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

* kernel header update (requested by David and Vijay)
* GuestPanicInformation fixups (Anton)
* record/replay icount fixes (Pavel)
* cpu-exec cleanup, unification of icount_decr with tcg_exit_req (me)
* KVM_CAP_IMMEDIATE_EXIT support (me)
* vmxcap update (me)
* iscsi locking fix (me)
* VFIO ram device fix (Yongji)
* scsi-hd vs. default CD-ROM (Hervé)
* SMI migration fix (Dave)
* spice-char segfault (Li Qiang)
* improved "info mtree -f" (me)

# gpg: Signature made Fri 03 Mar 2017 15:43:04 GMT
# 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: (21 commits)
  iscsi: fix missing unlock
  memory: show region offset and ROM/RAM type in "info mtree -f"
  x86: Work around SMI migration breakages
  spice-char: fix segfault in char_spice_finalize
  vl: disable default cdrom when using explicitely scsi-hd
  memory: Introduce DEVICE_HOST_ENDIAN for ram device
  qmp-events: fix GUEST_PANICKED description formatting
  qapi: flatten GuestPanicInformation union
  vmxcap: update for September 2016 SDM
  vmxcap: port to Python 3
  KVM: use KVM_CAP_IMMEDIATE_EXIT
  kvm: use atomic_read/atomic_set to access cpu->exit_request
  KVM: move SIG_IPI handling to kvm-all.c
  KVM: do not use sigtimedwait to catch SIGBUS
  KVM: remove kvm_arch_on_sigbus
  cpus: reorganize signal handling code
  KVM: x86: cleanup SIGBUS handlers
  cpus: remove ugly cast on sigbus_handler
  cpu-exec: remove unnecessary check of cpu->exit_request
  replay: check icount in cpu exec loop
  ...

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

7 files changed, 85 insertions, 83 deletions

diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h
index 8c305aa4fa..b62f0d82e4 100644
--- a/include/exec/cpu-common.h
+++ b/include/exec/cpu-common.h
@@ -36,6 +36,12 @@ enum device_endian {
     DEVICE_LITTLE_ENDIAN,
 };
 
+#if defined(HOST_WORDS_BIGENDIAN)
+#define DEVICE_HOST_ENDIAN DEVICE_BIG_ENDIAN
+#else
+#define DEVICE_HOST_ENDIAN DEVICE_LITTLE_ENDIAN
+#endif
+
 /* address in the RAM (different from a physical address) */
 #if defined(CONFIG_XEN_BACKEND)
 typedef uint64_t ram_addr_t;
diff --git a/include/exec/gen-icount.h b/include/exec/gen-icount.h
index 050de59b38..62d462e494 100644
--- a/include/exec/gen-icount.h
+++ b/include/exec/gen-icount.h
@@ -6,58 +6,55 @@
 /* Helpers for instruction counting code generation.  */
 
 static int icount_start_insn_idx;
-static TCGLabel *icount_label;
 static TCGLabel *exitreq_label;
 
 static inline void gen_tb_start(TranslationBlock *tb)
 {
-    TCGv_i32 count, flag, imm;
+    TCGv_i32 count, imm;
 
     exitreq_label = gen_new_label();
-    flag = tcg_temp_new_i32();
-    tcg_gen_ld_i32(flag, cpu_env,
-                   offsetof(CPUState, tcg_exit_req) - ENV_OFFSET);
-    tcg_gen_brcondi_i32(TCG_COND_NE, flag, 0, exitreq_label);
-    tcg_temp_free_i32(flag);
-
-    if (!(tb->cflags & CF_USE_ICOUNT)) {
-        return;
+    if (tb->cflags & CF_USE_ICOUNT) {
+        count = tcg_temp_local_new_i32();
+    } else {
+        count = tcg_temp_new_i32();
     }
 
-    icount_label = gen_new_label();
-    count = tcg_temp_local_new_i32();
     tcg_gen_ld_i32(count, cpu_env,
                    -ENV_OFFSET + offsetof(CPUState, icount_decr.u32));
 
-    imm = tcg_temp_new_i32();
-    /* We emit a movi with a dummy immediate argument. Keep the insn index
-     * of the movi so that we later (when we know the actual insn count)
-     * can update the immediate argument with the actual insn count.  */
-    icount_start_insn_idx = tcg_op_buf_count();
-    tcg_gen_movi_i32(imm, 0xdeadbeef);
+    if (tb->cflags & CF_USE_ICOUNT) {
+        imm = tcg_temp_new_i32();
+        /* We emit a movi with a dummy immediate argument. Keep the insn index
+         * of the movi so that we later (when we know the actual insn count)
+         * can update the immediate argument with the actual insn count.  */
+        icount_start_insn_idx = tcg_op_buf_count();
+        tcg_gen_movi_i32(imm, 0xdeadbeef);
+
+        tcg_gen_sub_i32(count, count, imm);
+        tcg_temp_free_i32(imm);
+    }
+
+    tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, exitreq_label);
 
