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>

1 files changed, 69 insertions, 40 deletions

diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index a7a2ededf9..fd17ce7a94 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -28,13 +28,13 @@
 #include "hw/i386/pc.h"
 #include "hw/char/serial.h"
 #include "hw/char/parallel.h"
-#include "hw/i386/apic.h"
 #include "hw/i386/topology.h"
 #include "hw/i386/fw_cfg.h"
 #include "hw/i386/vmport.h"
 #include "sysemu/cpus.h"
 #include "hw/block/fdc.h"
-#include "hw/ide.h"
+#include "hw/ide/internal.h"
+#include "hw/ide/isa.h"
 #include "hw/pci/pci.h"
 #include "hw/pci/pci_bus.h"
 #include "hw/pci-bridge/pci_expander_bridge.h"
@@ -47,6 +47,7 @@
 #include "multiboot.h"
 #include "hw/rtc/mc146818rtc.h"
 #include "hw/intc/i8259.h"
+#include "hw/intc/ioapic.h"
 #include "hw/timer/i8254.h"
 #include "hw/input/i8042.h"
 #include "hw/irq.h"
@@ -89,6 +90,10 @@
 #include "hw/virtio/virtio-iommu.h"
 #include "hw/virtio/virtio-pmem-pci.h"
 #include "hw/virtio/virtio-mem-pci.h"
+#include "hw/i386/kvm/xen_overlay.h"
+#include "hw/i386/kvm/xen_evtchn.h"
+#include "hw/i386/kvm/xen_gnttab.h"
+#include "hw/i386/kvm/xen_xenstore.h"
 #include "hw/mem/memory-device.h"
 #include "sysemu/replay.h"
 #include "target/i386/cpu.h"
@@ -405,7 +410,7 @@ GSIState *pc_gsi_create(qemu_irq **irqs, bool pci_enabled)
     if (kvm_ioapic_in_kernel()) {
         kvm_pc_setup_irq_routing(pci_enabled);
     }
-    *irqs = qemu_allocate_irqs(gsi_handler, s, GSI_NUM_PINS);
+    *irqs = qemu_allocate_irqs(gsi_handler, s, IOAPIC_NUM_PINS);
 
     return s;
 }
@@ -438,19 +443,19 @@ static uint64_t ioportF0_read(void *opaque, hwaddr addr, unsigned size)
 
 #define REG_EQUIPMENT_BYTE          0x14
 
-static void cmos_init_hd(ISADevice *s, int type_ofs, int info_ofs,
+static void cmos_init_hd(MC146818RtcState *s, int type_ofs, int info_ofs,
                          int16_t cylinders, int8_t heads, int8_t sectors)
 {
-    rtc_set_memory(s, type_ofs, 47);
-    rtc_set_memory(s, info_ofs, cylinders);
-    rtc_set_memory(s, info_ofs + 1, cylinders >> 8);
-    rtc_set_memory(s, info_ofs + 2, heads);
-    rtc_set_memory(s, info_ofs + 3, 0xff);
-    rtc_set_memory(s, info_ofs + 4, 0xff);
-    rtc_set_memory(s, info_ofs + 5, 0xc0 | ((heads > 8) << 3));
-    rtc_set_memory(s, info_ofs + 6, cylinders);
-    rtc_set_memory(s, info_ofs + 7, cylinders >> 8);
-    rtc_set_memory(s, info_ofs + 8, sectors);
+    mc146818rtc_set_cmos_data(s, type_ofs, 47);
+    mc146818rtc_set_cmos_data(s, info_ofs, cylinders);
+    mc146818rtc_set_cmos_data(s, info_ofs + 1, cylinders >> 8);
+    mc146818rtc_set_cmos_data(s, info_ofs + 2, heads);
+    mc146818rtc_set_cmos_data(s, info_ofs + 3, 0xff);
+    mc146818rtc_set_cmos_data(s, info_ofs + 4, 0xff);
+    mc146818rtc_set_cmos_data(s, info_ofs + 5, 0xc0 | ((heads > 8) << 3));
+    mc146818rtc_set_cmos_data(s, info_ofs + 6, cylinders);
+    mc146818rtc_set_cmos_data(s, info_ofs + 7, cylinders >> 8);
+    mc146818rtc_set_cmos_data(s, info_ofs + 8, sectors);
 }
 
 /* convert boot_device letter to something recognizable by the bios */
@@ -470,7 +475,8 @@ static int boot_device2nibble(char boot_device)
     return 0;
 }
 
