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

* RTC fixes (Artem)
* icount fixes (Artem)
* rr fixes (Pavel, myself)
* hotplug cleanup (Igor)
* SCSI fixes (myself)
* 4.20-rc1 KVM header update (myself)
* coalesced PIO support (Peng Hao)
* HVF fixes (Roman B.)
* Hyper-V refactoring (Roman K.)
* Support for Hyper-V IPI (Vitaly)

# gpg: Signature made Fri 19 Oct 2018 12:47:58 BST
# gpg:                using RSA key BFFBD25F78C7AE83
# 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: (47 commits)
  replay: pass raw icount value to replay_save_clock
  target/i386: kvm: just return after migrate_add_blocker failed
  hyperv_testdev: add SynIC message and event testmodes
  hyperv: process POST_MESSAGE hypercall
  hyperv: add support for KVM_HYPERV_EVENTFD
  hyperv: process SIGNAL_EVENT hypercall
  hyperv: add synic event flag signaling
  hyperv: add synic message delivery
  hyperv: make overlay pages for SynIC
  hyperv: only add SynIC in compatible configurations
  hyperv: qom-ify SynIC
  hyperv:synic: split capability testing and setting
  i386: add hyperv-stub for CONFIG_HYPERV=n
  default-configs: collect CONFIG_HYPERV* in hyperv.mak
  hyperv: factor out arch-independent API into hw/hyperv
  hyperv: make hyperv_vp_index inline
  hyperv: split hyperv-proto.h into x86 and arch-independent parts
  hyperv: rename kvm_hv_sint_route_set_sint
  hyperv: make HvSintRoute reference-counted
  hyperv: address HvSintRoute by X86CPU pointer
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

12 files changed, 222 insertions, 281 deletions

diff --git a/target/i386/Makefile.objs b/target/i386/Makefile.objs
index 04678f5503..32bf966300 100644
--- a/target/i386/Makefile.objs
+++ b/target/i386/Makefile.objs
@@ -3,17 +3,20 @@ obj-$(CONFIG_TCG) += translate.o
 obj-$(CONFIG_TCG) += bpt_helper.o cc_helper.o excp_helper.o fpu_helper.o
 obj-$(CONFIG_TCG) += int_helper.o mem_helper.o misc_helper.o mpx_helper.o
 obj-$(CONFIG_TCG) += seg_helper.o smm_helper.o svm_helper.o
-obj-$(CONFIG_SOFTMMU) += machine.o arch_memory_mapping.o arch_dump.o monitor.o
-obj-$(CONFIG_KVM) += kvm.o hyperv.o
-obj-$(CONFIG_SEV) += sev.o
+ifeq ($(CONFIG_SOFTMMU),y)
+obj-y += machine.o arch_memory_mapping.o arch_dump.o monitor.o
+obj-$(CONFIG_KVM) += kvm.o
 obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
-obj-$(call lnot,$(CONFIG_SEV)) += sev-stub.o
-# HAX support
-ifdef CONFIG_WIN32
+obj-$(CONFIG_HYPERV) += hyperv.o
+obj-$(call lnot,$(CONFIG_HYPERV)) += hyperv-stub.o
+ifeq ($(CONFIG_WIN32),y)
 obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-windows.o
 endif
-ifdef CONFIG_DARWIN
+ifeq ($(CONFIG_DARWIN),y)
 obj-$(CONFIG_HAX) += hax-all.o hax-mem.o hax-darwin.o
 obj-$(CONFIG_HVF) += hvf/
 endif
 obj-$(CONFIG_WHPX) += whpx-all.o
+endif
+obj-$(CONFIG_SEV) += sev.o
+obj-$(call lnot,$(CONFIG_SEV)) += sev-stub.o
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index c88876dfe3..f0d9f7cf49 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5564,6 +5564,7 @@ static Property x86_cpu_properties[] = {
     DEFINE_PROP_BOOL("hv-frequencies", X86CPU, hyperv_frequencies, false),
     DEFINE_PROP_BOOL("hv-reenlightenment", X86CPU, hyperv_reenlightenment, false),
     DEFINE_PROP_BOOL("hv-tlbflush", X86CPU, hyperv_tlbflush, false),
+    DEFINE_PROP_BOOL("hv-ipi", X86CPU, hyperv_ipi, false),
     DEFINE_PROP_BOOL("check", X86CPU, check_cpuid, true),
     DEFINE_PROP_BOOL("enforce", X86CPU, enforce_cpuid, false),
     DEFINE_PROP_BOOL("kvm", X86CPU, expose_kvm, true),
@@ -5606,6 +5607,8 @@ static Property x86_cpu_properties[] = {
      * to the specific Windows version being used."
      */
     DEFINE_PROP_INT32("x-hv-max-vps", X86CPU, hv_max_vps, -1),
+    DEFINE_PROP_BOOL("x-hv-synic-kvm-only", X86CPU, hyperv_synic_kvm_only,
+                     false),
     DEFINE_PROP_END_OF_LIST()
 };
 