-    tcg_gen_sub_i32(count, count, imm);
-    tcg_temp_free_i32(imm);
+    if (tb->cflags & CF_USE_ICOUNT) {
+        tcg_gen_st16_i32(count, cpu_env,
+                         -ENV_OFFSET + offsetof(CPUState, icount_decr.u16.low));
+    }
 
-    tcg_gen_brcondi_i32(TCG_COND_LT, count, 0, icount_label);
-    tcg_gen_st16_i32(count, cpu_env,
-                     -ENV_OFFSET + offsetof(CPUState, icount_decr.u16.low));
     tcg_temp_free_i32(count);
 }
 
 static void gen_tb_end(TranslationBlock *tb, int num_insns)
 {
-    gen_set_label(exitreq_label);
-    tcg_gen_exit_tb((uintptr_t)tb + TB_EXIT_REQUESTED);
-
     if (tb->cflags & CF_USE_ICOUNT) {
         /* Update the num_insn immediate parameter now that we know
          * the actual insn count.  */
         tcg_set_insn_param(icount_start_insn_idx, 1, num_insns);
-        gen_set_label(icount_label);
-        tcg_gen_exit_tb((uintptr_t)tb + TB_EXIT_ICOUNT_EXPIRED);
     }
 
+    gen_set_label(exitreq_label);
+    tcg_gen_exit_tb((uintptr_t)tb + TB_EXIT_REQUESTED);
+
     /* Terminate the linked list.  */
     tcg_ctx.gen_op_buf[tcg_ctx.gen_op_buf[0].prev].next = 0;
 }
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index d1f45540a1..ab303c7fee 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -623,6 +623,10 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
         .driver   = "Broadwell-noTSX" "-" TYPE_X86_CPU,\
         .property = "xlevel",\
         .value    = stringify(0x8000000a),\
+    },{\
+        .driver = TYPE_X86_CPU,\
+        .property = "kvm-no-smi-migration",\
+        .value    = "on",\
     },
 
 #define PC_COMPAT_2_2 \
diff --git a/include/qemu/compatfd.h b/include/qemu/compatfd.h
deleted file mode 100644
index aa12ee9364..0000000000
--- a/include/qemu/compatfd.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * signalfd/eventfd compatibility
- *
- * Copyright IBM, Corp. 2008
- *
- * Authors:
- *  Anthony Liguori   <aliguori@us.ibm.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- */
-
-#ifndef QEMU_COMPATFD_H
-#define QEMU_COMPATFD_H
-
-
-struct qemu_signalfd_siginfo {
-    uint32_t ssi_signo;   /* Signal number */
-    int32_t  ssi_errno;   /* Error number (unused) */
-    int32_t  ssi_code;    /* Signal code */
-    uint32_t ssi_pid;     /* PID of sender */
-    uint32_t ssi_uid;     /* Real UID of sender */
-    int32_t  ssi_fd;      /* File descriptor (SIGIO) */
-    uint32_t ssi_tid;     /* Kernel timer ID (POSIX timers) */
-    uint32_t ssi_band;    /* Band event (SIGIO) */
-    uint32_t ssi_overrun; /* POSIX timer overrun count */
-    uint32_t ssi_trapno;  /* Trap number that caused signal */
-    int32_t  ssi_status;  /* Exit status or signal (SIGCHLD) */
-    int32_t  ssi_int;     /* Integer sent by sigqueue(2) */
-    uint64_t ssi_ptr;     /* Pointer sent by sigqueue(2) */
-    uint64_t ssi_utime;   /* User CPU time consumed (SIGCHLD) */
-    uint64_t ssi_stime;   /* System CPU time consumed (SIGCHLD) */
-    uint64_t ssi_addr;    /* Address that generated signal
-                             (for hardware-generated signals) */
-    uint8_t  pad[48];     /* Pad size to 128 bytes (allow for
-                             additional fields in the future) */
-};
-
-int qemu_signalfd(const sigset_t *mask);
-
-#endif
diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h
index 56c9e22405..af37195fef 100644
--- a/include/qemu/osdep.h
+++ b/include/qemu/osdep.h
@@ -284,6 +284,15 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 
 #endif
 
+#if defined(CONFIG_LINUX)
+#ifndef BUS_MCEERR_AR
+#define BUS_MCEERR_AR 4
+#endif
+#ifndef BUS_MCEERR_AO
+#define BUS_MCEERR_AO 5
+#endif
+#endif
+
 #if defined(__linux__) && \
     (defined(__x86_64__) || defined(__arm__) || defined(__aarch64__))
    /* Use 2 MiB alignment so transparent hugepages can be used by KVM.
@@ -297,6 +306,34 @@ void qemu_anon_ram_free(void *ptr, size_t size);
 #  define QEMU_VMALLOC_ALIGN getpagesize()
 #endif
 
