keymaps: correct keymaps.c following Qemu coding style

It's hard to read because of the confused coding
style in this file. Let's correct it following Qemu
coding style.

Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

MAINTAINERS

@@ -880,6 +880,12 @@ S: Maintained
 F: qobject/
 T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
 
+QEMU Guest Agent
+M: Michael Roth <mdroth@linux.vnet.ibm.com>
+S: Maintained
+F: qga/
+T: git git://github.com/mdroth/qemu.git qga
+
 QOM
 M: Anthony Liguori <aliguori@amazon.com>
 M: Andreas Färber <afaerber@suse.de>
@@ -920,6 +926,15 @@ M: Blue Swirl <blauwirbel@gmail.com>
 S: Odd Fixes
 F: scripts/checkpatch.pl
 
+Migration
+M: Juan Quintela <quintela@redhat.com>
+S: Maintained
+F: include/migration/
+F: migration*
+F: savevm.c
+F: arch_init.c
+F: vmstate.c
+
 Seccomp
 M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
 S: Supported
@@ -1078,3 +1093,8 @@ M: Chrysostomos Nanakos <cnanakos@grnet.gr>
 M: Chrysostomos Nanakos <chris@include.gr>
 S: Maintained
 F: block/archipelago.c
+
+Bootdevice
+M: Gonglei <arei.gonglei@huawei.com>
+S: Maintained
+F: bootdevice.c

VERSION

@@ -1 +1 @@
-2.1.90
+2.2.0

arch_init.c

@@ -486,15 +486,23 @@ static void migration_bitmap_sync_range(ram_addr_t start, ram_addr_t length)
 
 
 /* Needs iothread lock! */
+/* Fix me: there are too many global variables used in migration process. */
+static int64_t start_time;
+static int64_t bytes_xfer_prev;
+static int64_t num_dirty_pages_period;
+
+static void migration_bitmap_sync_init(void)
+{
+    start_time = 0;
+    bytes_xfer_prev = 0;
+    num_dirty_pages_period = 0;
+}
 
 static void migration_bitmap_sync(void)
 {
     RAMBlock *block;
     uint64_t num_dirty_pages_init = migration_dirty_pages;
     MigrationState *s = migrate_get_current();
-    static int64_t start_time;
-    static int64_t bytes_xfer_prev;
-    static int64_t num_dirty_pages_period;
     int64_t end_time;
     int64_t bytes_xfer_now;
     static uint64_t xbzrle_cache_miss_prev;
@@ -774,6 +782,7 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
     mig_throttle_on = false;
     dirty_rate_high_cnt = 0;
     bitmap_sync_count = 0;
+    migration_bitmap_sync_init();
 
     if (migrate_use_xbzrle()) {
         XBZRLE_cache_lock();
@@ -1006,7 +1015,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
     uint8_t len;
 
     if (flags & RAM_SAVE_FLAG_CONTINUE) {
-        if (!block) {
+        if (!block || block->length <= offset) {
             error_report("Ack, bad migration stream!");
             return NULL;
         }
@@ -1019,8 +1028,9 @@ static inline void *host_from_stream_offset(QEMUFile *f,
     id[len] = 0;
 
     QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-        if (!strncmp(id, block->idstr, sizeof(id)))
+        if (!strncmp(id, block->idstr, sizeof(id)) && block->length > offset) {
             return memory_region_get_ram_ptr(block->mr) + offset;
+        }
     }
 
     error_report("Can't find block %s!", id);

block.c

@@ -2790,8 +2790,8 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
         if (nb_sectors <= 0) {
             return 0;
         }
-        if (nb_sectors > INT_MAX) {
-            nb_sectors = INT_MAX;
+        if (nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+            nb_sectors = INT_MAX / BDRV_SECTOR_SIZE;
         }
         ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
         if (ret < 0) {
@@ -3903,9 +3903,9 @@ typedef struct BdrvCoGetBlockStatusData {
 } BdrvCoGetBlockStatusData;
 
 /*
- * Returns true iff the specified sector is present in the disk image. Drivers
- * not implementing the functionality are assumed to not support backing files,
- * hence all their sectors are reported as allocated.
+ * Returns the allocation status of the specified sectors.
+ * Drivers not implementing the functionality are assumed to not support
+ * backing files, hence all their sectors are reported as allocated.
  *
  * If 'sector_num' is beyond the end of the disk image the return value is 0
  * and 'pnum' is set to 0.

