stb_p(ptr, cpu_inb(port));
-                break;
-            case 2:
-                stw_p(ptr, cpu_inw(port));
-                break;
-            case 4:
-                stl_p(ptr, cpu_inl(port));
-                break;
-            }
-        } else {
-            switch (size) {
-            case 1:
-                cpu_outb(port, ldub_p(ptr));
-                break;
-            case 2:
-                cpu_outw(port, lduw_p(ptr));
-                break;
-            case 4:
-                cpu_outl(port, ldl_p(ptr));
-                break;
-            }
-        }
-
+        address_space_rw(&address_space_io, port, ptr, size,
+                         direction == KVM_EXIT_IO_OUT);
         ptr += size;
     }
 }
diff --git a/kvm-stub.c b/kvm-stub.c
index 771360b3ca..548f471c17 100644
--- a/kvm-stub.c
+++ b/kvm-stub.c
@@ -135,7 +135,8 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg)
     return -ENOSYS;
 }
 
-int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
+int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n,
+                                   EventNotifier *rn, int virq)
 {
     return -ENOSYS;
 }
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 8a3d0fda32..5723eff9a8 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -37,9 +37,9 @@
 #define TARGET_HAS_ICE 1
 
 #ifdef TARGET_X86_64
-#define ELF_MACHINE	EM_X86_64
+#define ELF_MACHINE     EM_X86_64
 #else
-#define ELF_MACHINE	EM_386
+#define ELF_MACHINE     EM_386
 #endif
 
 #define CPUArchState struct CPUX86State
@@ -98,10 +98,10 @@
 #define DESC_TSS_BUSY_MASK (1 << 9)
 
 /* eflags masks */
-#define CC_C   	0x0001
-#define CC_P 	0x0004
-#define CC_A	0x0010
-#define CC_Z	0x0040
+#define CC_C    0x0001
+#define CC_P    0x0004
+#define CC_A    0x0010
+#define CC_Z    0x0040
 #define CC_S    0x0080
 #define CC_O    0x0800
 
@@ -109,14 +109,14 @@
 #define IOPL_SHIFT 12
 #define VM_SHIFT   17
 
-#define TF_MASK 		0x00000100
-#define IF_MASK 		0x00000200
-#define DF_MASK 		0x00000400
-#define IOPL_MASK		0x00003000
-#define NT_MASK	         	0x00004000
-#define RF_MASK			0x00010000
-#define VM_MASK			0x00020000
-#define AC_MASK			0x00040000
+#define TF_MASK                 0x00000100
+#define IF_MASK                 0x00000200
+#define DF_MASK                 0x00000400
+#define IOPL_MASK               0x00003000
+#define NT_MASK                 0x00004000
+#define RF_MASK                 0x00010000
+#define VM_MASK                 0x00020000
+#define AC_MASK                 0x00040000
 #define VIF_MASK                0x00080000
 #define VIP_MASK                0x00100000
 #define ID_MASK                 0x00200000
@@ -238,28 +238,28 @@
 #define DR7_TYPE_IO_RW       0x2
 #define DR7_TYPE_DATA_RW     0x3
 
-#define PG_PRESENT_BIT	0
-#define PG_RW_BIT	1
-#define PG_USER_BIT	2
-#define PG_PWT_BIT	3
-#define PG_PCD_BIT	4
-#define PG_ACCESSED_BIT	5
-#define PG_DIRTY_BIT	6
-#define PG_PSE_BIT	7
-#define PG_GLOBAL_BIT	8
-#define PG_NX_BIT	63
+#define PG_PRESENT_BIT  0
+#define PG_RW_BIT       1
+#define PG_USER_BIT     2
+#define PG_PWT_BIT      3
+#define PG_PCD_BIT      4
+#define PG_ACCESSED_BIT 5
+#define PG_DIRTY_BIT    6
+#define PG_PSE_BIT      7
+#define PG_GLOBAL_BIT   8
+#define PG_NX_BIT       63
 
