qapi: promote input-send-event to stable

With all fixups being in place now, we can promote input-send-event
to stable abi by removing the x- prefix.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>

MAINTAINERS

@@ -363,6 +363,7 @@ M: Dmitry Solodkiy <d.solodkiy@samsung.com>
 L: qemu-arm@nongnu.org
 S: Maintained
 F: hw/*/exynos*
+F: include/hw/arm/exynos4210.h
 
 Calxeda Highbank
 M: Rob Herring <robh@kernel.org>
@@ -390,6 +391,7 @@ L: qemu-arm@nongnu.org
 S: Odd fixes
 F: hw/*/imx*
 F: hw/arm/kzm.c
+F: include/hw/arm/fsl-imx31.h
 
 Integrator CP
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -432,6 +434,7 @@ F: hw/arm/spitz.c
 F: hw/arm/tosa.c
 F: hw/arm/z2.c
 F: hw/*/pxa2xx*
+F: include/hw/arm/pxa.h
 
 Stellaris
 M: Peter Maydell <peter.maydell@linaro.org>
@@ -768,6 +771,7 @@ OMAP
 M: Peter Maydell <peter.maydell@linaro.org>
 S: Maintained
 F: hw/*/omap*
+F: include/hw/arm/omap.h
 
 IPack
 M: Alberto Garcia <berto@igalia.com>
@@ -853,6 +857,10 @@ M: Gerd Hoffmann <kraxel@redhat.com>
 S: Maintained
 F: hw/usb/*
 F: tests/usb-*-test.c
+F: docs/usb2.txt
+F: docs/usb-storage.txt
+F: include/hw/usb.h
+F: include/hw/usb/
 
 USB (serial adapter)
 M: Gerd Hoffmann <kraxel@redhat.com>
@@ -1083,6 +1091,7 @@ SPICE
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Supported
 F: include/ui/qemu-spice.h
+F: include/ui/spice-display.h
 F: ui/spice-*.c
 F: audio/spiceaudio.c
 F: hw/display/qxl*
@@ -1091,6 +1100,7 @@ Graphics
 M: Gerd Hoffmann <kraxel@redhat.com>
 S: Odd Fixes
 F: ui/
+F: include/ui/
 
 Cocoa graphics
 M: Andreas Färber <andreas.faerber@web.de>
@@ -1241,6 +1251,7 @@ F: include/migration/
 F: migration/
 F: scripts/vmstate-static-checker.py
 F: tests/vmstate-static-checker-data/
+F: docs/migration.txt
 
 Seccomp
 M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
@@ -1283,6 +1294,15 @@ S: Maintained
 F: include/qemu/sockets.h
 F: util/qemu-sockets.c
 
+Throttling infrastructure
+M: Alberto Garcia <berto@igalia.com>
+S: Supported
+F: block/throttle-groups.c
+F: include/block/throttle-groups.h
+F: include/qemu/throttle.h
+F: util/throttle.c
+L: qemu-block@nongnu.org
+
 Usermode Emulation
 ------------------
 Overall

Makefile

@@ -391,7 +391,7 @@ bepo    cz
 ifdef INSTALL_BLOBS
 BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
 vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin vgabios-virtio.bin \
-acpi-dsdt.aml q35-acpi-dsdt.aml \
+acpi-dsdt.aml \
 ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
 pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
 pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \

audio/audio.h

@@ -24,7 +24,6 @@
 #ifndef QEMU_AUDIO_H
 #define QEMU_AUDIO_H
 
-#include "config-host.h"
 #include "qemu/queue.h"
 
 typedef void (*audio_callback_fn) (void *opaque, int avail);

block.c

@@ -1191,10 +1191,6 @@ static int bdrv_fill_options(QDict **options, const char *filename,
         }
     }
 
-    if (runstate_check(RUN_STATE_INMIGRATE)) {
-        *flags |= BDRV_O_INACTIVE;
-    }
-
     return 0;
 }
 

block/qapi.c

@@ -92,6 +92,26 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
         info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
         info->iops_wr_max     = cfg.buckets[THROTTLE_OPS_WRITE].max;
 
+        info->has_bps_max_length     = info->has_bps_max;
+        info->bps_max_length         =
+            cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
+        info->has_bps_rd_max_length  = info->has_bps_rd_max;
+        info->bps_rd_max_length      =
+            cfg.buckets[THROTTLE_BPS_READ].burst_length;
+        info->has_bps_wr_max_length  = info->has_bps_wr_max;
+        info->bps_wr_max_length      =
+            cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
+
+        info->has_iops_max_length    = info->has_iops_max;
+        info->iops_max_length        =
+            cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
+        info->has_iops_rd_max_length = info->has_iops_rd_max;
+        info->iops_rd_max_length     =
+            cfg.buckets[THROTTLE_OPS_READ].burst_length;
+        info->has_iops_wr_max_length = info->has_iops_wr_max;
+        info->iops_wr_max_length     =
+            cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
+
         info->has_iops_size = cfg.op_size;
         info->iops_size = cfg.op_size;
 

block/quorum.c

@@ -286,7 +286,8 @@ static void quorum_aio_cb(void *opaque, int ret)
 
     if (acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO) {
         /* We try to read next child in FIFO order if we fail to read */
-        if (ret < 0 && ++acb->child_iter < s->num_children) {
+        if (ret < 0 && (acb->child_iter + 1) < s->num_children) {
+            acb->child_iter++;
             read_fifo_child(acb);
             return;
         }

blockdev.c

@@ -343,29 +343,6 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
     return true;
 }
 
-static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
-{
-    if (throttle_conflicting(cfg)) {
-        error_setg(errp, "bps/iops/max total values and read/write values"
-                         " cannot be used at the same time");
-        return false;
-    }
-
-    if (!throttle_is_valid(cfg)) {
-        error_setg(errp, "bps/iops/max values must be within [0, %lld]",
-                   THROTTLE_VALUE_MAX);
-        return false;
-    }
-
-    if (throttle_max_is_missing_limit(cfg)) {
-        error_setg(errp, "bps_max/iops_max require corresponding"
-                         " bps/iops values");
-        return false;
-    }
-
-    return true;
-}
-
 typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
 
 /* All parameters but @opts are optional and may be set to NULL. */
@@ -410,7 +387,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
     }
 
     if (throttle_cfg) {
-        memset(throttle_cfg, 0, sizeof(*throttle_cfg));
+        throttle_config_init(throttle_cfg);
         throttle_cfg->buckets[THROTTLE_BPS_TOTAL].avg =
             qemu_opt_get_number(opts, "throttling.bps-total", 0);
         throttle_cfg->buckets[THROTTLE_BPS_READ].avg  =
@@ -437,10 +414,23 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
         throttle_cfg->buckets[THROTTLE_OPS_WRITE].max =
             qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
 
+        throttle_cfg->buckets[THROTTLE_BPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_READ].burst_length  =
+            qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_BPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_TOTAL].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_READ].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
+        throttle_cfg->buckets[THROTTLE_OPS_WRITE].burst_length =
+            qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
+
         throttle_cfg->op_size =
             qemu_opt_get_number(opts, "throttling.iops-size", 0);
 
-        if (!check_throttle_config(throttle_cfg, errp)) {
+        if (!throttle_is_valid(throttle_cfg, errp)) {
             return;
         }
     }
@@ -610,6 +600,10 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
             qdict_put(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, qstring_from_str("on"));
         }
 
+        if (runstate_check(RUN_STATE_INMIGRATE)) {
+            bdrv_flags |= BDRV_O_INACTIVE;
+        }
+
         blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
                            errp);
         if (!blk) {
@@ -688,6 +682,10 @@ static BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
         goto fail;
     }
 
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        bdrv_flags |= BDRV_O_INACTIVE;
+    }
+
     bs = NULL;
     ret = bdrv_open(&bs, NULL, NULL, bs_opts, bdrv_flags, errp);
     if (ret < 0) {
@@ -2515,6 +2513,8 @@ void qmp_blockdev_change_medium(const char *device, const char *filename,
     }
 
     bdrv_flags = blk_get_open_flags_from_root_state(blk);
+    bdrv_flags &= ~(BDRV_O_TEMPORARY | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING |
+        BDRV_O_PROTOCOL);
 
     if (!has_read_only) {
         read_only = BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN;
@@ -2600,6 +2600,18 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
                                int64_t iops_rd_max,
                                bool has_iops_wr_max,
                                int64_t iops_wr_max,
+                               bool has_bps_max_length,
+                               int64_t bps_max_length,
+                               bool has_bps_rd_max_length,
+                               int64_t bps_rd_max_length,
+                               bool has_bps_wr_max_length,
+                               int64_t bps_wr_max_length,
+                               bool has_iops_max_length,
+                               int64_t iops_max_length,
+                               bool has_iops_rd_max_length,
+                               int64_t iops_rd_max_length,
+                               bool has_iops_wr_max_length,
+                               int64_t iops_wr_max_length,
                                bool has_iops_size,
                                int64_t iops_size,
                                bool has_group,
@@ -2626,7 +2638,7 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         goto out;
     }
 
-    memset(&cfg, 0, sizeof(cfg));
+    throttle_config_init(&cfg);
     cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps;
     cfg.buckets[THROTTLE_BPS_READ].avg  = bps_rd;
     cfg.buckets[THROTTLE_BPS_WRITE].avg = bps_wr;
@@ -2654,11 +2666,30 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
         cfg.buckets[THROTTLE_OPS_WRITE].max = iops_wr_max;
     }
 
+    if (has_bps_max_length) {
+        cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = bps_max_length;
+    }
+    if (has_bps_rd_max_length) {
+        cfg.buckets[THROTTLE_BPS_READ].burst_length = bps_rd_max_length;
+    }
+    if (has_bps_wr_max_length) {
+        cfg.buckets[THROTTLE_BPS_WRITE].burst_length = bps_wr_max_length;
+    }
+    if (has_iops_max_length) {
+        cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = iops_max_length;
+    }
+    if (has_iops_rd_max_length) {
+        cfg.buckets[THROTTLE_OPS_READ].burst_length = iops_rd_max_length;
+    }
+    if (has_iops_wr_max_length) {
+        cfg.buckets[THROTTLE_OPS_WRITE].burst_length = iops_wr_max_length;
+    }
+
     if (has_iops_size) {
         cfg.op_size = iops_size;
     }
 
-    if (!check_throttle_config(&cfg, errp)) {
+    if (!throttle_is_valid(&cfg, errp)) {
         goto out;
     }
 
@@ -4086,6 +4117,30 @@ QemuOptsList qemu_common_drive_opts = {
             .name = "throttling.bps-write-max",
             .type = QEMU_OPT_NUMBER,
             .help = "total bytes write burst",
+        },{
+            .name = "throttling.iops-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-total-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-read-max burst period, in seconds",
+        },{
+            .name = "throttling.iops-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-write-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-total-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-read-max burst period, in seconds",
+        },{
+            .name = "throttling.bps-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-write-max burst period, in seconds",
         },{
             .name = "throttling.iops-size",
             .type = QEMU_OPT_NUMBER,

bsd-user/i386/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 /* default linux values for the selectors */
 #define __USER_CS	(0x23)
 #define __USER_DS	(0x2B)
@@ -159,3 +162,4 @@ struct target_vm86plus_struct {
 
 #define UNAME_MACHINE "i386"
 
+#endif  /* TARGET_SYSCALL_H */

bsd-user/qemu.h

@@ -17,15 +17,12 @@
 #ifndef QEMU_H
 #define QEMU_H
 
-#include <signal.h>
-#include <string.h>
 
 #include "cpu.h"
 #include "exec/cpu_ldst.h"
 
 #undef DEBUG_REMAP
 #ifdef DEBUG_REMAP
-#include <stdlib.h>
 #endif /* DEBUG_REMAP */
 
 #include "exec/user/abitypes.h"
@@ -38,7 +35,7 @@ enum BSDType {
 extern enum BSDType bsd_type;
 
 #include "syscall_defs.h"
-#include "syscall.h"
+#include "target_syscall.h"
 #include "target_signal.h"
 #include "exec/gdbstub.h"
 

bsd-user/sparc/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 struct target_pt_regs {
 	abi_ulong psr;
 	abi_ulong pc;
@@ -7,3 +10,5 @@ struct target_pt_regs {
 };
 
 #define UNAME_MACHINE "sun4"
+
+#endif  /* TARGET_SYSCALL_H */

bsd-user/sparc64/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 struct target_pt_regs {
 	abi_ulong u_regs[16];
 	abi_ulong tstate;
@@ -8,3 +11,5 @@ struct target_pt_regs {
 };
 
 #define UNAME_MACHINE "sun4u"
+
+#endif  /* TARGET_SYSCALL_H */

bsd-user/x86_64/target_syscall.h

@@ -1,3 +1,6 @@
+#ifndef TARGET_SYSCALL_H
+#define TARGET_SYSCALL_H
+
 #define __USER_CS	(0x33)
 #define __USER_DS	(0x2B)
 
@@ -114,3 +117,5 @@ struct target_msqid64_ds {
 #define TARGET_ARCH_SET_FS 0x1002
 #define TARGET_ARCH_GET_FS 0x1003
 #define TARGET_ARCH_GET_GS 0x1004
+
+#endif  /* TARGET_SYSCALL_H */

configure

@@ -279,6 +279,7 @@ smartcard=""
 libusb=""
 usb_redir=""
 opengl=""
+opengl_dmabuf="no"
 zlib="yes"
 lzo=""
 snappy=""
@@ -3274,7 +3275,7 @@ libs_softmmu="$libs_softmmu $fdt_libs"
 # opengl probe (for sdl2, gtk, milkymist-tmu2)
 
 if test "$opengl" != "no" ; then
-  opengl_pkgs="epoxy"
+  opengl_pkgs="epoxy libdrm gbm"
   if $pkg_config $opengl_pkgs x11; then
     opengl_cflags="$($pkg_config --cflags $opengl_pkgs) $x11_cflags"
     opengl_libs="$($pkg_config --libs $opengl_pkgs) $x11_libs"
@@ -3292,6 +3293,18 @@ if test "$opengl" != "no" ; then
   fi
 fi
 
+if test "$opengl" = "yes"; then
+  cat > $TMPC << EOF
+#include <epoxy/egl.h>
+#ifndef EGL_MESA_image_dma_buf_export
+# error mesa/epoxy lacks support for dmabufs (mesa 10.6+)
+#endif
+int main(void) { return 0; }
+EOF
+  if compile_prog "" "" ; then
+    opengl_dmabuf=yes
+  fi
+fi
 
 ##########################################
 # archipelago probe
@@ -4752,6 +4765,7 @@ echo "smartcard support $smartcard"
 echo "libusb            $libusb"
 echo "usb net redir     $usb_redir"
 echo "OpenGL support    $opengl"
+echo "OpenGL dmabufs    $opengl_dmabuf"
 echo "libiscsi support  $libiscsi"
 echo "libnfs support    $libnfs"
 echo "build guest agent $guest_agent"
@@ -5050,6 +5064,7 @@ if test "$gtk" = "yes" ; then
   echo "CONFIG_GTK=y" >> $config_host_mak
   echo "CONFIG_GTKABI=$gtkabi" >> $config_host_mak
   echo "GTK_CFLAGS=$gtk_cflags" >> $config_host_mak
+  echo "GTK_LIBS=$gtk_libs" >> $config_host_mak
   if test "$gtk_gl" = "yes" ; then
     echo "CONFIG_GTK_GL=y" >> $config_host_mak
   fi
@@ -5158,6 +5173,9 @@ if test "$opengl" = "yes" ; then
   echo "CONFIG_OPENGL=y" >> $config_host_mak
   echo "OPENGL_CFLAGS=$opengl_cflags" >> $config_host_mak
   echo "OPENGL_LIBS=$opengl_libs" >> $config_host_mak
+  if test "$opengl_dmabuf" = "yes" ; then
+    echo "CONFIG_OPENGL_DMABUF=y" >> $config_host_mak
+  fi
 fi
 
 if test "$lzo" = "yes" ; then

contrib/ivshmem-client/ivshmem-client.h

@@ -19,7 +19,6 @@
  * purposes.
  */
 
-#include <limits.h>
 #include <sys/select.h>
 
 #include "qemu/queue.h"

contrib/ivshmem-server/ivshmem-server.h

@@ -26,10 +26,7 @@
  * associated to the ivshmem shared memory.
  */
 
-#include <limits.h>
 #include <sys/select.h>
-#include <stdint.h>
-#include <stdbool.h>
 
 #include "qemu/event_notifier.h"
 #include "qemu/queue.h"

disas/arm-a64.cc

@@ -17,12 +17,13 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include "vixl/a64/disasm-a64.h"
-
 extern "C" {
+#include "qemu/osdep.h"
 #include "disas/bfd.h"
 }
 
+#include "vixl/a64/disasm-a64.h"
+
 using namespace vixl;
 
 static Decoder *vixl_decoder = NULL;

disas/mips.c

@@ -1405,6 +1405,10 @@ const struct mips_opcode mips_builtin_opcodes[] =
 {"cmp.sor.d",  "D,S,T", 0x46a00019, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
 {"cmp.sune.d", "D,S,T", 0x46a0001a, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
 {"cmp.sne.d",  "D,S,T", 0x46a0001b, 0xffe0003f, RD_S|RD_T|WR_D|FP_D,  0, I32R6},
+{"dvp",        "",      0x41600024, 0xffffffff, TRAP,                 0, I32R6},
+{"dvp",        "t",     0x41600024, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
+{"evp",        "",      0x41600004, 0xffffffff, TRAP,                 0, I32R6},
+{"evp",        "t",     0x41600004, 0xffe0ffff, TRAP|WR_t,            0, I32R6},
 
 /* MSA */
 {"sll.b",   "+d,+e,+f", 0x7800000d, 0xffe0003f, WR_VD|RD_VS|RD_VT,  0, MSA},

docs/qmp-events.txt

@@ -220,6 +220,24 @@ Data:
   },
   "timestamp": { "seconds": 1265044230, "microseconds": 450486 } }
 
+DUMP_COMPLETED
+--------------
+
+Emitted when the guest has finished one memory dump.
+
+Data:
+
+- "result": DumpQueryResult type described in qapi-schema.json
+- "error": Error message when dump failed. This is only a
+  human-readable string provided when dump failed. It should not be
+  parsed in any way (json-string, optional)
+
+Example:
+
+{ "event": "DUMP_COMPLETED",
+  "data": {"result": {"total": 1090650112, "status": "completed",
+                      "completed": 1090650112} } }
+
 GUEST_PANICKED
 --------------
 

docs/specs/qcow2.txt

@@ -103,7 +103,18 @@ in the description of a field.
                     write to an image with unknown auto-clear features if it
                     clears the respective bits from this field first.
 
-                    Bits 0-63:  Reserved (set to 0)
+                    Bit 0:      Bitmaps extension bit
+                                This bit indicates consistency for the bitmaps
+                                extension data.
+
+                                It is an error if this bit is set without the
+                                bitmaps extension present.
+
+                                If the bitmaps extension is present but this
+                                bit is unset, the bitmaps extension data must be
+                                considered inconsistent.
+
+                    Bits 1-63:  Reserved (set to 0)
 
          96 -  99:  refcount_order
                     Describes the width of a reference count block entry (width
@@ -123,6 +134,7 @@ be stored. Each extension has a structure like the following:
                         0x00000000 - End of the header extension area
                         0xE2792ACA - Backing file format name
                         0x6803f857 - Feature name table
+                        0x23852875 - Bitmaps extension
                         other      - Unknown header extension, can be safely
                                      ignored
 
@@ -166,6 +178,36 @@ the header extension data. Each entry look like this:
                     terminated if it has full length)
 
