Merge branch 'xenfv-kvm-15' of git://git.infradead.org/users/dwmw2/qemu into HEAD

This adds support for emulating Xen under Linux/KVM, based on kernel
patches which have been present since Linux v5.12. As with the kernel
support, it's derived from work started by João Martins of Oracle in
2018.

This series just adds the basic platform support — CPUID, hypercalls,
event channels, a stub of XenStore.

A full single-tenant internal implementation of XenStore, and patches
to make QEMU's Xen PV drivers work with this Xen emulation, are waiting
in the wings to be submitted in a follow-on patch series.

As noted in the documentation, it's enabled by setting the xen-version
property on the KVM accelerator, e.g.:

 qemu-system-x86_64 -serial mon:stdio -M q35 -display none -m 1G -smp 2 \
    -accel kvm,xen-version=0x4000e,kernel-irqchip=split \
    -kernel vmlinuz-6.0.7-301.fc37.x86_64 \
    -append "console=ttyS0 root=/dev/sda1" \
    -drive file=/var/lib/libvirt/images/fedora28.qcow2,if=none,id=disk \
    -device ahci,id=ahci -device ide-hd,drive=disk,bus=ahci.0

Even before this was merged, we've already been using it to find and fix
bugs in the Linux kernel Xen guest support:

https://lore.kernel.org/all/4bffa69a949bfdc92c4a18e5a1c3cbb3b94a0d32.camel@infradead.org/
https://lore.kernel.org/all/871qnunycr.ffs@tglx/

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

13 files changed, 141 insertions, 126 deletions

diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c
index 9b26582..f2a6ea6 100644
--- a/accel/kvm/kvm-all.c
+++ b/accel/kvm/kvm-all.c
@@ -2361,13 +2361,13 @@ static int kvm_init(MachineState *ms)
     static const char upgrade_note[] =
         "Please upgrade to at least kernel 2.6.29 or recent kvm-kmod\n"
         "(see http://sourceforge.net/projects/kvm).\n";
-    struct {
+    const struct {
         const char *name;
         int num;
     } num_cpus[] = {
         { "SMP",          ms->smp.cpus },
         { "hotpluggable", ms->smp.max_cpus },
-        { NULL, }
+        { /* end of list */ }
     }, *nc = num_cpus;
     int soft_vcpus_limit, hard_vcpus_limit;
     KVMState *s;
@@ -3305,7 +3305,7 @@ bool kvm_supports_guest_debug(void)
     return kvm_has_guest_debug;
 }
 
-int kvm_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
+int kvm_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
 {
     struct kvm_sw_breakpoint *bp;
     int err;
@@ -3343,7 +3343,7 @@ int kvm_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
     return 0;
 }
 
-int kvm_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len)
+int kvm_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len)
 {
     struct kvm_sw_breakpoint *bp;
     int err;
@@ -3703,6 +3703,9 @@ static void kvm_accel_instance_init(Object *obj)
     s->kvm_dirty_ring_size = 0;
     s->notify_vmexit = NOTIFY_VMEXIT_OPTION_RUN;
     s->notify_window = 0;
+    s->xen_version = 0;
+    s->xen_gnttab_max_frames = 64;
+    s->xen_evtchn_max_pirq = 256;
 }
 
 /**
diff --git a/accel/kvm/kvm-cpus.h b/accel/kvm/kvm-cpus.h
index fd63fe6..ca40add 100644
--- a/accel/kvm/kvm-cpus.h
+++ b/accel/kvm/kvm-cpus.h
@@ -19,8 +19,8 @@ void kvm_cpu_synchronize_post_reset(CPUState *cpu);
 void kvm_cpu_synchronize_post_init(CPUState *cpu);
 void kvm_cpu_synchronize_pre_loadvm(CPUState *cpu);
 bool kvm_supports_guest_debug(void);
-int kvm_insert_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len);
-int kvm_remove_breakpoint(CPUState *cpu, int type, hwaddr addr, hwaddr len);
+int kvm_insert_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
+int kvm_remove_breakpoint(CPUState *cpu, int type, vaddr addr, vaddr len);
 void kvm_remove_all_breakpoints(CPUState *cpu);
 