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 730c06f80a..663f3a5e67 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1378,10 +1378,12 @@ struct X86CPU {
     bool hyperv_vpindex;
     bool hyperv_runtime;
     bool hyperv_synic;
+    bool hyperv_synic_kvm_only;
     bool hyperv_stimer;
     bool hyperv_frequencies;
     bool hyperv_reenlightenment;
     bool hyperv_tlbflush;
+    bool hyperv_ipi;
     bool check_cpuid;
     bool enforce_cpuid;
     bool expose_kvm;
diff --git a/target/i386/hvf/hvf.c b/target/i386/hvf/hvf.c
index 9f52bc413a..e193022c03 100644
--- a/target/i386/hvf/hvf.c
+++ b/target/i386/hvf/hvf.c
@@ -73,7 +73,6 @@
 #include "target/i386/cpu.h"
 
 HVFState *hvf_state;
-int hvf_disabled = 1;
 
 static void assert_hvf_ok(hv_return_t ret)
 {
@@ -604,11 +603,6 @@ int hvf_init_vcpu(CPUState *cpu)
     return 0;
 }
 
-void hvf_disable(int shouldDisable)
-{
-    hvf_disabled = shouldDisable;
-}
-
 static void hvf_store_events(CPUState *cpu, uint32_t ins_len, uint64_t idtvec_info)
 {
     X86CPU *x86_cpu = X86_CPU(cpu);
@@ -934,7 +928,7 @@ int hvf_vcpu_exec(CPUState *cpu)
     return ret;
 }
 
-static bool hvf_allowed;
+bool hvf_allowed;
 
 static int hvf_accel_init(MachineState *ms)
 {
@@ -942,7 +936,6 @@ static int hvf_accel_init(MachineState *ms)
     hv_return_t ret;
     HVFState *s;
 
-    hvf_disable(0);
     ret = hv_vm_create(HV_VM_DEFAULT);
     assert_hvf_ok(ret);
 
diff --git a/target/i386/hvf/x86_decode.c b/target/i386/hvf/x86_decode.c
index 2d7540fe7c..2e33b69541 100644
--- a/target/i386/hvf/x86_decode.c
+++ b/target/i386/hvf/x86_decode.c
@@ -113,7 +113,8 @@ static void decode_modrm_reg(CPUX86State *env, struct x86_decode *decode,
 {
     op->type = X86_VAR_REG;
     op->reg = decode->modrm.reg;
-    op->ptr = get_reg_ref(env, op->reg, decode->rex.r, decode->operand_size);
+    op->ptr = get_reg_ref(env, op->reg, decode->rex.rex, decode->rex.r,
+                          decode->operand_size);
 }
 
 static void decode_rax(CPUX86State *env, struct x86_decode *decode,
@@ -121,7 +122,8 @@ static void decode_rax(CPUX86State *env, struct x86_decode *decode,
 {
     op->type = X86_VAR_REG;
     op->reg = R_EAX;
-    op->ptr = get_reg_ref(env, op->reg, 0, decode->operand_size);
+    op->ptr = get_reg_ref(env, op->reg, decode->rex.rex, 0,
+                          decode->operand_size);
 }
 
 static inline void decode_immediate(CPUX86State *env, struct x86_decode *decode,
@@ -263,16 +265,16 @@ static void decode_incgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0x40;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_decgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0x48;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_incgroup2(CPUX86State *env, struct x86_decode *decode)
@@ -288,16 +290,16 @@ static void decode_pushgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0x50;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_popgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0x58;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_jxx(CPUX86State *env, struct x86_decode *decode)
@@ -378,16 +380,16 @@ static void decode_xchgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0x90;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_movgroup(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0xb8;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
     decode_immediate(env, decode, &decode->op[1], decode->operand_size);
 }
 
@@ -402,8 +404,8 @@ static void decode_movgroup8(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[0] - 0xb0;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
     decode_immediate(env, decode, &decode->op[1], decode->operand_size);
 }
 
@@ -412,7 +414,8 @@ static void decode_rcx(CPUX86State *env, struct x86_decode *decode,
 {
     op->type = X86_VAR_REG;
     op->reg = R_ECX;
-    op->ptr = get_reg_ref(env, op->reg, decode->rex.b, decode->operand_size);
+    op->ptr = get_reg_ref(env, op->reg, decode->rex.rex, decode->rex.b,
+                          decode->operand_size);
 }
 
 struct decode_tbl {
@@ -639,8 +642,8 @@ static void decode_bswap(CPUX86State *env, struct x86_decode *decode)
 {
     decode->op[0].type = X86_VAR_REG;
     decode->op[0].reg = decode->opcode[1] - 0xc8;
-    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.b,
-                                    decode->operand_size);
+    decode->op[0].ptr = get_reg_ref(env, decode->op[0].reg, decode->rex.rex,
+                                    decode->rex.b, decode->operand_size);
 }
 
 static void decode_d9_4(CPUX86State *env, struct x86_decode *decode)
@@ -1686,7 +1689,8 @@ calc_addr:
     }
 }
 