 
+== Bitmaps extension ==
+
+The bitmaps extension is an optional header extension. It provides the ability
+to store bitmaps related to a virtual disk. For now, there is only one bitmap
+type: the dirty tracking bitmap, which tracks virtual disk changes from some
+point in time.
+
+The data of the extension should be considered consistent only if the
+corresponding auto-clear feature bit is set, see autoclear_features above.
+
+The fields of the bitmaps extension are:
+
+    Byte  0 -  3:  nb_bitmaps
+                   The number of bitmaps contained in the image. Must be
+                   greater than or equal to 1.
+
+                   Note: Qemu currently only supports up to 65535 bitmaps per
+                   image.
+
+          4 -  7:  Reserved, must be zero.
+
+          8 - 15:  bitmap_directory_size
+                   Size of the bitmap directory in bytes. It is the cumulative
+                   size of all (nb_bitmaps) bitmap headers.
+
+         16 - 23:  bitmap_directory_offset
+                   Offset into the image file at which the bitmap directory
+                   starts. Must be aligned to a cluster boundary.
+
+
 == Host cluster management ==
 
 qcow2 manages the allocation of host clusters by maintaining a reference count
@@ -360,3 +402,180 @@ Snapshot table entry:
 
         variable:   Padding to round up the snapshot table entry size to the
                     next multiple of 8.
+
+
+== Bitmaps ==
+
+As mentioned above, the bitmaps extension provides the ability to store bitmaps
+related to a virtual disk. This section describes how these bitmaps are stored.
+
+All stored bitmaps are related to the virtual disk stored in the same image, so
+each bitmap size is equal to the virtual disk size.
+
+Each bit of the bitmap is responsible for strictly defined range of the virtual
+disk. For bit number bit_nr the corresponding range (in bytes) will be:
+
+    [bit_nr * bitmap_granularity .. (bit_nr + 1) * bitmap_granularity - 1]
+
+Granularity is a property of the concrete bitmap, see below.
+
+
+=== Bitmap directory ===
+
+Each bitmap saved in the image is described in a bitmap directory entry. The
+bitmap directory is a contiguous area in the image file, whose starting offset
+and length are given by the header extension fields bitmap_directory_offset and
+bitmap_directory_size. The entries of the bitmap directory have variable
+length, depending on the lengths of the bitmap name and extra data. These
+entries are also called bitmap headers.
+
+Structure of a bitmap directory entry:
+
+    Byte 0 -  7:    bitmap_table_offset
+                    Offset into the image file at which the bitmap table
+                    (described below) for the bitmap starts. Must be aligned to
+                    a cluster boundary.
+
+         8 - 11:    bitmap_table_size
+                    Number of entries in the bitmap table of the bitmap.
+
+        12 - 15:    flags
+                    Bit
+                      0: in_use
+                         The bitmap was not saved correctly and may be
+                         inconsistent.
+
+                      1: auto
+                         The bitmap must reflect all changes of the virtual
+                         disk by any application that would write to this qcow2
+                         file (including writes, snapshot switching, etc.). The
+                         type of this bitmap must be 'dirty tracking bitmap'.
+
+                      2: extra_data_compatible
+                         This flags is meaningful when the extra data is
+                         unknown to the software (currently any extra data is
+                         unknown to Qemu).
+                         If it is set, the bitmap may be used as expected, extra
+                         data must be left as is.
+                         If it is not set, the bitmap must not be used, but
+                         both it and its extra data be left as is.
+
+                    Bits 3 - 31 are reserved and must be 0.
+
+             16:    type
+                    This field describes the sort of the bitmap.
+                    Values:
+                      1: Dirty tracking bitmap
+
+                    Values 0, 2 - 255 are reserved.
+
+             17:    granularity_bits
+                    Granularity bits. Valid values: 0 - 63.
+
+                    Note: Qemu currently doesn't support granularity_bits
+                    greater than 31.
+
+                    Granularity is calculated as
+                        granularity = 1 << granularity_bits
+
+                    A bitmap's granularity is how many bytes of the image
+                    accounts for one bit of the bitmap.
+
+        18 - 19:    name_size
+                    Size of the bitmap name. Must be non-zero.
+
+                    Note: Qemu currently doesn't support values greater than
+                    1023.
+
+        20 - 23:    extra_data_size
+                    Size of type-specific extra data.
+
+                    For now, as no extra data is defined, extra_data_size is
+                    reserved and should be zero. If it is non-zero the
+                    behavior is defined by extra_data_compatible flag.
+
+        variable:   extra_data
+                    Extra data for the bitmap, occupying extra_data_size bytes.
+                    Extra data must never contain references to clusters or in
+                    some other way allocate additional clusters.
+
+        variable:   name
+                    The name of the bitmap (not null terminated), occupying
+                    name_size bytes. Must be unique among all bitmap names
+                    within the bitmaps extension.
+
+        variable:   Padding to round up the bitmap directory entry size to the
+                    next multiple of 8. All bytes of the padding must be zero.
+
+
+=== Bitmap table ===
+
+Each bitmap is stored using a one-level structure (as opposed to two-level
+structures like for refcounts and guest clusters mapping) for the mapping of
+bitmap data to host clusters. This structure is called the bitmap table.
+
+Each bitmap table has a variable size (stored in the bitmap directory entry)
+and may use multiple clusters, however, it must be contiguous in the image
+file.
+
+Structure of a bitmap table entry:
+
+    Bit       0:    Reserved and must be zero if bits 9 - 55 are non-zero.
+                    If bits 9 - 55 are zero:
+                      0: Cluster should be read as all zeros.
+                      1: Cluster should be read as all ones.
+
+         1 -  8:    Reserved and must be zero.
+
+         9 - 55:    Bits 9 - 55 of the host cluster offset. Must be aligned to
+                    a cluster boundary. If the offset is 0, the cluster is
+                    unallocated; in that case, bit 0 determines how this
+                    cluster should be treated during reads.
+
+        56 - 63:    Reserved and must be zero.
+
+
+=== Bitmap data ===
+
+As noted above, bitmap data is stored in separate clusters, described by the
+bitmap table. Given an offset (in bytes) into the bitmap data, the offset into
+the image file can be obtained as follows:
+
+    image_offset(bitmap_data_offset) =
+        bitmap_table[bitmap_data_offset / cluster_size] +
+            (bitmap_data_offset % cluster_size)
+
+This offset is not defined if bits 9 - 55 of bitmap table entry are zero (see
+above).
+
+Given an offset byte_nr into the virtual disk and the bitmap's granularity, the
+bit offset into the image file to the corresponding bit of the bitmap can be
+calculated like this:
+
+    bit_offset(byte_nr) =
+        image_offset(byte_nr / granularity / 8) * 8 +
+            (byte_nr / granularity) % 8
+
+If the size of the bitmap data is not a multiple of the cluster size then the
+last cluster of the bitmap data contains some unused tail bits. These bits must
+be zero.
+
+
+=== Dirty tracking bitmaps ===
+
+Bitmaps with 'type' field equal to one are dirty tracking bitmaps.
+
+When the virtual disk is in use dirty tracking bitmap may be 'enabled' or
+'disabled'. While the bitmap is 'enabled', all writes to the virtual disk
+should be reflected in the bitmap. A set bit in the bitmap means that the
+corresponding range of the virtual disk (see above) was written to while the
+bitmap was 'enabled'. An unset bit means that this range was not written to.
+
+The software doesn't have to sync the bitmap in the image file with its
+representation in RAM after each write. Flag 'in_use' should be set while the
+bitmap is not synced.
+
+In the image file the 'enabled' state is reflected by the 'auto' flag. If this
+flag is set, the software must consider the bitmap as 'enabled' and start
+tracking virtual disk changes to this bitmap from the first write to the
+virtual disk. If this flag is not set then the bitmap is disabled.

docs/throttle.txt

@@ -0,0 +1,252 @@
+The QEMU throttling infrastructure
+==================================
+Copyright (C) 2016 Igalia, S.L.
+Author: Alberto Garcia <berto@igalia.com>
+
+This work is licensed under the terms of the GNU GPL, version 2 or
+later. See the COPYING file in the top-level directory.
+
+Introduction
+------------
+QEMU includes a throttling module that can be used to set limits to
+I/O operations. The code itself is generic and independent of the I/O
+units, but it is currenly used to limit the number of bytes per second
+and operations per second (IOPS) when performing disk I/O.
+
+This document explains how to use the throttling code in QEMU, and how
+it works internally. The implementation is in throttle.c.
+
+
+Using throttling to limit disk I/O
+----------------------------------
+Two aspects of the disk I/O can be limited: the number of bytes per
+second and the number of operations per second (IOPS). For each one of
+them the user can set a global limit or separate limits for read and
+write operations. This gives us a total of six different parameters.
+
+I/O limits can be set using the throttling.* parameters of -drive, or
+using the QMP 'block_set_io_throttle' command. These are the names of
+the parameters for both cases:
+
+|-----------------------+-----------------------|
+| -drive                | block_set_io_throttle |
+|-----------------------+-----------------------|
+| throttling.iops-total | iops                  |
+| throttling.iops-read  | iops_rd               |
+| throttling.iops-write | iops_wr               |
+| throttling.bps-total  | bps                   |
+| throttling.bps-read   | bps_rd                |
+| throttling.bps-write  | bps_wr                |
+|-----------------------+-----------------------|
+
+It is possible to set limits for both IOPS and bps and the same time,
+and for each case we can decide whether to have separate read and
+write limits or not, but note that if iops-total is set then neither
+iops-read nor iops-write can be set. The same applies to bps-total and
+bps-read/write.
+
+The default value of these parameters is 0, and it means 'unlimited'.
+
+In its most basic usage, the user can add a drive to QEMU with a limit
+of 100 IOPS with the following -drive line:
+
+   -drive file=hd0.qcow2,throttling.iops-total=100
+
+We can do the same using QMP. In this case all these parameters are
+mandatory, so we must set to 0 the ones that we don't want to limit:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0
+     }
+   }
+
+
+I/O bursts
+----------
+In addition to the basic limits we have just seen, QEMU allows the
+user to do bursts of I/O for a configurable amount of time. A burst is
+an amount of I/O that can exceed the basic limit. Bursts are useful to
+allow better performance when there are peaks of activity (the OS
+boots, a service needs to be restarted) while keeping the average
+limits lower the rest of the time.
+
+Two parameters control bursts: their length and the maximum amount of
+I/O they allow. These two can be configured separately for each one of
+the six basic parameters described in the previous section, but in
+this section we'll use 'iops-total' as an example.
+
+The I/O limit during bursts is set using 'iops-total-max', and the
+maximum length (in seconds) is set with 'iops-total-max-length'. So if
+we want to configure a drive with a basic limit of 100 IOPS and allow
+bursts of 2000 IOPS for 60 seconds, we would do it like this (the line
+is split for clarity):
+
+   -drive file=hd0.qcow2,
+          throttling.iops-total=100,
+          throttling.iops-total-max=2000,
+          throttling.iops-total-max-length=60
+
+Or, with QMP:
+
+   { "execute": "block_set_io_throttle",
+     "arguments": {
+        "device": "virtio0",
+        "iops": 100,
+        "iops_rd": 0,
+        "iops_wr": 0,
+        "bps": 0,
+        "bps_rd": 0,
+        "bps_wr": 0,
+        "iops_max": 2000,
+        "iops_max_length": 60,
+     }
+   }
+
+With this, the user can perform I/O on hd0.qcow2 at a rate of 2000
+IOPS for 1 minute before it's throttled down to 100 IOPS.
+
+The user will be able to do bursts again if there's a sufficiently
+long period of time with unused I/O (see below for details).
+
+The default value for 'iops-total-max' is 0 and it means that bursts
+are not allowed. 'iops-total-max-length' can only be set if
+'iops-total-max' is set as well, and its default value is 1 second.
+
+Here's the complete list of parameters for configuring bursts:
+
+|----------------------------------+-----------------------|
+| -drive                           | block_set_io_throttle |
+|----------------------------------+-----------------------|
+| throttling.iops-total-max        | iops_max              |
+| throttling.iops-total-max-length | iops_max_length       |
+| throttling.iops-read-max         | iops_rd_max           |
+| throttling.iops-read-max-length  | iops_rd_max_length    |
+| throttling.iops-write-max        | iops_wr_max           |
+| throttling.iops-write-max-length | iops_wr_max_length    |
+| throttling.bps-total-max         | bps_max               |
+| throttling.bps-total-max-length  | bps_max_length        |
+| throttling.bps-read-max          | bps_rd_max            |
+| throttling.bps-read-max-length   | bps_rd_max_length     |
+| throttling.bps-write-max         | bps_wr_max            |
+| throttling.bps-write-max-length  | bps_wr_max_length     |
+|----------------------------------+-----------------------|
+
+
+Controlling the size of I/O operations
+--------------------------------------
+When applying IOPS limits all I/O operations are treated equally
+regardless of their size. This means that the user can take advantage
+of this in order to circumvent the limits and submit one huge I/O
+request instead of several smaller ones.
+
+QEMU provides a setting called throttling.iops-size to prevent this
+from happening. This setting specifies the size (in bytes) of an I/O
+request for accounting purposes. Larger requests will be counted
+proportionally to this size.
+
+For example, if iops-size is set to 4096 then an 8KB request will be
+counted as two, and a 6KB request will be counted as one and a
+half. This only applies to requests larger than iops-size: smaller
+requests will be always counted as one, no matter their size.
+
+The default value of iops-size is 0 and it means that the size of the
+requests is never taken into account when applying IOPS limits.
+
+
+Applying I/O limits to groups of disks
+--------------------------------------
+In all the examples so far we have seen how to apply limits to the I/O
+performed on individual drives, but QEMU allows grouping drives so
+they all share the same limits.
+
+The way it works is that each drive with I/O limits is assigned to a
+group named using the throttling.group parameter. If this parameter is
+not specified, then the device name (i.e. 'virtio0', 'ide0-hd0') will
+be used as the group name.
+
+Limits set using the throttling.* parameters discussed earlier in this
+document apply to the combined I/O of all members of a group.
+
+Consider this example:
+
+   -drive file=hd1.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd2.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd3.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd4.qcow2,throttling.iops-total=6000,throttling.group=foo
+   -drive file=hd5.qcow2,throttling.iops-total=3000,throttling.group=bar
+   -drive file=hd6.qcow2,throttling.iops-total=5000
+
+Here hd1, hd2 and hd4 are all members of a group named 'foo' with a
+combined IOPS limit of 6000, and hd3 and hd5 are members of 'bar'. hd6
+is left alone (technically it is part of a 1-member group).
+
+Limits are applied in a round-robin fashion so if there are concurrent
+I/O requests on several drives of the same group they will be
+distributed evenly.
+
+When I/O limits are applied to an existing drive using the QMP command
+'block_set_io_throttle', the following things need to be taken into
+account:
+
+   - I/O limits are shared within the same group, so new values will
+     affect all members and overwrite the previous settings. In other
+     words: if different limits are applied to members of the same
+     group, the last one wins.
+
+   - If 'group' is unset it is assumed to be the current group of that
+     drive. If the drive is not in a group yet, it will be added to a
+     group named after the device name.
+
+   - If 'group' is set then the drive will be moved to that group if
+     it was member of a different one. In this case the limits
+     specified in the parameters will be applied to the new group
+     only.
+
+   - I/O limits can be disabled by setting all of them to 0. In this
+     case the device will be removed from its group and the rest of
+     its members will not be affected. The 'group' parameter is
+     ignored.
+
+
+The Leaky Bucket algorithm
+--------------------------
+I/O limits in QEMU are implemented using the leaky bucket algorithm
+(specifically the "Leaky bucket as a meter" variant).
+
+This algorithm uses the analogy of a bucket that leaks water
+constantly. The water that gets into the bucket represents the I/O
+that has been performed, and no more I/O is allowed once the bucket is
+full.
+
+To see the way this corresponds to the throttling parameters in QEMU,
+consider the following values:
+
+  iops-total=100
+  iops-total-max=2000
+  iops-total-max-length=60
+
+  - Water leaks from the bucket at a rate of 100 IOPS.
+  - Water can be added to the bucket at a rate of 2000 IOPS.
+  - The size of the bucket is 2000 x 60 = 120000
+  - If 'iops-total-max-length' is unset then the bucket size is 100.
+
+The bucket is initially empty, therefore water can be added until it's
+full at a rate of 2000 IOPS (the burst rate). Once the bucket is full
+we can only add as much water as it leaks, therefore the I/O rate is
+reduced to 100 IOPS. If we add less water than it leaks then the
+bucket will start to empty, allowing for bursts again.
+
+Note that since water is leaking from the bucket even during bursts,
+it will take a bit more than 60 seconds at 2000 IOPS to fill it
+up. After those 60 seconds the bucket will have leaked 60 x 100 =
+6000, allowing for 3 more seconds of I/O at 2000 IOPS.
+
+Also, due to the way the algorithm works, longer burst can be done at
+a lower I/O rate, e.g. 1000 IOPS during 120 seconds.

dump.c

@@ -25,6 +25,7 @@
 #include "sysemu/cpus.h"
 #include "qapi/qmp/qerror.h"
 #include "qmp-commands.h"
+#include "qapi-event.h"
 
 #include <zlib.h>
 #ifdef CONFIG_LZO
@@ -82,12 +83,6 @@ static int dump_cleanup(DumpState *s)
     return 0;
 }
 
-static void dump_error(DumpState *s, const char *reason, Error **errp)
-{
-    dump_cleanup(s);
-    error_setg(errp, "%s", reason);
-}
-
 static int fd_write_vmcore(const void *buf, size_t size, void *opaque)
 {
     DumpState *s = opaque;
@@ -128,7 +123,7 @@ static void write_elf64_header(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write elf header", errp);
+        error_setg(errp, "dump: failed to write elf header");
     }
 }
 
@@ -159,7 +154,7 @@ static void write_elf32_header(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&elf_header, sizeof(elf_header), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write elf header", errp);
+        error_setg(errp, "dump: failed to write elf header");
     }
 }
 
@@ -182,7 +177,7 @@ static void write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -205,7 +200,7 @@ static void write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -225,7 +220,7 @@ static void write_elf64_note(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -245,7 +240,7 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
         id = cpu_index(cpu);
         ret = cpu_write_elf64_note(f, cpu, id, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write elf notes", errp);
+            error_setg(errp, "dump: failed to write elf notes");
             return;
         }
     }
@@ -253,7 +248,7 @@ static void write_elf64_notes(WriteCoreDumpFunction f, DumpState *s,
     CPU_FOREACH(cpu) {
         ret = cpu_write_elf64_qemunote(f, cpu, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write CPU status", errp);
+            error_setg(errp, "dump: failed to write CPU status");
             return;
         }
     }
@@ -275,7 +270,7 @@ static void write_elf32_note(DumpState *s, Error **errp)
 
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write program header table", errp);
+        error_setg(errp, "dump: failed to write program header table");
     }
 }
 
@@ -290,7 +285,7 @@ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
         id = cpu_index(cpu);
         ret = cpu_write_elf32_note(f, cpu, id, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write elf notes", errp);
+            error_setg(errp, "dump: failed to write elf notes");
             return;
         }
     }
@@ -298,7 +293,7 @@ static void write_elf32_notes(WriteCoreDumpFunction f, DumpState *s,
     CPU_FOREACH(cpu) {
         ret = cpu_write_elf32_qemunote(f, cpu, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to write CPU status", errp);
+            error_setg(errp, "dump: failed to write CPU status");
             return;
         }
     }
@@ -326,7 +321,7 @@ static void write_elf_section(DumpState *s, int type, Error **errp)
 
     ret = fd_write_vmcore(&shdr, shdr_size, s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write section header table", errp);
+        error_setg(errp, "dump: failed to write section header table");
     }
 }
 
@@ -336,7 +331,9 @@ static void write_data(DumpState *s, void *buf, int length, Error **errp)
 
     ret = fd_write_vmcore(buf, length, s);
     if (ret < 0) {
-        dump_error(s, "dump: failed to save memory", errp);
+        error_setg(errp, "dump: failed to save memory");
+    } else {
+        s->written_size += length;
     }
 }
 
@@ -568,11 +565,6 @@ static void dump_begin(DumpState *s, Error **errp)
     }
 }
 
-static void dump_completed(DumpState *s)
-{
-    dump_cleanup(s);
-}
-
 static int get_next_block(DumpState *s, GuestPhysBlock *block)
 {
     while (1) {
@@ -624,8 +616,6 @@ static void dump_iterate(DumpState *s, Error **errp)
         }
 
     } while (!get_next_block(s, block));
-
-    dump_completed(s);
 }
 
 static void create_vmcore(DumpState *s, Error **errp)
@@ -765,7 +755,7 @@ static void create_header32(DumpState *s, Error **errp)
     dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
-        dump_error(s, "dump: failed to write disk dump header", errp);
+        error_setg(errp, "dump: failed to write disk dump header");
         goto out;
     }
 
@@ -784,7 +774,7 @@ static void create_header32(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
-        dump_error(s, "dump: failed to write kdump sub header", errp);
+        error_setg(errp, "dump: failed to write kdump sub header");
         goto out;
     }
 
@@ -800,7 +790,7 @@ static void create_header32(DumpState *s, Error **errp)
     }
     if (write_buffer(s->fd, offset_note, s->note_buf,
                      s->note_size) < 0) {
-        dump_error(s, "dump: failed to write notes", errp);
+        error_setg(errp, "dump: failed to write notes");
         goto out;
     }
 
@@ -865,7 +855,7 @@ static void create_header64(DumpState *s, Error **errp)
     dh->status = cpu_to_dump32(s, status);
 
     if (write_buffer(s->fd, 0, dh, size) < 0) {
-        dump_error(s, "dump: failed to write disk dump header", errp);
+        error_setg(errp, "dump: failed to write disk dump header");
         goto out;
     }
 
@@ -884,7 +874,7 @@ static void create_header64(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, DISKDUMP_HEADER_BLOCKS *
                      block_size, kh, size) < 0) {
-        dump_error(s, "dump: failed to write kdump sub header", errp);
+        error_setg(errp, "dump: failed to write kdump sub header");
         goto out;
     }
 
@@ -901,7 +891,7 @@ static void create_header64(DumpState *s, Error **errp)
 
     if (write_buffer(s->fd, offset_note, s->note_buf,
                      s->note_size) < 0) {
-        dump_error(s, "dump: failed to write notes", errp);
+        error_setg(errp, "dump: failed to write notes");
         goto out;
     }
 
@@ -1087,7 +1077,7 @@ static void write_dump_bitmap(DumpState *s, Error **errp)
     while (get_next_page(&block_iter, &pfn, NULL, s)) {
         ret = set_dump_bitmap(last_pfn, pfn, true, dump_bitmap_buf, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to set dump_bitmap", errp);
+            error_setg(errp, "dump: failed to set dump_bitmap");
             goto out;
         }
 
@@ -1104,7 +1094,7 @@ static void write_dump_bitmap(DumpState *s, Error **errp)
         ret = set_dump_bitmap(last_pfn, last_pfn + bits_per_buf, false,
                               dump_bitmap_buf, s);
         if (ret < 0) {
-            dump_error(s, "dump: failed to sync dump_bitmap", errp);
+            error_setg(errp, "dump: failed to sync dump_bitmap");
             goto out;
         }
     }
@@ -1237,7 +1227,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
     ret = write_cache(&page_data, buf, s->dump_info.page_size, false);
     g_free(buf);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write page data (zero page)", errp);
+        error_setg(errp, "dump: failed to write page data (zero page)");
         goto out;
     }
 
@@ -1253,7 +1243,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
             ret = write_cache(&page_desc, &pd_zero, sizeof(PageDescriptor),
                               false);
             if (ret < 0) {
-                dump_error(s, "dump: failed to write page desc", errp);
+                error_setg(errp, "dump: failed to write page desc");
                 goto out;
             }
         } else {
@@ -1278,7 +1268,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #ifdef CONFIG_LZO
@@ -1291,7 +1281,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #endif
@@ -1305,7 +1295,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
                 ret = write_cache(&page_data, buf_out, size_out, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
 #endif
@@ -1321,7 +1311,7 @@ static void write_dump_pages(DumpState *s, Error **errp)
                 ret = write_cache(&page_data, buf,
                                   s->dump_info.page_size, false);
                 if (ret < 0) {
-                    dump_error(s, "dump: failed to write page data", errp);
+                    error_setg(errp, "dump: failed to write page data");
                     goto out;
                 }
             }
@@ -1333,20 +1323,21 @@ static void write_dump_pages(DumpState *s, Error **errp)
 
             ret = write_cache(&page_desc, &pd, sizeof(PageDescriptor), false);
             if (ret < 0) {
-                dump_error(s, "dump: failed to write page desc", errp);
+                error_setg(errp, "dump: failed to write page desc");
                 goto out;
             }
         }
+        s->written_size += s->dump_info.page_size;
     }
 
     ret = write_cache(&page_desc, NULL, 0, true);
     if (ret < 0) {
-        dump_error(s, "dump: failed to sync cache for page_desc", errp);
+        error_setg(errp, "dump: failed to sync cache for page_desc");
         goto out;
     }
     ret = write_cache(&page_data, NULL, 0, true);
     if (ret < 0) {
-        dump_error(s, "dump: failed to sync cache for page_data", errp);
+        error_setg(errp, "dump: failed to sync cache for page_data");
         goto out;
     }
 
@@ -1390,7 +1381,7 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
 
     ret = write_start_flat_header(s->fd);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write start flat header", errp);
+        error_setg(errp, "dump: failed to write start flat header");
         return;
     }
 