 #define PG_PRESENT_MASK  (1 << PG_PRESENT_BIT)
-#define PG_RW_MASK	 (1 << PG_RW_BIT)
-#define PG_USER_MASK	 (1 << PG_USER_BIT)
-#define PG_PWT_MASK	 (1 << PG_PWT_BIT)
-#define PG_PCD_MASK	 (1 << PG_PCD_BIT)
+#define PG_RW_MASK       (1 << PG_RW_BIT)
+#define PG_USER_MASK     (1 << PG_USER_BIT)
+#define PG_PWT_MASK      (1 << PG_PWT_BIT)
+#define PG_PCD_MASK      (1 << PG_PCD_BIT)
 #define PG_ACCESSED_MASK (1 << PG_ACCESSED_BIT)
-#define PG_DIRTY_MASK	 (1 << PG_DIRTY_BIT)
-#define PG_PSE_MASK	 (1 << PG_PSE_BIT)
-#define PG_GLOBAL_MASK	 (1 << PG_GLOBAL_BIT)
+#define PG_DIRTY_MASK    (1 << PG_DIRTY_BIT)
+#define PG_PSE_MASK      (1 << PG_PSE_BIT)
+#define PG_GLOBAL_MASK   (1 << PG_GLOBAL_BIT)
 #define PG_HI_USER_MASK  0x7ff0000000000000LL
-#define PG_NX_MASK	 (1LL << PG_NX_BIT)
+#define PG_NX_MASK       (1LL << PG_NX_BIT)
 
 #define PG_ERROR_W_BIT     1
 
@@ -269,45 +269,48 @@
 #define PG_ERROR_RSVD_MASK 0x08
 #define PG_ERROR_I_D_MASK  0x10
 
-#define MCG_CTL_P	(1ULL<<8)   /* MCG_CAP register available */
-#define MCG_SER_P	(1ULL<<24) /* MCA recovery/new status bits */
+#define MCG_CTL_P       (1ULL<<8)   /* MCG_CAP register available */
+#define MCG_SER_P       (1ULL<<24) /* MCA recovery/new status bits */
 
-#define MCE_CAP_DEF	(MCG_CTL_P|MCG_SER_P)
-#define MCE_BANKS_DEF	10
+#define MCE_CAP_DEF     (MCG_CTL_P|MCG_SER_P)
+#define MCE_BANKS_DEF   10
 
-#define MCG_STATUS_RIPV	(1ULL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV	(1ULL<<1)   /* ip points to correct instruction */
-#define MCG_STATUS_MCIP	(1ULL<<2)   /* machine check in progress */
+#define MCG_STATUS_RIPV (1ULL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV (1ULL<<1)   /* ip points to correct instruction */
+#define MCG_STATUS_MCIP (1ULL<<2)   /* machine check in progress */
 
-#define MCI_STATUS_VAL	(1ULL<<63)  /* valid error */
-#define MCI_STATUS_OVER	(1ULL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC	(1ULL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN	(1ULL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1ULL<<59) /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1ULL<<58) /* addr reg. valid */
-#define MCI_STATUS_PCC	(1ULL<<57)  /* processor context corrupt */
-#define MCI_STATUS_S	(1ULL<<56)  /* Signaled machine check */
-#define MCI_STATUS_AR	(1ULL<<55)  /* Action required */
+#define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1ULL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1ULL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1ULL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1ULL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1ULL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
+#define MCI_STATUS_S     (1ULL<<56)  /* Signaled machine check */
+#define MCI_STATUS_AR    (1ULL<<55)  /* Action required */
 
 /* MISC register defines */
-#define MCM_ADDR_SEGOFF	0	/* segment offset */
-#define MCM_ADDR_LINEAR	1	/* linear address */
-#define MCM_ADDR_PHYS	2	/* physical address */
-#define MCM_ADDR_MEM	3	/* memory address */
-#define MCM_ADDR_GENERIC 7	/* generic */
+#define MCM_ADDR_SEGOFF  0      /* segment offset */
+#define MCM_ADDR_LINEAR  1      /* linear address */
+#define MCM_ADDR_PHYS    2      /* physical address */
+#define MCM_ADDR_MEM     3      /* memory address */
+#define MCM_ADDR_GENERIC 7      /* generic */
 