-target_ulong get_reg_ref(CPUX86State *env, int reg, int is_extended, int size)
+target_ulong get_reg_ref(CPUX86State *env, int reg, int rex, int is_extended,
+                         int size)
 {
     target_ulong ptr = 0;
     int which = 0;
@@ -1698,7 +1702,7 @@ target_ulong get_reg_ref(CPUX86State *env, int reg, int is_extended, int size)
 
     switch (size) {
     case 1:
-        if (is_extended || reg < 4) {
+        if (is_extended || reg < 4 || rex) {
             which = 1;
             ptr = (target_ulong)&RL(env, reg);
         } else {
@@ -1714,10 +1718,11 @@ target_ulong get_reg_ref(CPUX86State *env, int reg, int is_extended, int size)
     return ptr;
 }
 
-target_ulong get_reg_val(CPUX86State *env, int reg, int is_extended, int size)
+target_ulong get_reg_val(CPUX86State *env, int reg, int rex, int is_extended,
+                         int size)
 {
     target_ulong val = 0;
-    memcpy(&val, (void *)get_reg_ref(env, reg, is_extended, size), size);
+    memcpy(&val, (void *)get_reg_ref(env, reg, rex, is_extended, size), size);
     return val;
 }
 
@@ -1739,7 +1744,8 @@ static target_ulong get_sib_val(CPUX86State *env, struct x86_decode *decode,
         if (base_reg == R_ESP || base_reg == R_EBP) {
             *sel = R_SS;
         }
-        base = get_reg_val(env, decode->sib.base, decode->rex.b, addr_size);
+        base = get_reg_val(env, decode->sib.base, decode->rex.rex,
+                           decode->rex.b, addr_size);
     }
 
     if (decode->rex.x) {
@@ -1747,7 +1753,8 @@ static target_ulong get_sib_val(CPUX86State *env, struct x86_decode *decode,
     }
 
     if (index_reg != R_ESP) {
-        scaled_index = get_reg_val(env, index_reg, decode->rex.x, addr_size) <<
+        scaled_index = get_reg_val(env, index_reg, decode->rex.rex,
+                                   decode->rex.x, addr_size) <<
                                    decode->sib.scale;
     }
     return base + scaled_index;
@@ -1776,7 +1783,8 @@ void calc_modrm_operand32(CPUX86State *env, struct x86_decode *decode,
         if (decode->modrm.rm == R_EBP || decode->modrm.rm == R_ESP) {
             seg = R_SS;
         }
-        ptr += get_reg_val(env, decode->modrm.rm, decode->rex.b, addr_size);
+        ptr += get_reg_val(env, decode->modrm.rm, decode->rex.rex,
+                           decode->rex.b, addr_size);
     }
 
     if (X86_DECODE_CMD_LEA == decode->cmd) {
@@ -1805,7 +1813,8 @@ void calc_modrm_operand64(CPUX86State *env, struct x86_decode *decode,
     } else if (0 == mod && 5 == rm) {
         ptr = RIP(env) + decode->len + (int32_t) offset;
     } else {
-        ptr = get_reg_val(env, src, decode->rex.b, 8) + (int64_t) offset;
+        ptr = get_reg_val(env, src, decode->rex.rex, decode->rex.b, 8) +
+              (int64_t) offset;
     }
 
     if (X86_DECODE_CMD_LEA == decode->cmd) {
@@ -1822,8 +1831,8 @@ void calc_modrm_operand(CPUX86State *env, struct x86_decode *decode,
     if (3 == decode->modrm.mod) {
         op->reg = decode->modrm.reg;
         op->type = X86_VAR_REG;
-        op->ptr = get_reg_ref(env, decode->modrm.rm, decode->rex.b,
-                              decode->operand_size);
+        op->ptr = get_reg_ref(env, decode->modrm.rm, decode->rex.rex,
+                              decode->rex.b, decode->operand_size);
         return;
     }
 
diff --git a/target/i386/hvf/x86_decode.h b/target/i386/hvf/x86_decode.h
index 5ab6f31fa5..ef4bcab310 100644
--- a/target/i386/hvf/x86_decode.h
+++ b/target/i386/hvf/x86_decode.h
@@ -303,8 +303,10 @@ uint64_t sign(uint64_t val, int size);
 
 uint32_t decode_instruction(CPUX86State *env, struct x86_decode *decode);
 