@@ -1414,11 +1405,9 @@ static void create_kdump_vmcore(DumpState *s, Error **errp)
 
     ret = write_end_flat_header(s->fd);
     if (ret < 0) {
-        dump_error(s, "dump: failed to write end flat header", errp);
+        error_setg(errp, "dump: failed to write end flat header");
         return;
     }
-
-    dump_completed(s);
 }
 
 static ram_addr_t get_start_block(DumpState *s)
@@ -1457,6 +1446,44 @@ static void get_max_mapnr(DumpState *s)
     s->max_mapnr = dump_paddr_to_pfn(s, last_block->target_end);
 }
 
+static DumpState dump_state_global = { .status = DUMP_STATUS_NONE };
+
+static void dump_state_prepare(DumpState *s)
+{
+    /* zero the struct, setting status to active */
+    *s = (DumpState) { .status = DUMP_STATUS_ACTIVE };
+}
+
+bool dump_in_progress(void)
+{
+    DumpState *state = &dump_state_global;
+    return (atomic_read(&state->status) == DUMP_STATUS_ACTIVE);
+}
+
+/* calculate total size of memory to be dumped (taking filter into
+ * acoount.) */
+static int64_t dump_calculate_size(DumpState *s)
+{
+    GuestPhysBlock *block;
+    int64_t size = 0, total = 0, left = 0, right = 0;
+
+    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+        if (s->has_filter) {
+            /* calculate the overlapped region. */
+            left = MAX(s->begin, block->target_start);
+            right = MIN(s->begin + s->length, block->target_end);
+            size = right - left;
+            size = size > 0 ? size : 0;
+        } else {
+            /* count the whole region in */
+            size = (block->target_end - block->target_start);
+        }
+        total += size;
+    }
+
+    return total;
+}
+
 static void dump_init(DumpState *s, int fd, bool has_format,
                       DumpGuestMemoryFormat format, bool paging, bool has_filter,
                       int64_t begin, int64_t length, Error **errp)
@@ -1466,6 +1493,10 @@ static void dump_init(DumpState *s, int fd, bool has_format,
     Error *err = NULL;
     int ret;
 
+    s->has_format = has_format;
+    s->format = format;
+    s->written_size = 0;
+
     /* kdump-compressed is conflict with paging and filter */
     if (has_format && format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
         assert(!paging && !has_filter);
@@ -1496,6 +1527,10 @@ static void dump_init(DumpState *s, int fd, bool has_format,
 
     guest_phys_blocks_init(&s->guest_phys_blocks);
     guest_phys_blocks_append(&s->guest_phys_blocks);
+    s->total_size = dump_calculate_size(s);
+#ifdef DEBUG_DUMP_GUEST_MEMORY
+    fprintf(stderr, "DUMP: total memory to dump: %lu\n", s->total_size);
+#endif
 
     s->start = get_start_block(s);
     if (s->start == -1) {
@@ -1624,8 +1659,60 @@ cleanup:
     dump_cleanup(s);
 }
 
-void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
-                           int64_t begin, bool has_length,
+/* this operation might be time consuming. */
+static void dump_process(DumpState *s, Error **errp)
+{
+    Error *local_err = NULL;
+    DumpQueryResult *result = NULL;
+
+    if (s->has_format && s->format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
+        create_kdump_vmcore(s, &local_err);
+    } else {
+        create_vmcore(s, &local_err);
+    }
+
+    /* make sure status is written after written_size updates */
+    smp_wmb();
+    atomic_set(&s->status,
+               (local_err ? DUMP_STATUS_FAILED : DUMP_STATUS_COMPLETED));
+
+    /* send DUMP_COMPLETED message (unconditionally) */
+    result = qmp_query_dump(NULL);
+    /* should never fail */
+    assert(result);
+    qapi_event_send_dump_completed(result, !!local_err, (local_err ? \
+                                   error_get_pretty(local_err) : NULL),
+                                   &error_abort);
+    qapi_free_DumpQueryResult(result);
+
+    error_propagate(errp, local_err);
+    dump_cleanup(s);
+}
+
+static void *dump_thread(void *data)
+{
+    Error *err = NULL;
+    DumpState *s = (DumpState *)data;
+    dump_process(s, &err);
+    error_free(err);
+    return NULL;
+}
+
+DumpQueryResult *qmp_query_dump(Error **errp)
+{
+    DumpQueryResult *result = g_new(DumpQueryResult, 1);
+    DumpState *state = &dump_state_global;
+    result->status = atomic_read(&state->status);
+    /* make sure we are reading status and written_size in order */
+    smp_rmb();
+    result->completed = state->written_size;
+    result->total = state->total_size;
+    return result;
+}
+
+void qmp_dump_guest_memory(bool paging, const char *file,
+                           bool has_detach, bool detach,
+                           bool has_begin, int64_t begin, bool has_length,
                            int64_t length, bool has_format,
                            DumpGuestMemoryFormat format, Error **errp)
 {
@@ -1633,6 +1720,19 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
     int fd = -1;
     DumpState *s;
     Error *local_err = NULL;
+    bool detach_p = false;
+
+    if (runstate_check(RUN_STATE_INMIGRATE)) {
+        error_setg(errp, "Dump not allowed during incoming migration.");
+        return;
+    }
+
+    /* if there is a dump in background, we should wait until the dump
+     * finished */
+    if (dump_in_progress()) {
+        error_setg(errp, "There is a dump in process, please wait.");
+        return;
+    }
 
     /*
      * kdump-compressed format need the whole memory dumped, so paging or
@@ -1652,6 +1752,9 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
         error_setg(errp, QERR_MISSING_PARAMETER, "begin");
         return;
     }
+    if (has_detach) {
+        detach_p = detach;
+    }
 
     /* check whether lzo/snappy is supported */
 #ifndef CONFIG_LZO
@@ -1690,23 +1793,25 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
         return;
     }
 
-    s = g_malloc0(sizeof(DumpState));
+    s = &dump_state_global;
+    dump_state_prepare(s);
 
     dump_init(s, fd, has_format, format, paging, has_begin,
               begin, length, &local_err);
     if (local_err) {
-        g_free(s);
         error_propagate(errp, local_err);
+        atomic_set(&s->status, DUMP_STATUS_FAILED);
         return;
     }
 
-    if (has_format && format != DUMP_GUEST_MEMORY_FORMAT_ELF) {
-        create_kdump_vmcore(s, errp);
+    if (detach_p) {
+        /* detached dump */
+        qemu_thread_create(&s->dump_thread, "dump_thread", dump_thread,
+                           s, QEMU_THREAD_DETACHED);
     } else {
-        create_vmcore(s, errp);
+        /* sync dump */
+        dump_process(s, errp);
     }
-
-    g_free(s);
 }
 
 DumpGuestMemoryCapability *qmp_query_dump_guest_memory_capability(Error **errp)

exec.c

@@ -1717,6 +1717,8 @@ ram_addr_t qemu_ram_alloc_internal(ram_addr_t size, ram_addr_t max_size,
         error_propagate(errp, local_err);
         return -1;
     }
+
+    mr->ram_block = new_block;
     return addr;
 }
 
@@ -1866,9 +1868,13 @@ void *qemu_get_ram_block_host_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-void *qemu_get_ram_ptr(ram_addr_t addr)
+void *qemu_get_ram_ptr(RAMBlock *ram_block, ram_addr_t addr)
 {
-    RAMBlock *block = qemu_get_ram_block(addr);
+    RAMBlock *block = ram_block;
+
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
 
     if (xen_enabled() && block->host == NULL) {
         /* We need to check if the requested address is in the RAM
@@ -1889,15 +1895,18 @@ void *qemu_get_ram_ptr(ram_addr_t addr)
  *
  * Called within RCU critical section.
  */
-static void *qemu_ram_ptr_length(ram_addr_t addr, hwaddr *size)
+static void *qemu_ram_ptr_length(RAMBlock *ram_block, ram_addr_t addr,
+                                 hwaddr *size)
 {
-    RAMBlock *block;
+    RAMBlock *block = ram_block;
     ram_addr_t offset_inside_block;
     if (*size == 0) {
         return NULL;
     }
 
-    block = qemu_get_ram_block(addr);
+    if (block == NULL) {
+        block = qemu_get_ram_block(addr);
+    }
     offset_inside_block = addr - block->offset;
     *size = MIN(*size, block->max_length - offset_inside_block);
 
@@ -2025,13 +2034,13 @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr,
     }
     switch (size) {
     case 1:
-        stb_p(qemu_get_ram_ptr(ram_addr), val);
+        stb_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 2:
-        stw_p(qemu_get_ram_ptr(ram_addr), val);
+        stw_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     case 4:
-        stl_p(qemu_get_ram_ptr(ram_addr), val);
+        stl_p(qemu_get_ram_ptr(NULL, ram_addr), val);
         break;
     default:
         abort();
@@ -2607,7 +2616,7 @@ static MemTxResult address_space_write_continue(AddressSpace *as, hwaddr addr,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             memcpy(ptr, buf, l);
             invalidate_and_set_dirty(mr, addr1, l);
         }
@@ -2698,7 +2707,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
             }
         } else {
             /* RAM case */
-            ptr = qemu_get_ram_ptr(mr->ram_addr + addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, mr->ram_addr + addr1);
             memcpy(buf, ptr, l);
         }
 
@@ -2783,7 +2792,7 @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as,
         } else {
             addr1 += memory_region_get_ram_addr(mr);
             /* ROM/RAM case */
-            ptr = qemu_get_ram_ptr(addr1);
+            ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
             switch (type) {
             case WRITE_DATA:
                 memcpy(ptr, buf, l);
@@ -2995,7 +3004,7 @@ void *address_space_map(AddressSpace *as,
 
     memory_region_ref(mr);
     *plen = done;
-    ptr = qemu_ram_ptr_length(raddr + base, plen);
+    ptr = qemu_ram_ptr_length(mr->ram_block, raddr + base, plen);
     rcu_read_unlock();
 
     return ptr;
@@ -3079,7 +3088,8 @@ static inline uint32_t address_space_ldl_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3174,7 +3184,8 @@ static inline uint64_t address_space_ldq_internal(AddressSpace *as, hwaddr addr,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3289,7 +3300,8 @@ static inline uint32_t address_space_lduw_internal(AddressSpace *as,
 #endif
     } else {
         /* RAM case */
-        ptr = qemu_get_ram_ptr((memory_region_get_ram_addr(mr)
+        ptr = qemu_get_ram_ptr(mr->ram_block,
+                               (memory_region_get_ram_addr(mr)
                                 & TARGET_PAGE_MASK)
                                + addr1);
         switch (endian) {
@@ -3374,7 +3386,7 @@ void address_space_stl_notdirty(AddressSpace *as, hwaddr addr, uint32_t val,
         r = memory_region_dispatch_write(mr, addr1, val, 4, attrs);
     } else {
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         stl_p(ptr, val);
 
         dirty_log_mask = memory_region_get_dirty_log_mask(mr);
@@ -3429,7 +3441,7 @@ static inline void address_space_stl_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stl_le_p(ptr, val);
@@ -3539,7 +3551,7 @@ static inline void address_space_stw_internal(AddressSpace *as,
     } else {
         /* RAM case */
         addr1 += memory_region_get_ram_addr(mr) & TARGET_PAGE_MASK;
-        ptr = qemu_get_ram_ptr(addr1);
+        ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
         switch (endian) {
         case DEVICE_LITTLE_ENDIAN:
             stw_le_p(ptr, val);

fsdev/file-op-9p.h

@@ -12,11 +12,8 @@
  */
 #ifndef _FILEOP_H
 #define _FILEOP_H
-#include <sys/types.h>
 #include <dirent.h>
-#include <sys/time.h>
 #include <utime.h>
-#include <sys/stat.h>
 #include <sys/uio.h>
 #include <sys/vfs.h>
 

hmp-commands-info.hx

@@ -784,6 +784,20 @@ STEXI
 @item info skeys @var{address}
 @findex skeys
 Display the value of a storage key (s390 only)
+ETEXI
+
+    {
+        .name       = "dump",
+        .args_type  = "",
+        .params     = "",
+        .help       = "Display the latest dump status",
+        .mhandler.cmd = hmp_info_dump,
+    },
+
+STEXI
+@item info dump
+@findex dump
+Display the latest dump status.
 ETEXI
 
 STEXI

hmp-commands.hx

@@ -1056,10 +1056,11 @@ ETEXI
 
     {
         .name       = "dump-guest-memory",
-        .args_type  = "paging:-p,zlib:-z,lzo:-l,snappy:-s,filename:F,begin:i?,length:i?",
-        .params     = "[-p] [-z|-l|-s] filename [begin length]",
+        .args_type  = "paging:-p,detach:-d,zlib:-z,lzo:-l,snappy:-s,filename:F,begin:i?,length:i?",
+        .params     = "[-p] [-d] [-z|-l|-s] filename [begin length]",
         .help       = "dump guest memory into file 'filename'.\n\t\t\t"
                       "-p: do paging to get guest's memory mapping.\n\t\t\t"
+                      "-d: return immediately (do not wait for completion).\n\t\t\t"
                       "-z: dump in kdump-compressed format, with zlib compression.\n\t\t\t"
                       "-l: dump in kdump-compressed format, with lzo compression.\n\t\t\t"
                       "-s: dump in kdump-compressed format, with snappy compression.\n\t\t\t"

hmp.c

@@ -1414,6 +1414,18 @@ void hmp_block_set_io_throttle(Monitor *mon, const QDict *qdict)
                               0,
                               false,
                               0,
+                              false, /* no burst length via HMP */
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
+                              false,
+                              0,
                               false, /* No default I/O size */
                               0,
                               false,
@@ -1587,8 +1599,10 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     const char *file = qdict_get_str(qdict, "filename");
     bool has_begin = qdict_haskey(qdict, "begin");
     bool has_length = qdict_haskey(qdict, "length");
+    bool has_detach = qdict_haskey(qdict, "detach");
     int64_t begin = 0;
     int64_t length = 0;
+    bool detach = false;
     enum DumpGuestMemoryFormat dump_format = DUMP_GUEST_MEMORY_FORMAT_ELF;
     char *prot;
 
@@ -1616,11 +1630,14 @@ void hmp_dump_guest_memory(Monitor *mon, const QDict *qdict)
     if (has_length) {
         length = qdict_get_int(qdict, "length");
     }
+    if (has_detach) {
+        detach = qdict_get_bool(qdict, "detach");
+    }
 
     prot = g_strconcat("file:", file, NULL);
 
-    qmp_dump_guest_memory(paging, prot, has_begin, begin, has_length, length,
-                          true, dump_format, &err);
+    qmp_dump_guest_memory(paging, prot, true, detach, has_begin, begin,
+                          has_length, length, true, dump_format, &err);
     hmp_handle_error(mon, &err);
     g_free(prot);
 }
@@ -2346,3 +2363,20 @@ void hmp_rocker_of_dpa_groups(Monitor *mon, const QDict *qdict)
 
     qapi_free_RockerOfDpaGroupList(list);
 }
+
+void hmp_info_dump(Monitor *mon, const QDict *qdict)
+{
+    DumpQueryResult *result = qmp_query_dump(NULL);
+
+    assert(result && result->status < DUMP_STATUS__MAX);
+    monitor_printf(mon, "Status: %s\n", DumpStatus_lookup[result->status]);
+
+    if (result->status == DUMP_STATUS_ACTIVE) {
+        float percent = 0;
+        assert(result->total != 0);
+        percent = 100.0 * result->completed / result->total;
+        monitor_printf(mon, "Finished: %.2f %%\n", percent);
+    }
+
+    qapi_free_DumpQueryResult(result);
+}

hmp.h

@@ -131,5 +131,6 @@ void hmp_rocker(Monitor *mon, const QDict *qdict);
 void hmp_rocker_ports(Monitor *mon, const QDict *qdict);
 void hmp_rocker_of_dpa_flows(Monitor *mon, const QDict *qdict);
 void hmp_rocker_of_dpa_groups(Monitor *mon, const QDict *qdict);
+void hmp_info_dump(Monitor *mon, const QDict *qdict);
 
 #endif

hw/9pfs/9p-synth.h

@@ -13,9 +13,6 @@
 #ifndef HW_9PFS_SYNTH_H
 #define HW_9PFS_SYNTH_H 1
 
-#include <unistd.h>
-#include <sys/types.h>
-#include <limits.h>
 
 typedef struct V9fsSynthNode V9fsSynthNode;
 typedef ssize_t (*v9fs_synth_read)(void *buf, int len, off_t offset,

hw/9pfs/9p.h

@@ -1,9 +1,7 @@
 #ifndef _QEMU_9P_H
 #define _QEMU_9P_H
 
-#include <sys/types.h>
 #include <dirent.h>
-#include <sys/time.h>
 #include <utime.h>
 #include <sys/resource.h>
 #include <glib.h>

hw/acpi/aml-build.c

@@ -1451,7 +1451,7 @@ build_header(GArray *linker, GArray *table_data,
     h->checksum = 0;
     /* Checksum to be filled in by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_TABLE_FILE,
-                                    table_data->data, h, len, &h->checksum);
+                                    table_data, h, len, &h->checksum);
 }
 
 void *acpi_data_push(GArray *table_data, unsigned size)

hw/acpi/bios-linker-loader.c

@@ -25,6 +25,13 @@
 
 #include "qemu/bswap.h"
 
+/*
+ * Linker/loader is a paravirtualized interface that passes commands to guest.
+ * The commands can be used to request guest to
+ * - allocate memory chunks and initialize them from QEMU FW CFG files
+ * - link allocated chunks by storing pointer to one chunk into another
+ * - calculate ACPI checksum of part of the chunk and store into same chunk
+ */
 #define BIOS_LINKER_LOADER_FILESZ FW_CFG_MAX_FILE_PATH
 
 struct BiosLinkerLoaderEntry {
@@ -88,6 +95,12 @@ enum {
     BIOS_LINKER_LOADER_ALLOC_ZONE_FSEG = 0x2,
 };
 
+/*
+ * bios_linker_loader_init: allocate a new linker file blob array.
+ *
+ * After initialization, linker commands can be added, and will
+ * be stored in the array.
+ */
 GArray *bios_linker_loader_init(void)
 {
     return g_array_new(false, true /* clear */, 1);
@@ -99,6 +112,16 @@ void *bios_linker_loader_cleanup(GArray *linker)
     return g_array_free(linker, false);
 }
 
+/*
+ * bios_linker_loader_alloc: ask guest to load file into guest memory.
+ *
+ * @linker: linker file blob array
+ * @file: file to be loaded
+ * @alloc_align: required minimal alignment in bytes. Must be a power of 2.
+ * @alloc_fseg: request allocation in FSEG zone (useful for the RSDP ACPI table)
+ *
+ * Note: this command must precede any other linker command using this file.
+ */
 void bios_linker_loader_alloc(GArray *linker,
                               const char *file,
                               uint32_t alloc_align,
@@ -106,6 +129,8 @@ void bios_linker_loader_alloc(GArray *linker,
 {
     BiosLinkerLoaderEntry entry;
 
+    assert(!(alloc_align & (alloc_align - 1)));
+
     memset(&entry, 0, sizeof entry);
     strncpy(entry.alloc.file, file, sizeof entry.alloc.file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ALLOCATE);
@@ -118,23 +143,77 @@ void bios_linker_loader_alloc(GArray *linker,
     g_array_prepend_vals(linker, &entry, sizeof entry);
 }
 
+/*
+ * bios_linker_loader_add_checksum: ask guest to add checksum of file data
+ * into (same) file at the specified pointer.
+ *
+ * Checksum calculation simply sums -X for each byte X in the range
+ * using 8-bit math (i.e. ACPI checksum).
+ *
+ * @linker: linker file blob array
+ * @file: file that includes the checksum to be calculated
+ *        and the data to be checksummed
+ * @table: @file blob contents
+ * @start, @size: range of data to checksum
+ * @checksum: location of the checksum to be patched within file blob
+ *
+ * Notes:
+ * - checksum byte initial value must have been pushed into @table
+ *   and reside at address @checksum.
+ * - @size bytes must have been pushed into @table and reside at address
+ *   @start.
+ * - Guest calculates checksum of specified range of data, result is added to
+ *   initial value at @checksum into copy of @file in Guest memory.
+ * - Range might include the checksum itself.
+ * - To avoid confusion, caller must always put 0x0 at @checksum.
+ * - @file must be loaded into Guest memory using bios_linker_loader_alloc
+ */
 void bios_linker_loader_add_checksum(GArray *linker, const char *file,
-                                     void *table,
+                                     GArray *table,
                                      void *start, unsigned size,
                                      uint8_t *checksum)
 {
     BiosLinkerLoaderEntry entry;
+    ptrdiff_t checksum_offset = (gchar *)checksum - table->data;
+    ptrdiff_t start_offset = (gchar *)start - table->data;
+
+    assert(checksum_offset >= 0);
+    assert(start_offset >= 0);
+    assert(checksum_offset + 1 <= table->len);
+    assert(start_offset + size <= table->len);
+    assert(*checksum == 0x0);
 
     memset(&entry, 0, sizeof entry);
     strncpy(entry.cksum.file, file, sizeof entry.cksum.file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_CHECKSUM);
-    entry.cksum.offset = cpu_to_le32(checksum - (uint8_t *)table);
-    entry.cksum.start = cpu_to_le32((uint8_t *)start - (uint8_t *)table);
+    entry.cksum.offset = cpu_to_le32(checksum_offset);
+    entry.cksum.start = cpu_to_le32(start_offset);
     entry.cksum.length = cpu_to_le32(size);
 
     g_array_append_vals(linker, &entry, sizeof entry);
 }
 
+/*
+ * bios_linker_loader_add_pointer: ask guest to add address of source file
+ * into destination file at the specified pointer.
+ *
+ * @linker: linker file blob array
+ * @dest_file: destination file that must be changed
+ * @src_file: source file who's address must be taken
+ * @table: @dest_file blob contents array
+ * @pointer: location of the pointer to be patched within destination file blob
+ * @pointer_size: size of pointer to be patched, in bytes
+ *
+ * Notes:
+ * - @pointer_size bytes must have been pushed into @table
+ *   and reside at address @pointer.
+ * - Guest address is added to initial value at @pointer
+ *   into copy of @dest_file in Guest memory.
+ *   e.g. to get start of src_file in guest memory, put 0x0 there
+ *   to get address of a field at offset 0x10 in src_file, put 0x10 there
+ * - Both @dest_file and @src_file must be
+ *   loaded into Guest memory using bios_linker_loader_alloc
+ */
 void bios_linker_loader_add_pointer(GArray *linker,
                                     const char *dest_file,
                                     const char *src_file,
@@ -142,7 +221,10 @@ void bios_linker_loader_add_pointer(GArray *linker,
                                     uint8_t pointer_size)
 {
     BiosLinkerLoaderEntry entry;
-    size_t offset = (gchar *)pointer - table->data;
+    ptrdiff_t offset = (gchar *)pointer - table->data;
+
+    assert(offset >= 0);
+    assert(offset + pointer_size <= table->len);
 
     memset(&entry, 0, sizeof entry);
     strncpy(entry.pointer.dest_file, dest_file,
@@ -150,7 +232,6 @@ void bios_linker_loader_add_pointer(GArray *linker,
     strncpy(entry.pointer.src_file, src_file,
             sizeof entry.pointer.src_file - 1);
     entry.command = cpu_to_le32(BIOS_LINKER_LOADER_COMMAND_ADD_POINTER);
-    assert(table->len >= offset + pointer_size);
     entry.pointer.offset = cpu_to_le32(offset);
     entry.pointer.size = pointer_size;
     assert(pointer_size == 1 || pointer_size == 2 ||

hw/acpi/ich9.c

@@ -240,7 +240,7 @@ static void pm_powerdown_req(Notifier *n, void *opaque)
 }
 
 void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
-                  bool smm_enabled, bool enable_tco,
+                  bool smm_enabled,
                   qemu_irq sci_irq)
 {
     memory_region_init(&pm->io, OBJECT(lpc_pci), "ich9-pm", ICH9_PMIO_SIZE);
@@ -264,10 +264,8 @@ void ich9_pm_init(PCIDevice *lpc_pci, ICH9LPCPMRegs *pm,
 
     pm->smm_enabled = smm_enabled;
 