block/qapi.c

@@ -29,13 +29,6 @@
 #include "qapi/qmp-output-visitor.h"
 #include "qapi/qmp/types.h"
 #include "sysemu/block-backend.h"
-#ifdef __linux__
-#include <linux/fs.h>
-#include <sys/ioctl.h>
-#ifndef FS_NOCOW_FL
-#define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
-#endif
-#endif
 
 BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
 {
@@ -180,9 +173,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
     int ret;
     Error *err = NULL;
     ImageInfo *info;
-#ifdef __linux__
-    int fd, attr;
-#endif
 
     size = bdrv_getlength(bs);
     if (size < 0) {
@@ -212,18 +202,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
     info->format_specific     = bdrv_get_specific_info(bs);
     info->has_format_specific = info->format_specific != NULL;
 
-#ifdef __linux__
-    /* get NOCOW info */
-    fd = qemu_open(bs->filename, O_RDONLY | O_NONBLOCK);
-    if (fd >= 0) {
-        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0 && (attr & FS_NOCOW_FL)) {
-            info->has_nocow = true;
-            info->nocow = true;
-        }
-        qemu_close(fd);
-    }
-#endif
-
     backing_filename = bs->backing_file;
     if (backing_filename[0] != '\0') {
         info->backing_filename = g_strdup(backing_filename);
@@ -655,8 +633,4 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
         func_fprintf(f, "Format specific information:\n");
         bdrv_image_info_specific_dump(func_fprintf, f, info->format_specific);
     }
-
-    if (info->has_nocow && info->nocow) {
-        func_fprintf(f, "NOCOW flag: set\n");
-    }
 }

block/raw-posix.c

@@ -60,9 +60,6 @@
 #define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
 #endif
 #endif
-#ifdef CONFIG_FIEMAP
-#include <linux/fiemap.h>
-#endif
 #ifdef CONFIG_FALLOCATE_PUNCH_HOLE
 #include <linux/falloc.h>
 #endif
@@ -151,9 +148,6 @@ typedef struct BDRVRawState {
     bool has_write_zeroes:1;
     bool discard_zeroes:1;
     bool needs_alignment;
-#ifdef CONFIG_FIEMAP
-    bool skip_fiemap;
-#endif
 } BDRVRawState;
 
 typedef struct BDRVRawReopenState {
@@ -1457,9 +1451,16 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
                                  "Could not write to the new file");
                 break;
             }
-            left -= num;
+            left -= result;
+        }
+        if (result >= 0) {
+            result = fsync(fd);
+            if (result < 0) {
+                result = -errno;
+                error_setg_errno(errp, -result,
+                                 "Could not flush new file to disk");
+            }
         }
-        fsync(fd);
         g_free(buf);
         break;
     }
@@ -1481,83 +1482,93 @@ out:
     return result;
 }
 
-static int try_fiemap(BlockDriverState *bs, off_t start, off_t *data,
-                      off_t *hole, int nb_sectors)
-{
-#ifdef CONFIG_FIEMAP
-    BDRVRawState *s = bs->opaque;
-    int ret = 0;
-    struct {
-        struct fiemap fm;
-        struct fiemap_extent fe;
-    } f;
-
-    if (s->skip_fiemap) {
-        return -ENOTSUP;
-    }
-
-    f.fm.fm_start = start;
-    f.fm.fm_length = (int64_t)nb_sectors * BDRV_SECTOR_SIZE;
-    f.fm.fm_flags = FIEMAP_FLAG_SYNC;
-    f.fm.fm_extent_count = 1;
-    f.fm.fm_reserved = 0;
-    if (ioctl(s->fd, FS_IOC_FIEMAP, &f) == -1) {
-        s->skip_fiemap = true;
-        return -errno;
-    }
-
-    if (f.fm.fm_mapped_extents == 0) {
-        /* No extents found, data is beyond f.fm.fm_start + f.fm.fm_length.
-         * f.fm.fm_start + f.fm.fm_length must be clamped to the file size!
-         */
-        off_t length = lseek(s->fd, 0, SEEK_END);
-        *hole = f.fm.fm_start;
-        *data = MIN(f.fm.fm_start + f.fm.fm_length, length);
-    } else {
-        *data = f.fe.fe_logical;
-        *hole = f.fe.fe_logical + f.fe.fe_length;
-        if (f.fe.fe_flags & FIEMAP_EXTENT_UNWRITTEN) {
-            ret |= BDRV_BLOCK_ZERO;
-        }
-    }
-
-    return ret;
-#else
-    return -ENOTSUP;
-#endif
-}
-
-static int try_seek_hole(BlockDriverState *bs, off_t start, off_t *data,
-                         off_t *hole)
+/*
+ * Find allocation range in @bs around offset @start.
+ * May change underlying file descriptor's file offset.
+ * If @start is not in a hole, store @start in @data, and the
+ * beginning of the next hole in @hole, and return 0.
+ * If @start is in a non-trailing hole, store @start in @hole and the
+ * beginning of the next non-hole in @data, and return 0.
+ * If @start is in a trailing hole or beyond EOF, return -ENXIO.
+ * If we can't find out, return a negative errno other than -ENXIO.
+ */
+static int find_allocation(BlockDriverState *bs, off_t start,
+                           off_t *data, off_t *hole)
 {
 #if defined SEEK_HOLE && defined SEEK_DATA
     BDRVRawState *s = bs->opaque;
+    off_t offs;
 