-target_ulong get_reg_ref(CPUX86State *env, int reg, int is_extended, int size);
-target_ulong get_reg_val(CPUX86State *env, int reg, int is_extended, int size);
+target_ulong get_reg_ref(CPUX86State *env, int reg, int rex, int is_extended,
+                         int size);
+target_ulong get_reg_val(CPUX86State *env, int reg, int rex, int is_extended,
+                         int size);
 void calc_modrm_operand(CPUX86State *env, struct x86_decode *decode,
                         struct x86_decode_op *op);
 target_ulong decode_linear_addr(CPUX86State *env, struct x86_decode *decode,
diff --git a/target/i386/hyperv-proto.h b/target/i386/hyperv-proto.h
index d6d5a79293..8c572cd7c2 100644
--- a/target/i386/hyperv-proto.h
+++ b/target/i386/hyperv-proto.h
@@ -1,7 +1,7 @@
 /*
- * Definitions for Hyper-V guest/hypervisor interaction
+ * Definitions for Hyper-V guest/hypervisor interaction - x86-specific part
  *
- * Copyright (C) 2017 Parallels International GmbH
+ * Copyright (c) 2017-2018 Virtuozzo International GmbH.
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or later.
  * See the COPYING file in the top-level directory.
@@ -10,7 +10,7 @@
 #ifndef TARGET_I386_HYPERV_PROTO_H
 #define TARGET_I386_HYPERV_PROTO_H
 
-#include "qemu/bitmap.h"
+#include "hw/hyperv/hyperv-proto.h"
 
 #define HV_CPUID_VENDOR_AND_MAX_FUNCTIONS     0x40000000
 #define HV_CPUID_INTERFACE                    0x40000001
@@ -58,6 +58,7 @@
 #define HV_APIC_ACCESS_RECOMMENDED          (1u << 3)
 #define HV_SYSTEM_RESET_RECOMMENDED         (1u << 4)
 #define HV_RELAXED_TIMING_RECOMMENDED       (1u << 5)
+#define HV_CLUSTER_IPI_RECOMMENDED          (1u << 10)
 #define HV_EX_PROCESSOR_MASKS_RECOMMENDED   (1u << 11)
 
 /*
@@ -138,25 +139,6 @@
 #define HV_X64_MSR_TSC_EMULATION_STATUS         0x40000108
 
 /*
- * Hypercall status code
- */
-#define HV_STATUS_SUCCESS                     0
-#define HV_STATUS_INVALID_HYPERCALL_CODE      2
-#define HV_STATUS_INVALID_HYPERCALL_INPUT     3
-#define HV_STATUS_INVALID_ALIGNMENT           4
-#define HV_STATUS_INVALID_PARAMETER           5
-#define HV_STATUS_INSUFFICIENT_MEMORY         11
-#define HV_STATUS_INVALID_CONNECTION_ID       18
-#define HV_STATUS_INSUFFICIENT_BUFFERS        19
-
-/*
- * Hypercall numbers
- */
-#define HV_POST_MESSAGE                       0x005c
-#define HV_SIGNAL_EVENT                       0x005d
-#define HV_HYPERCALL_FAST                     (1u << 16)
-
-/*
  * Hypercall MSR bits
  */
 #define HV_HYPERCALL_ENABLE                   (1u << 0)
@@ -165,7 +147,6 @@
  * Synthetic interrupt controller definitions
  */
 #define HV_SYNIC_VERSION                      1
-#define HV_SINT_COUNT                         16
 #define HV_SYNIC_ENABLE                       (1u << 0)
 #define HV_SIMP_ENABLE                        (1u << 0)
 #define HV_SIEFP_ENABLE                       (1u << 0)
@@ -175,94 +156,5 @@
 
 #define HV_STIMER_COUNT                       4
 
-/*
- * Message size
- */
-#define HV_MESSAGE_PAYLOAD_SIZE               240
-
-/*
- * Message types
- */
-#define HV_MESSAGE_NONE                       0x00000000
-#define HV_MESSAGE_VMBUS                      0x00000001
-#define HV_MESSAGE_UNMAPPED_GPA               0x80000000
-#define HV_MESSAGE_GPA_INTERCEPT              0x80000001
-#define HV_MESSAGE_TIMER_EXPIRED              0x80000010
-#define HV_MESSAGE_INVALID_VP_REGISTER_VALUE  0x80000020
-#define HV_MESSAGE_UNRECOVERABLE_EXCEPTION    0x80000021
-#define HV_MESSAGE_UNSUPPORTED_FEATURE        0x80000022
-#define HV_MESSAGE_EVENTLOG_BUFFERCOMPLETE    0x80000040
-#define HV_MESSAGE_X64_IOPORT_INTERCEPT       0x80010000
-#define HV_MESSAGE_X64_MSR_INTERCEPT          0x80010001
-#define HV_MESSAGE_X64_CPUID_INTERCEPT        0x80010002
-#define HV_MESSAGE_X64_EXCEPTION_INTERCEPT    0x80010003
-#define HV_MESSAGE_X64_APIC_EOI               0x80010004
-#define HV_MESSAGE_X64_LEGACY_FP_ERROR        0x80010005
-
-/*
- * Message flags
- */
-#define HV_MESSAGE_FLAG_PENDING               0x1
-
-/*
- * Event flags number per SINT
- */
-#define HV_EVENT_FLAGS_COUNT                  (256 * 8)
-
-/*
- * Connection id valid bits
- */
-#define HV_CONNECTION_ID_MASK                 0x00ffffff
-
-/*
- * Input structure for POST_MESSAGE hypercall
- */
-struct hyperv_post_message_input {
-    uint32_t connection_id;
-    uint32_t _reserved;
-    uint32_t message_type;
-    uint32_t payload_size;
-    uint8_t  payload[HV_MESSAGE_PAYLOAD_SIZE];
-};
-
-/*
- * Input structure for SIGNAL_EVENT hypercall
- */
-struct hyperv_signal_event_input {
-    uint32_t connection_id;
-    uint16_t flag_number;
-    uint16_t _reserved_zero;
-};
-
-/*
- * SynIC message structures
- */
-struct hyperv_message_header {
-    uint32_t message_type;
-    uint8_t  payload_size;
-    uint8_t  message_flags; /* HV_MESSAGE_FLAG_XX */
-    uint8_t  _reserved[2];
-    uint64_t sender;
-};
-
-struct hyperv_message {
-    struct hyperv_message_header header;
-    uint8_t payload[HV_MESSAGE_PAYLOAD_SIZE];
-};
-
-struct hyperv_message_page {
-    struct hyperv_message slot[HV_SINT_COUNT];
-};
-
-/*
- * SynIC event flags structures
- */
-struct hyperv_event_flags {
-    DECLARE_BITMAP(flags, HV_EVENT_FLAGS_COUNT);
-};
-
-struct hyperv_event_flags_page {
-    struct hyperv_event_flags slot[HV_SINT_COUNT];
-};
 