-    pm->enable_tco = enable_tco;
-    if (pm->enable_tco) {
-        acpi_pm_tco_init(&pm->tco_regs, &pm->io);
-    }
+    pm->enable_tco = true;
+    acpi_pm_tco_init(&pm->tco_regs, &pm->io);
 
     pm->irq = sci_irq;
     qemu_register_reset(pm_reset, pm);

hw/arm/bcm2835_peripherals.c

@@ -182,6 +182,13 @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
     sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhci), 0,
         qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
                                INTERRUPT_ARASANSDIO));
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->sdhci), "sd-bus",
+                              &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
 }
 
 static void bcm2835_peripherals_class_init(ObjectClass *oc, void *data)

hw/arm/bcm2836.c

@@ -73,6 +73,13 @@ static void bcm2836_realize(DeviceState *dev, Error **errp)
         return;
     }
 
+    object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->peripherals),
+                              "sd-bus", &err);
+    if (err) {
+        error_propagate(errp, err);
+        return;
+    }
+
     sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->peripherals), 0,
                             BCM2836_PERI_BASE, 1);
 

hw/arm/raspi.c

@@ -113,6 +113,10 @@ static void setup_boot(MachineState *machine, int version, size_t ram_size)
 static void raspi2_init(MachineState *machine)
 {
     RasPiState *s = g_new0(RasPiState, 1);
+    DriveInfo *di;
+    BlockBackend *blk;
+    BusState *bus;
+    DeviceState *carddev;
 
     object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM2836);
     object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc),
@@ -133,6 +137,18 @@ static void raspi2_init(MachineState *machine)
                             &error_abort);
     object_property_set_bool(OBJECT(&s->soc), true, "realized", &error_abort);
 
+    /* Create and plug in the SD cards */
+    di = drive_get_next(IF_SD);
+    blk = di ? blk_by_legacy_dinfo(di) : NULL;
+    bus = qdev_get_child_bus(DEVICE(&s->soc), "sd-bus");
+    if (bus == NULL) {
+        error_report("No SD bus found in SOC object");
+        exit(1);
+    }
+    carddev = qdev_create(bus, TYPE_SD_CARD);
+    qdev_prop_set_drive(carddev, "drive", blk, &error_fatal);
+    object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal);
+
     setup_boot(machine, 2, machine->ram_size);
 }
 

hw/arm/virt-acpi-build.c

@@ -359,7 +359,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
     rsdp->checksum = 0;
     /* Checksum to be filled by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE,
-                                    rsdp, rsdp, sizeof *rsdp, &rsdp->checksum);
+                                    rsdp_table, rsdp, sizeof *rsdp,
+                                    &rsdp->checksum);
 
     return rsdp_table;
 }

hw/audio/gusemu.h

@@ -34,7 +34,6 @@
  typedef signed char GUSchar;
  typedef signed short GUSsample;
 #else
- #include <stdint.h>
  typedef int8_t GUSchar;
  typedef uint8_t GUSbyte;
  typedef uint16_t GUSword;

hw/block/dataplane/virtio-blk.c

@@ -18,8 +18,6 @@
 #include "qemu/thread.h"
 #include "qemu/error-report.h"
 #include "hw/virtio/virtio-access.h"
-#include "hw/virtio/dataplane/vring.h"
-#include "hw/virtio/dataplane/vring-accessors.h"
 #include "sysemu/block-backend.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -28,7 +26,6 @@
 #include "qom/object_interfaces.h"
 
 struct VirtIOBlockDataPlane {
-    bool started;
     bool starting;
     bool stopping;
     bool disabled;
@@ -36,7 +33,7 @@ struct VirtIOBlockDataPlane {
     VirtIOBlkConf *conf;
 
     VirtIODevice *vdev;
-    Vring vring;                    /* virtqueue vring */
+    VirtQueue *vq;                  /* virtqueue vring */
     EventNotifier *guest_notifier;  /* irq */
     QEMUBH *bh;                     /* bh for guest notification */
 
@@ -49,93 +46,26 @@ struct VirtIOBlockDataPlane {
      */
     IOThread *iothread;
     AioContext *ctx;
-    EventNotifier host_notifier;    /* doorbell */
 
     /* Operation blocker on BDS */
     Error *blocker;
-    void (*saved_complete_request)(struct VirtIOBlockReq *req,
-                                   unsigned char status);
 };
 
 /* Raise an interrupt to signal guest, if necessary */
-static void notify_guest(VirtIOBlockDataPlane *s)
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s)
 {
-    if (!vring_should_notify(s->vdev, &s->vring)) {
-        return;
-    }
-
-    event_notifier_set(s->guest_notifier);
+    qemu_bh_schedule(s->bh);
 }
 
 static void notify_guest_bh(void *opaque)
 {
     VirtIOBlockDataPlane *s = opaque;
 
-    notify_guest(s);
-}
-
-static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
-{
-    VirtIOBlockDataPlane *s = req->dev->dataplane;
-    stb_p(&req->in->status, status);
-
-    vring_push(s->vdev, &req->dev->dataplane->vring, &req->elem, req->in_len);
-
-    /* Suppress notification to guest by BH and its scheduled
-     * flag because requests are completed as a batch after io
-     * plug & unplug is introduced, and the BH can still be
-     * executed in dataplane aio context even after it is
-     * stopped, so needn't worry about notification loss with BH.
-     */
-    qemu_bh_schedule(s->bh);
-}
-
-static void handle_notify(EventNotifier *e)
-{
-    VirtIOBlockDataPlane *s = container_of(e, VirtIOBlockDataPlane,
-                                           host_notifier);
-    VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
-
-    event_notifier_test_and_clear(&s->host_notifier);
-    blk_io_plug(s->conf->conf.blk);
-    for (;;) {
-        MultiReqBuffer mrb = {};
-
-        /* Disable guest->host notifies to avoid unnecessary vmexits */
-        vring_disable_notification(s->vdev, &s->vring);
-
-        for (;;) {
-            VirtIOBlockReq *req = vring_pop(s->vdev, &s->vring,
-                                            sizeof(VirtIOBlockReq));
-
-            if (req == NULL) {
-                break; /* no more requests */
-            }
-
-            virtio_blk_init_request(vblk, req);
-            trace_virtio_blk_data_plane_process_request(s, req->elem.out_num,
-                                                        req->elem.in_num,
-                                                        req->elem.index);
-
-            virtio_blk_handle_request(req, &mrb);
-        }
-
-        if (mrb.num_reqs) {
-            virtio_blk_submit_multireq(s->conf->conf.blk, &mrb);
-        }
-
-        if (likely(!vring_more_avail(s->vdev, &s->vring))) { /* vring emptied */
-            /* Re-enable guest->host notifies and stop processing the vring.
-             * But if the guest has snuck in more descriptors, keep processing.
-             */
-            if (vring_enable_notification(s->vdev, &s->vring)) {
-                break;
-            }
-        } else { /* fatal error */
-            break;
-        }
+    if (!virtio_should_notify(s->vdev, s->vq)) {
+        return;
     }
-    blk_io_unplug(s->conf->conf.blk);
+
+    event_notifier_set(s->guest_notifier);
 }
 
 static void data_plane_set_up_op_blockers(VirtIOBlockDataPlane *s)
@@ -260,23 +190,14 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s->vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
-    VirtQueue *vq;
     int r;
 
-    if (s->started || s->disabled) {
-        return;
-    }
-
-    if (s->starting) {
+    if (vblk->dataplane_started || s->starting) {
         return;
     }
 
     s->starting = true;
-
-    vq = virtio_get_queue(s->vdev, 0);
-    if (!vring_setup(&s->vring, s->vdev, 0)) {
-        goto fail_vring;
-    }
+    s->vq = virtio_get_queue(s->vdev, 0);
 
     /* Set up guest notifier (irq) */
     r = k->set_guest_notifiers(qbus->parent, 1, true);
@@ -285,7 +206,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
                 "ensure -enable-kvm is set\n", r);
         goto fail_guest_notifiers;
     }
-    s->guest_notifier = virtio_queue_get_guest_notifier(vq);
+    s->guest_notifier = virtio_queue_get_guest_notifier(s->vq);
 
     /* Set up virtqueue notify */
     r = k->set_host_notifier(qbus->parent, 0, true);
@@ -293,34 +214,28 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
         fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
         goto fail_host_notifier;
     }
-    s->host_notifier = *virtio_queue_get_host_notifier(vq);
-
-    s->saved_complete_request = vblk->complete_request;
-    vblk->complete_request = complete_request_vring;
 
     s->starting = false;
-    s->started = true;
+    vblk->dataplane_started = true;
     trace_virtio_blk_data_plane_start(s);
 
     blk_set_aio_context(s->conf->conf.blk, s->ctx);
 
     /* Kick right away to begin processing requests already in vring */
-    event_notifier_set(virtio_queue_get_host_notifier(vq));
+    event_notifier_set(virtio_queue_get_host_notifier(s->vq));
 
     /* Get this show started by hooking up our callbacks */
     aio_context_acquire(s->ctx);
-    aio_set_event_notifier(s->ctx, &s->host_notifier, true,
-                           handle_notify);
+    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, true, true);
     aio_context_release(s->ctx);
     return;
 
   fail_host_notifier:
     k->set_guest_notifiers(qbus->parent, 1, false);
   fail_guest_notifiers:
-    vring_teardown(&s->vring, s->vdev, 0);
     s->disabled = true;
-  fail_vring:
     s->starting = false;
+    vblk->dataplane_started = true;
 }
 
 /* Context: QEMU global mutex held */
@@ -330,39 +245,34 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
     VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
 
+    if (!vblk->dataplane_started || s->stopping) {
+        return;
+    }
 
     /* Better luck next time. */
     if (s->disabled) {
         s->disabled = false;
-        return;
-    }
-    if (!s->started || s->stopping) {
+        vblk->dataplane_started = false;
         return;
     }
     s->stopping = true;
-    vblk->complete_request = s->saved_complete_request;
     trace_virtio_blk_data_plane_stop(s);
 
     aio_context_acquire(s->ctx);
 
     /* Stop notifications for new requests from guest */
-    aio_set_event_notifier(s->ctx, &s->host_notifier, true, NULL);
+    virtio_queue_aio_set_host_notifier_handler(s->vq, s->ctx, false, false);
 
     /* Drain and switch bs back to the QEMU main loop */
     blk_set_aio_context(s->conf->conf.blk, qemu_get_aio_context());
 
     aio_context_release(s->ctx);
 
-    /* Sync vring state back to virtqueue so that non-dataplane request
-     * processing can continue when we disable the host notifier below.
-     */
-    vring_teardown(&s->vring, s->vdev, 0);
-
     k->set_host_notifier(qbus->parent, 0, false);
 
     /* Clean up guest notifier (irq) */
     k->set_guest_notifiers(qbus->parent, 1, false);
 
-    s->started = false;
+    vblk->dataplane_started = false;
     s->stopping = false;
 }

hw/block/dataplane/virtio-blk.h

@@ -26,5 +26,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s);
 void virtio_blk_data_plane_drain(VirtIOBlockDataPlane *s);
+void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s);
 
 #endif /* HW_DATAPLANE_VIRTIO_BLK_H */

hw/block/virtio-blk.c

@@ -21,7 +21,6 @@
 #include "sysemu/blockdev.h"
 #include "hw/virtio/virtio-blk.h"
 #include "dataplane/virtio-blk.h"
-#include "migration/migration.h"
 #include "block/scsi.h"
 #ifdef __linux__
 # include <scsi/sg.h>
@@ -45,8 +44,7 @@ void virtio_blk_free_request(VirtIOBlockReq *req)
     }
 }
 
-static void virtio_blk_complete_request(VirtIOBlockReq *req,
-                                        unsigned char status)
+static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
 {
     VirtIOBlock *s = req->dev;
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
@@ -55,12 +53,11 @@ static void virtio_blk_complete_request(VirtIOBlockReq *req,
 
     stb_p(&req->in->status, status);
     virtqueue_push(s->vq, &req->elem, req->in_len);
-    virtio_notify(vdev, s->vq);
-}
-
-static void virtio_blk_req_complete(VirtIOBlockReq *req, unsigned char status)
-{
-    req->dev->complete_request(req, status);
+    if (s->dataplane) {
+        virtio_blk_data_plane_notify(s->dataplane);
+    } else {
+        virtio_notify(vdev, s->vq);
+    }
 }
 
 static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
@@ -589,7 +586,7 @@ static void virtio_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
     /* Some guests kick before setting VIRTIO_CONFIG_S_DRIVER_OK so start
      * dataplane here instead of waiting for .set_status().
      */
-    if (s->dataplane) {
+    if (s->dataplane && !s->dataplane_started) {
         virtio_blk_data_plane_start(s->dataplane);
         return;
     }
@@ -852,36 +849,6 @@ static const BlockDevOps virtio_block_ops = {
     .resize_cb = virtio_blk_resize,
 };
 
-/* Disable dataplane thread during live migration since it does not
- * update the dirty memory bitmap yet.
- */
-static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
-{
-    VirtIOBlock *s = container_of(notifier, VirtIOBlock,
-                                  migration_state_notifier);
-    MigrationState *mig = data;
-    Error *err = NULL;
-
-    if (migration_in_setup(mig)) {
-        if (!s->dataplane) {
-            return;
-        }
-        virtio_blk_data_plane_destroy(s->dataplane);
-        s->dataplane = NULL;
-    } else if (migration_has_finished(mig) ||
-               migration_has_failed(mig)) {
-        if (s->dataplane) {
-            return;
-        }
-        blk_drain_all(); /* complete in-flight non-dataplane requests */
-        virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->conf,
-                                     &s->dataplane, &err);
-        if (err != NULL) {
-            error_report_err(err);
-        }
-    }
-}
-
 static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -916,15 +883,12 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp)
     s->sector_mask = (s->conf.conf.logical_block_size / BDRV_SECTOR_SIZE) - 1;
 
     s->vq = virtio_add_queue(vdev, 128, virtio_blk_handle_output);
-    s->complete_request = virtio_blk_complete_request;
     virtio_blk_data_plane_create(vdev, conf, &s->dataplane, &err);
     if (err != NULL) {
         error_propagate(errp, err);
         virtio_cleanup(vdev);
         return;
     }
-    s->migration_state_notifier.notify = virtio_blk_migration_state_changed;
-    add_migration_state_change_notifier(&s->migration_state_notifier);
 
     s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
     register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
@@ -940,7 +904,6 @@ static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOBlock *s = VIRTIO_BLK(dev);
 
-    remove_migration_state_change_notifier(&s->migration_state_notifier);
     virtio_blk_data_plane_destroy(s->dataplane);
     s->dataplane = NULL;
     qemu_del_vm_change_state_handler(s->change);

hw/core/machine.c

@@ -312,6 +312,21 @@ static bool machine_get_suppress_vmdesc(Object *obj, Error **errp)
     return ms->suppress_vmdesc;
 }
 
+static void machine_set_enforce_config_section(Object *obj, bool value,
+                                             Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->enforce_config_section = value;
+}
+
+static bool machine_get_enforce_config_section(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->enforce_config_section;
+}
+
 static int error_on_sysbus_device(SysBusDevice *sbdev, void *opaque)
 {
     error_report("Option '-device %s' cannot be handled by this machine",
@@ -467,6 +482,12 @@ static void machine_initfn(Object *obj)
     object_property_set_description(obj, "suppress-vmdesc",
                                     "Set on to disable self-describing migration",
                                     NULL);
+    object_property_add_bool(obj, "enforce-config-section",
+                             machine_get_enforce_config_section,
+                             machine_set_enforce_config_section, NULL);
+    object_property_set_description(obj, "enforce-config-section",
+                                    "Set on to enforce configuration section migration",
+                                    NULL);
 
     /* Register notifier when init is done for sysbus sanity checks */
     ms->sysbus_notifier.notify = machine_init_notify;

hw/display/vga_int.h

@@ -25,7 +25,6 @@
 #define HW_VGA_INT_H 1
 
 #include <hw/hw.h>
-#include "qapi/error.h"
 #include "exec/memory.h"
 
 #define ST01_V_RETRACE      0x08

hw/gpio/pl061.c

@@ -60,6 +60,7 @@ typedef struct PL061State {
     qemu_irq irq;
     qemu_irq out[8];
     const unsigned char *id;
+    uint32_t rsvd_start; /* reserved area: [rsvd_start, 0xfcc] */
 } PL061State;
 
 static const VMStateDescription vmstate_pl061 = {
@@ -152,12 +153,15 @@ static uint64_t pl061_read(void *opaque, hwaddr offset,
 {
     PL061State *s = (PL061State *)opaque;
 
-    if (offset >= 0xfd0 && offset < 0x1000) {
-        return s->id[(offset - 0xfd0) >> 2];
-    }
     if (offset < 0x400) {
         return s->data & (offset >> 2);
     }
+    if (offset >= s->rsvd_start && offset <= 0xfcc) {
+        goto err_out;
+    }
+    if (offset >= 0xfd0 && offset < 0x1000) {
+        return s->id[(offset - 0xfd0) >> 2];
+    }
     switch (offset) {
     case 0x400: /* Direction */
         return s->dir;
@@ -198,10 +202,12 @@ static uint64_t pl061_read(void *opaque, hwaddr offset,
     case 0x528: /* Analog mode select */
         return s->amsel;
     default:
-        qemu_log_mask(LOG_GUEST_ERROR,
-                      "pl061_read: Bad offset %x\n", (int)offset);
-        return 0;
+        break;
     }
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR,
+                  "pl061_read: Bad offset %x\n", (int)offset);
+    return 0;
 }
 
 static void pl061_write(void *opaque, hwaddr offset,
@@ -216,6 +222,9 @@ static void pl061_write(void *opaque, hwaddr offset,
         pl061_update(s);
         return;
     }
+    if (offset >= s->rsvd_start) {
+        goto err_out;
+    }
     switch (offset) {
     case 0x400: /* Direction */
         s->dir = value & 0xff;
@@ -274,10 +283,13 @@ static void pl061_write(void *opaque, hwaddr offset,
         s->amsel = value & 0xff;
         break;
     default:
-        qemu_log_mask(LOG_GUEST_ERROR,
-                      "pl061_write: Bad offset %x\n", (int)offset);
+        goto err_out;
     }
     pl061_update(s);
+    return;
+err_out:
+    qemu_log_mask(LOG_GUEST_ERROR,
+                  "pl061_write: Bad offset %x\n", (int)offset);
 }
 
 static void pl061_reset(DeviceState *dev)
@@ -347,6 +359,7 @@ static void pl061_luminary_init(Object *obj)
     PL061State *s = PL061(obj);
 
     s->id = pl061_id_luminary;
+    s->rsvd_start = 0x52c;
 }
 
 static void pl061_init(Object *obj)
@@ -354,6 +367,7 @@ static void pl061_init(Object *obj)
     PL061State *s = PL061(obj);
 
     s->id = pl061_id;
+    s->rsvd_start = 0x424;
 }
 
 static void pl061_class_init(ObjectClass *klass, void *data)

hw/i386/acpi-build.c

@@ -2532,7 +2532,8 @@ build_rsdp(GArray *rsdp_table, GArray *linker, unsigned rsdt)
     rsdp->checksum = 0;
     /* Checksum to be filled by Guest linker */
     bios_linker_loader_add_checksum(linker, ACPI_BUILD_RSDP_FILE,
-                                    rsdp, rsdp, sizeof *rsdp, &rsdp->checksum);
+                                    rsdp_table, rsdp, sizeof *rsdp,
+                                    &rsdp->checksum);
 
     return rsdp_table;
 }

hw/i386/pc_q35.c

@@ -81,11 +81,9 @@ static void pc_q35_init(MachineState *machine)
      * If it doesn't, we need to split it in chunks below and above 4G.
      * In any case, try to make sure that guest addresses aligned at
      * 1G boundaries get mapped to host addresses aligned at 1G boundaries.
-     * For old machine types, use whatever split we used historically to avoid
-     * breaking migration.
      */
     if (machine->ram_size >= 0xb0000000) {
-        lowmem = pcmc->gigabyte_align ? 0x80000000 : 0xb0000000;
+        lowmem = 0x80000000;
     } else {
         lowmem = 0xb0000000;
     }
@@ -116,10 +114,6 @@ static void pc_q35_init(MachineState *machine)
     }
 
     pc_cpus_init(pcms);
-    if (!pcmc->has_acpi_build) {
-        /* only machine types 1.7 & older need this */
-        pc_acpi_init("q35-acpi-dsdt.aml");
-    }
 
     kvmclock_create();
 
@@ -225,7 +219,7 @@ static void pc_q35_init(MachineState *machine)
                          (pcms->vmport != ON_OFF_AUTO_ON), 0xff0104);
 
     /* connect pm stuff to lpc */
-    ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms), !mc->no_tco);
+    ich9_lpc_pm_init(lpc, pc_machine_is_smm_enabled(pcms));
 
     /* ahci and SATA device, for q35 1 ahci controller is built-in */
     ahci = pci_create_simple_multifunction(host_bus,
@@ -259,62 +253,6 @@ static void pc_q35_init(MachineState *machine)
     }
 }
 