-static void set_boot_dev(ISADevice *s, const char *boot_device, Error **errp)
+static void set_boot_dev(MC146818RtcState *s, const char *boot_device,
+                         Error **errp)
 {
 #define PC_MAX_BOOT_DEVICES 3
     int nbds, bds[3] = { 0, };
@@ -489,8 +495,8 @@ static void set_boot_dev(ISADevice *s, const char *boot_device, Error **errp)
             return;
         }
     }
-    rtc_set_memory(s, 0x3d, (bds[1] << 4) | bds[0]);
-    rtc_set_memory(s, 0x38, (bds[2] << 4) | (fd_bootchk ? 0x0 : 0x1));
+    mc146818rtc_set_cmos_data(s, 0x3d, (bds[1] << 4) | bds[0]);
+    mc146818rtc_set_cmos_data(s, 0x38, (bds[2] << 4) | (fd_bootchk ? 0x0 : 0x1));
 }
 
 static void pc_boot_set(void *opaque, const char *boot_device, Error **errp)
@@ -498,7 +504,7 @@ static void pc_boot_set(void *opaque, const char *boot_device, Error **errp)
     set_boot_dev(opaque, boot_device, errp);
 }
 
-static void pc_cmos_init_floppy(ISADevice *rtc_state, ISADevice *floppy)
+static void pc_cmos_init_floppy(MC146818RtcState *rtc_state, ISADevice *floppy)
 {
     int val, nb, i;
     FloppyDriveType fd_type[2] = { FLOPPY_DRIVE_TYPE_NONE,
@@ -512,9 +518,9 @@ static void pc_cmos_init_floppy(ISADevice *rtc_state, ISADevice *floppy)
     }
     val = (cmos_get_fd_drive_type(fd_type[0]) << 4) |
         cmos_get_fd_drive_type(fd_type[1]);
-    rtc_set_memory(rtc_state, 0x10, val);
+    mc146818rtc_set_cmos_data(rtc_state, 0x10, val);
 
-    val = rtc_get_memory(rtc_state, REG_EQUIPMENT_BYTE);
+    val = mc146818rtc_get_cmos_data(rtc_state, REG_EQUIPMENT_BYTE);
     nb = 0;
     if (fd_type[0] != FLOPPY_DRIVE_TYPE_NONE) {
         nb++;
@@ -532,11 +538,11 @@ static void pc_cmos_init_floppy(ISADevice *rtc_state, ISADevice *floppy)
         val |= 0x41; /* 2 drives, ready for boot */
         break;
     }
-    rtc_set_memory(rtc_state, REG_EQUIPMENT_BYTE, val);
+    mc146818rtc_set_cmos_data(rtc_state, REG_EQUIPMENT_BYTE, val);
 }
 
 typedef struct pc_cmos_init_late_arg {
-    ISADevice *rtc_state;
+    MC146818RtcState *rtc_state;
     BusState *idebus[2];
 } pc_cmos_init_late_arg;
 
@@ -603,7 +609,7 @@ static ISADevice *pc_find_fdc0(void)
 static void pc_cmos_init_late(void *opaque)
 {
     pc_cmos_init_late_arg *arg = opaque;
-    ISADevice *s = arg->rtc_state;
+    MC146818RtcState *s = arg->rtc_state;
     int16_t cylinders;
     int8_t heads, sectors;
     int val;
@@ -620,7 +626,7 @@ static void pc_cmos_init_late(void *opaque)
         cmos_init_hd(s, 0x1a, 0x24, cylinders, heads, sectors);
         val |= 0x0f;
     }
-    rtc_set_memory(s, 0x12, val);
+    mc146818rtc_set_cmos_data(s, 0x12, val);
 
     val = 0;
     for (i = 0; i < 4; i++) {
@@ -636,7 +642,7 @@ static void pc_cmos_init_late(void *opaque)
             val |= trans << (i * 2);
         }
     }
-    rtc_set_memory(s, 0x39, val);
+    mc146818rtc_set_cmos_data(s, 0x39, val);
 
     pc_cmos_init_floppy(s, pc_find_fdc0());
 
@@ -645,19 +651,20 @@ static void pc_cmos_init_late(void *opaque)
 
 void pc_cmos_init(PCMachineState *pcms,
                   BusState *idebus0, BusState *idebus1,
-                  ISADevice *s)
+                  ISADevice *rtc)
 {
     int val;
     static pc_cmos_init_late_arg arg;
     X86MachineState *x86ms = X86_MACHINE(pcms);
+    MC146818RtcState *s = MC146818_RTC(rtc);
 