 #define MSR_IA32_TSC                    0x10
 #define MSR_IA32_APICBASE               0x1b
 #define MSR_IA32_APICBASE_BSP           (1<<8)
 #define MSR_IA32_APICBASE_ENABLE        (1<<11)
 #define MSR_IA32_APICBASE_BASE          (0xfffff<<12)
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
 #define MSR_TSC_ADJUST                  0x0000003b
 #define MSR_IA32_TSCDEADLINE            0x6e0
 
-#define MSR_MTRRcap			0xfe
-#define MSR_MTRRcap_VCNT		8
-#define MSR_MTRRcap_FIXRANGE_SUPPORT	(1 << 8)
-#define MSR_MTRRcap_WC_SUPPORTED	(1 << 10)
+#define MSR_P6_PERFCTR0                 0xc1
+
+#define MSR_MTRRcap                     0xfe
+#define MSR_MTRRcap_VCNT                8
+#define MSR_MTRRcap_FIXRANGE_SUPPORT    (1 << 8)
+#define MSR_MTRRcap_WC_SUPPORTED        (1 << 10)
 
 #define MSR_IA32_SYSENTER_CS            0x174
 #define MSR_IA32_SYSENTER_ESP           0x175
@@ -317,35 +320,45 @@
 #define MSR_MCG_STATUS                  0x17a
 #define MSR_MCG_CTL                     0x17b
 
+#define MSR_P6_EVNTSEL0                 0x186
+
 #define MSR_IA32_PERF_STATUS            0x198
 
-#define MSR_IA32_MISC_ENABLE		0x1a0
+#define MSR_IA32_MISC_ENABLE            0x1a0
 /* Indicates good rep/movs microcode on some processors: */
 #define MSR_IA32_MISC_ENABLE_DEFAULT    1
 
-#define MSR_MTRRphysBase(reg)		(0x200 + 2 * (reg))
-#define MSR_MTRRphysMask(reg)		(0x200 + 2 * (reg) + 1)
-
-#define MSR_MTRRfix64K_00000		0x250
-#define MSR_MTRRfix16K_80000		0x258
-#define MSR_MTRRfix16K_A0000		0x259
-#define MSR_MTRRfix4K_C0000		0x268
-#define MSR_MTRRfix4K_C8000		0x269
-#define MSR_MTRRfix4K_D0000		0x26a
-#define MSR_MTRRfix4K_D8000		0x26b
-#define MSR_MTRRfix4K_E0000		0x26c
-#define MSR_MTRRfix4K_E8000		0x26d
-#define MSR_MTRRfix4K_F0000		0x26e
-#define MSR_MTRRfix4K_F8000		0x26f
+#define MSR_MTRRphysBase(reg)           (0x200 + 2 * (reg))
+#define MSR_MTRRphysMask(reg)           (0x200 + 2 * (reg) + 1)
+
+#define MSR_MTRRfix64K_00000            0x250
+#define MSR_MTRRfix16K_80000            0x258
+#define MSR_MTRRfix16K_A0000            0x259
+#define MSR_MTRRfix4K_C0000             0x268
+#define MSR_MTRRfix4K_C8000             0x269
+#define MSR_MTRRfix4K_D0000             0x26a
+#define MSR_MTRRfix4K_D8000             0x26b
+#define MSR_MTRRfix4K_E0000             0x26c
+#define MSR_MTRRfix4K_E8000             0x26d
+#define MSR_MTRRfix4K_F0000             0x26e
+#define MSR_MTRRfix4K_F8000             0x26f
 
 #define MSR_PAT                         0x277
 
-#define MSR_MTRRdefType			0x2ff
+#define MSR_MTRRdefType                 0x2ff
+
+#define MSR_CORE_PERF_FIXED_CTR0        0x309
+#define MSR_CORE_PERF_FIXED_CTR1        0x30a
+#define MSR_CORE_PERF_FIXED_CTR2        0x30b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL    0x38d
+#define MSR_CORE_PERF_GLOBAL_STATUS     0x38e
+#define MSR_CORE_PERF_GLOBAL_CTRL       0x38f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL   0x390
 
