Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging

* iothread bugfix (Eduardo)
* Linux headers sync (Dave)
* .gitignore fix (Eric)
* KVM capability check fixes (Greg)
* kvmclock fix (Jim)

# gpg: Signature made Mon 02 Oct 2017 14:31:09 BST
# gpg:                using RSA key 0xBFFBD25F78C7AE83
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>"
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>"
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* remotes/bonzini/tags/for-upstream:
  kvmclock: use the updated system_timer_msr
  kvm: check KVM_CAP_NR_VCPUS with kvm_vm_check_extension()
  kvm: check KVM_CAP_SYNC_MMU with kvm_vm_check_extension()
  linux-headers: sync against v4.14-rc1
  iothread: Make iothread_stop() idempotent
  scsi: Ignore executable for in-tree builds
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

.gitignore

@@ -49,6 +49,7 @@
 /qemu-version.h
 /qemu-version.h.tmp
 /module_block.h
+/scsi/qemu-pr-helper
 /vscclient
 /vhost-user-scsi
 /fsdev/virtfs-proxy-helper

accel/kvm/kvm-all.c

@@ -87,6 +87,7 @@ struct KVMState
 #endif
     int many_ioeventfds;
     int intx_set_mask;
+    bool sync_mmu;
     /* The man page (and posix) say ioctl numbers are signed int, but
      * they're not.  Linux, glibc and *BSD all treat ioctl numbers as
      * unsigned, and treating them as signed here can break things */
@@ -1439,7 +1440,7 @@ static void kvm_irqchip_create(MachineState *machine, KVMState *s)
  */
 static int kvm_recommended_vcpus(KVMState *s)
 {
-    int ret = kvm_check_extension(s, KVM_CAP_NR_VCPUS);
+    int ret = kvm_vm_check_extension(s, KVM_CAP_NR_VCPUS);
     return (ret) ? ret : 4;
 }
 
@@ -1529,26 +1530,6 @@ static int kvm_init(MachineState *ms)
         s->nr_slots = 32;
     }
 
-    /* check the vcpu limits */
-    soft_vcpus_limit = kvm_recommended_vcpus(s);
-    hard_vcpus_limit = kvm_max_vcpus(s);
-
-    while (nc->name) {
-        if (nc->num > soft_vcpus_limit) {
-            warn_report("Number of %s cpus requested (%d) exceeds "
-                        "the recommended cpus supported by KVM (%d)",
-                        nc->name, nc->num, soft_vcpus_limit);
-
-            if (nc->num > hard_vcpus_limit) {
-                fprintf(stderr, "Number of %s cpus requested (%d) exceeds "
-                        "the maximum cpus supported by KVM (%d)\n",
-                        nc->name, nc->num, hard_vcpus_limit);
-                exit(1);
-            }
-        }
-        nc++;
-    }
-
     kvm_type = qemu_opt_get(qemu_get_machine_opts(), "kvm-type");
     if (mc->kvm_type) {
         type = mc->kvm_type(kvm_type);
@@ -1583,6 +1564,27 @@ static int kvm_init(MachineState *ms)
     }
 
     s->vmfd = ret;
+
+    /* check the vcpu limits */
+    soft_vcpus_limit = kvm_recommended_vcpus(s);
+    hard_vcpus_limit = kvm_max_vcpus(s);
+
+    while (nc->name) {
+        if (nc->num > soft_vcpus_limit) {
+            warn_report("Number of %s cpus requested (%d) exceeds "
+                        "the recommended cpus supported by KVM (%d)",
+                        nc->name, nc->num, soft_vcpus_limit);
+
+            if (nc->num > hard_vcpus_limit) {
+                fprintf(stderr, "Number of %s cpus requested (%d) exceeds "
+                        "the maximum cpus supported by KVM (%d)\n",
+                        nc->name, nc->num, hard_vcpus_limit);
+                exit(1);
+            }
+        }
+        nc++;
+    }
+
     missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
     if (!missing_cap) {
         missing_cap =
@@ -1664,6 +1666,8 @@ static int kvm_init(MachineState *ms)
 
     s->many_ioeventfds = kvm_check_many_ioeventfds();
 