 #endif /* KVM_CPUS_H */
diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index 5357608..ef557e5 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -20,7 +20,6 @@
 #include "qemu/osdep.h"
 #include "qemu/qemu-print.h"
 #include "qapi/error.h"
-#include "qapi/qapi-commands-machine.h"
 #include "qapi/type-helpers.h"
 #include "hw/core/tcg-cpu-ops.h"
 #include "trace.h"
@@ -28,7 +27,6 @@
 #include "exec/exec-all.h"
 #include "tcg/tcg.h"
 #include "qemu/atomic.h"
-#include "qemu/timer.h"
 #include "qemu/rcu.h"
 #include "exec/log.h"
 #include "qemu/main-loop.h"
@@ -38,7 +36,7 @@
 #include "sysemu/cpus.h"
 #include "exec/cpu-all.h"
 #include "sysemu/cpu-timers.h"
-#include "sysemu/replay.h"
+#include "exec/replay-core.h"
 #include "sysemu/tcg.h"
 #include "exec/helper-proto.h"
 #include "tb-jmp-cache.h"
@@ -64,8 +62,8 @@ typedef struct SyncClocks {
 #define MAX_DELAY_PRINT_RATE 2000000000LL
 #define MAX_NB_PRINTS 100
 
-static int64_t max_delay;
-static int64_t max_advance;
+int64_t max_delay;
+int64_t max_advance;
 
 static void align_clocks(SyncClocks *sc, CPUState *cpu)
 {
@@ -1072,86 +1070,3 @@ void tcg_exec_unrealizefn(CPUState *cpu)
     tlb_destroy(cpu);
     g_free_rcu(cpu->tb_jmp_cache, rcu);
 }
-
-#ifndef CONFIG_USER_ONLY
-
-static void dump_drift_info(GString *buf)
-{
-    if (!icount_enabled()) {
-        return;
-    }
-
-    g_string_append_printf(buf, "Host - Guest clock  %"PRIi64" ms\n",
-                           (cpu_get_clock() - icount_get()) / SCALE_MS);
-    if (icount_align_option) {
-        g_string_append_printf(buf, "Max guest delay     %"PRIi64" ms\n",
-                               -max_delay / SCALE_MS);
-        g_string_append_printf(buf, "Max guest advance   %"PRIi64" ms\n",
-                               max_advance / SCALE_MS);
-    } else {
-        g_string_append_printf(buf, "Max guest delay     NA\n");
-        g_string_append_printf(buf, "Max guest advance   NA\n");
-    }
-}
-
-HumanReadableText *qmp_x_query_jit(Error **errp)
-{
-    g_autoptr(GString) buf = g_string_new("");
-
-    if (!tcg_enabled()) {
-        error_setg(errp, "JIT information is only available with accel=tcg");
-        return NULL;
-    }
-
-    dump_exec_info(buf);
-    dump_drift_info(buf);
-
-    return human_readable_text_from_str(buf);
-}
-
-HumanReadableText *qmp_x_query_opcount(Error **errp)
-{
-    g_autoptr(GString) buf = g_string_new("");
-
-    if (!tcg_enabled()) {
-        error_setg(errp, "Opcode count information is only available with accel=tcg");
-        return NULL;
-    }
-
-    tcg_dump_op_count(buf);
-
-    return human_readable_text_from_str(buf);
-}
-
-#ifdef CONFIG_PROFILER
-
-int64_t dev_time;
-
-HumanReadableText *qmp_x_query_profile(Error **errp)
-{
-    g_autoptr(GString) buf = g_string_new("");
-    static int64_t last_cpu_exec_time;
-    int64_t cpu_exec_time;
-    int64_t delta;
-
-    cpu_exec_time = tcg_cpu_exec_time();
-    delta = cpu_exec_time - last_cpu_exec_time;
-
-    g_string_append_printf(buf, "async time  %" PRId64 " (%0.3f)\n",
-                           dev_time, dev_time / (double)NANOSECONDS_PER_SECOND);
-    g_string_append_printf(buf, "qemu time   %" PRId64 " (%0.3f)\n",
-                           delta, delta / (double)NANOSECONDS_PER_SECOND);
-    last_cpu_exec_time = cpu_exec_time;
-    dev_time = 0;
-
-    return human_readable_text_from_str(buf);
-}
-#else
-HumanReadableText *qmp_x_query_profile(Error **errp)
-{
-    error_setg(errp, "Internal profiler not compiled");
-    return NULL;
-}
-#endif
-
-#endif /* !CONFIG_USER_ONLY */
diff --git a/accel/tcg/hmp.c b/accel/tcg/hmp.c
deleted file mode 100644
index bb67941..0000000
--- a/accel/tcg/hmp.c
+++ /dev/null
@@ -1,14 +0,0 @@
-#include "qemu/osdep.h"
-#include "qemu/error-report.h"
-#include "qapi/error.h"
-#include "qapi/qapi-commands-machine.h"
-#include "exec/exec-all.h"
-#include "monitor/monitor.h"
-
-static void hmp_tcg_register(void)
-{
-    monitor_register_hmp_info_hrt("jit", qmp_x_query_jit);
-    monitor_register_hmp_info_hrt("opcount", qmp_x_query_opcount);
-}
-
-type_init(hmp_tcg_register);
diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h
index 6edff16..130d7fd 100644
--- a/accel/tcg/internal.h
+++ b/accel/tcg/internal.h
@@ -64,4 +64,7 @@ static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb)
 #endif
 }
 