-#define MSR_MC0_CTL			0x400
-#define MSR_MC0_STATUS			0x401
-#define MSR_MC0_ADDR			0x402
-#define MSR_MC0_MISC			0x403
+#define MSR_MC0_CTL                     0x400
+#define MSR_MC0_STATUS                  0x401
+#define MSR_MC0_ADDR                    0x402
+#define MSR_MC0_MISC                    0x403
 
 #define MSR_EFER                        0xc0000080
 
@@ -724,6 +737,9 @@ typedef struct {
 #define CPU_NB_REGS CPU_NB_REGS32
 #endif
 
+#define MAX_FIXED_COUNTERS 3
+#define MAX_GP_COUNTERS    (MSR_IA32_PERF_STATUS - MSR_P6_EVNTSEL0)
+
 #define NB_MMU_MODES 3
 
 typedef enum TPRAccess {
@@ -817,6 +833,15 @@ typedef struct CPUX86State {
 
     uint64_t mcg_status;
     uint64_t msr_ia32_misc_enable;
+    uint64_t msr_ia32_feature_control;
+
+    uint64_t msr_fixed_ctr_ctrl;
+    uint64_t msr_global_ctrl;
+    uint64_t msr_global_status;
+    uint64_t msr_global_ovf_ctrl;
+    uint64_t msr_fixed_counters[MAX_FIXED_COUNTERS];
+    uint64_t msr_gp_counters[MAX_GP_COUNTERS];
+    uint64_t msr_gp_evtsel[MAX_GP_COUNTERS];
 
     /* exception/interrupt handling */
     int error_code;
@@ -1089,7 +1114,7 @@ static inline CPUX86State *cpu_init(const char *cpu_model)
 #define cpu_gen_code cpu_x86_gen_code
 #define cpu_signal_handler cpu_x86_signal_handler
 #define cpu_list x86_cpu_list
-#define cpudef_setup	x86_cpudef_setup
+#define cpudef_setup x86_cpudef_setup
 
 /* MMU modes definitions */
 #define MMU_MODE0_SUFFIX _kernel
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 0b6eb0155c..749aa09a21 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -65,12 +65,16 @@ static bool has_msr_star;
 static bool has_msr_hsave_pa;
 static bool has_msr_tsc_adjust;
 static bool has_msr_tsc_deadline;
+static bool has_msr_feature_control;
 static bool has_msr_async_pf_en;
 static bool has_msr_pv_eoi_en;
 static bool has_msr_misc_enable;
 static bool has_msr_kvm_steal_time;
 static int lm_capable_kernel;
 
+static bool has_msr_architectural_pmu;
+static uint32_t num_architectural_pmu_counters;
+
 bool kvm_allows_irq0_override(void)
 {
     return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing();
@@ -597,6 +601,25 @@ int kvm_arch_init_vcpu(CPUState *cs)
             break;
         }
     }
+
+    if (limit >= 0x0a) {
+        uint32_t ver;
+
+        cpu_x86_cpuid(env, 0x0a, 0, &ver, &unused, &unused, &unused);
+        if ((ver & 0xff) > 0) {
+            has_msr_architectural_pmu = true;
+            num_architectural_pmu_counters = (ver & 0xff00) >> 8;
+
+            /* Shouldn't be more than 32, since that's the number of bits
+             * available in EBX to tell us _which_ counters are available.
+             * Play it safe.
+             */
+            if (num_architectural_pmu_counters > MAX_GP_COUNTERS) {
+                num_architectural_pmu_counters = MAX_GP_COUNTERS;
+            }
+        }
+    }
+
     cpu_x86_cpuid(env, 0x80000000, 0, &limit, &unused, &unused, &unused);
 
     for (i = 0x80000000; i <= limit; i++) {
@@ -660,6 +683,12 @@ int kvm_arch_init_vcpu(CPUState *cs)
 
     qemu_add_vm_change_state_handler(cpu_update_state, env);
 