+    s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
+
     return 0;
 
 err:
@@ -2130,10 +2134,9 @@ int kvm_device_access(int fd, int group, uint64_t attr,
     return err;
 }
 
-/* Return 1 on success, 0 on failure */
-int kvm_has_sync_mmu(void)
+bool kvm_has_sync_mmu(void)
 {
-    return kvm_check_extension(kvm_state, KVM_CAP_SYNC_MMU);
+    return kvm_state->sync_mmu;
 }
 
 int kvm_has_vcpu_events(void)

accel/stubs/kvm-stub.c

@@ -64,9 +64,9 @@ int kvm_cpu_exec(CPUState *cpu)
     abort();
 }
 
-int kvm_has_sync_mmu(void)
+bool kvm_has_sync_mmu(void)
 {
-    return 0;
+    return false;
 }
 
 int kvm_has_many_ioeventfds(void)

hw/i386/kvm/clock.c

@@ -62,7 +62,7 @@ static uint64_t kvmclock_current_nsec(KVMClockState *s)
 {
     CPUState *cpu = first_cpu;
     CPUX86State *env = cpu->env_ptr;
-    hwaddr kvmclock_struct_pa = env->system_time_msr & ~1ULL;
+    hwaddr kvmclock_struct_pa;
     uint64_t migration_tsc = env->tsc;
     struct pvclock_vcpu_time_info time;
     uint64_t delta;
@@ -77,6 +77,7 @@ static uint64_t kvmclock_current_nsec(KVMClockState *s)
         return 0;
     }
 
+    kvmclock_struct_pa = env->system_time_msr & ~1ULL;
     cpu_physical_memory_read(kvmclock_struct_pa, &time, sizeof(time));
 
     assert(time.tsc_timestamp <= migration_tsc);

include/standard-headers/asm-x86/hyperv.h

@@ -149,12 +149,9 @@
  */
 #define HV_X64_DEPRECATING_AEOI_RECOMMENDED	(1 << 9)
 
-/*
- * HV_VP_SET available
- */
+/* Recommend using the newer ExProcessorMasks interface */
 #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED	(1 << 11)
 
-
 /*
  * Crash notification flag.
  */
@@ -242,7 +239,11 @@
 		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
 
 /* Declare the various hypercall operations. */
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
 #define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX  0x0013
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX   0x0014
 #define HVCALL_POST_MESSAGE			0x005c
 #define HVCALL_SIGNAL_EVENT			0x005d
 
@@ -259,6 +260,16 @@
 #define HV_PROCESSOR_POWER_STATE_C2		2
 #define HV_PROCESSOR_POWER_STATE_C3		3
 
+#define HV_FLUSH_ALL_PROCESSORS			BIT(0)
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	BIT(1)
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	BIT(2)
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
+
+enum HV_GENERIC_SET_FORMAT {
+	HV_GENERIC_SET_SPARCE_4K,
+	HV_GENERIC_SET_ALL,
+};
+
 /* hypercall status code */
 #define HV_STATUS_SUCCESS			0
 #define HV_STATUS_INVALID_HYPERCALL_CODE	2