-    *hole = lseek(s->fd, start, SEEK_HOLE);
-    if (*hole == -1) {
-        return -errno;
+    /*
+     * SEEK_DATA cases:
+     * D1. offs == start: start is in data
+     * D2. offs > start: start is in a hole, next data at offs
+     * D3. offs < 0, errno = ENXIO: either start is in a trailing hole
+     *                              or start is beyond EOF
+     *     If the latter happens, the file has been truncated behind
+     *     our back since we opened it.  All bets are off then.
+     *     Treating like a trailing hole is simplest.
+     * D4. offs < 0, errno != ENXIO: we learned nothing
+     */
+    offs = lseek(s->fd, start, SEEK_DATA);
+    if (offs < 0) {
+        return -errno;          /* D3 or D4 */
+    }
+    assert(offs >= start);
+
+    if (offs > start) {
+        /* D2: in hole, next data at offs */
+        *hole = start;
+        *data = offs;
+        return 0;
     }
 
-    if (*hole > start) {
+    /* D1: in data, end not yet known */
+
+    /*
+     * SEEK_HOLE cases:
+     * H1. offs == start: start is in a hole
+     *     If this happens here, a hole has been dug behind our back
+     *     since the previous lseek().
+     * H2. offs > start: either start is in data, next hole at offs,
+     *                   or start is in trailing hole, EOF at offs
+     *     Linux treats trailing holes like any other hole: offs ==
+     *     start.  Solaris seeks to EOF instead: offs > start (blech).
+     *     If that happens here, a hole has been dug behind our back
+     *     since the previous lseek().
+     * H3. offs < 0, errno = ENXIO: start is beyond EOF
+     *     If this happens, the file has been truncated behind our
+     *     back since we opened it.  Treat it like a trailing hole.
+     * H4. offs < 0, errno != ENXIO: we learned nothing
+     *     Pretend we know nothing at all, i.e. "forget" about D1.
+     */
+    offs = lseek(s->fd, start, SEEK_HOLE);
+    if (offs < 0) {
+        return -errno;          /* D1 and (H3 or H4) */
+    }
+    assert(offs >= start);
+
+    if (offs > start) {
+        /*
+         * D1 and H2: either in data, next hole at offs, or it was in
+         * data but is now in a trailing hole.  In the latter case,
+         * all bets are off.  Treating it as if it there was data all
+         * the way to EOF is safe, so simply do that.
+         */
         *data = start;
-    } else {
-        /* On a hole.  We need another syscall to find its end.  */
-        *data = lseek(s->fd, start, SEEK_DATA);
-        if (*data == -1) {
-            *data = lseek(s->fd, 0, SEEK_END);
-        }
+        *hole = offs;
+        return 0;
     }
 
-    return 0;
+    /* D1 and H1 */
+    return -EBUSY;
 #else
     return -ENOTSUP;
 #endif
 }
 
 /*
- * Returns true iff the specified sector is present in the disk image. Drivers
- * not implementing the functionality are assumed to not support backing files,
- * hence all their sectors are reported as allocated.
+ * Returns the allocation status of the specified sectors.
  *
  * If 'sector_num' is beyond the end of the disk image the return value is 0
  * and 'pnum' is set to 0.
@@ -1593,28 +1604,26 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
         nb_sectors = DIV_ROUND_UP(total_size - start, BDRV_SECTOR_SIZE);
     }
 