+    c = cpuid_find_entry(&cpuid_data.cpuid, 1, 0);
+    if (c) {
+        has_msr_feature_control = !!(c->ecx & CPUID_EXT_VMX) ||
+                                  !!(c->ecx & CPUID_EXT_SMX);
+    }
+
     cpuid_data.cpuid.padding = 0;
     r = kvm_vcpu_ioctl(cs, KVM_SET_CPUID2, &cpuid_data);
     if (r) {
@@ -1060,6 +1089,26 @@ static void kvm_msr_entry_set(struct kvm_msr_entry *entry,
     entry->data = value;
 }
 
+static int kvm_put_tscdeadline_msr(X86CPU *cpu)
+{
+    CPUX86State *env = &cpu->env;
+    struct {
+        struct kvm_msrs info;
+        struct kvm_msr_entry entries[1];
+    } msr_data;
+    struct kvm_msr_entry *msrs = msr_data.entries;
+
+    if (!has_msr_tsc_deadline) {
+        return 0;
+    }
+
+    kvm_msr_entry_set(&msrs[0], MSR_IA32_TSCDEADLINE, env->tsc_deadline);
+
+    msr_data.info.nmsrs = 1;
+
+    return kvm_vcpu_ioctl(CPU(cpu), KVM_SET_MSRS, &msr_data);
+}
+
 static int kvm_put_msrs(X86CPU *cpu, int level)
 {
     CPUX86State *env = &cpu->env;
@@ -1068,7 +1117,7 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
         struct kvm_msr_entry entries[100];
     } msr_data;
     struct kvm_msr_entry *msrs = msr_data.entries;
-    int n = 0;
+    int n = 0, i;
 
     kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);
     kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);
@@ -1083,9 +1132,6 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
     if (has_msr_tsc_adjust) {
         kvm_msr_entry_set(&msrs[n++], MSR_TSC_ADJUST, env->tsc_adjust);
     }
-    if (has_msr_tsc_deadline) {
-        kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSCDEADLINE, env->tsc_deadline);
-    }
     if (has_msr_misc_enable) {
         kvm_msr_entry_set(&msrs[n++], MSR_IA32_MISC_ENABLE,
                           env->msr_ia32_misc_enable);
@@ -1110,9 +1156,8 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
         }
     }
     /*
-     * The following paravirtual MSRs have side effects on the guest or are
-     * too heavy for normal writeback. Limit them to reset or full state
-     * updates.
+     * The following MSRs have side effects on the guest or are too heavy
+     * for normal writeback. Limit them to reset or full state updates.
      */
     if (level >= KVM_PUT_RESET_STATE) {
         kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME,
@@ -1130,6 +1175,33 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
             kvm_msr_entry_set(&msrs[n++], MSR_KVM_STEAL_TIME,
                               env->steal_time_msr);
         }
+        if (has_msr_architectural_pmu) {
+            /* Stop the counter.  */
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_GLOBAL_CTRL, 0);
+
+            /* Set the counter values.  */
+            for (i = 0; i < MAX_FIXED_COUNTERS; i++) {
+                kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_FIXED_CTR0 + i,
+                                  env->msr_fixed_counters[i]);
+            }
+            for (i = 0; i < num_architectural_pmu_counters; i++) {
+                kvm_msr_entry_set(&msrs[n++], MSR_P6_PERFCTR0 + i,
+                                  env->msr_gp_counters[i]);
+                kvm_msr_entry_set(&msrs[n++], MSR_P6_EVNTSEL0 + i,
+                                  env->msr_gp_evtsel[i]);
+            }
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_GLOBAL_STATUS,
+                              env->msr_global_status);
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_GLOBAL_OVF_CTRL,
+                              env->msr_global_ovf_ctrl);
+
+            /* Now start the PMU.  */
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_FIXED_CTR_CTRL,
+                              env->msr_fixed_ctr_ctrl);
+            kvm_msr_entry_set(&msrs[n++], MSR_CORE_PERF_GLOBAL_CTRL,
+                              env->msr_global_ctrl);
+        }
         if (hyperv_hypercall_available(cpu)) {
             kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_GUEST_OS_ID, 0);
             kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_HYPERCALL, 0);
@@ -1137,6 +1209,10 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
         if (cpu->hyperv_vapic) {
             kvm_msr_entry_set(&msrs[n++], HV_X64_MSR_APIC_ASSIST_PAGE, 0);
         }
+        if (has_msr_feature_control) {
+            kvm_msr_entry_set(&msrs[n++], MSR_IA32_FEATURE_CONTROL,
+                              env->msr_ia32_feature_control);
+        }
     }
     if (env->mcg_cap) {
         int i;
@@ -1361,6 +1437,9 @@ static int kvm_get_msrs(X86CPU *cpu)
     if (has_msr_misc_enable) {
         msrs[n++].index = MSR_IA32_MISC_ENABLE;
     }
+    if (has_msr_feature_control) {
+        msrs[n++].index = MSR_IA32_FEATURE_CONTROL;
+    }
 