 #endif
diff --git a/target/i386/hyperv-stub.c b/target/i386/hyperv-stub.c
new file mode 100644
index 0000000000..fe548cbae2
--- /dev/null
+++ b/target/i386/hyperv-stub.c
@@ -0,0 +1,48 @@
+/*
+ * Stubs for CONFIG_HYPERV=n
+ *
+ * Copyright (c) 2015-2018 Virtuozzo International GmbH.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "hyperv.h"
+
+#ifdef CONFIG_KVM
+int kvm_hv_handle_exit(X86CPU *cpu, struct kvm_hyperv_exit *exit)
+{
+    switch (exit->type) {
+    case KVM_EXIT_HYPERV_SYNIC:
+        if (!cpu->hyperv_synic) {
+            return -1;
+        }
+
+        /*
+         * Tracking the changes in the MSRs is unnecessary as there are no
+         * users for them beside save/load, which is handled nicely by the
+         * generic MSR save/load code
+         */
+        return 0;
+    case KVM_EXIT_HYPERV_HCALL:
+        exit->u.hcall.result = HV_STATUS_INVALID_HYPERCALL_CODE;
+        return 0;
+    default:
+        return -1;
+    }
+}
+#endif
+
+int hyperv_x86_synic_add(X86CPU *cpu)
+{
+    return -ENOSYS;
+}
+
+void hyperv_x86_synic_reset(X86CPU *cpu)
+{
+}
+
+void hyperv_x86_synic_update(X86CPU *cpu)
+{
+}
diff --git a/target/i386/hyperv.c b/target/i386/hyperv.c
index 3065d765ed..b264a28620 100644
--- a/target/i386/hyperv.c
+++ b/target/i386/hyperv.c
@@ -14,16 +14,36 @@
 #include "qemu/osdep.h"
 #include "qemu/main-loop.h"
 #include "hyperv.h"
+#include "hw/hyperv/hyperv.h"
 #include "hyperv-proto.h"
 
-uint32_t hyperv_vp_index(X86CPU *cpu)
+int hyperv_x86_synic_add(X86CPU *cpu)
 {
-    return CPU(cpu)->cpu_index;
+    hyperv_synic_add(CPU(cpu));
+    return 0;
 }
 
-X86CPU *hyperv_find_vcpu(uint32_t vp_index)
+void hyperv_x86_synic_reset(X86CPU *cpu)
 {
-    return X86_CPU(qemu_get_cpu(vp_index));
+    hyperv_synic_reset(CPU(cpu));
+}
+
+void hyperv_x86_synic_update(X86CPU *cpu)
+{
+    CPUX86State *env = &cpu->env;
+    bool enable = env->msr_hv_synic_control & HV_SYNIC_ENABLE;
+    hwaddr msg_page_addr = (env->msr_hv_synic_msg_page & HV_SIMP_ENABLE) ?
+        (env->msr_hv_synic_msg_page & TARGET_PAGE_MASK) : 0;
+    hwaddr event_page_addr = (env->msr_hv_synic_evt_page & HV_SIEFP_ENABLE) ?
+        (env->msr_hv_synic_evt_page & TARGET_PAGE_MASK) : 0;
+    hyperv_synic_update(CPU(cpu), enable, msg_page_addr, event_page_addr);
+}
+
+static void async_synic_update(CPUState *cs, run_on_cpu_data data)
+{
+    qemu_mutex_lock_iothread();
+    hyperv_x86_synic_update(X86_CPU(cs));
+    qemu_mutex_unlock_iothread();
 }
 
 int kvm_hv_handle_exit(X86CPU *cpu, struct kvm_hyperv_exit *exit)
@@ -36,11 +56,6 @@ int kvm_hv_handle_exit(X86CPU *cpu, struct kvm_hyperv_exit *exit)
             return -1;
         }
 