+extern int64_t max_delay;
+extern int64_t max_advance;
+
 #endif /* ACCEL_TCG_INTERNAL_H */
diff --git a/accel/tcg/meson.build b/accel/tcg/meson.build
index 77740b1..aeb20a6 100644
--- a/accel/tcg/meson.build
+++ b/accel/tcg/meson.build
@@ -18,7 +18,7 @@ specific_ss.add_all(when: 'CONFIG_TCG', if_true: tcg_ss)
 
 specific_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files(
   'cputlb.c',
-  'hmp.c',
+  'monitor.c',
 ))
 
 tcg_module_ss.add(when: ['CONFIG_SOFTMMU', 'CONFIG_TCG'], if_true: files(
diff --git a/accel/tcg/monitor.c b/accel/tcg/monitor.c
new file mode 100644
index 0000000..1450e16
--- /dev/null
+++ b/accel/tcg/monitor.c
@@ -0,0 +1,106 @@
+/*
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ *
+ *  QEMU TCG monitor
+ *
+ *  Copyright (c) 2003-2005 Fabrice Bellard
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qapi/type-helpers.h"
+#include "qapi/qapi-commands-machine.h"
+#include "monitor/monitor.h"
+#include "sysemu/cpus.h"
+#include "sysemu/cpu-timers.h"
+#include "sysemu/tcg.h"
+#include "internal.h"
+
+
+static void dump_drift_info(GString *buf)
+{
+    if (!icount_enabled()) {
+        return;
+    }
+
+    g_string_append_printf(buf, "Host - Guest clock  %"PRIi64" ms\n",
+                           (cpu_get_clock() - icount_get()) / SCALE_MS);
+    if (icount_align_option) {
+        g_string_append_printf(buf, "Max guest delay     %"PRIi64" ms\n",
+                               -max_delay / SCALE_MS);
+        g_string_append_printf(buf, "Max guest advance   %"PRIi64" ms\n",
+                               max_advance / SCALE_MS);
+    } else {
+        g_string_append_printf(buf, "Max guest delay     NA\n");
+        g_string_append_printf(buf, "Max guest advance   NA\n");
+    }
+}
+
+HumanReadableText *qmp_x_query_jit(Error **errp)
+{
+    g_autoptr(GString) buf = g_string_new("");
+
+    if (!tcg_enabled()) {
+        error_setg(errp, "JIT information is only available with accel=tcg");
+        return NULL;
+    }
+
+    dump_exec_info(buf);
+    dump_drift_info(buf);
+
+    return human_readable_text_from_str(buf);
+}
+
+HumanReadableText *qmp_x_query_opcount(Error **errp)
+{
+    g_autoptr(GString) buf = g_string_new("");
+
+    if (!tcg_enabled()) {
+        error_setg(errp,
+                   "Opcode count information is only available with accel=tcg");
+        return NULL;
+    }
+
+    tcg_dump_op_count(buf);
+
+    return human_readable_text_from_str(buf);
+}
+
+#ifdef CONFIG_PROFILER
+
+int64_t dev_time;
+
+HumanReadableText *qmp_x_query_profile(Error **errp)
+{
+    g_autoptr(GString) buf = g_string_new("");
+    static int64_t last_cpu_exec_time;
+    int64_t cpu_exec_time;
+    int64_t delta;
+
+    cpu_exec_time = tcg_cpu_exec_time();
+    delta = cpu_exec_time - last_cpu_exec_time;
+
+    g_string_append_printf(buf, "async time  %" PRId64 " (%0.3f)\n",
+                           dev_time, dev_time / (double)NANOSECONDS_PER_SECOND);
+    g_string_append_printf(buf, "qemu time   %" PRId64 " (%0.3f)\n",
+                           delta, delta / (double)NANOSECONDS_PER_SECOND);
+    last_cpu_exec_time = cpu_exec_time;
+    dev_time = 0;
+
+    return human_readable_text_from_str(buf);
+}
+#else
+HumanReadableText *qmp_x_query_profile(Error **errp)
+{
+    error_setg(errp, "Internal profiler not compiled");
+    return NULL;
+}
+#endif
+
+static void hmp_tcg_register(void)
+{
+    monitor_register_hmp_info_hrt("jit", qmp_x_query_jit);
+    monitor_register_hmp_info_hrt("opcount", qmp_x_query_opcount);
+}
+
+type_init(hmp_tcg_register);
diff --git a/accel/tcg/tcg-accel-ops.c b/accel/tcg/tcg-accel-ops.c
index 19cbf1d..aeb1cba 100644
--- a/accel/tcg/tcg-accel-ops.c
+++ b/accel/tcg/tcg-accel-ops.c
@@ -44,7 +44,18 @@
 