-/* Looking for a pc_compat_2_4() function? It doesn't exist.
- * pc_compat_*() functions that run on machine-init time and
- * change global QEMU state are deprecated. Please don't create
- * one, and implement any pc-*-2.4 (and newer) compat code in
- * HW_COMPAT_*, PC_COMPAT_*, or * pc_*_machine_options().
- */
-
-static void pc_compat_2_3(MachineState *machine)
-{
-    PCMachineState *pcms = PC_MACHINE(machine);
-    savevm_skip_section_footers();
-    if (kvm_enabled()) {
-        pcms->smm = ON_OFF_AUTO_OFF;
-    }
-    global_state_set_optional();
-    savevm_skip_configuration();
-}
-
-static void pc_compat_2_2(MachineState *machine)
-{
-    pc_compat_2_3(machine);
-    machine->suppress_vmdesc = true;
-}
-
-static void pc_compat_2_1(MachineState *machine)
-{
-    pc_compat_2_2(machine);
-    x86_cpu_change_kvm_default("svm", NULL);
-}
-
-static void pc_compat_2_0(MachineState *machine)
-{
-    pc_compat_2_1(machine);
-}
-
-static void pc_compat_1_7(MachineState *machine)
-{
-    pc_compat_2_0(machine);
-    x86_cpu_change_kvm_default("x2apic", NULL);
-}
-
-static void pc_compat_1_6(MachineState *machine)
-{
-    pc_compat_1_7(machine);
-}
-
-static void pc_compat_1_5(MachineState *machine)
-{
-    pc_compat_1_6(machine);
-}
-
-static void pc_compat_1_4(MachineState *machine)
-{
-    pc_compat_1_5(machine);
-}
-
 #define DEFINE_Q35_MACHINE(suffix, name, compatfn, optionfn) \
     static void pc_init_##suffix(MachineState *machine) \
     { \
@@ -336,7 +274,6 @@ static void pc_q35_machine_options(MachineClass *m)
     m->default_machine_opts = "firmware=bios-256k.bin";
     m->default_display = "std";
     m->no_floppy = 1;
-    m->no_tco = 0;
 }
 
 static void pc_q35_2_6_machine_options(MachineClass *m)
@@ -371,112 +308,3 @@ static void pc_q35_2_4_machine_options(MachineClass *m)
 
 DEFINE_Q35_MACHINE(v2_4, "pc-q35-2.4", NULL,
                    pc_q35_2_4_machine_options);
-
-
-static void pc_q35_2_3_machine_options(MachineClass *m)
-{
-    pc_q35_2_4_machine_options(m);
-    m->hw_version = "2.3.0";
-    m->no_floppy = 0;
-    m->no_tco = 1;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_3);
-}
-
-DEFINE_Q35_MACHINE(v2_3, "pc-q35-2.3", pc_compat_2_3,
-                   pc_q35_2_3_machine_options);
-
-
-static void pc_q35_2_2_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_3_machine_options(m);
-    m->hw_version = "2.2.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_2);
-    pcmc->rsdp_in_ram = false;
-}
-
-DEFINE_Q35_MACHINE(v2_2, "pc-q35-2.2", pc_compat_2_2,
-                   pc_q35_2_2_machine_options);
-
-
-static void pc_q35_2_1_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_2_machine_options(m);
-    m->hw_version = "2.1.0";
-    m->default_display = NULL;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_1);
-    pcmc->smbios_uuid_encoded = false;
-    pcmc->enforce_aligned_dimm = false;
-}
-
-DEFINE_Q35_MACHINE(v2_1, "pc-q35-2.1", pc_compat_2_1,
-                   pc_q35_2_1_machine_options);
-
-
-static void pc_q35_2_0_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_1_machine_options(m);
-    m->hw_version = "2.0.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_2_0);
-    pcmc->has_reserved_memory = false;
-    pcmc->smbios_legacy_mode = true;
-    pcmc->acpi_data_size = 0x10000;
-}
-
-DEFINE_Q35_MACHINE(v2_0, "pc-q35-2.0", pc_compat_2_0,
-                   pc_q35_2_0_machine_options);
-
-
-static void pc_q35_1_7_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_2_0_machine_options(m);
-    m->hw_version = "1.7.0";
-    m->default_machine_opts = NULL;
-    m->option_rom_has_mr = true;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_7);
-    pcmc->smbios_defaults = false;
-    pcmc->gigabyte_align = false;
-}
-
-DEFINE_Q35_MACHINE(v1_7, "pc-q35-1.7", pc_compat_1_7,
-                   pc_q35_1_7_machine_options);
-
-
-static void pc_q35_1_6_machine_options(MachineClass *m)
-{
-    PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
-    pc_q35_machine_options(m);
-    m->hw_version = "1.6.0";
-    m->rom_file_has_mr = false;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_6);
-    pcmc->has_acpi_build = false;
-}
-
-DEFINE_Q35_MACHINE(v1_6, "pc-q35-1.6", pc_compat_1_6,
-                   pc_q35_1_6_machine_options);
-
-
-static void pc_q35_1_5_machine_options(MachineClass *m)
-{
-    pc_q35_1_6_machine_options(m);
-    m->hw_version = "1.5.0";
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_5);
-}
-
-DEFINE_Q35_MACHINE(v1_5, "pc-q35-1.5", pc_compat_1_5,
-                   pc_q35_1_5_machine_options);
-
-
-static void pc_q35_1_4_machine_options(MachineClass *m)
-{
-    pc_q35_1_5_machine_options(m);
-    m->hw_version = "1.4.0";
-    m->hot_add_cpu = NULL;
-    SET_MACHINE_COMPAT(m, PC_COMPAT_1_4);
-}
-
-DEFINE_Q35_MACHINE(v1_4, "pc-q35-1.4", pc_compat_1_4,
-                   pc_q35_1_4_machine_options);

hw/input/hid.c

@@ -140,9 +140,9 @@ static void hid_pointer_event(DeviceState *dev, QemuConsole *src,
     case INPUT_EVENT_KIND_BTN:
         if (evt->u.btn->down) {
             e->buttons_state |= bmap[evt->u.btn->button];
-            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
+            if (evt->u.btn->button == INPUT_BUTTON_WHEEL_UP) {
                 e->dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
+            } else if (evt->u.btn->button == INPUT_BUTTON_WHEEL_DOWN) {
                 e->dz++;
             }
         } else {

hw/input/ps2.c

@@ -406,9 +406,9 @@ static void ps2_mouse_event(DeviceState *dev, QemuConsole *src,
     case INPUT_EVENT_KIND_BTN:
         if (evt->u.btn->down) {
             s->mouse_buttons |= bmap[evt->u.btn->button];
-            if (evt->u.btn->button == INPUT_BUTTON_WHEELUP) {
+            if (evt->u.btn->button == INPUT_BUTTON_WHEEL_UP) {
                 s->mouse_dz--;
-            } else if (evt->u.btn->button == INPUT_BUTTON_WHEELDOWN) {
+            } else if (evt->u.btn->button == INPUT_BUTTON_WHEEL_DOWN) {
                 s->mouse_dz++;
             }
         } else {

hw/input/virtio-input-hid.c

@@ -143,8 +143,8 @@ static const unsigned int keymap_button[INPUT_BUTTON__MAX] = {
     [INPUT_BUTTON_LEFT]              = BTN_LEFT,
     [INPUT_BUTTON_RIGHT]             = BTN_RIGHT,
     [INPUT_BUTTON_MIDDLE]            = BTN_MIDDLE,
-    [INPUT_BUTTON_WHEELUP]           = BTN_GEAR_UP,
-    [INPUT_BUTTON_WHEELDOWN]         = BTN_GEAR_DOWN,
+    [INPUT_BUTTON_WHEEL_UP]          = BTN_GEAR_UP,
+    [INPUT_BUTTON_WHEEL_DOWN]        = BTN_GEAR_DOWN,
 };
 
 static const unsigned int axismap_rel[INPUT_AXIS__MAX] = {

hw/intc/xics.c

@@ -712,7 +712,7 @@ static int ics_find_free_block(ICSState *ics, int num, int alignnum)
     return -1;
 }
 
-int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
+int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi, Error **errp)
 {
     ICSState *ics = &icp->ics[src];
     int irq;
@@ -720,14 +720,14 @@ int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
     if (irq_hint) {
         assert(src == xics_find_source(icp, irq_hint));
         if (!ICS_IRQ_FREE(ics, irq_hint - ics->offset)) {
-            trace_xics_alloc_failed_hint(src, irq_hint);
+            error_setg(errp, "can't allocate IRQ %d: already in use", irq_hint);
             return -1;
         }
         irq = irq_hint;
     } else {
         irq = ics_find_free_block(ics, 1, 1);
         if (irq < 0) {
-            trace_xics_alloc_failed_no_left(src);
+            error_setg(errp, "can't allocate IRQ: no IRQ left");
             return -1;
         }
         irq += ics->offset;
@@ -743,7 +743,8 @@ int xics_alloc(XICSState *icp, int src, int irq_hint, bool lsi)
  * Allocate block of consecutive IRQs, and return the number of the first IRQ in the block.
  * If align==true, aligns the first IRQ number to num.
  */
-int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align)
+int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align,
+                     Error **errp)
 {
     int i, first = -1;
     ICSState *ics = &icp->ics[src];
@@ -763,6 +764,10 @@ int xics_alloc_block(XICSState *icp, int src, int num, bool lsi, bool align)
     } else {
         first = ics_find_free_block(ics, num, 1);
     }
+    if (first < 0) {
+        error_setg(errp, "can't find a free %d-IRQ block", num);
+        return -1;
+    }
 
     if (first >= 0) {
         for (i = first; i < first + num; ++i) {

hw/isa/lpc_ich9.c

@@ -369,13 +369,13 @@ static void ich9_set_sci(void *opaque, int irq_num, int level)
     }
 }
 
-void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled, bool enable_tco)
+void ich9_lpc_pm_init(PCIDevice *lpc_pci, bool smm_enabled)
 {
     ICH9LPCState *lpc = ICH9_LPC_DEVICE(lpc_pci);
     qemu_irq sci_irq;
 
     sci_irq = qemu_allocate_irq(ich9_set_sci, lpc, 0);
-    ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, enable_tco, sci_irq);
+    ich9_pm_init(lpc_pci, &lpc->pm, smm_enabled, sci_irq);
     ich9_lpc_reset(&lpc->d.qdev);
 }
 

hw/mem/pc-dimm.c

@@ -192,32 +192,6 @@ int qmp_pc_dimm_device_list(Object *obj, void *opaque)
     return 0;
 }
 
-ram_addr_t get_current_ram_size(void)
-{
-    MemoryDeviceInfoList *info_list = NULL;
-    MemoryDeviceInfoList **prev = &info_list;
-    MemoryDeviceInfoList *info;
-    ram_addr_t size = ram_size;
-
-    qmp_pc_dimm_device_list(qdev_get_machine(), &prev);
-    for (info = info_list; info; info = info->next) {
-        MemoryDeviceInfo *value = info->value;
-
-        if (value) {
-            switch (value->type) {
-            case MEMORY_DEVICE_INFO_KIND_DIMM:
-                size += value->u.dimm->size;
-                break;
-            default:
-                break;
-            }
-        }
-    }
-    qapi_free_MemoryDeviceInfoList(info_list);
-
-    return size;
-}
-
 static int pc_dimm_slot2bitmap(Object *obj, void *opaque)
 {
     unsigned long *bitmap = opaque;

hw/misc/macio/mac_dbdma.c

@@ -557,11 +557,13 @@ void DBDMA_register_channel(void *dbdma, int nchan, qemu_irq irq,
 
     DBDMA_DPRINTF("DBDMA_register_channel 0x%x\n", nchan);
 
+    assert(rw);
+    assert(flush);
+
     ch->irq = irq;
     ch->rw = rw;
     ch->flush = flush;
     ch->io.opaque = opaque;
-    ch->io.channel = ch;
 }
 
 static void
@@ -775,6 +777,20 @@ static void dbdma_reset(void *opaque)
         memset(s->channels[i].regs, 0, DBDMA_SIZE);
 }
 
+static void dbdma_unassigned_rw(DBDMA_io *io)
+{
+    DBDMA_channel *ch = io->channel;
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: use of unassigned channel %d\n",
+                  __func__, ch->channel);
+}
+
+static void dbdma_unassigned_flush(DBDMA_io *io)
+{
+    DBDMA_channel *ch = io->channel;
+    qemu_log_mask(LOG_GUEST_ERROR, "%s: use of unassigned channel %d\n",
+                  __func__, ch->channel);
+}
+
 void* DBDMA_init (MemoryRegion **dbdma_mem)
 {
     DBDMAState *s;
@@ -784,8 +800,13 @@ void* DBDMA_init (MemoryRegion **dbdma_mem)
 
     for (i = 0; i < DBDMA_CHANNELS; i++) {
         DBDMA_io *io = &s->channels[i].io;
+        DBDMA_channel *ch = &s->channels[i];
         qemu_iovec_init(&io->iov, 1);
-        s->channels[i].channel = i;
+
+        ch->rw = dbdma_unassigned_rw;
+        ch->flush = dbdma_unassigned_flush;
+        ch->channel = i;
+        ch->io.channel = ch;
     }
 
     memory_region_init_io(&s->mem, NULL, &dbdma_ops, s, "dbdma", 0x1000);

hw/net/fsl_etsec/registers.h

@@ -24,7 +24,6 @@
 #ifndef _ETSEC_REGISTERS_H_
 #define _ETSEC_REGISTERS_H_
 
-#include <stdint.h>
 
 enum eTSEC_Register_Access_Type {
     ACC_RW      = 1,            /* Read/Write */

hw/nvram/fw_cfg.c

@@ -778,17 +778,19 @@ FWCfgState *fw_cfg_init_io_dma(uint32_t iobase, uint32_t dma_iobase,
     DeviceState *dev;
     FWCfgState *s;
     uint32_t version = FW_CFG_VERSION;
-    bool dma_enabled = dma_iobase && dma_as;
+    bool dma_requested = dma_iobase && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_IO);
     qdev_prop_set_uint32(dev, "iobase", iobase);
     qdev_prop_set_uint32(dev, "dma_iobase", dma_iobase);
-    qdev_prop_set_bit(dev, "dma_enabled", dma_enabled);
+    if (!dma_requested) {
+        qdev_prop_set_bit(dev, "dma_enabled", false);
+    }
 
     fw_cfg_init1(dev);
     s = FW_CFG(dev);
 
-    if (dma_enabled) {
+    if (s->dma_enabled) {
         /* 64 bits for the address field */
         s->dma_as = dma_as;
         s->dma_addr = 0;
@@ -814,11 +816,13 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
     SysBusDevice *sbd;
     FWCfgState *s;
     uint32_t version = FW_CFG_VERSION;
-    bool dma_enabled = dma_addr && dma_as;
+    bool dma_requested = dma_addr && dma_as;
 
     dev = qdev_create(NULL, TYPE_FW_CFG_MEM);
     qdev_prop_set_uint32(dev, "data_width", data_width);
-    qdev_prop_set_bit(dev, "dma_enabled", dma_enabled);
+    if (!dma_requested) {
+        qdev_prop_set_bit(dev, "dma_enabled", false);
+    }
 
     fw_cfg_init1(dev);
 
@@ -828,7 +832,7 @@ FWCfgState *fw_cfg_init_mem_wide(hwaddr ctl_addr,
 
     s = FW_CFG(dev);
 
-    if (dma_enabled) {
+    if (s->dma_enabled) {
         s->dma_as = dma_as;
         s->dma_addr = 0;
         sysbus_mmio_map(sbd, 2, dma_addr);
@@ -873,7 +877,7 @@ static Property fw_cfg_io_properties[] = {
     DEFINE_PROP_UINT32("iobase", FWCfgIoState, iobase, -1),
     DEFINE_PROP_UINT32("dma_iobase", FWCfgIoState, dma_iobase, -1),
     DEFINE_PROP_BOOL("dma_enabled", FWCfgIoState, parent_obj.dma_enabled,
-                     false),
+                     true),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -913,7 +917,7 @@ static const TypeInfo fw_cfg_io_info = {
 static Property fw_cfg_mem_properties[] = {
     DEFINE_PROP_UINT32("data_width", FWCfgMemState, data_width, -1),
     DEFINE_PROP_BOOL("dma_enabled", FWCfgMemState, parent_obj.dma_enabled,
-                     false),
+                     true),
     DEFINE_PROP_END_OF_LIST(),
 };
 

hw/pci/pci.c

@@ -278,9 +278,9 @@ static void pcibus_reset(BusState *qbus)
     }
 }
 
-static void pci_host_bus_register(PCIBus *bus, DeviceState *parent)
+static void pci_host_bus_register(DeviceState *host)
 {
-    PCIHostState *host_bridge = PCI_HOST_BRIDGE(parent);
+    PCIHostState *host_bridge = PCI_HOST_BRIDGE(host);
 
     QLIST_INSERT_HEAD(&pci_host_bridges, host_bridge, next);
 }
@@ -331,7 +331,6 @@ const char *pci_root_bus_path(PCIDevice *dev)
 }
 
 static void pci_bus_init(PCIBus *bus, DeviceState *parent,
-                         const char *name,
                          MemoryRegion *address_space_mem,
                          MemoryRegion *address_space_io,
                          uint8_t devfn_min)
@@ -344,7 +343,7 @@ static void pci_bus_init(PCIBus *bus, DeviceState *parent,
     /* host bridge */
     QLIST_INIT(&bus->child);
 
-    pci_host_bus_register(bus, parent);
+    pci_host_bus_register(parent);
 }
 
 bool pci_bus_is_express(PCIBus *bus)
@@ -364,8 +363,7 @@ void pci_bus_new_inplace(PCIBus *bus, size_t bus_size, DeviceState *parent,
                          uint8_t devfn_min, const char *typename)
 {
     qbus_create_inplace(bus, bus_size, typename, parent, name);
-    pci_bus_init(bus, parent, name, address_space_mem,
-                 address_space_io, devfn_min);
+    pci_bus_init(bus, parent, address_space_mem, address_space_io, devfn_min);
 }
 
 PCIBus *pci_bus_new(DeviceState *parent, const char *name,
@@ -376,8 +374,7 @@ PCIBus *pci_bus_new(DeviceState *parent, const char *name,
     PCIBus *bus;
 
     bus = PCI_BUS(qbus_create(typename, parent, name));
-    pci_bus_init(bus, parent, name, address_space_mem,
-                 address_space_io, devfn_min);
+    pci_bus_init(bus, parent, address_space_mem, address_space_io, devfn_min);
     return bus;
 }
 

hw/ppc/spapr.c

@@ -1528,7 +1528,7 @@ static int htab_load(QEMUFile *f, void *opaque, int version_id)
     section_hdr = qemu_get_be32(f);
 
     if (section_hdr) {
-        Error *local_err;
+        Error *local_err = NULL;
 
         /* First section gives the htab size */
         spapr_reallocate_hpt(spapr, section_hdr, &local_err);
@@ -2427,6 +2427,7 @@ static void spapr_machine_2_3_instance_options(MachineState *machine)
     spapr_machine_2_4_instance_options(machine);
     savevm_skip_section_footers();
     global_state_set_optional();
+    savevm_skip_configuration();
 }
 
 static void spapr_machine_2_3_class_options(MachineClass *mc)
@@ -2452,6 +2453,7 @@ DEFINE_SPAPR_MACHINE(2_3, "2.3", false);
 static void spapr_machine_2_2_instance_options(MachineState *machine)
 {
     spapr_machine_2_3_instance_options(machine);
+    machine->suppress_vmdesc = true;
 }
 
 static void spapr_machine_2_2_class_options(MachineClass *mc)

hw/ppc/spapr_events.c

@@ -588,7 +588,8 @@ out_no_events:
 void spapr_events_init(sPAPRMachineState *spapr)
 {
     QTAILQ_INIT(&spapr->pending_events);
-    spapr->check_exception_irq = xics_alloc(spapr->icp, 0, 0, false);
+    spapr->check_exception_irq = xics_alloc(spapr->icp, 0, 0, false,
+                                            &error_fatal);
     spapr->epow_notifier.notify = spapr_powerdown_req;
     qemu_register_powerdown_notifier(&spapr->epow_notifier);
     spapr_rtas_register(RTAS_CHECK_EXCEPTION, "check-exception",

hw/ppc/spapr_hcall.c

@@ -386,6 +386,65 @@ static target_ulong h_set_xdabr(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     return H_SUCCESS;
 }
 
+static target_ulong h_page_init(PowerPCCPU *cpu, sPAPRMachineState *spapr,
+                                target_ulong opcode, target_ulong *args)
+{
+    target_ulong flags = args[0];
+    hwaddr dst = args[1];
+    hwaddr src = args[2];
+    hwaddr len = TARGET_PAGE_SIZE;
+    uint8_t *pdst, *psrc;
+    target_long ret = H_SUCCESS;
+
+    if (flags & ~(H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE
+                  | H_COPY_PAGE | H_ZERO_PAGE)) {
+        qemu_log_mask(LOG_UNIMP, "h_page_init: Bad flags (" TARGET_FMT_lx "\n",
+                      flags);
+        return H_PARAMETER;
+    }
+
+    /* Map-in destination */
+    if (!is_ram_address(spapr, dst) || (dst & ~TARGET_PAGE_MASK) != 0) {
+        return H_PARAMETER;
+    }
+    pdst = cpu_physical_memory_map(dst, &len, 1);
+    if (!pdst || len != TARGET_PAGE_SIZE) {
+        return H_PARAMETER;
+    }
+
+    if (flags & H_COPY_PAGE) {
+        /* Map-in source, copy to destination, and unmap source again */
+        if (!is_ram_address(spapr, src) || (src & ~TARGET_PAGE_MASK) != 0) {
+            ret = H_PARAMETER;
+            goto unmap_out;
+        }
+        psrc = cpu_physical_memory_map(src, &len, 0);
+        if (!psrc || len != TARGET_PAGE_SIZE) {
+            ret = H_PARAMETER;
+            goto unmap_out;
+        }
+        memcpy(pdst, psrc, len);
+        cpu_physical_memory_unmap(psrc, len, 0, len);
+    } else if (flags & H_ZERO_PAGE) {
+        memset(pdst, 0, len);          /* Just clear the destination page */
+    }
+
+    if (kvm_enabled() && (flags & H_ICACHE_SYNCHRONIZE) != 0) {
+        kvmppc_dcbst_range(cpu, pdst, len);
+    }
+    if (flags & (H_ICACHE_SYNCHRONIZE | H_ICACHE_INVALIDATE)) {
+        if (kvm_enabled()) {
+            kvmppc_icbi_range(cpu, pdst, len);
+        } else {
+            tb_flush(CPU(cpu));
+        }
+    }
+
+unmap_out:
+    cpu_physical_memory_unmap(pdst, TARGET_PAGE_SIZE, 1, len);
+    return ret;
+}
+
 #define FLAGS_REGISTER_VPA         0x0000200000000000ULL
 #define FLAGS_REGISTER_DTL         0x0000400000000000ULL
 #define FLAGS_REGISTER_SLBSHADOW   0x0000600000000000ULL
@@ -1045,6 +1104,7 @@ static void hypercall_register_types(void)
     spapr_register_hypercall(H_SET_SPRG0, h_set_sprg0);
     spapr_register_hypercall(H_SET_DABR, h_set_dabr);
     spapr_register_hypercall(H_SET_XDABR, h_set_xdabr);
+    spapr_register_hypercall(H_PAGE_INIT, h_page_init);
     spapr_register_hypercall(H_SET_MODE, h_set_mode);
 