-        /*
-         * For now just track changes in SynIC control and msg/evt pages msr's.
-         * When SynIC messaging/events processing will be added in future
-         * here we will do messages queues flushing and pages remapping.
-         */
         switch (exit->u.synic.msr) {
         case HV_X64_MSR_SCONTROL:
             env->msr_hv_synic_control = exit->u.synic.control;
@@ -54,98 +69,33 @@ int kvm_hv_handle_exit(X86CPU *cpu, struct kvm_hyperv_exit *exit)
         default:
             return -1;
         }
+
+        /*
+         * this will run in this cpu thread before it returns to KVM, but in a
+         * safe environment (i.e. when all cpus are quiescent) -- this is
+         * necessary because memory hierarchy is being changed
+         */
+        async_safe_run_on_cpu(CPU(cpu), async_synic_update, RUN_ON_CPU_NULL);
+
         return 0;
     case KVM_EXIT_HYPERV_HCALL: {
-        uint16_t code;
+        uint16_t code = exit->u.hcall.input & 0xffff;
+        bool fast = exit->u.hcall.input & HV_HYPERCALL_FAST;
+        uint64_t param = exit->u.hcall.params[0];
 
-        code  = exit->u.hcall.input & 0xffff;
         switch (code) {
         case HV_POST_MESSAGE:
+            exit->u.hcall.result = hyperv_hcall_post_message(param, fast);
+            break;
         case HV_SIGNAL_EVENT:
+            exit->u.hcall.result = hyperv_hcall_signal_event(param, fast);
+            break;
         default:
             exit->u.hcall.result = HV_STATUS_INVALID_HYPERCALL_CODE;
-            return 0;
         }
+        return 0;
     }
     default:
         return -1;
     }
 }
-
-static void kvm_hv_sint_ack_handler(EventNotifier *notifier)
-{
-    HvSintRoute *sint_route = container_of(notifier, HvSintRoute,
-                                           sint_ack_notifier);
-    event_notifier_test_and_clear(notifier);
-    if (sint_route->sint_ack_clb) {
-        sint_route->sint_ack_clb(sint_route);
-    }
-}
-
-HvSintRoute *kvm_hv_sint_route_create(uint32_t vp_index, uint32_t sint,
-                                      HvSintAckClb sint_ack_clb)
-{
-    HvSintRoute *sint_route;
-    int r, gsi;
-
-    sint_route = g_malloc0(sizeof(*sint_route));
-    r = event_notifier_init(&sint_route->sint_set_notifier, false);
-    if (r) {
-        goto err;
-    }
-
-    r = event_notifier_init(&sint_route->sint_ack_notifier, false);
-    if (r) {
-        goto err_sint_set_notifier;
-    }
-
-    event_notifier_set_handler(&sint_route->sint_ack_notifier,
-                               kvm_hv_sint_ack_handler);
-
-    gsi = kvm_irqchip_add_hv_sint_route(kvm_state, vp_index, sint);
-    if (gsi < 0) {
-        goto err_gsi;
-    }
-
-    r = kvm_irqchip_add_irqfd_notifier_gsi(kvm_state,
-                                           &sint_route->sint_set_notifier,
-                                           &sint_route->sint_ack_notifier, gsi);
-    if (r) {
-        goto err_irqfd;
-    }
-    sint_route->gsi = gsi;
-    sint_route->sint_ack_clb = sint_ack_clb;
-    sint_route->vp_index = vp_index;
-    sint_route->sint = sint;
-
-    return sint_route;
-
-err_irqfd:
-    kvm_irqchip_release_virq(kvm_state, gsi);
-err_gsi:
-    event_notifier_set_handler(&sint_route->sint_ack_notifier, NULL);
-    event_notifier_cleanup(&sint_route->sint_ack_notifier);
-err_sint_set_notifier:
-    event_notifier_cleanup(&sint_route->sint_set_notifier);
-err:
-    g_free(sint_route);
-
-    return NULL;
-}
-
-void kvm_hv_sint_route_destroy(HvSintRoute *sint_route)
-{
-    kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state,
-                                          &sint_route->sint_set_notifier,
-                                          sint_route->gsi);
-    kvm_irqchip_release_virq(kvm_state, sint_route->gsi);
-    event_notifier_set_handler(&sint_route->sint_ack_notifier, NULL);
-    event_notifier_cleanup(&sint_route->sint_ack_notifier);
-    event_notifier_cleanup(&sint_route->sint_set_notifier);
-    g_free(sint_route);
-}
-
-int kvm_hv_sint_route_set_sint(HvSintRoute *sint_route)
-{
-    return event_notifier_set(&sint_route->sint_set_notifier);
-}
diff --git a/target/i386/hyperv.h b/target/i386/hyperv.h
index 00c9b454bb..67543296c3 100644
--- a/target/i386/hyperv.h
+++ b/target/i386/hyperv.h
@@ -16,30 +16,14 @@
 