 void tcg_cpu_init_cflags(CPUState *cpu, bool parallel)
 {
-    uint32_t cflags = cpu->cluster_index << CF_CLUSTER_SHIFT;
+    uint32_t cflags;
+
+    /*
+     * Include the cluster number in the hash we use to look up TBs.
+     * This is important because a TB that is valid for one cluster at
+     * a given physical address and set of CPU flags is not necessarily
+     * valid for another:
+     * the two clusters may have different views of physical memory, or
+     * may have different CPU features (eg FPU present or absent).
+     */
+    cflags = cpu->cluster_index << CF_CLUSTER_SHIFT;
+
     cflags |= parallel ? CF_PARALLEL : 0;
     cflags |= icount_enabled() ? CF_USE_ICOUNT : 0;
     cpu->tcg_cflags = cflags;
@@ -116,7 +127,7 @@ static inline int xlat_gdb_type(CPUState *cpu, int gdbtype)
     return cputype;
 }
 
-static int tcg_insert_breakpoint(CPUState *cs, int type, hwaddr addr, hwaddr len)
+static int tcg_insert_breakpoint(CPUState *cs, int type, vaddr addr, vaddr len)
 {
     CPUState *cpu;
     int err = 0;
@@ -147,7 +158,7 @@ static int tcg_insert_breakpoint(CPUState *cs, int type, hwaddr addr, hwaddr len
     }
 }
 
-static int tcg_remove_breakpoint(CPUState *cs, int type, hwaddr addr, hwaddr len)
+static int tcg_remove_breakpoint(CPUState *cs, int type, vaddr addr, vaddr len)
 {
     CPUState *cpu;
     int err = 0;
diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c
index 30b503f..5dab1ae 100644
--- a/accel/tcg/tcg-all.c
+++ b/accel/tcg/tcg-all.c
@@ -25,7 +25,7 @@
 
 #include "qemu/osdep.h"
 #include "sysemu/tcg.h"
-#include "sysemu/replay.h"
+#include "exec/replay-core.h"
 #include "sysemu/cpu-timers.h"
 #include "tcg/tcg.h"
 #include "qapi/error.h"
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 9e925c1..84f1293 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -49,7 +49,6 @@
 #include "exec/translator.h"
 #include "qemu/bitmap.h"
 #include "qemu/qemu-print.h"
-#include "qemu/timer.h"
 #include "qemu/main-loop.h"
 #include "qemu/cacheinfo.h"
 #include "exec/log.h"
diff --git a/accel/tcg/translator.c b/accel/tcg/translator.c
index 1cf404c..15d11fa 100644
--- a/accel/tcg/translator.c
+++ b/accel/tcg/translator.c
@@ -16,7 +16,7 @@
 #include "exec/log.h"
 #include "exec/translator.h"
 #include "exec/plugin-gen.h"
-#include "sysemu/replay.h"
+#include "exec/replay-core.h"
 
 /* Pairs with tcg_clear_temp_count.
    To be called by #TranslatorOps.{translate_insn,tb_stop} if
diff --git a/accel/tcg/user-exec-stub.c b/accel/tcg/user-exec-stub.c
index 968cd3c..874e1f1 100644
--- a/accel/tcg/user-exec-stub.c
+++ b/accel/tcg/user-exec-stub.c
@@ -1,6 +1,6 @@
 #include "qemu/osdep.h"
 #include "hw/core/cpu.h"
-#include "sysemu/replay.h"
+#include "exec/replay-core.h"
 
 bool enable_cpu_pm = false;
 
diff --git a/accel/xen/xen-all.c b/accel/xen/xen-all.c
index 69aa7d0..e85e4ae 100644
--- a/accel/xen/xen-all.c
+++ b/accel/xen/xen-all.c
@@ -23,16 +23,6 @@
 #include "migration/global_state.h"
 #include "hw/boards.h"
 
-//#define DEBUG_XEN
-
-#ifdef DEBUG_XEN
-#define DPRINTF(fmt, ...) \
-    do { fprintf(stderr, "xen: " fmt, ## __VA_ARGS__); } while (0)
-#else
-#define DPRINTF(fmt, ...) \
-    do { } while (0)
-#endif
-
 bool xen_allowed;
 
 xc_interface *xen_xc;
@@ -181,6 +171,8 @@ static int xen_init(MachineState *ms)
      * opt out of system RAM being allocated by generic code
      */
     mc->default_ram_id = NULL;
+
+    xen_mode = XEN_ATTACH;
     return 0;
 }