+#ifdef CONFIG_POSIX
+struct qemu_signalfd_siginfo {
+    uint32_t ssi_signo;   /* Signal number */
+    int32_t  ssi_errno;   /* Error number (unused) */
+    int32_t  ssi_code;    /* Signal code */
+    uint32_t ssi_pid;     /* PID of sender */
+    uint32_t ssi_uid;     /* Real UID of sender */
+    int32_t  ssi_fd;      /* File descriptor (SIGIO) */
+    uint32_t ssi_tid;     /* Kernel timer ID (POSIX timers) */
+    uint32_t ssi_band;    /* Band event (SIGIO) */
+    uint32_t ssi_overrun; /* POSIX timer overrun count */
+    uint32_t ssi_trapno;  /* Trap number that caused signal */
+    int32_t  ssi_status;  /* Exit status or signal (SIGCHLD) */
+    int32_t  ssi_int;     /* Integer sent by sigqueue(2) */
+    uint64_t ssi_ptr;     /* Pointer sent by sigqueue(2) */
+    uint64_t ssi_utime;   /* User CPU time consumed (SIGCHLD) */
+    uint64_t ssi_stime;   /* System CPU time consumed (SIGCHLD) */
+    uint64_t ssi_addr;    /* Address that generated signal
+                             (for hardware-generated signals) */
+    uint8_t  pad[48];     /* Pad size to 128 bytes (allow for
+                             additional fields in the future) */
+};
+
+int qemu_signalfd(const sigset_t *mask);
+void sigaction_invoke(struct sigaction *action,
+                      struct qemu_signalfd_siginfo *info);
+#endif
+
 int qemu_madvise(void *addr, size_t len, int advice);
 
 int qemu_open(const char *name, int flags, ...);
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 3e61c880da..c3292efe1c 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -275,11 +275,11 @@ struct qemu_work_item;
  * @stopped: Indicates the CPU has been artificially stopped.
  * @unplug: Indicates a pending CPU unplug request.
  * @crash_occurred: Indicates the OS reported a crash (panic) for this CPU
- * @tcg_exit_req: Set to force TCG to stop executing linked TBs for this
- *           CPU and return to its top level loop.
  * @singlestep_enabled: Flags for single-stepping.
  * @icount_extra: Instructions until next timer event.
- * @icount_decr: Number of cycles left, with interrupt flag in high bit.
+ * @icount_decr: Low 16 bits: number of cycles left, only used in icount mode.
+ * High 16 bits: Set to -1 to force TCG to stop executing linked TBs for this
+ * CPU and return to its top level loop (even in non-icount mode).
  * This allows a single read-compare-cbranch-write sequence to test
  * for both decrementer underflow and exceptions.
  * @can_do_io: Nonzero if memory-mapped IO is safe. Deterministic execution
@@ -382,10 +382,6 @@ struct CPUState {
     /* TODO Move common fields from CPUArchState here. */
     int cpu_index; /* used by alpha TCG */
     uint32_t halted; /* used by alpha, cris, ppc TCG */
-    union {
-        uint32_t u32;
-        icount_decr_u16 u16;
-    } icount_decr;
     uint32_t can_do_io;
     int32_t exception_index; /* used by m68k TCG */
 
@@ -398,7 +394,10 @@ struct CPUState {
        offset from AREG0.  Leave this field at the end so as to make the
        (absolute value) offset as small as possible.  This reduces code
        size, especially for hosts without large memory offsets.  */
-    uint32_t tcg_exit_req;
+    union {
+        uint32_t u32;
+        icount_decr_u16 u16;
+    } icount_decr;
 
     bool hax_vcpu_dirty;
     struct hax_vcpu_state *hax_vcpu;
diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h
index 3045ee7678..24281fc7f8 100644
--- a/include/sysemu/kvm.h
+++ b/include/sysemu/kvm.h
@@ -238,9 +238,6 @@ int kvm_remove_breakpoint(CPUState *cpu, target_ulong addr,
                           target_ulong len, int type);
 void kvm_remove_all_breakpoints(CPUState *cpu);
 int kvm_update_guest_debug(CPUState *cpu, unsigned long reinject_trap);
-#ifndef _WIN32
-int kvm_set_signal_mask(CPUState *cpu, const sigset_t *sigset);
-#endif
 
 int kvm_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
 int kvm_on_sigbus(int code, void *addr);
@@ -357,8 +354,10 @@ bool kvm_vcpu_id_is_valid(int vcpu_id);
 /* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */
 unsigned long kvm_arch_vcpu_id(CPUState *cpu);
 
-int kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
-int kvm_arch_on_sigbus(int code, void *addr);
+#ifdef TARGET_I386
+#define KVM_HAVE_MCE_INJECTION 1
+void kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr);
+#endif
 
 void kvm_arch_init_irq_routing(KVMState *s);
 
@@ -461,6 +460,8 @@ void kvm_cpu_synchronize_state(CPUState *cpu);
 void kvm_cpu_synchronize_post_reset(CPUState *cpu);
 void kvm_cpu_synchronize_post_init(CPUState *cpu);
 
+void kvm_init_cpu_signals(CPUState *cpu);
+
 /**
  * kvm_irqchip_add_msi_route - Add MSI route for specific vector
  * @s:      KVM state