 #include "cpu.h"
 #include "sysemu/kvm.h"
-#include "qemu/event_notifier.h"
-
-typedef struct HvSintRoute HvSintRoute;
-typedef void (*HvSintAckClb)(HvSintRoute *sint_route);
-
-struct HvSintRoute {
-    uint32_t sint;
-    uint32_t vp_index;
-    int gsi;
-    EventNotifier sint_set_notifier;
-    EventNotifier sint_ack_notifier;
-    HvSintAckClb sint_ack_clb;
-};
+#include "hw/hyperv/hyperv.h"
 
+#ifdef CONFIG_KVM
 int kvm_hv_handle_exit(X86CPU *cpu, struct kvm_hyperv_exit *exit);
+#endif
 
-HvSintRoute *kvm_hv_sint_route_create(uint32_t vp_index, uint32_t sint,
-                                      HvSintAckClb sint_ack_clb);
-
-void kvm_hv_sint_route_destroy(HvSintRoute *sint_route);
-
-int kvm_hv_sint_route_set_sint(HvSintRoute *sint_route);
-
-uint32_t hyperv_vp_index(X86CPU *cpu);
-X86CPU *hyperv_find_vcpu(uint32_t vp_index);
+int hyperv_x86_synic_add(X86CPU *cpu);
+void hyperv_x86_synic_reset(X86CPU *cpu);
+void hyperv_x86_synic_update(X86CPU *cpu);
 
 #endif
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index dc4047b02f..115d8b4c14 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -608,7 +608,8 @@ static bool hyperv_enabled(X86CPU *cpu)
             cpu->hyperv_synic ||
             cpu->hyperv_stimer ||
             cpu->hyperv_reenlightenment ||
-            cpu->hyperv_tlbflush);
+            cpu->hyperv_tlbflush ||
+            cpu->hyperv_ipi);
 }
 
 static int kvm_arch_set_tsc_khz(CPUState *cs)
@@ -733,9 +734,20 @@ static int hyperv_handle_properties(CPUState *cs)
         env->features[FEAT_HYPERV_EAX] |= HV_VP_RUNTIME_AVAILABLE;
     }
     if (cpu->hyperv_synic) {
-        if (!has_msr_hv_synic ||
-            kvm_vcpu_enable_cap(cs, KVM_CAP_HYPERV_SYNIC, 0)) {
-            fprintf(stderr, "Hyper-V SynIC is not supported by kernel\n");
+        unsigned int cap = KVM_CAP_HYPERV_SYNIC;
+        if (!cpu->hyperv_synic_kvm_only) {
+            if (!cpu->hyperv_vpindex) {
+                fprintf(stderr, "Hyper-V SynIC "
+                        "(requested by 'hv-synic' cpu flag) "
+                        "requires Hyper-V VP_INDEX ('hv-vpindex')\n");
+            return -ENOSYS;
+            }
+            cap = KVM_CAP_HYPERV_SYNIC2;
+        }
+
+        if (!has_msr_hv_synic || !kvm_check_extension(cs->kvm_state, cap)) {
+            fprintf(stderr, "Hyper-V SynIC (requested by 'hv-synic' cpu flag) "
+                    "is not supported by kernel\n");
             return -ENOSYS;
         }
 
@@ -753,12 +765,14 @@ static int hyperv_handle_properties(CPUState *cs)
 
 static int hyperv_init_vcpu(X86CPU *cpu)
 {
+    CPUState *cs = CPU(cpu);
+    int ret;
+
     if (cpu->hyperv_vpindex && !hv_vpindex_settable) {
         /*
          * the kernel doesn't support setting vp_index; assert that its value
          * is in sync
          */
-        int ret;
         struct {
             struct kvm_msrs info;
             struct kvm_msr_entry entries[1];
@@ -767,18 +781,38 @@ static int hyperv_init_vcpu(X86CPU *cpu)
             .entries[0].index = HV_X64_MSR_VP_INDEX,
         };
 
-        ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, &msr_data);
+        ret = kvm_vcpu_ioctl(cs, KVM_GET_MSRS, &msr_data);
         if (ret < 0) {
             return ret;
         }
         assert(ret == 1);
 
-        if (msr_data.entries[0].data != hyperv_vp_index(cpu)) {
+        if (msr_data.entries[0].data != hyperv_vp_index(CPU(cpu))) {
             error_report("kernel's vp_index != QEMU's vp_index");
             return -ENXIO;
         }
     }
 