-    ret = try_seek_hole(bs, start, &data, &hole);
-    if (ret < 0) {
-        ret = try_fiemap(bs, start, &data, &hole, nb_sectors);
-        if (ret < 0) {
-            /* Assume everything is allocated. */
-            data = 0;
-            hole = start + nb_sectors * BDRV_SECTOR_SIZE;
-            ret = 0;
-        }
-    }
-
-    assert(ret >= 0);
-
-    if (data <= start) {
+    ret = find_allocation(bs, start, &data, &hole);
+    if (ret == -ENXIO) {
+        /* Trailing hole */
+        *pnum = nb_sectors;
+        ret = BDRV_BLOCK_ZERO;
+    } else if (ret < 0) {
+        /* No info available, so pretend there are no holes */
+        *pnum = nb_sectors;
+        ret = BDRV_BLOCK_DATA;
+    } else if (data == start) {
         /* On a data extent, compute sectors to the end of the extent.  */
         *pnum = MIN(nb_sectors, (hole - start) / BDRV_SECTOR_SIZE);
-        return ret | BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
+        ret = BDRV_BLOCK_DATA;
     } else {
         /* On a hole, compute sectors to the beginning of the next extent.  */
+        assert(hole == start);
         *pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
-        return ret | BDRV_BLOCK_ZERO | BDRV_BLOCK_OFFSET_VALID | start;
+        ret = BDRV_BLOCK_ZERO;
     }
+    return ret | BDRV_BLOCK_OFFSET_VALID | start;
 }
 
 static coroutine_fn BlockAIOCB *raw_aio_discard(BlockDriverState *bs,

block/vmdk.c

@@ -2137,23 +2137,29 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
     return spec_info;
 }
 
+static bool vmdk_extents_type_eq(const VmdkExtent *a, const VmdkExtent *b)
+{
+    return a->flat == b->flat &&
+           a->compressed == b->compressed &&
+           (a->flat || a->cluster_sectors == b->cluster_sectors);
+}
+
 static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
 {
     int i;
     BDRVVmdkState *s = bs->opaque;
     assert(s->num_extents);
+
+    /* See if we have multiple extents but they have different cases */
+    for (i = 1; i < s->num_extents; i++) {
+        if (!vmdk_extents_type_eq(&s->extents[0], &s->extents[i])) {
+            return -ENOTSUP;
+        }
+    }
     bdi->needs_compressed_writes = s->extents[0].compressed;
     if (!s->extents[0].flat) {
         bdi->cluster_size = s->extents[0].cluster_sectors << BDRV_SECTOR_BITS;
     }
-    /* See if we have multiple extents but they have different cases */
-    for (i = 1; i < s->num_extents; i++) {
-        if (bdi->needs_compressed_writes != s->extents[i].compressed ||
-            (bdi->cluster_size && bdi->cluster_size !=
-                s->extents[i].cluster_sectors << BDRV_SECTOR_BITS)) {
-            return -ENOTSUP;
-        }
-    }
     return 0;
 }
 

configure

@@ -1823,7 +1823,8 @@ fi
 # libseccomp check
 
 if test "$seccomp" != "no" ; then
-    if $pkg_config --atleast-version=2.1.0 libseccomp; then
+    if test "$cpu" = "i386" || test "$cpu" = "x86_64" &&
+        $pkg_config --atleast-version=2.1.1 libseccomp; then
         libs_softmmu="$libs_softmmu `$pkg_config --libs libseccomp`"
         QEMU_CFLAGS="$QEMU_CFLAGS `$pkg_config --cflags libseccomp`"
 	seccomp="yes"

coroutine-sigaltstack.c

@@ -155,7 +155,7 @@ Coroutine *qemu_coroutine_new(void)
     stack_t oss;
     sigset_t sigs;
     sigset_t osigs;
-    jmp_buf old_env;
+    sigjmp_buf old_env;
 
     /* The way to manipulate stack is with the sigaltstack function. We
      * prepare a stack, with it delivering a signal to ourselves and then

docs/tracing.txt

@@ -139,12 +139,12 @@ events are not tightly coupled to a specific trace backend, such as LTTng or
 SystemTap.  Support for trace backends can be added by extending the "tracetool"
 script.
 
-The trace backend is chosen at configure time and only one trace backend can
-be built into the binary:
+The trace backends are chosen at configure time:
 
-    ./configure --trace-backends=simple
+    ./configure --enable-trace-backends=simple
 
 For a list of supported trace backends, try ./configure --help or see below.
+If multiple backends are enabled, the trace is sent to them all.
 