     /* various important CMOS locations needed by PC/Bochs bios */
 
     /* memory size */
     /* base memory (first MiB) */
     val = MIN(x86ms->below_4g_mem_size / KiB, 640);
-    rtc_set_memory(s, 0x15, val);
-    rtc_set_memory(s, 0x16, val >> 8);
+    mc146818rtc_set_cmos_data(s, 0x15, val);
+    mc146818rtc_set_cmos_data(s, 0x16, val >> 8);
     /* extended memory (next 64MiB) */
     if (x86ms->below_4g_mem_size > 1 * MiB) {
         val = (x86ms->below_4g_mem_size - 1 * MiB) / KiB;
@@ -666,10 +673,10 @@ void pc_cmos_init(PCMachineState *pcms,
     }
     if (val > 65535)
         val = 65535;
-    rtc_set_memory(s, 0x17, val);
-    rtc_set_memory(s, 0x18, val >> 8);
-    rtc_set_memory(s, 0x30, val);
-    rtc_set_memory(s, 0x31, val >> 8);
+    mc146818rtc_set_cmos_data(s, 0x17, val);
+    mc146818rtc_set_cmos_data(s, 0x18, val >> 8);
+    mc146818rtc_set_cmos_data(s, 0x30, val);
+    mc146818rtc_set_cmos_data(s, 0x31, val >> 8);
     /* memory between 16MiB and 4GiB */
     if (x86ms->below_4g_mem_size > 16 * MiB) {
         val = (x86ms->below_4g_mem_size - 16 * MiB) / (64 * KiB);
@@ -678,13 +685,13 @@ void pc_cmos_init(PCMachineState *pcms,
     }
     if (val > 65535)
         val = 65535;
-    rtc_set_memory(s, 0x34, val);
-    rtc_set_memory(s, 0x35, val >> 8);
+    mc146818rtc_set_cmos_data(s, 0x34, val);
+    mc146818rtc_set_cmos_data(s, 0x35, val >> 8);
     /* memory above 4GiB */
     val = x86ms->above_4g_mem_size / 65536;
-    rtc_set_memory(s, 0x5b, val);
-    rtc_set_memory(s, 0x5c, val >> 8);
-    rtc_set_memory(s, 0x5d, val >> 16);
+    mc146818rtc_set_cmos_data(s, 0x5b, val);
+    mc146818rtc_set_cmos_data(s, 0x5c, val >> 8);
+    mc146818rtc_set_cmos_data(s, 0x5d, val >> 16);
 
     object_property_add_link(OBJECT(pcms), "rtc_state",
                              TYPE_ISA_DEVICE,
@@ -699,7 +706,7 @@ void pc_cmos_init(PCMachineState *pcms,
     val = 0;
     val |= 0x02; /* FPU is there */
     val |= 0x04; /* PS/2 mouse installed */
-    rtc_set_memory(s, REG_EQUIPMENT_BYTE, val);
+    mc146818rtc_set_cmos_data(s, REG_EQUIPMENT_BYTE, val);
 
     /* hard drives and FDC */
     arg.rtc_state = s;
@@ -1296,14 +1303,23 @@ void pc_basic_device_init(struct PCMachineState *pcms,
         sysbus_realize_and_unref(SYS_BUS_DEVICE(hpet), &error_fatal);
         sysbus_mmio_map(SYS_BUS_DEVICE(hpet), 0, HPET_BASE);
 
-        for (i = 0; i < GSI_NUM_PINS; i++) {
+        for (i = 0; i < IOAPIC_NUM_PINS; i++) {
             sysbus_connect_irq(SYS_BUS_DEVICE(hpet), i, gsi[i]);
         }
         pit_isa_irq = -1;
         pit_alt_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_PIT_INT);
         rtc_irq = qdev_get_gpio_in(hpet, HPET_LEGACY_RTC_INT);
     }
-    *rtc_state = mc146818_rtc_init(isa_bus, 2000, rtc_irq);
+    *rtc_state = ISA_DEVICE(mc146818_rtc_init(isa_bus, 2000, rtc_irq));
+
+#ifdef CONFIG_XEN_EMU
+    if (xen_mode == XEN_EMULATE) {
+        xen_evtchn_connect_gsis(gsi);
+        if (pcms->bus) {
+            pci_create_simple(pcms->bus, -1, "xen-platform");
+        }
+    }
+#endif
 
     qemu_register_boot_set(pc_boot_set, *rtc_state);
 
@@ -1843,6 +1859,19 @@ static void pc_machine_initfn(Object *obj)
     cxl_machine_init(obj, &pcms->cxl_devices_state);
 }
 
+int pc_machine_kvm_type(MachineState *machine, const char *kvm_type)
+{
+#ifdef CONFIG_XEN_EMU
+    if (xen_mode == XEN_EMULATE) {
+        xen_overlay_create();
+        xen_evtchn_create();
+        xen_gnttab_create();
+        xen_xenstore_create();
+    }
+#endif
+    return 0;
+}
+
 static void pc_machine_reset(MachineState *machine, ShutdownCause reason)
 {
     CPUState *cs;