     if (!env->tsc_valid) {
         msrs[n++].index = MSR_IA32_TSC;
@@ -1386,6 +1465,19 @@ static int kvm_get_msrs(X86CPU *cpu)
     if (has_msr_kvm_steal_time) {
         msrs[n++].index = MSR_KVM_STEAL_TIME;
     }
+    if (has_msr_architectural_pmu) {
+        msrs[n++].index = MSR_CORE_PERF_FIXED_CTR_CTRL;
+        msrs[n++].index = MSR_CORE_PERF_GLOBAL_CTRL;
+        msrs[n++].index = MSR_CORE_PERF_GLOBAL_STATUS;
+        msrs[n++].index = MSR_CORE_PERF_GLOBAL_OVF_CTRL;
+        for (i = 0; i < MAX_FIXED_COUNTERS; i++) {
+            msrs[n++].index = MSR_CORE_PERF_FIXED_CTR0 + i;
+        }
+        for (i = 0; i < num_architectural_pmu_counters; i++) {
+            msrs[n++].index = MSR_P6_PERFCTR0 + i;
+            msrs[n++].index = MSR_P6_EVNTSEL0 + i;
+        }
+    }
 
     if (env->mcg_cap) {
         msrs[n++].index = MSR_MCG_STATUS;
@@ -1402,7 +1494,8 @@ static int kvm_get_msrs(X86CPU *cpu)
     }
 
     for (i = 0; i < ret; i++) {
-        switch (msrs[i].index) {
+        uint32_t index = msrs[i].index;
+        switch (index) {
         case MSR_IA32_SYSENTER_CS:
             env->sysenter_cs = msrs[i].data;
             break;
@@ -1459,6 +1552,9 @@ static int kvm_get_msrs(X86CPU *cpu)
         case MSR_IA32_MISC_ENABLE:
             env->msr_ia32_misc_enable = msrs[i].data;
             break;
+        case MSR_IA32_FEATURE_CONTROL:
+            env->msr_ia32_feature_control = msrs[i].data;
+            break;
         default:
             if (msrs[i].index >= MSR_MC0_CTL &&
                 msrs[i].index < MSR_MC0_CTL + (env->mcg_cap & 0xff) * 4) {
@@ -1474,6 +1570,27 @@ static int kvm_get_msrs(X86CPU *cpu)
         case MSR_KVM_STEAL_TIME:
             env->steal_time_msr = msrs[i].data;
             break;
+        case MSR_CORE_PERF_FIXED_CTR_CTRL:
+            env->msr_fixed_ctr_ctrl = msrs[i].data;
+            break;
+        case MSR_CORE_PERF_GLOBAL_CTRL:
+            env->msr_global_ctrl = msrs[i].data;
+            break;
+        case MSR_CORE_PERF_GLOBAL_STATUS:
+            env->msr_global_status = msrs[i].data;
+            break;
+        case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
+            env->msr_global_ovf_ctrl = msrs[i].data;
+            break;
+        case MSR_CORE_PERF_FIXED_CTR0 ... MSR_CORE_PERF_FIXED_CTR0 + MAX_FIXED_COUNTERS - 1:
+            env->msr_fixed_counters[index - MSR_CORE_PERF_FIXED_CTR0] = msrs[i].data;
+            break;
+        case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR0 + MAX_GP_COUNTERS - 1:
+            env->msr_gp_counters[index - MSR_P6_PERFCTR0] = msrs[i].data;
+            break;
+        case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL0 + MAX_GP_COUNTERS - 1:
+            env->msr_gp_evtsel[index - MSR_P6_EVNTSEL0] = msrs[i].data;
+            break;
         }
     }
 