     /* "debugger" hcalls (also used by SLOF). Note: We do -not- differenciate

hw/ppc/spapr_pci.c

@@ -275,11 +275,12 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPRMachineState *spapr,
     unsigned int req_num = rtas_ld(args, 4); /* 0 == remove all */
     unsigned int seq_num = rtas_ld(args, 5);
     unsigned int ret_intr_type;
-    unsigned int irq, max_irqs = 0, num = 0;
+    unsigned int irq, max_irqs = 0;
     sPAPRPHBState *phb = NULL;
     PCIDevice *pdev = NULL;
     spapr_pci_msi *msi;
     int *config_addr_key;
+    Error *err = NULL;
 
     switch (func) {
     case RTAS_CHANGE_MSI_FN:
@@ -305,9 +306,10 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPRMachineState *spapr,
         return;
     }
 
+    msi = (spapr_pci_msi *) g_hash_table_lookup(phb->msi, &config_addr);
+
     /* Releasing MSIs */
     if (!req_num) {
-        msi = (spapr_pci_msi *) g_hash_table_lookup(phb->msi, &config_addr);
         if (!msi) {
             trace_spapr_pci_msi("Releasing wrong config", config_addr);
             rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
@@ -316,10 +318,10 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 
         xics_free(spapr->icp, msi->first_irq, msi->num);
         if (msi_present(pdev)) {
-            spapr_msi_setmsg(pdev, 0, false, 0, num);
+            spapr_msi_setmsg(pdev, 0, false, 0, 0);
         }
         if (msix_present(pdev)) {
-            spapr_msi_setmsg(pdev, 0, true, 0, num);
+            spapr_msi_setmsg(pdev, 0, true, 0, 0);
         }
         g_hash_table_remove(phb->msi, &config_addr);
 
@@ -353,13 +355,20 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPRMachineState *spapr,
 
     /* Allocate MSIs */
     irq = xics_alloc_block(spapr->icp, 0, req_num, false,
-                           ret_intr_type == RTAS_TYPE_MSI);
-    if (!irq) {
-        error_report("Cannot allocate MSIs for device %x", config_addr);
+                           ret_intr_type == RTAS_TYPE_MSI, &err);
+    if (err) {
+        error_reportf_err(err, "Can't allocate MSIs for device %x: ",
+                          config_addr);
         rtas_st(rets, 0, RTAS_OUT_HW_ERROR);
         return;
     }
 
+    /* Release previous MSIs */
+    if (msi) {
+        xics_free(spapr->icp, msi->first_irq, msi->num);
+        g_hash_table_remove(phb->msi, &config_addr);
+    }
+
     /* Setup MSI/MSIX vectors in the device (via cfgspace or MSIX BAR) */
     spapr_msi_setmsg(pdev, SPAPR_PCI_MSI_WINDOW, ret_intr_type == RTAS_TYPE_MSIX,
                      irq, req_num);
@@ -1360,10 +1369,12 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp)
     /* Initialize the LSI table */
     for (i = 0; i < PCI_NUM_PINS; i++) {
         uint32_t irq;
+        Error *local_err = NULL;
 
-        irq = xics_alloc_block(spapr->icp, 0, 1, true, false);
-        if (!irq) {
-            error_setg(errp, "spapr_allocate_lsi failed");
+        irq = xics_alloc_block(spapr->icp, 0, 1, true, false, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            error_prepend(errp, "can't allocate LSIs: ");
             return;
         }
 

hw/ppc/spapr_rng.c

@@ -170,6 +170,7 @@ static void spapr_rng_class_init(ObjectClass *oc, void *data)
     dc->realize = spapr_rng_realize;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     dc->props = spapr_rng_properties;
+    dc->hotpluggable = false;
 }
 
 static const TypeInfo spapr_rng_info = {

hw/ppc/spapr_vio.c

@@ -431,6 +431,7 @@ static void spapr_vio_busdev_realize(DeviceState *qdev, Error **errp)
     VIOsPAPRDevice *dev = (VIOsPAPRDevice *)qdev;
     VIOsPAPRDeviceClass *pc = VIO_SPAPR_DEVICE_GET_CLASS(dev);
     char *id;
+    Error *local_err = NULL;
 
     if (dev->reg != -1) {
         /*
@@ -463,9 +464,9 @@ static void spapr_vio_busdev_realize(DeviceState *qdev, Error **errp)
         dev->qdev.id = id;
     }
 
-    dev->irq = xics_alloc(spapr->icp, 0, dev->irq, false);
-    if (!dev->irq) {
-        error_setg(errp, "can't allocate IRQ");
+    dev->irq = xics_alloc(spapr->icp, 0, dev->irq, false, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         return;
     }
 

hw/scsi/virtio-scsi-dataplane.c

@@ -39,14 +39,10 @@ void virtio_scsi_set_iothread(VirtIOSCSI *s, IOThread *iothread)
     }
 }
 
-static VirtIOSCSIVring *virtio_scsi_vring_init(VirtIOSCSI *s,
-                                               VirtQueue *vq,
-                                               EventNotifierHandler *handler,
-                                               int n)
+static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n)
 {
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
-    VirtIOSCSIVring *r;
     int rc;
 
     /* Set up virtqueue notify */
@@ -55,105 +51,17 @@ static VirtIOSCSIVring *virtio_scsi_vring_init(VirtIOSCSI *s,
         fprintf(stderr, "virtio-scsi: Failed to set host notifier (%d)\n",
                 rc);
         s->dataplane_fenced = true;
-        return NULL;
+        return rc;
     }
 
-    r = g_new(VirtIOSCSIVring, 1);
-    r->host_notifier = *virtio_queue_get_host_notifier(vq);
-    r->guest_notifier = *virtio_queue_get_guest_notifier(vq);
-    aio_set_event_notifier(s->ctx, &r->host_notifier, true, handler);
-
-    r->parent = s;
-
-    if (!vring_setup(&r->vring, VIRTIO_DEVICE(s), n)) {
-        fprintf(stderr, "virtio-scsi: VRing setup failed\n");
-        goto fail_vring;
-    }
-    return r;
-
-fail_vring:
-    aio_set_event_notifier(s->ctx, &r->host_notifier, true, NULL);
-    k->set_host_notifier(qbus->parent, n, false);
-    g_free(r);
-    return NULL;
+    virtio_queue_aio_set_host_notifier_handler(vq, s->ctx, true, true);
+    return 0;
 }
 
-VirtIOSCSIReq *virtio_scsi_pop_req_vring(VirtIOSCSI *s,
-                                         VirtIOSCSIVring *vring)
+void virtio_scsi_dataplane_notify(VirtIODevice *vdev, VirtIOSCSIReq *req)
 {
-    VirtIOSCSICommon *vs = (VirtIOSCSICommon *)s;
-    VirtIOSCSIReq *req;
-
-    req = vring_pop((VirtIODevice *)s, &vring->vring,
-                    sizeof(VirtIOSCSIReq) + vs->cdb_size);
-    if (!req) {
-        return NULL;
-    }
-    virtio_scsi_init_req(s, NULL, req);
-    req->vring = vring;
-    return req;
-}
-
-void virtio_scsi_vring_push_notify(VirtIOSCSIReq *req)
-{
-    VirtIODevice *vdev = VIRTIO_DEVICE(req->vring->parent);
-
-    vring_push(vdev, &req->vring->vring, &req->elem,
-               req->qsgl.size + req->resp_iov.size);
-
-    if (vring_should_notify(vdev, &req->vring->vring)) {
-        event_notifier_set(&req->vring->guest_notifier);
-    }
-}
-
-static void virtio_scsi_iothread_handle_ctrl(EventNotifier *notifier)
-{
-    VirtIOSCSIVring *vring = container_of(notifier,
-                                          VirtIOSCSIVring, host_notifier);
-    VirtIOSCSI *s = VIRTIO_SCSI(vring->parent);
-    VirtIOSCSIReq *req;
-
-    event_notifier_test_and_clear(notifier);
-    while ((req = virtio_scsi_pop_req_vring(s, vring))) {
-        virtio_scsi_handle_ctrl_req(s, req);
-    }
-}
-
-static void virtio_scsi_iothread_handle_event(EventNotifier *notifier)
-{
-    VirtIOSCSIVring *vring = container_of(notifier,
-                                          VirtIOSCSIVring, host_notifier);
-    VirtIOSCSI *s = vring->parent;
-    VirtIODevice *vdev = VIRTIO_DEVICE(s);
-
-    event_notifier_test_and_clear(notifier);
-
-    if (!(vdev->status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-        return;
-    }
-
-    if (s->events_dropped) {
-        virtio_scsi_push_event(s, NULL, VIRTIO_SCSI_T_NO_EVENT, 0);
-    }
-}
-
-static void virtio_scsi_iothread_handle_cmd(EventNotifier *notifier)
-{
-    VirtIOSCSIVring *vring = container_of(notifier,
-                                          VirtIOSCSIVring, host_notifier);
-    VirtIOSCSI *s = (VirtIOSCSI *)vring->parent;
-    VirtIOSCSIReq *req, *next;
-    QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs);
-
-    event_notifier_test_and_clear(notifier);
-    while ((req = virtio_scsi_pop_req_vring(s, vring))) {
-        if (virtio_scsi_handle_cmd_req_prepare(s, req)) {
-            QTAILQ_INSERT_TAIL(&reqs, req, next);
-        }
-    }
-
-    QTAILQ_FOREACH_SAFE(req, &reqs, next, next) {
-        virtio_scsi_handle_cmd_req_submit(s, req);
+    if (virtio_should_notify(vdev, req->vq)) {
+        event_notifier_set(virtio_queue_get_guest_notifier(req->vq));
     }
 }
 
@@ -163,46 +71,10 @@ static void virtio_scsi_clear_aio(VirtIOSCSI *s)
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
     int i;
 
-    if (s->ctrl_vring) {
-        aio_set_event_notifier(s->ctx, &s->ctrl_vring->host_notifier,
-                               true, NULL);
-    }
-    if (s->event_vring) {
-        aio_set_event_notifier(s->ctx, &s->event_vring->host_notifier,
-                               true, NULL);
-    }
-    if (s->cmd_vrings) {
-        for (i = 0; i < vs->conf.num_queues && s->cmd_vrings[i]; i++) {
-            aio_set_event_notifier(s->ctx, &s->cmd_vrings[i]->host_notifier,
-                                   true, NULL);
-        }
-    }
-}
-
-static void virtio_scsi_vring_teardown(VirtIOSCSI *s)
-{
-    VirtIODevice *vdev = VIRTIO_DEVICE(s);
-    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
-    int i;
-
-    if (s->ctrl_vring) {
-        vring_teardown(&s->ctrl_vring->vring, vdev, 0);
-        g_free(s->ctrl_vring);
-        s->ctrl_vring = NULL;
-    }
-    if (s->event_vring) {
-        vring_teardown(&s->event_vring->vring, vdev, 1);
-        g_free(s->event_vring);
-        s->event_vring = NULL;
-    }
-    if (s->cmd_vrings) {
-        for (i = 0; i < vs->conf.num_queues && s->cmd_vrings[i]; i++) {
-            vring_teardown(&s->cmd_vrings[i]->vring, vdev, 2 + i);
-            g_free(s->cmd_vrings[i]);
-            s->cmd_vrings[i] = NULL;
-        }
-        free(s->cmd_vrings);
-        s->cmd_vrings = NULL;
+    virtio_queue_aio_set_host_notifier_handler(vs->ctrl_vq, s->ctx, false, false);
+    virtio_queue_aio_set_host_notifier_handler(vs->event_vq, s->ctx, false, false);
+    for (i = 0; i < vs->conf.num_queues; i++) {
+        virtio_queue_aio_set_host_notifier_handler(vs->cmd_vqs[i], s->ctx, false, false);
     }
 }
 
@@ -229,30 +101,21 @@ void virtio_scsi_dataplane_start(VirtIOSCSI *s)
     if (rc != 0) {
         fprintf(stderr, "virtio-scsi: Failed to set guest notifiers (%d), "
                 "ensure -enable-kvm is set\n", rc);
-        s->dataplane_fenced = true;
         goto fail_guest_notifiers;
     }
 
     aio_context_acquire(s->ctx);
-    s->ctrl_vring = virtio_scsi_vring_init(s, vs->ctrl_vq,
-                                           virtio_scsi_iothread_handle_ctrl,
-                                           0);
-    if (!s->ctrl_vring) {
+    rc = virtio_scsi_vring_init(s, vs->ctrl_vq, 0);
+    if (rc) {
         goto fail_vrings;
     }
-    s->event_vring = virtio_scsi_vring_init(s, vs->event_vq,
-                                            virtio_scsi_iothread_handle_event,
-                                            1);
-    if (!s->event_vring) {
+    rc = virtio_scsi_vring_init(s, vs->event_vq, 1);
+    if (rc) {
         goto fail_vrings;
     }
-    s->cmd_vrings = g_new(VirtIOSCSIVring *, vs->conf.num_queues);
     for (i = 0; i < vs->conf.num_queues; i++) {
-        s->cmd_vrings[i] =
-            virtio_scsi_vring_init(s, vs->cmd_vqs[i],
-                                   virtio_scsi_iothread_handle_cmd,
-                                   i + 2);
-        if (!s->cmd_vrings[i]) {
+        rc = virtio_scsi_vring_init(s, vs->cmd_vqs[i], i + 2);
+        if (rc) {
             goto fail_vrings;
         }
     }
@@ -265,13 +128,14 @@ void virtio_scsi_dataplane_start(VirtIOSCSI *s)
 fail_vrings:
     virtio_scsi_clear_aio(s);
     aio_context_release(s->ctx);
-    virtio_scsi_vring_teardown(s);
     for (i = 0; i < vs->conf.num_queues + 2; i++) {
         k->set_host_notifier(qbus->parent, i, false);
     }
     k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, false);
 fail_guest_notifiers:
+    s->dataplane_fenced = true;
     s->dataplane_starting = false;
+    s->dataplane_started = true;
 }
 
 /* Context: QEMU global mutex held */
@@ -282,12 +146,14 @@ void virtio_scsi_dataplane_stop(VirtIOSCSI *s)
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
     int i;
 
+    if (!s->dataplane_started || s->dataplane_stopping) {
+        return;
+    }
+
     /* Better luck next time. */
     if (s->dataplane_fenced) {
         s->dataplane_fenced = false;
-        return;
-    }
-    if (!s->dataplane_started || s->dataplane_stopping) {
+        s->dataplane_started = false;
         return;
     }
     s->dataplane_stopping = true;
@@ -295,24 +161,12 @@ void virtio_scsi_dataplane_stop(VirtIOSCSI *s)
 
     aio_context_acquire(s->ctx);
 
-    aio_set_event_notifier(s->ctx, &s->ctrl_vring->host_notifier,
-                           true, NULL);
-    aio_set_event_notifier(s->ctx, &s->event_vring->host_notifier,
-                           true, NULL);
-    for (i = 0; i < vs->conf.num_queues; i++) {
-        aio_set_event_notifier(s->ctx, &s->cmd_vrings[i]->host_notifier,
-                               true, NULL);
-    }
+    virtio_scsi_clear_aio(s);
 
     blk_drain_all(); /* ensure there are no in-flight requests */
 
     aio_context_release(s->ctx);
 
-    /* Sync vring state back to virtqueue so that non-dataplane request
-     * processing can continue when we disable the host notifier below.
-     */
-    virtio_scsi_vring_teardown(s);
-
     for (i = 0; i < vs->conf.num_queues + 2; i++) {
         k->set_host_notifier(qbus->parent, i, false);
     }

hw/scsi/virtio-scsi.c

@@ -23,7 +23,6 @@
 #include <block/scsi.h>
 #include <hw/virtio/virtio-bus.h>
 #include "hw/virtio/virtio-access.h"
-#include "migration/migration.h"
 
 static inline int virtio_scsi_get_lun(uint8_t *lun)
 {
@@ -43,7 +42,8 @@ static inline SCSIDevice *virtio_scsi_device_find(VirtIOSCSI *s, uint8_t *lun)
 
 void virtio_scsi_init_req(VirtIOSCSI *s, VirtQueue *vq, VirtIOSCSIReq *req)
 {
-    const size_t zero_skip = offsetof(VirtIOSCSIReq, vring);
+    const size_t zero_skip =
+        offsetof(VirtIOSCSIReq, resp_iov) + sizeof(req->resp_iov);
 
     req->vq = vq;
     req->dev = s;
@@ -66,11 +66,10 @@ static void virtio_scsi_complete_req(VirtIOSCSIReq *req)
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
 
     qemu_iovec_from_buf(&req->resp_iov, 0, &req->resp, req->resp_size);
-    if (req->vring) {
-        assert(req->vq == NULL);
-        virtio_scsi_vring_push_notify(req);
+    virtqueue_push(vq, &req->elem, req->qsgl.size + req->resp_iov.size);
+    if (s->dataplane_started) {
+        virtio_scsi_dataplane_notify(vdev, req);
     } else {
-        virtqueue_push(vq, &req->elem, req->qsgl.size + req->resp_iov.size);
         virtio_notify(vdev, vq);
     }
 
@@ -417,7 +416,7 @@ static void virtio_scsi_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
     VirtIOSCSI *s = (VirtIOSCSI *)vdev;
     VirtIOSCSIReq *req;
 
-    if (s->ctx && !s->dataplane_disabled) {
+    if (s->ctx && !s->dataplane_started) {
         virtio_scsi_dataplane_start(s);
         return;
     }
@@ -567,7 +566,7 @@ static void virtio_scsi_handle_cmd(VirtIODevice *vdev, VirtQueue *vq)
     VirtIOSCSIReq *req, *next;
     QTAILQ_HEAD(, VirtIOSCSIReq) reqs = QTAILQ_HEAD_INITIALIZER(reqs);
 
-    if (s->ctx && !s->dataplane_disabled) {
+    if (s->ctx && !s->dataplane_started) {
         virtio_scsi_dataplane_start(s);
         return;
     }
@@ -687,11 +686,7 @@ void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
         aio_context_acquire(s->ctx);
     }
 
-    if (s->dataplane_started) {
-        req = virtio_scsi_pop_req_vring(s, s->event_vring);
-    } else {
-        req = virtio_scsi_pop_req(s, vs->event_vq);
-    }
+    req = virtio_scsi_pop_req(s, vs->event_vq);
     if (!req) {
         s->events_dropped = true;
         goto out;
@@ -733,7 +728,7 @@ static void virtio_scsi_handle_event(VirtIODevice *vdev, VirtQueue *vq)
 {
     VirtIOSCSI *s = VIRTIO_SCSI(vdev);
 
-    if (s->ctx && !s->dataplane_disabled) {
+    if (s->ctx && !s->dataplane_started) {
         virtio_scsi_dataplane_start(s);
         return;
     }
@@ -901,31 +896,6 @@ void virtio_scsi_common_realize(DeviceState *dev, Error **errp,
     }
 }
 
-/* Disable dataplane thread during live migration since it does not
- * update the dirty memory bitmap yet.
- */
-static void virtio_scsi_migration_state_changed(Notifier *notifier, void *data)
-{
-    VirtIOSCSI *s = container_of(notifier, VirtIOSCSI,
-                                 migration_state_notifier);
-    MigrationState *mig = data;
-
-    if (migration_in_setup(mig)) {
-        if (!s->dataplane_started) {
-            return;
-        }
-        virtio_scsi_dataplane_stop(s);
-        s->dataplane_disabled = true;
-    } else if (migration_has_finished(mig) ||
-               migration_has_failed(mig)) {
-        if (s->dataplane_started) {
-            return;
-        }
-        blk_drain_all(); /* complete in-flight non-dataplane requests */
-        s->dataplane_disabled = false;
-    }
-}
-
 static void virtio_scsi_device_realize(DeviceState *dev, Error **errp)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
@@ -956,8 +926,6 @@ static void virtio_scsi_device_realize(DeviceState *dev, Error **errp)
 
     register_savevm(dev, "virtio-scsi", virtio_scsi_id++, 1,
                     virtio_scsi_save, virtio_scsi_load, s);
-    s->migration_state_notifier.notify = virtio_scsi_migration_state_changed;
-    add_migration_state_change_notifier(&s->migration_state_notifier);
 
     error_setg(&s->blocker, "block device is in use by data plane");
 
@@ -991,8 +959,6 @@ static void virtio_scsi_device_unrealize(DeviceState *dev, Error **errp)
     error_free(s->blocker);
 
     unregister_savevm(dev, "virtio-scsi", s);
-    remove_migration_state_change_notifier(&s->migration_state_notifier);
-
     virtio_scsi_common_unrealize(dev, errp);
 }
 

hw/sd/sdhci.c

@@ -198,14 +198,13 @@ static void sdhci_reset(SDHCIState *s)
      * initialization */
     memset(&s->sdmasysad, 0, (uintptr_t)&s->capareg - (uintptr_t)&s->sdmasysad);
 