include/standard-headers/linux/pci_regs.h

@@ -513,6 +513,7 @@
 #define  PCI_EXP_DEVSTA_URD	0x0008	/* Unsupported Request Detected */
 #define  PCI_EXP_DEVSTA_AUXPD	0x0010	/* AUX Power Detected */
 #define  PCI_EXP_DEVSTA_TRPND	0x0020	/* Transactions Pending */
+#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V1	12	/* v1 endpoints without link end here */
 #define PCI_EXP_LNKCAP		12	/* Link Capabilities */
 #define  PCI_EXP_LNKCAP_SLS	0x0000000f /* Supported Link Speeds */
 #define  PCI_EXP_LNKCAP_SLS_2_5GB 0x00000001 /* LNKCAP2 SLS Vector bit 0 */
@@ -556,7 +557,7 @@
 #define  PCI_EXP_LNKSTA_DLLLA	0x2000	/* Data Link Layer Link Active */
 #define  PCI_EXP_LNKSTA_LBMS	0x4000	/* Link Bandwidth Management Status */
 #define  PCI_EXP_LNKSTA_LABS	0x8000	/* Link Autonomous Bandwidth Status */
-#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1	20	/* v1 endpoints end here */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1	20	/* v1 endpoints with link end here */
 #define PCI_EXP_SLTCAP		20	/* Slot Capabilities */
 #define  PCI_EXP_SLTCAP_ABP	0x00000001 /* Attention Button Present */
 #define  PCI_EXP_SLTCAP_PCP	0x00000002 /* Power Controller Present */
@@ -639,7 +640,7 @@
 #define  PCI_EXP_DEVCTL2_OBFF_MSGB_EN	0x4000	/* Enable OBFF Message type B */
 #define  PCI_EXP_DEVCTL2_OBFF_WAKE_EN	0x6000	/* OBFF using WAKE# signaling */
 #define PCI_EXP_DEVSTA2		42	/* Device Status 2 */
-#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	44	/* v2 endpoints end here */
+#define PCI_CAP_EXP_RC_ENDPOINT_SIZEOF_V2	44	/* v2 endpoints without link end here */
 #define PCI_EXP_LNKCAP2		44	/* Link Capabilities 2 */
 #define  PCI_EXP_LNKCAP2_SLS_2_5GB	0x00000002 /* Supported Speed 2.5GT/s */
 #define  PCI_EXP_LNKCAP2_SLS_5_0GB	0x00000004 /* Supported Speed 5.0GT/s */
@@ -647,6 +648,7 @@
 #define  PCI_EXP_LNKCAP2_CROSSLINK	0x00000100 /* Crosslink supported */
 #define PCI_EXP_LNKCTL2		48	/* Link Control 2 */
 #define PCI_EXP_LNKSTA2		50	/* Link Status 2 */
+#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2	52	/* v2 endpoints with link end here */
 #define PCI_EXP_SLTCAP2		52	/* Slot Capabilities 2 */
 #define PCI_EXP_SLTCTL2		56	/* Slot Control 2 */
 #define PCI_EXP_SLTSTA2		58	/* Slot Status 2 */
@@ -733,23 +735,17 @@
 #define  PCI_ERR_CAP_ECRC_CHKE	0x00000100	/* ECRC Check Enable */
 #define PCI_ERR_HEADER_LOG	28	/* Header Log Register (16 bytes) */
 #define PCI_ERR_ROOT_COMMAND	44	/* Root Error Command */
-/* Correctable Err Reporting Enable */
-#define PCI_ERR_ROOT_CMD_COR_EN		0x00000001
-/* Non-fatal Err Reporting Enable */
-#define PCI_ERR_ROOT_CMD_NONFATAL_EN	0x00000002
-/* Fatal Err Reporting Enable */
-#define PCI_ERR_ROOT_CMD_FATAL_EN	0x00000004
+#define PCI_ERR_ROOT_CMD_COR_EN		0x00000001 /* Correctable Err Reporting Enable */
+#define PCI_ERR_ROOT_CMD_NONFATAL_EN	0x00000002 /* Non-Fatal Err Reporting Enable */
+#define PCI_ERR_ROOT_CMD_FATAL_EN	0x00000004 /* Fatal Err Reporting Enable */
 #define PCI_ERR_ROOT_STATUS	48
-#define PCI_ERR_ROOT_COR_RCV		0x00000001	/* ERR_COR Received */
-/* Multi ERR_COR Received */
-#define PCI_ERR_ROOT_MULTI_COR_RCV	0x00000002
-/* ERR_FATAL/NONFATAL Received */
-#define PCI_ERR_ROOT_UNCOR_RCV		0x00000004
-/* Multi ERR_FATAL/NONFATAL Received */
-#define PCI_ERR_ROOT_MULTI_UNCOR_RCV	0x00000008
-#define PCI_ERR_ROOT_FIRST_FATAL	0x00000010	/* First Fatal */
-#define PCI_ERR_ROOT_NONFATAL_RCV	0x00000020	/* Non-Fatal Received */
-#define PCI_ERR_ROOT_FATAL_RCV		0x00000040	/* Fatal Received */
+#define PCI_ERR_ROOT_COR_RCV		0x00000001 /* ERR_COR Received */
+#define PCI_ERR_ROOT_MULTI_COR_RCV	0x00000002 /* Multiple ERR_COR */
+#define PCI_ERR_ROOT_UNCOR_RCV		0x00000004 /* ERR_FATAL/NONFATAL */
+#define PCI_ERR_ROOT_MULTI_UNCOR_RCV	0x00000008 /* Multiple FATAL/NONFATAL */
+#define PCI_ERR_ROOT_FIRST_FATAL	0x00000010 /* First UNC is Fatal */
+#define PCI_ERR_ROOT_NONFATAL_RCV	0x00000020 /* Non-Fatal Received */
+#define PCI_ERR_ROOT_FATAL_RCV		0x00000040 /* Fatal Received */
 #define PCI_ERR_ROOT_ERR_SRC	52	/* Error Source Identification */
 