@@ -1724,6 +1841,12 @@ int kvm_arch_put_registers(CPUState *cpu, int level)
             return ret;
         }
     }
+
+    ret = kvm_put_tscdeadline_msr(x86_cpu);
+    if (ret < 0) {
+        return ret;
+    }
+
     ret = kvm_put_vcpu_events(x86_cpu, level);
     if (ret < 0) {
         return ret;
diff --git a/target-i386/machine.c b/target-i386/machine.c
index f9ec581faa..dc81cde535 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -435,6 +435,14 @@ static bool misc_enable_needed(void *opaque)
     return env->msr_ia32_misc_enable != MSR_IA32_MISC_ENABLE_DEFAULT;
 }
 
+static bool feature_control_needed(void *opaque)
+{
+    X86CPU *cpu = opaque;
+    CPUX86State *env = &cpu->env;
+
+    return env->msr_ia32_feature_control != 0;
+}
+
 static const VMStateDescription vmstate_msr_ia32_misc_enable = {
     .name = "cpu/msr_ia32_misc_enable",
     .version_id = 1,
@@ -446,6 +454,58 @@ static const VMStateDescription vmstate_msr_ia32_misc_enable = {
     }
 };
 
+static const VMStateDescription vmstate_msr_ia32_feature_control = {
+    .name = "cpu/msr_ia32_feature_control",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT64(env.msr_ia32_feature_control, X86CPU),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool pmu_enable_needed(void *opaque)
+{
+    X86CPU *cpu = opaque;
+    CPUX86State *env = &cpu->env;
+    int i;
+
+    if (env->msr_fixed_ctr_ctrl || env->msr_global_ctrl ||
+        env->msr_global_status || env->msr_global_ovf_ctrl) {
+        return true;
+    }
+    for (i = 0; i < MAX_FIXED_COUNTERS; i++) {
+        if (env->msr_fixed_counters[i]) {
+            return true;
+        }
+    }
+    for (i = 0; i < MAX_GP_COUNTERS; i++) {
+        if (env->msr_gp_counters[i] || env->msr_gp_evtsel[i]) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+static const VMStateDescription vmstate_msr_architectural_pmu = {
+    .name = "cpu/msr_architectural_pmu",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .fields      = (VMStateField []) {
+        VMSTATE_UINT64(env.msr_fixed_ctr_ctrl, X86CPU),
+        VMSTATE_UINT64(env.msr_global_ctrl, X86CPU),
+        VMSTATE_UINT64(env.msr_global_status, X86CPU),
+        VMSTATE_UINT64(env.msr_global_ovf_ctrl, X86CPU),
+        VMSTATE_UINT64_ARRAY(env.msr_fixed_counters, X86CPU, MAX_FIXED_COUNTERS),
+        VMSTATE_UINT64_ARRAY(env.msr_gp_counters, X86CPU, MAX_GP_COUNTERS),
+        VMSTATE_UINT64_ARRAY(env.msr_gp_evtsel, X86CPU, MAX_GP_COUNTERS),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 const VMStateDescription vmstate_x86_cpu = {
     .name = "cpu",
     .version_id = 12,
@@ -571,6 +631,12 @@ const VMStateDescription vmstate_x86_cpu = {
         }, {
             .vmsd = &vmstate_msr_ia32_misc_enable,
             .needed = misc_enable_needed,
+        }, {
+            .vmsd = &vmstate_msr_ia32_feature_control,
+            .needed = feature_control_needed,
+        }, {
+            .vmsd = &vmstate_msr_architectural_pmu,
+            .needed = pmu_enable_needed,
         } , {
             /* empty */
         }