-    if (!s->noeject_quirk) {
-        /* Reset other state based on current card insertion/readonly status */
-        sdhci_set_inserted(dev, sdbus_get_inserted(&s->sdbus));
-        sdhci_set_readonly(dev, sdbus_get_readonly(&s->sdbus));
-    }
+    /* Reset other state based on current card insertion/readonly status */
+    sdhci_set_inserted(dev, sdbus_get_inserted(&s->sdbus));
+    sdhci_set_readonly(dev, sdbus_get_readonly(&s->sdbus));
 
     s->data_count = 0;
     s->stopped_state = sdhc_not_stopped;
+    s->pending_insert_state = false;
 }
 
 static void sdhci_data_transfer(void *opaque);
@@ -1097,6 +1096,13 @@ sdhci_write(void *opaque, hwaddr offset, uint64_t val, unsigned size)
         } else {
             s->norintsts &= ~SDHC_NIS_ERR;
         }
+        /* Quirk for Raspberry Pi: pending card insert interrupt
+         * appears when first enabled after power on */
+        if ((s->norintstsen & SDHC_NISEN_INSERT) && s->pending_insert_state) {
+            assert(s->pending_insert_quirk);
+            s->norintsts |= SDHC_NIS_INSERT;
+            s->pending_insert_state = false;
+        }
         sdhci_update_irq(s);
         break;
     case SDHC_NORINTSIGEN:
@@ -1183,6 +1189,24 @@ static void sdhci_uninitfn(SDHCIState *s)
     s->fifo_buffer = NULL;
 }
 
+static bool sdhci_pending_insert_vmstate_needed(void *opaque)
+{
+    SDHCIState *s = opaque;
+
+    return s->pending_insert_state;
+}
+
+static const VMStateDescription sdhci_pending_insert_vmstate = {
+    .name = "sdhci/pending-insert",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = sdhci_pending_insert_vmstate_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_BOOL(pending_insert_state, SDHCIState),
+        VMSTATE_END_OF_LIST()
+    },
+};
+
 const VMStateDescription sdhci_vmstate = {
     .name = "sdhci",
     .version_id = 1,
@@ -1217,7 +1241,11 @@ const VMStateDescription sdhci_vmstate = {
         VMSTATE_TIMER_PTR(insert_timer, SDHCIState),
         VMSTATE_TIMER_PTR(transfer_timer, SDHCIState),
         VMSTATE_END_OF_LIST()
-    }
+    },
+    .subsections = (const VMStateDescription*[]) {
+        &sdhci_pending_insert_vmstate,
+        NULL
+    },
 };
 
 /* Capabilities registers provide information on supported features of this
@@ -1275,7 +1303,8 @@ static Property sdhci_sysbus_properties[] = {
     DEFINE_PROP_UINT32("capareg", SDHCIState, capareg,
             SDHC_CAPAB_REG_DEFAULT),
     DEFINE_PROP_UINT32("maxcurr", SDHCIState, maxcurr, 0),
-    DEFINE_PROP_BOOL("noeject-quirk", SDHCIState, noeject_quirk, false),
+    DEFINE_PROP_BOOL("pending-insert-quirk", SDHCIState, pending_insert_quirk,
+                     false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -1303,6 +1332,10 @@ static void sdhci_sysbus_realize(DeviceState *dev, Error ** errp)
     memory_region_init_io(&s->iomem, OBJECT(s), &sdhci_mmio_ops, s, "sdhci",
             SDHC_REGISTERS_MAP_SIZE);
     sysbus_init_mmio(sbd, &s->iomem);
+
+    if (s->pending_insert_quirk) {
+        s->pending_insert_state = true;
+    }
 }
 
 static void sdhci_sysbus_class_init(ObjectClass *klass, void *data)

hw/timer/Makefile.objs

@@ -25,7 +25,6 @@ obj-$(CONFIG_OMAP) += omap_gptimer.o
 obj-$(CONFIG_OMAP) += omap_synctimer.o
 obj-$(CONFIG_PXA2XX) += pxa2xx_timer.o
 obj-$(CONFIG_SH4) += sh_timer.o
-obj-$(CONFIG_TUSB6010) += tusb6010.o
 obj-$(CONFIG_DIGIC) += digic-timer.o
 
 obj-$(CONFIG_MC146818RTC) += mc146818rtc.o

hw/usb/Makefile.objs

@@ -10,6 +10,8 @@ common-obj-$(CONFIG_USB_EHCI_SYSBUS) += hcd-ehci-sysbus.o
 common-obj-$(CONFIG_USB_XHCI) += hcd-xhci.o
 common-obj-$(CONFIG_USB_MUSB) += hcd-musb.o
 
+obj-$(CONFIG_TUSB6010) += tusb6010.o
+
 # emulated usb devices
 common-obj-$(CONFIG_USB) += dev-hub.o
 common-obj-$(CONFIG_USB) += dev-hid.o

hw/usb/core.c

@@ -129,9 +129,16 @@ static void do_token_setup(USBDevice *s, USBPacket *p)
     }
 
     usb_packet_copy(p, s->setup_buf, p->iov.size);
+    s->setup_index = 0;
     p->actual_length = 0;
     s->setup_len   = (s->setup_buf[7] << 8) | s->setup_buf[6];
-    s->setup_index = 0;
+    if (s->setup_len > sizeof(s->data_buf)) {
+        fprintf(stderr,
+                "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n",
+                s->setup_len, sizeof(s->data_buf));
+        p->status = USB_RET_STALL;
+        return;
+    }
 
     request = (s->setup_buf[0] << 8) | s->setup_buf[1];
     value   = (s->setup_buf[3] << 8) | s->setup_buf[2];
@@ -152,13 +159,6 @@ static void do_token_setup(USBDevice *s, USBPacket *p)
         }
         s->setup_state = SETUP_STATE_DATA;
     } else {
-        if (s->setup_len > sizeof(s->data_buf)) {
-            fprintf(stderr,
-                "usb_generic_handle_packet: ctrl buffer too small (%d > %zu)\n",
-                s->setup_len, sizeof(s->data_buf));
-            p->status = USB_RET_STALL;
-            return;
-        }
         if (s->setup_len == 0)
             s->setup_state = SETUP_STATE_ACK;
         else
@@ -177,7 +177,7 @@ static void do_token_in(USBDevice *s, USBPacket *p)
     request = (s->setup_buf[0] << 8) | s->setup_buf[1];
     value   = (s->setup_buf[3] << 8) | s->setup_buf[2];
     index   = (s->setup_buf[5] << 8) | s->setup_buf[4];
- 
+
     switch(s->setup_state) {
     case SETUP_STATE_ACK:
         if (!(s->setup_buf[0] & USB_DIR_IN)) {

hw/usb/desc.h

@@ -1,7 +1,6 @@
 #ifndef QEMU_HW_USB_DESC_H
 #define QEMU_HW_USB_DESC_H
 
-#include <inttypes.h>
 #include <wchar.h>
 
 /* binary representation */

hw/usb/dev-network.c

@@ -654,7 +654,8 @@ typedef struct USBNetState {
 
 static int is_rndis(USBNetState *s)
 {
-    return s->dev.config->bConfigurationValue == DEV_RNDIS_CONFIG_VALUE;
+    return s->dev.config ?
+            s->dev.config->bConfigurationValue == DEV_RNDIS_CONFIG_VALUE : 0;
 }
 
 static int ndis_query(USBNetState *s, uint32_t oid,
@@ -915,8 +916,9 @@ static int rndis_query_response(USBNetState *s,
 
     bufoffs = le32_to_cpu(buf->InformationBufferOffset) + 8;
     buflen = le32_to_cpu(buf->InformationBufferLength);
-    if (bufoffs + buflen > length)
+    if (buflen > length || bufoffs >= length || bufoffs + buflen > length) {
         return USB_RET_STALL;
+    }
 
     infobuflen = ndis_query(s, le32_to_cpu(buf->OID),
                             bufoffs + (uint8_t *) buf, buflen, infobuf,
@@ -961,8 +963,9 @@ static int rndis_set_response(USBNetState *s,
 
     bufoffs = le32_to_cpu(buf->InformationBufferOffset) + 8;
     buflen = le32_to_cpu(buf->InformationBufferLength);
-    if (bufoffs + buflen > length)
+    if (buflen > length || bufoffs >= length || bufoffs + buflen > length) {
         return USB_RET_STALL;
+    }
 
     ret = ndis_set(s, le32_to_cpu(buf->OID),
                     bufoffs + (uint8_t *) buf, buflen);
@@ -1212,8 +1215,9 @@ static void usb_net_handle_dataout(USBNetState *s, USBPacket *p)
     if (le32_to_cpu(msg->MessageType) == RNDIS_PACKET_MSG) {
         uint32_t offs = 8 + le32_to_cpu(msg->DataOffset);
         uint32_t size = le32_to_cpu(msg->DataLength);
-        if (offs + size <= len)
+        if (offs < len && size < len && offs + size <= len) {
             qemu_send_packet(qemu_get_queue(s->nic), s->out_buf + offs, size);
+        }
     }
     s->out_ptr -= len;
     memmove(s->out_buf, &s->out_buf[len], s->out_ptr);

hw/usb/hcd-ohci.c

@@ -1347,16 +1347,6 @@ static void ohci_frame_boundary(void *opaque)
  */
 static int ohci_bus_start(OHCIState *ohci)
 {
-    ohci->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
-                    ohci_frame_boundary,
-                    ohci);
-
-    if (ohci->eof_timer == NULL) {
-        trace_usb_ohci_bus_eof_timer_failed(ohci->name);
-        ohci_die(ohci);
-        return 0;
-    }
-
     trace_usb_ohci_start(ohci->name);
 
     /* Delay the first SOF event by one frame time as
@@ -1373,11 +1363,7 @@ static int ohci_bus_start(OHCIState *ohci)
 static void ohci_bus_stop(OHCIState *ohci)
 {
     trace_usb_ohci_stop(ohci->name);
-    if (ohci->eof_timer) {
-        timer_del(ohci->eof_timer);
-        timer_free(ohci->eof_timer);
-    }
-    ohci->eof_timer = NULL;
+    timer_del(ohci->eof_timer);
 }
 
 /* Sets a flag in a port status register but only set it if the port is
@@ -1907,6 +1893,9 @@ static void usb_ohci_init(OHCIState *ohci, DeviceState *dev,
     usb_packet_init(&ohci->usb_packet);
 
     ohci->async_td = 0;
+
+    ohci->eof_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
+                                   ohci_frame_boundary, ohci);
 }
 
 #define TYPE_PCI_OHCI "pci-ohci"
@@ -1976,6 +1965,9 @@ static void usb_ohci_exit(PCIDevice *dev)
     if (!ohci->masterbus) {
         usb_bus_release(&s->bus);
     }
+
+    timer_del(s->eof_timer);
+    timer_free(s->eof_timer);
 }
 
 static void usb_ohci_reset_pci(DeviceState *d)
@@ -2041,23 +2033,13 @@ static bool ohci_eof_timer_needed(void *opaque)
 {
     OHCIState *ohci = opaque;
 
-    return ohci->eof_timer != NULL;
-}
-
-static int ohci_eof_timer_pre_load(void *opaque)
-{
-    OHCIState *ohci = opaque;
-
-    ohci_bus_start(ohci);
-
-    return 0;
+    return timer_pending(ohci->eof_timer);
 }
 
 static const VMStateDescription vmstate_ohci_eof_timer = {
     .name = "ohci-core/eof-timer",
     .version_id = 1,
     .minimum_version_id = 1,
-    .pre_load = ohci_eof_timer_pre_load,
     .needed = ohci_eof_timer_needed,
     .fields = (VMStateField[]) {
         VMSTATE_TIMER_PTR(eof_timer, OHCIState),

hw/usb/hcd-uhci.c

@@ -773,8 +773,22 @@ static int uhci_handle_td(UHCIState *s, UHCIQueue *q, uint32_t qh_addr,
     bool spd;
     bool queuing = (q != NULL);
     uint8_t pid = td->token & 0xff;
-    UHCIAsync *async = uhci_async_find_td(s, td_addr);
+    UHCIAsync *async;
 
+    switch (pid) {
+    case USB_TOKEN_OUT:
+    case USB_TOKEN_SETUP:
+    case USB_TOKEN_IN:
+        break;
+    default:
+        /* invalid pid : frame interrupted */
+        s->status |= UHCI_STS_HCPERR;
+        s->cmd &= ~UHCI_CMD_RS;
+        uhci_update_irq(s);
+        return TD_RESULT_STOP_FRAME;
+    }
+
+    async = uhci_async_find_td(s, td_addr);
     if (async) {
         if (uhci_queue_verify(async->queue, qh_addr, td, td_addr, queuing)) {
             assert(q == NULL || q == async->queue);
@@ -880,11 +894,7 @@ static int uhci_handle_td(UHCIState *s, UHCIQueue *q, uint32_t qh_addr,
         break;
 
     default:
-        /* invalid pid : frame interrupted */
-        uhci_async_free(async);
-        s->status |= UHCI_STS_HCPERR;
-        uhci_update_irq(s);
-        return TD_RESULT_STOP_FRAME;
+        abort(); /* Never to execute */
     }
 
     if (async->packet.status == USB_RET_ASYNC) {

hw/usb/redirect.c

@@ -447,7 +447,7 @@ static USBPacket *usbredir_find_packet_by_id(USBRedirDevice *dev,
     return p;
 }
 
-static void bufp_alloc(USBRedirDevice *dev, uint8_t *data, uint16_t len,
+static int bufp_alloc(USBRedirDevice *dev, uint8_t *data, uint16_t len,
     uint8_t status, uint8_t ep, void *free_on_destroy)
 {
     struct buf_packet *bufp;
@@ -464,7 +464,7 @@ static void bufp_alloc(USBRedirDevice *dev, uint8_t *data, uint16_t len,
         if (dev->endpoint[EP2I(ep)].bufpq_size >
                 dev->endpoint[EP2I(ep)].bufpq_target_size) {
             free(data);
-            return;
+            return -1;
         }
         dev->endpoint[EP2I(ep)].bufpq_dropping_packets = 0;
     }
@@ -477,6 +477,7 @@ static void bufp_alloc(USBRedirDevice *dev, uint8_t *data, uint16_t len,
     bufp->free_on_destroy = free_on_destroy;
     QTAILQ_INSERT_TAIL(&dev->endpoint[EP2I(ep)].bufpq, bufp, next);
     dev->endpoint[EP2I(ep)].bufpq_size++;
+    return 0;
 }
 
 static void bufp_free(USBRedirDevice *dev, struct buf_packet *bufp,
@@ -2082,13 +2083,17 @@ static void usbredir_buffered_bulk_packet(void *priv, uint64_t id,
     status = usb_redir_success;
     free_on_destroy = NULL;
     for (i = 0; i < data_len; i += len) {
+        int r;
         if (len >= (data_len - i)) {
             len = data_len - i;
             status = buffered_bulk_packet->status;
             free_on_destroy = data;
         }
         /* bufp_alloc also adds the packet to the ep queue */
-        bufp_alloc(dev, data + i, len, status, ep, free_on_destroy);
+        r = bufp_alloc(dev, data + i, len, status, ep, free_on_destroy);
+        if (r) {
+            break;
+        }
     }
 
     if (dev->endpoint[EP2I(ep)].pending_async_packet) {

hw/vfio/amd-xgbe.c

@@ -11,6 +11,7 @@
  *
  */
 
+#include "qemu/osdep.h"
 #include "hw/vfio/vfio-amd-xgbe.h"
 
 static void amd_xgbe_realize(DeviceState *dev, Error **errp)

hw/virtio/Makefile.objs

@@ -2,7 +2,6 @@ common-obj-y += virtio-rng.o
 common-obj-$(CONFIG_VIRTIO_PCI) += virtio-pci.o
 common-obj-y += virtio-bus.o
 common-obj-y += virtio-mmio.o
-obj-$(CONFIG_VIRTIO) += dataplane/
 
 obj-y += virtio.o virtio-balloon.o 
 obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o vhost-user.o