 /* Virtual Channel */
@@ -967,6 +963,7 @@
 #define  PCI_EXP_DPC_CAP_RP_EXT		0x20	/* Root Port Extensions for DPC */
 #define  PCI_EXP_DPC_CAP_POISONED_TLP	0x40	/* Poisoned TLP Egress Blocking Supported */
 #define  PCI_EXP_DPC_CAP_SW_TRIGGER	0x80	/* Software Triggering Supported */
+#define  PCI_EXP_DPC_RP_PIO_LOG_SIZE	0xF00	/* RP PIO log size */
 #define  PCI_EXP_DPC_CAP_DL_ACTIVE	0x1000	/* ERR_COR signal on DL_Active supported */
 
 #define PCI_EXP_DPC_CTL			6	/* DPC control */
@@ -980,6 +977,15 @@
 
 #define PCI_EXP_DPC_SOURCE_ID		10	/* DPC Source Identifier */
 
+#define PCI_EXP_DPC_RP_PIO_STATUS	 0x0C	/* RP PIO Status */
+#define PCI_EXP_DPC_RP_PIO_MASK		 0x10	/* RP PIO MASK */
+#define PCI_EXP_DPC_RP_PIO_SEVERITY	 0x14	/* RP PIO Severity */
+#define PCI_EXP_DPC_RP_PIO_SYSERROR	 0x18	/* RP PIO SysError */
+#define PCI_EXP_DPC_RP_PIO_EXCEPTION	 0x1C	/* RP PIO Exception */
+#define PCI_EXP_DPC_RP_PIO_HEADER_LOG	 0x20	/* RP PIO Header Log */
+#define PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG	 0x30	/* RP PIO ImpSpec Log */
+#define PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG 0x34	/* RP PIO TLP Prefix Log */
+
 /* Precision Time Measurement */
 #define PCI_PTM_CAP			0x04	    /* PTM Capability */
 #define  PCI_PTM_CAP_REQ		0x00000001  /* Requester capable */

include/standard-headers/linux/virtio_ring.h

 #ifndef _LINUX_VIRTIO_RING_H
 #define _LINUX_VIRTIO_RING_H
-/* An interface for efficient virtio implementation, currently for use by KVM
- * and lguest, but hopefully others soon.  Do NOT change this since it will
+/* An interface for efficient virtio implementation, currently for use by KVM,
+ * but hopefully others soon.  Do NOT change this since it will
  * break existing servers and clients.
  *
  * This header is BSD licensed so anyone can use the definitions to implement