+    if (cpu->hyperv_synic) {
+        uint32_t synic_cap = cpu->hyperv_synic_kvm_only ?
+            KVM_CAP_HYPERV_SYNIC : KVM_CAP_HYPERV_SYNIC2;
+        ret = kvm_vcpu_enable_cap(cs, synic_cap, 0);
+        if (ret < 0) {
+            error_report("failed to turn on HyperV SynIC in KVM: %s",
+                         strerror(-ret));
+            return ret;
+        }
+
+        if (!cpu->hyperv_synic_kvm_only) {
+            ret = hyperv_x86_synic_add(cpu);
+            if (ret < 0) {
+                error_report("failed to create HyperV SynIC: %s",
+                             strerror(-ret));
+                return ret;
+            }
+        }
+    }
+
     return 0;
 }
 
@@ -888,6 +922,17 @@ int kvm_arch_init_vcpu(CPUState *cs)
             c->eax |= HV_REMOTE_TLB_FLUSH_RECOMMENDED;
             c->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
         }
+        if (cpu->hyperv_ipi) {
+            if (kvm_check_extension(cs->kvm_state,
+                                    KVM_CAP_HYPERV_SEND_IPI) <= 0) {
+                fprintf(stderr, "Hyper-V IPI send support "
+                        "(requested by 'hv-ipi' cpu flag) "
+                        " is not supported by kernel\n");
+                return -ENOSYS;
+            }
+            c->eax |= HV_CLUSTER_IPI_RECOMMENDED;
+            c->eax |= HV_EX_PROCESSOR_MASKS_RECOMMENDED;
+        }
 
         c->ebx = cpu->hyperv_spinlock_attempts;
 
@@ -1153,7 +1198,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
             if (local_err) {
                 error_report_err(local_err);
                 error_free(invtsc_mig_blocker);
-                goto fail;
+                return r;
             }
             /* for savevm */
             vmstate_x86_cpu.unmigratable = 1;
@@ -1226,6 +1271,8 @@ void kvm_arch_reset_vcpu(X86CPU *cpu)
         for (i = 0; i < ARRAY_SIZE(env->msr_hv_synic_sint); i++) {
             env->msr_hv_synic_sint[i] = HV_SINT_MASKED;
         }
+
+        hyperv_x86_synic_reset(cpu);
     }
 }
 
@@ -1937,7 +1984,8 @@ static int kvm_put_msrs(X86CPU *cpu, int level)
             kvm_msr_entry_add(cpu, HV_X64_MSR_VP_RUNTIME, env->msr_hv_runtime);
         }
         if (cpu->hyperv_vpindex && hv_vpindex_settable) {
-            kvm_msr_entry_add(cpu, HV_X64_MSR_VP_INDEX, hyperv_vp_index(cpu));
+            kvm_msr_entry_add(cpu, HV_X64_MSR_VP_INDEX,
+                              hyperv_vp_index(CPU(cpu)));
         }
         if (cpu->hyperv_synic) {
             int j;
@@ -2686,7 +2734,6 @@ static int kvm_put_vcpu_events(X86CPU *cpu, int level)
     events.exception.nr = env->exception_injected;
     events.exception.has_error_code = env->has_error_code;
     events.exception.error_code = env->error_code;
-    events.exception.pad = 0;
 
     events.interrupt.injected = (env->interrupt_injected >= 0);
     events.interrupt.nr = env->interrupt_injected;
@@ -2695,7 +2742,6 @@ static int kvm_put_vcpu_events(X86CPU *cpu, int level)
     events.nmi.injected = env->nmi_injected;
     events.nmi.pending = env->nmi_pending;
     events.nmi.masked = !!(env->hflags2 & HF2_NMI_MASK);
-    events.nmi.pad = 0;
 
     events.sipi_vector = env->sipi_vector;
     events.flags = 0;
diff --git a/target/i386/machine.c b/target/i386/machine.c
index 084c2c73a8..225b5d433b 100644
--- a/target/i386/machine.c
+++ b/target/i386/machine.c
@@ -7,6 +7,7 @@
 #include "hw/i386/pc.h"
 #include "hw/isa/isa.h"
 #include "migration/cpu.h"
+#include "hyperv.h"
 
 #include "sysemu/kvm.h"
 
@@ -672,11 +673,19 @@ static bool hyperv_synic_enable_needed(void *opaque)
     return false;
 }
 
+static int hyperv_synic_post_load(void *opaque, int version_id)
+{
+    X86CPU *cpu = opaque;
+    hyperv_x86_synic_update(cpu);
+    return 0;
+}
+
 static const VMStateDescription vmstate_msr_hyperv_synic = {
     .name = "cpu/msr_hyperv_synic",
     .version_id = 1,
     .minimum_version_id = 1,
     .needed = hyperv_synic_enable_needed,
+    .post_load = hyperv_synic_post_load,
     .fields = (VMStateField[]) {
         VMSTATE_UINT64(env.msr_hv_synic_control, X86CPU),
         VMSTATE_UINT64(env.msr_hv_synic_evt_page, X86CPU),