hw/virtio/dataplane/Makefile.objs

@@ -1 +0,0 @@
-obj-y += vring.o

hw/virtio/dataplane/vring.c

@@ -1,549 +0,0 @@
-/* Copyright 2012 Red Hat, Inc.
- * Copyright IBM, Corp. 2012
- *
- * Based on Linux 2.6.39 vhost code:
- * Copyright (C) 2009 Red Hat, Inc.
- * Copyright (C) 2006 Rusty Russell IBM Corporation
- *
- * Author: Michael S. Tsirkin <mst@redhat.com>
- *         Stefan Hajnoczi <stefanha@redhat.com>
- *
- * Inspiration, some code, and most witty comments come from
- * Documentation/virtual/lguest/lguest.c, by Rusty Russell
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
- */
-
-#include "qemu/osdep.h"
-#include "trace.h"
-#include "hw/hw.h"
-#include "exec/memory.h"
-#include "exec/address-spaces.h"
-#include "hw/virtio/virtio-access.h"
-#include "hw/virtio/dataplane/vring.h"
-#include "hw/virtio/dataplane/vring-accessors.h"
-#include "qemu/error-report.h"
-
-/* vring_map can be coupled with vring_unmap or (if you still have the
- * value returned in *mr) memory_region_unref.
- * Returns NULL on failure.
- * Callers that can handle a partial mapping must supply mapped_len pointer to
- * get the actual length mapped.
- * Passing mapped_len == NULL requires either a full mapping or a failure.
- */
-static void *vring_map(MemoryRegion **mr, hwaddr phys,
-                       hwaddr len, hwaddr *mapped_len,
-                       bool is_write)
-{
-    MemoryRegionSection section = memory_region_find(get_system_memory(), phys, len);
-    uint64_t size;
-
-    if (!section.mr) {
-        goto out;
-    }
-
-    size = int128_get64(section.size);
-    assert(size);
-
-    /* Passing mapped_len == NULL requires either a full mapping or a failure. */
-    if (!mapped_len && size < len) {
-        goto out;
-    }
-
-    if (is_write && section.readonly) {
-        goto out;
-    }
-    if (!memory_region_is_ram(section.mr)) {
-        goto out;
-    }
-
-    /* Ignore regions with dirty logging, we cannot mark them dirty */
-    if (memory_region_get_dirty_log_mask(section.mr)) {
-        goto out;
-    }
-
-    if (mapped_len) {
-        *mapped_len = MIN(size, len);
-    }
-
-    *mr = section.mr;
-    return memory_region_get_ram_ptr(section.mr) + section.offset_within_region;
-
-out:
-    memory_region_unref(section.mr);
-    *mr = NULL;
-    return NULL;
-}
-
-static void vring_unmap(void *buffer, bool is_write)
-{
-    ram_addr_t addr;
-    MemoryRegion *mr;
-
-    mr = qemu_ram_addr_from_host(buffer, &addr);
-    memory_region_unref(mr);
-}
-
-/* Map the guest's vring to host memory */
-bool vring_setup(Vring *vring, VirtIODevice *vdev, int n)
-{
-    struct vring *vr = &vring->vr;
-    hwaddr addr;
-    hwaddr size;
-    void *ptr;
-
-    vring->broken = false;
-    vr->num = virtio_queue_get_num(vdev, n);
-
-    addr = virtio_queue_get_desc_addr(vdev, n);
-    size = virtio_queue_get_desc_size(vdev, n);
-    /* Map the descriptor area as read only */
-    ptr = vring_map(&vring->mr_desc, addr, size, NULL, false);
-    if (!ptr) {
-        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring desc "
-                     "at 0x%" HWADDR_PRIx,
-                      size, addr);
-        goto out_err_desc;
-    }
-    vr->desc = ptr;
-
-    addr = virtio_queue_get_avail_addr(vdev, n);
-    size = virtio_queue_get_avail_size(vdev, n);
-    /* Add the size of the used_event_idx */
-    size += sizeof(uint16_t);
-    /* Map the driver area as read only */
-    ptr = vring_map(&vring->mr_avail, addr, size, NULL, false);
-    if (!ptr) {
-        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring avail "
-                     "at 0x%" HWADDR_PRIx,
-                      size, addr);
-        goto out_err_avail;
-    }
-    vr->avail = ptr;
-
-    addr = virtio_queue_get_used_addr(vdev, n);
-    size = virtio_queue_get_used_size(vdev, n);
-    /* Add the size of the avail_event_idx */
-    size += sizeof(uint16_t);
-    /* Map the device area as read-write */
-    ptr = vring_map(&vring->mr_used, addr, size, NULL, true);
-    if (!ptr) {
-        error_report("Failed to map 0x%" HWADDR_PRIx " byte for vring used "
-                     "at 0x%" HWADDR_PRIx,
-                      size, addr);
-        goto out_err_used;
-    }
-    vr->used = ptr;
-
-    vring->last_avail_idx = virtio_queue_get_last_avail_idx(vdev, n);
-    vring->last_used_idx = vring_get_used_idx(vdev, vring);
-    vring->signalled_used = 0;
-    vring->signalled_used_valid = false;
-
-    trace_vring_setup(virtio_queue_get_ring_addr(vdev, n),
-                      vring->vr.desc, vring->vr.avail, vring->vr.used);
-    return true;
-
-out_err_used:
-    memory_region_unref(vring->mr_avail);
-out_err_avail:
-    memory_region_unref(vring->mr_desc);
-out_err_desc:
-    vring->broken = true;
-    return false;
-}
-
-void vring_teardown(Vring *vring, VirtIODevice *vdev, int n)
-{
-    virtio_queue_set_last_avail_idx(vdev, n, vring->last_avail_idx);
-    virtio_queue_invalidate_signalled_used(vdev, n);
-
-    memory_region_unref(vring->mr_desc);
-    memory_region_unref(vring->mr_avail);
-    memory_region_unref(vring->mr_used);
-}
-
-/* Disable guest->host notifies */
-void vring_disable_notification(VirtIODevice *vdev, Vring *vring)
-{
-    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
-        vring_set_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
-    }
-}
-
-/* Enable guest->host notifies
- *
- * Return true if the vring is empty, false if there are more requests.
- */
-bool vring_enable_notification(VirtIODevice *vdev, Vring *vring)
-{
-    if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
-        vring_avail_event(&vring->vr) = vring->vr.avail->idx;
-    } else {
-        vring_clear_used_flags(vdev, vring, VRING_USED_F_NO_NOTIFY);
-    }
-    smp_mb(); /* ensure update is seen before reading avail_idx */
-    return !vring_more_avail(vdev, vring);
-}
-
-/* This is stolen from linux/drivers/vhost/vhost.c:vhost_notify() */
-bool vring_should_notify(VirtIODevice *vdev, Vring *vring)
-{
-    uint16_t old, new;
-    bool v;
-    /* Flush out used index updates. This is paired
-     * with the barrier that the Guest executes when enabling
-     * interrupts. */
-    smp_mb();
-
-    if (virtio_vdev_has_feature(vdev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
-        unlikely(!vring_more_avail(vdev, vring))) {
-        return true;
-    }
-
-    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
-        return !(vring_get_avail_flags(vdev, vring) &
-                 VRING_AVAIL_F_NO_INTERRUPT);
-    }
-    old = vring->signalled_used;
-    v = vring->signalled_used_valid;
-    new = vring->signalled_used = vring->last_used_idx;
-    vring->signalled_used_valid = true;
-
-    if (unlikely(!v)) {
-        return true;
-    }
-
-    return vring_need_event(virtio_tswap16(vdev, vring_used_event(&vring->vr)),
-                            new, old);
-}
-
-typedef struct VirtQueueCurrentElement {
-    unsigned in_num;
-    unsigned out_num;
-    hwaddr addr[VIRTQUEUE_MAX_SIZE];
-    struct iovec iov[VIRTQUEUE_MAX_SIZE];
-} VirtQueueCurrentElement;
-
-static int get_desc(Vring *vring, VirtQueueCurrentElement *elem,
-                    struct vring_desc *desc)
-{
-    unsigned *num;
-    struct iovec *iov;
-    hwaddr *addr;
-    MemoryRegion *mr;
-    hwaddr len;
-
-    if (desc->flags & VRING_DESC_F_WRITE) {
-        num = &elem->in_num;
-        iov = &elem->iov[elem->out_num + *num];
-        addr = &elem->addr[elem->out_num + *num];
-    } else {
-        num = &elem->out_num;
-        iov = &elem->iov[*num];
-        addr = &elem->addr[*num];
-
-        /* If it's an output descriptor, they're all supposed
-         * to come before any input descriptors. */
-        if (unlikely(elem->in_num)) {
-            error_report("Descriptor has out after in");
-            return -EFAULT;
-        }
-    }
-
-    while (desc->len) {
-        /* Stop for now if there are not enough iovecs available. */
-        if (*num >= VIRTQUEUE_MAX_SIZE) {
-            error_report("Invalid SG num: %u", *num);
-            return -EFAULT;
-        }
-
-        iov->iov_base = vring_map(&mr, desc->addr, desc->len, &len,
-                                  desc->flags & VRING_DESC_F_WRITE);
-        if (!iov->iov_base) {
-            error_report("Failed to map descriptor addr %#" PRIx64 " len %u",
-                         (uint64_t)desc->addr, desc->len);
-            return -EFAULT;
-        }
-
-        /* The MemoryRegion is looked up again and unref'ed later, leave the
-         * ref in place.  */
-        (iov++)->iov_len = len;
-        *addr++ = desc->addr;
-        desc->len -= len;
-        desc->addr += len;
-        *num += 1;
-    }
-
-    return 0;
-}
-
-static void copy_in_vring_desc(VirtIODevice *vdev,
-                               const struct vring_desc *guest,
-                               struct vring_desc *host)
-{
-    host->addr = virtio_ldq_p(vdev, &guest->addr);
-    host->len = virtio_ldl_p(vdev, &guest->len);
-    host->flags = virtio_lduw_p(vdev, &guest->flags);
-    host->next = virtio_lduw_p(vdev, &guest->next);
-}
-
-static bool read_vring_desc(VirtIODevice *vdev,
-                            hwaddr guest,
-                            struct vring_desc *host)
-{
-    if (address_space_read(&address_space_memory, guest, MEMTXATTRS_UNSPECIFIED,
-                           (uint8_t *)host, sizeof *host)) {
-        return false;
-    }
-    host->addr = virtio_tswap64(vdev, host->addr);
-    host->len = virtio_tswap32(vdev, host->len);
-    host->flags = virtio_tswap16(vdev, host->flags);
-    host->next = virtio_tswap16(vdev, host->next);
-    return true;
-}
-
-/* This is stolen from linux/drivers/vhost/vhost.c. */
-static int get_indirect(VirtIODevice *vdev, Vring *vring,
-                        VirtQueueCurrentElement *cur_elem,
-                        struct vring_desc *indirect)
-{
-    struct vring_desc desc;
-    unsigned int i = 0, count, found = 0;
-    int ret;
-
-    /* Sanity check */
-    if (unlikely(indirect->len % sizeof(desc))) {
-        error_report("Invalid length in indirect descriptor: "
-                     "len %#x not multiple of %#zx",
-                     indirect->len, sizeof(desc));
-        vring->broken = true;
-        return -EFAULT;
-    }
-
-    count = indirect->len / sizeof(desc);
-    /* Buffers are chained via a 16 bit next field, so
-     * we can have at most 2^16 of these. */
-    if (unlikely(count > USHRT_MAX + 1)) {
-        error_report("Indirect buffer length too big: %d", indirect->len);
-        vring->broken = true;
-        return -EFAULT;
-    }
-
-    do {
-        /* Translate indirect descriptor */
-        if (!read_vring_desc(vdev, indirect->addr + found * sizeof(desc),
-                             &desc)) {
-            error_report("Failed to read indirect descriptor "
-                         "addr %#" PRIx64 " len %zu",
-                         (uint64_t)indirect->addr + found * sizeof(desc),
-                         sizeof(desc));
-            vring->broken = true;
-            return -EFAULT;
-        }
-
-        /* Ensure descriptor has been loaded before accessing fields */
-        barrier(); /* read_barrier_depends(); */
-
-        if (unlikely(++found > count)) {
-            error_report("Loop detected: last one at %u "
-                         "indirect size %u", i, count);
-            vring->broken = true;
-            return -EFAULT;
-        }
-
-        if (unlikely(desc.flags & VRING_DESC_F_INDIRECT)) {
-            error_report("Nested indirect descriptor");
-            vring->broken = true;
-            return -EFAULT;
-        }
-
-        ret = get_desc(vring, cur_elem, &desc);
-        if (ret < 0) {
-            vring->broken |= (ret == -EFAULT);
-            return ret;
-        }
-        i = desc.next;
-    } while (desc.flags & VRING_DESC_F_NEXT);
-    return 0;
-}
-
-static void vring_unmap_element(VirtQueueElement *elem)
-{
-    int i;
-
-    /* This assumes that the iovecs, if changed, are never moved past
-     * the end of the valid area.  This is true if iovec manipulations
-     * are done with iov_discard_front and iov_discard_back.
-     */
-    for (i = 0; i < elem->out_num; i++) {
-        vring_unmap(elem->out_sg[i].iov_base, false);
-    }
-
-    for (i = 0; i < elem->in_num; i++) {
-        vring_unmap(elem->in_sg[i].iov_base, true);
-    }
-}
-
-/* This looks in the virtqueue and for the first available buffer, and converts
- * it to an iovec for convenient access.  Since descriptors consist of some
- * number of output then some number of input descriptors, it's actually two
- * iovecs, but we pack them into one and note how many of each there were.
- *
- * This function returns the descriptor number found, or vq->num (which is
- * never a valid descriptor number) if none was found.  A negative code is
- * returned on error.
- *
- * Stolen from linux/drivers/vhost/vhost.c.
- */
-void *vring_pop(VirtIODevice *vdev, Vring *vring, size_t sz)
-{
-    struct vring_desc desc;
-    unsigned int i, head, found = 0, num = vring->vr.num;
-    uint16_t avail_idx, last_avail_idx;
-    VirtQueueCurrentElement cur_elem;
-    VirtQueueElement *elem = NULL;
-    int ret;
-
-    /* If there was a fatal error then refuse operation */
-    if (vring->broken) {
-        ret = -EFAULT;
-        goto out;
-    }
-
-    cur_elem.in_num = cur_elem.out_num = 0;
-
-    /* Check it isn't doing very strange things with descriptor numbers. */
-    last_avail_idx = vring->last_avail_idx;
-    avail_idx = vring_get_avail_idx(vdev, vring);
-    barrier(); /* load indices now and not again later */
-
-    if (unlikely((uint16_t)(avail_idx - last_avail_idx) > num)) {
-        error_report("Guest moved used index from %u to %u",
-                     last_avail_idx, avail_idx);
-        ret = -EFAULT;
-        goto out;
-    }
-
-    /* If there's nothing new since last we looked. */
-    if (avail_idx == last_avail_idx) {
-        ret = -EAGAIN;
-        goto out;
-    }
-
-    /* Only get avail ring entries after they have been exposed by guest. */
-    smp_rmb();
-
-    /* Grab the next descriptor number they're advertising, and increment
-     * the index we've seen. */
-    head = vring_get_avail_ring(vdev, vring, last_avail_idx % num);
-
-    /* If their number is silly, that's an error. */
-    if (unlikely(head >= num)) {
-        error_report("Guest says index %u > %u is available", head, num);
-        ret = -EFAULT;
-        goto out;
-    }
-
-    i = head;
-    do {
-        if (unlikely(i >= num)) {
-            error_report("Desc index is %u > %u, head = %u", i, num, head);
-            ret = -EFAULT;
-            goto out;
-        }
-        if (unlikely(++found > num)) {
-            error_report("Loop detected: last one at %u vq size %u head %u",
-                         i, num, head);
-            ret = -EFAULT;
-            goto out;
-        }
-        copy_in_vring_desc(vdev, &vring->vr.desc[i], &desc);
-
-        /* Ensure descriptor is loaded before accessing fields */
-        barrier();
-
-        if (desc.flags & VRING_DESC_F_INDIRECT) {
-            ret = get_indirect(vdev, vring, &cur_elem, &desc);
-            if (ret < 0) {
-                goto out;
-            }
-            continue;
-        }
-
-        ret = get_desc(vring, &cur_elem, &desc);
-        if (ret < 0) {
-            goto out;
-        }
-
-        i = desc.next;
-    } while (desc.flags & VRING_DESC_F_NEXT);
-
-    /* On success, increment avail index. */
-    vring->last_avail_idx++;
-    if (virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
-        vring_avail_event(&vring->vr) =
-            virtio_tswap16(vdev, vring->last_avail_idx);
-    }
-
-    /* Now copy what we have collected and mapped */
-    elem = virtqueue_alloc_element(sz, cur_elem.out_num, cur_elem.in_num);
-    elem->index = head;
-    for (i = 0; i < cur_elem.out_num; i++) {
-        elem->out_addr[i] = cur_elem.addr[i];
-        elem->out_sg[i] = cur_elem.iov[i];
-    }
-    for (i = 0; i < cur_elem.in_num; i++) {
-        elem->in_addr[i] = cur_elem.addr[cur_elem.out_num + i];
-        elem->in_sg[i] = cur_elem.iov[cur_elem.out_num + i];
-    }
-
-    return elem;
-
-out:
-    assert(ret < 0);
-    if (ret == -EFAULT) {
-        vring->broken = true;
-    }
-
-    for (i = 0; i < cur_elem.out_num + cur_elem.in_num; i++) {
-        vring_unmap(cur_elem.iov[i].iov_base, false);
-    }
-
-    g_free(elem);
-    return NULL;
-}
-
-/* After we've used one of their buffers, we tell them about it.
- *
- * Stolen from linux/drivers/vhost/vhost.c.
- */
-void vring_push(VirtIODevice *vdev, Vring *vring, VirtQueueElement *elem,
-                int len)
-{
-    unsigned int head = elem->index;
-    uint16_t new;
-
-    vring_unmap_element(elem);
-
-    /* Don't touch vring if a fatal error occurred */
-    if (vring->broken) {
-        return;
-    }
-
-    /* The virtqueue contains a ring of used buffers.  Get a pointer to the
-     * next entry in that used ring. */
-    vring_set_used_ring_id(vdev, vring, vring->last_used_idx % vring->vr.num,
-                           head);
-    vring_set_used_ring_len(vdev, vring, vring->last_used_idx % vring->vr.num,
-                            len);
-
-    /* Make sure buffer is written before we update index. */
-    smp_wmb();
-
-    new = ++vring->last_used_idx;
-    vring_set_used_idx(vdev, vring, new);
-    if (unlikely((int16_t)(new - vring->signalled_used) < (uint16_t)1)) {
-        vring->signalled_used_valid = false;
-    }
-}

hw/virtio/vhost-user.c

@@ -611,6 +611,25 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr)
     return -1;
 }
 
+static bool vhost_user_can_merge(struct vhost_dev *dev,
+                                 uint64_t start1, uint64_t size1,
+                                 uint64_t start2, uint64_t size2)
+{
+    ram_addr_t ram_addr;
+    int mfd, rfd;
+    MemoryRegion *mr;
+
+    mr = qemu_ram_addr_from_host((void *)(uintptr_t)start1, &ram_addr);
+    assert(mr);
+    mfd = qemu_get_ram_fd(ram_addr);
+
+    mr = qemu_ram_addr_from_host((void *)(uintptr_t)start2, &ram_addr);
+    assert(mr);
+    rfd = qemu_get_ram_fd(ram_addr);
+
+    return mfd == rfd;
+}
+
 const VhostOps user_ops = {
         .backend_type = VHOST_BACKEND_TYPE_USER,
         .vhost_backend_init = vhost_user_init,
@@ -633,4 +652,5 @@ const VhostOps user_ops = {
         .vhost_set_vring_enable = vhost_user_set_vring_enable,
         .vhost_requires_shm_log = vhost_user_requires_shm_log,
         .vhost_migration_done = vhost_user_migration_done,
+        .vhost_backend_can_merge = vhost_user_can_merge,
 };

hw/virtio/vhost.c

@@ -260,6 +260,13 @@ static void vhost_dev_assign_memory(struct vhost_dev *dev,
             continue;
         }
 
+        if (dev->vhost_ops->vhost_backend_can_merge &&
+            !dev->vhost_ops->vhost_backend_can_merge(dev, uaddr, size,
+                                                     reg->userspace_addr,
+                                                     reg->memory_size)) {
+            continue;
+        }
+
         if (merged) {
             --to;
             assert(to >= 0);

hw/virtio/virtio-balloon.c

@@ -305,6 +305,39 @@ static void virtio_balloon_get_config(VirtIODevice *vdev, uint8_t *config_data)
     memcpy(config_data, &config, sizeof(struct virtio_balloon_config));
 }
 
+static int build_dimm_list(Object *obj, void *opaque)
+{
+    GSList **list = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_PC_DIMM)) {
+        DeviceState *dev = DEVICE(obj);
+        if (dev->realized) { /* only realized DIMMs matter */
+            *list = g_slist_prepend(*list, dev);
+        }
+    }
+
+    object_child_foreach(obj, build_dimm_list, opaque);
+    return 0;
+}
+
+static ram_addr_t get_current_ram_size(void)
+{
+    GSList *list = NULL, *item;
+    ram_addr_t size = ram_size;
+
+    build_dimm_list(qdev_get_machine(), &list);
+    for (item = list; item; item = g_slist_next(item)) {
+        Object *obj = OBJECT(item->data);
+        if (!strcmp(object_get_typename(obj), TYPE_PC_DIMM)) {
+            size += object_property_get_int(obj, PC_DIMM_SIZE_PROP,
+                                            &error_abort);
+        }
+    }
+    g_slist_free(list);
+
+    return size;
+}
+
 static void virtio_balloon_set_config(VirtIODevice *vdev,
                                       const uint8_t *config_data)
 {

hw/virtio/virtio.c

@@ -1162,7 +1162,7 @@ void virtio_irq(VirtQueue *vq)
     virtio_notify_vector(vq->vdev, vq->vector);
 }
 
-static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq)
+bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq)
 {
     uint16_t old, new;
     bool v;
@@ -1187,7 +1187,7 @@ static bool vring_notify(VirtIODevice *vdev, VirtQueue *vq)
 
 void virtio_notify(VirtIODevice *vdev, VirtQueue *vq)
 {
-    if (!vring_notify(vdev, vq)) {
+    if (!virtio_should_notify(vdev, vq)) {
         return;
     }
 
@@ -1786,6 +1786,22 @@ static void virtio_queue_host_notifier_read(EventNotifier *n)
     }
 }
 
+void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx,
+                                                bool assign, bool set_handler)
+{
+    if (assign && set_handler) {
+        aio_set_event_notifier(ctx, &vq->host_notifier, true,
+                               virtio_queue_host_notifier_read);
+    } else {
+        aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL);
+    }
+    if (!assign) {
+        /* Test and clear notifier before after disabling event,
+         * in case poll callback didn't have time to run. */
+        virtio_queue_host_notifier_read(&vq->host_notifier);
+    }
+}
+
 void virtio_queue_set_host_notifier_fd_handler(VirtQueue *vq, bool assign,
                                                bool set_handler)
 {

include/block/accounting.h

@@ -25,8 +25,6 @@
 #ifndef BLOCK_ACCOUNTING_H
 #define BLOCK_ACCOUNTING_H
 
-#include <stdint.h>
-#include <stdbool.h>
 
 #include "qemu/typedefs.h"
 #include "qemu/timed-average.h"

include/block/nbd.h

@@ -19,7 +19,6 @@
 #ifndef NBD_H
 #define NBD_H
 
-#include <sys/types.h>
 
 #include "qemu-common.h"
 #include "qemu/option.h"

include/block/snapshot.h

@@ -26,7 +26,6 @@
 #define SNAPSHOT_H
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 #include "qemu/option.h"
 
 

include/block/write-threshold.h

@@ -12,7 +12,6 @@
 #ifndef BLOCK_WRITE_THRESHOLD_H
 #define BLOCK_WRITE_THRESHOLD_H
 
-#include <stdint.h>
 
 #include "qemu/typedefs.h"
 #include "qemu-common.h"

include/config.h

@@ -1,2 +1 @@
-#include "config-host.h"
 #include "config-target.h"

include/crypto/cipher.h

@@ -22,7 +22,6 @@
 #define QCRYPTO_CIPHER_H__
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 
 typedef struct QCryptoCipher QCryptoCipher;
 

include/crypto/hash.h

@@ -22,7 +22,6 @@
 #define QCRYPTO_HASH_H__
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 
 /* See also "QCryptoHashAlgorithm" defined in qapi/crypto.json */
 

include/crypto/init.h

@@ -22,7 +22,6 @@
 #define QCRYPTO_INIT_H__
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 
 int qcrypto_init(Error **errp);
 

include/crypto/secret.h

@@ -22,7 +22,6 @@
 #define QCRYPTO_SECRET_H__
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 #include "qom/object.h"
 
 #define TYPE_QCRYPTO_SECRET "secret"

include/crypto/tlscreds.h

@@ -22,7 +22,6 @@
 #define QCRYPTO_TLSCRED_H__
 
 #include "qemu-common.h"
-#include "qapi/error.h"
 #include "qom/object.h"
 
 #ifdef CONFIG_GNUTLS

include/elf.h

@@ -1,7 +1,6 @@
 #ifndef _QEMU_ELF_H
 #define _QEMU_ELF_H
 
-#include <inttypes.h>
 
 /* 32-bit ELF base types. */
 typedef uint32_t Elf32_Addr;

include/exec/cpu-all.h

@@ -154,7 +154,6 @@ static inline void tswap64s(uint64_t *s)
 /* MMU memory access macros */
 
 #if defined(CONFIG_USER_ONLY)
-#include <assert.h>
 #include "exec/user/abitypes.h"
 
 /* On some host systems the guest address space is reserved on the host.

include/exec/cpu-common.h

@@ -54,7 +54,6 @@ typedef uintptr_t ram_addr_t;
 #endif
 
 extern ram_addr_t ram_size;
-ram_addr_t get_current_ram_size(void);
 
 /* memory API */
 

include/exec/cpu-defs.h

@@ -23,9 +23,6 @@
 #error cpu.h included from common code
 #endif
 
-#include "config.h"
-#include <inttypes.h>
-#include "qemu/osdep.h"
 #include "qemu/queue.h"
 #include "tcg-target.h"
 #ifndef CONFIG_USER_ONLY

include/exec/helper-head.h

@@ -18,7 +18,6 @@
 #ifndef DEF_HELPER_H
 #define DEF_HELPER_H 1
 
-#include "qemu/osdep.h"
 
 #define HELPER(name) glue(helper_, name)
 

include/exec/memory.h

@@ -21,8 +21,6 @@
 #define DIRTY_MEMORY_MIGRATION 2
 #define DIRTY_MEMORY_NUM       3        /* num of dirty bits */
 
-#include <stdint.h>
-#include <stdbool.h>
 #include "exec/cpu-common.h"
 #ifndef CONFIG_USER_ONLY
 #include "exec/hwaddr.h"
@@ -31,9 +29,9 @@
 #include "qemu/queue.h"
 #include "qemu/int128.h"
 #include "qemu/notify.h"
-#include "qapi/error.h"
 #include "qom/object.h"
 #include "qemu/rcu.h"
+#include "qemu/typedefs.h"
 
 #define MAX_PHYS_ADDR_SPACE_BITS 62
 #define MAX_PHYS_ADDR            (((hwaddr)1 << MAX_PHYS_ADDR_SPACE_BITS) - 1)
@@ -172,6 +170,7 @@ struct MemoryRegion {
     bool global_locking;
     uint8_t dirty_log_mask;
     ram_addr_t ram_addr;
+    RAMBlock *ram_block;
     Object *owner;
     const MemoryRegionIOMMUOps *iommu_ops;
 
@@ -1389,7 +1388,7 @@ MemTxResult address_space_read_continue(AddressSpace *as, hwaddr addr,
 					MemoryRegion *mr);
 MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
                                     MemTxAttrs attrs, uint8_t *buf, int len);
-void *qemu_get_ram_ptr(ram_addr_t addr);
+void *qemu_get_ram_ptr(RAMBlock *ram_block, ram_addr_t addr);
 
 static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
 {
@@ -1398,8 +1397,6 @@ static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
     } else {
         return memory_region_is_ram(mr) || memory_region_is_romd(mr);
     }
-
-    return false;
 }
 
 /**
@@ -1430,7 +1427,7 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, MemTxAttrs attrs,
             mr = address_space_translate(as, addr, &addr1, &l, false);
             if (len == l && memory_access_is_direct(mr, false)) {
                 addr1 += memory_region_get_ram_addr(mr);
-                ptr = qemu_get_ram_ptr(addr1);
+                ptr = qemu_get_ram_ptr(mr->ram_block, addr1);
                 memcpy(buf, ptr, len);
             } else {
                 result = address_space_read_continue(as, addr, attrs, buf, len,

include/exec/user/thunk.h

@@ -19,7 +19,6 @@
 #ifndef THUNK_H
 #define THUNK_H
 
-#include <inttypes.h>
 #include "cpu.h"
 
 /* types enums definitions */

include/fpu/softfloat.h

@@ -86,9 +86,6 @@ this code that are retained.
 #include <sunmath.h>
 #endif
 
-#include <inttypes.h>
-#include "config-host.h"
-#include "qemu/osdep.h"
 
 /* This 'flag' type must be able to hold at least 0 and 1. It should
  * probably be replaced with 'bool' but the uses would need to be audited

include/hw/acpi/acpi.h

@@ -19,7 +19,6 @@
  * <http://www.gnu.org/licenses/>.
  */
 
-#include "qapi/error.h"
 #include "qemu/typedefs.h"
 #include "qemu/notify.h"
 #include "qemu/option.h"