include/sysemu/kvm.h

@@ -207,7 +207,7 @@ extern KVMState *kvm_state;
 /* external API */
 
 bool kvm_has_free_slot(MachineState *ms);
-int kvm_has_sync_mmu(void);
+bool kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_has_robust_singlestep(void);
 int kvm_has_debugregs(void);

iothread.c

@@ -85,7 +85,7 @@ static int iothread_stop(Object *object, void *opaque)
     IOThread *iothread;
 
     iothread = (IOThread *)object_dynamic_cast(object, TYPE_IOTHREAD);
-    if (!iothread || !iothread->ctx) {
+    if (!iothread || !iothread->ctx || iothread->stopping) {
         return 0;
     }
     iothread->stopping = true;

linux-headers/asm-s390/kvm.h

@@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
+#define KVM_S390_VM_TOD_EXT		2
+
+struct kvm_s390_vm_tod_clock {
+	__u8  epoch_idx;
+	__u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */

linux-headers/linux/kvm.h

@@ -711,7 +711,8 @@ struct kvm_ppc_one_seg_page_size {
 struct kvm_ppc_smmu_info {
 	__u64 flags;
 	__u32 slb_size;
-	__u32 pad;
+	__u16 data_keys;	/* # storage keys supported for data */
+	__u16 instr_keys;	/* # storage keys supported for instructions */
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 

linux-headers/linux/userfaultfd.h

@@ -23,7 +23,9 @@
 			   UFFD_FEATURE_EVENT_REMOVE |	\
 			   UFFD_FEATURE_EVENT_UNMAP |		\
 			   UFFD_FEATURE_MISSING_HUGETLBFS |	\
-			   UFFD_FEATURE_MISSING_SHMEM)
+			   UFFD_FEATURE_MISSING_SHMEM |		\
+			   UFFD_FEATURE_SIGBUS |		\
+			   UFFD_FEATURE_THREAD_ID)
 #define UFFD_API_IOCTLS				\
 	((__u64)1 << _UFFDIO_REGISTER |		\
 	 (__u64)1 << _UFFDIO_UNREGISTER |	\
@@ -78,6 +80,9 @@ struct uffd_msg {
 		struct {
 			__u64	flags;
 			__u64	address;
+			union {
+				__u32 ptid;
+			} feat;
 		} pagefault;
 
 		struct {
@@ -153,6 +158,13 @@ struct uffdio_api {
 	 * UFFD_FEATURE_MISSING_SHMEM works the same as
 	 * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem
 	 * (i.e. tmpfs and other shmem based APIs).
+	 *
+	 * UFFD_FEATURE_SIGBUS feature means no page-fault
+	 * (UFFD_EVENT_PAGEFAULT) event will be delivered, instead
+	 * a SIGBUS signal will be sent to the faulting process.
+	 *
+	 * UFFD_FEATURE_THREAD_ID pid of the page faulted task_struct will
+	 * be returned, if feature is not requested 0 will be returned.
 	 */
 #define UFFD_FEATURE_PAGEFAULT_FLAG_WP		(1<<0)
 #define UFFD_FEATURE_EVENT_FORK			(1<<1)
@@ -161,6 +173,8 @@ struct uffdio_api {
 #define UFFD_FEATURE_MISSING_HUGETLBFS		(1<<4)
 #define UFFD_FEATURE_MISSING_SHMEM		(1<<5)
 #define UFFD_FEATURE_EVENT_UNMAP		(1<<6)
+#define UFFD_FEATURE_SIGBUS			(1<<7)
+#define UFFD_FEATURE_THREAD_ID			(1<<8)
 	__u64 features;
 
 	__u64 ioctls;