 The following subsections describe the supported trace backends.
 

exec.c

@@ -909,14 +909,15 @@ static int subpage_register (subpage_t *mmio, uint32_t start, uint32_t end,
                              uint16_t section);
 static subpage_t *subpage_init(AddressSpace *as, hwaddr base);
 
-static void *(*phys_mem_alloc)(size_t size) = qemu_anon_ram_alloc;
+static void *(*phys_mem_alloc)(size_t size, uint64_t *align) =
+                               qemu_anon_ram_alloc;
 
 /*
  * Set a custom physical guest memory alloator.
  * Accelerators with unusual needs may need this.  Hopefully, we can
  * get rid of it eventually.
  */
-void phys_mem_set_alloc(void *(*alloc)(size_t))
+void phys_mem_set_alloc(void *(*alloc)(size_t, uint64_t *align))
 {
     phys_mem_alloc = alloc;
 }
@@ -1098,6 +1099,7 @@ static void *file_ram_alloc(RAMBlock *block,
         error_propagate(errp, local_err);
         goto error;
     }
+    block->mr->align = hpagesize;
 
     if (memory < hpagesize) {
         error_setg(errp, "memory size 0x" RAM_ADDR_FMT " must be equal to "
@@ -1309,7 +1311,8 @@ static ram_addr_t ram_block_add(RAMBlock *new_block, Error **errp)
         if (xen_enabled()) {
             xen_ram_alloc(new_block->offset, new_block->length, new_block->mr);
         } else {
-            new_block->host = phys_mem_alloc(new_block->length);
+            new_block->host = phys_mem_alloc(new_block->length,
+                                             &new_block->mr->align);
             if (!new_block->host) {
                 error_setg_errno(errp, errno,
                                  "cannot set up guest memory '%s'",
@@ -2066,10 +2069,8 @@ int cpu_memory_rw_debug(CPUState *cpu, target_ulong addr,
 static void invalidate_and_set_dirty(hwaddr addr,
                                      hwaddr length)
 {
-    if (cpu_physical_memory_is_clean(addr)) {
-        /* invalidate code */
-        tb_invalidate_phys_page_range(addr, addr + length, 0);
-        /* set dirty bit */
+    if (cpu_physical_memory_range_includes_clean(addr, length)) {
+        tb_invalidate_phys_range(addr, addr + length, 0);
         cpu_physical_memory_set_dirty_range_nocode(addr, length);
     }
     xen_modified_memory(addr, length);

gdbstub.c

@@ -823,7 +823,10 @@ static int gdb_handle_packet(GDBState *s, const char *line_buf)
                 action = *p++;
                 signal = 0;
                 if (action == 'C' || action == 'S') {
-                    signal = strtoul(p, (char **)&p, 16);
+                    signal = gdb_signal_to_target(strtoul(p, (char **)&p, 16));
+                    if (signal == -1) {
+                        signal = 0;
+                    }
                 } else if (action != 'c' && action != 's') {
                     res = 0;
                     break;

hw/acpi/core.c

@@ -376,8 +376,11 @@ static void acpi_notify_wakeup(Notifier *notifier, void *data)
 /* ACPI PM1a EVT */
 uint16_t acpi_pm1_evt_get_sts(ACPIREGS *ar)
 {
-    int64_t d = acpi_pm_tmr_get_clock();
-    if (d >= ar->tmr.overflow_time) {
+    /* Compare ns-clock, not PM timer ticks, because
+       acpi_pm_tmr_update function uses ns for setting the timer. */
+    int64_t d = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
+    if (d >= muldiv64(ar->tmr.overflow_time,
+                      get_ticks_per_sec(), PM_TIMER_FREQUENCY)) {
         ar->pm1.evt.sts |= ACPI_BITMASK_TIMER_STATUS;
     }
     return ar->pm1.evt.sts;

hw/acpi/piix4.c

@@ -36,6 +36,7 @@
 #include "hw/mem/pc-dimm.h"
 #include "hw/acpi/memory_hotplug.h"
 #include "hw/acpi/acpi_dev_interface.h"
+#include "hw/xen/xen.h"
 
 //#define DEBUG
 
@@ -501,6 +502,9 @@ I2CBus *piix4_pm_init(PCIBus *bus, int devfn, uint32_t smb_io_base,
     s->irq = sci_irq;
     s->smi_irq = smi_irq;
     s->kvm_enabled = kvm_enabled;
+    if (xen_enabled()) {
+        s->use_acpi_pci_hotplug = false;
+    }
 
     qdev_init_nofail(dev);
 

hw/arm/virt.c

@@ -389,7 +389,7 @@ static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic)
     qemu_fdt_setprop(vbi->fdt, nodename, "clock-names",
                          clocknames, sizeof(clocknames));
 
-    qemu_fdt_setprop_string(vbi->fdt, "/chosen", "linux,stdout-path", nodename);
+    qemu_fdt_setprop_string(vbi->fdt, "/chosen", "stdout-path", nodename);
     g_free(nodename);
 }
 

hw/block/nvme.c

@@ -583,8 +583,7 @@ static int nvme_start_ctrl(NvmeCtrl *n)
             NVME_CC_IOCQES(n->bar.cc) > NVME_CTRL_CQES_MAX(n->id_ctrl.cqes) ||
             NVME_CC_IOSQES(n->bar.cc) < NVME_CTRL_SQES_MIN(n->id_ctrl.sqes) ||
             NVME_CC_IOSQES(n->bar.cc) > NVME_CTRL_SQES_MAX(n->id_ctrl.sqes) ||
-            !NVME_AQA_ASQS(n->bar.aqa) || NVME_AQA_ASQS(n->bar.aqa) > 4095 ||
-            !NVME_AQA_ACQS(n->bar.aqa) || NVME_AQA_ACQS(n->bar.aqa) > 4095) {
+            !NVME_AQA_ASQS(n->bar.aqa) || !NVME_AQA_ACQS(n->bar.aqa)) {
         return -1;
     }
 

hw/block/xen_disk.c

@@ -59,6 +59,13 @@ struct PersistentGrant {
 
 typedef struct PersistentGrant PersistentGrant;
 
+struct PersistentRegion {
+    void *addr;
+    int num;
+};
+
+typedef struct PersistentRegion PersistentRegion;
+
 struct ioreq {
     blkif_request_t     req;
     int16_t             status;
@@ -118,6 +125,7 @@ struct XenBlkDev {
     gboolean            feature_discard;
     gboolean            feature_persistent;
     GTree               *persistent_gnts;
+    GSList              *persistent_regions;
     unsigned int        persistent_gnt_count;
     unsigned int        max_grants;
 
@@ -177,6 +185,23 @@ static void destroy_grant(gpointer pgnt)
     g_free(grant);
 }
 
+static void remove_persistent_region(gpointer data, gpointer dev)
+{
+    PersistentRegion *region = data;
+    struct XenBlkDev *blkdev = dev;
+    XenGnttab gnt = blkdev->xendev.gnttabdev;
+
+    if (xc_gnttab_munmap(gnt, region->addr, region->num) != 0) {
+        xen_be_printf(&blkdev->xendev, 0,
+                      "xc_gnttab_munmap region %p failed: %s\n",
+                      region->addr, strerror(errno));
+    }
+    xen_be_printf(&blkdev->xendev, 3,
+                  "unmapped grant region %p with %d pages\n",
+                  region->addr, region->num);
+    g_free(region);
+}
+
 static struct ioreq *ioreq_start(struct XenBlkDev *blkdev)
 {
     struct ioreq *ioreq = NULL;
@@ -343,6 +368,7 @@ static int ioreq_map(struct ioreq *ioreq)
     void *page[BLKIF_MAX_SEGMENTS_PER_REQUEST];
     int i, j, new_maps = 0;
     PersistentGrant *grant;
+    PersistentRegion *region;
     /* domids and refs variables will contain the information necessary
      * to map the grants that are needed to fulfill this request.
      *
@@ -421,7 +447,22 @@ static int ioreq_map(struct ioreq *ioreq)
             }
         }
     }
-    if (ioreq->blkdev->feature_persistent) {
+    if (ioreq->blkdev->feature_persistent && new_maps != 0 &&
+        (!batch_maps || (ioreq->blkdev->persistent_gnt_count + new_maps <=
+        ioreq->blkdev->max_grants))) {
+        /*
+         * If we are using persistent grants and batch mappings only
+         * add the new maps to the list of persistent grants if the whole
+         * area can be persistently mapped.
+         */
+        if (batch_maps) {
+            region = g_malloc0(sizeof(*region));
+            region->addr = ioreq->pages;
+            region->num = new_maps;
+            ioreq->blkdev->persistent_regions = g_slist_append(
+                                            ioreq->blkdev->persistent_regions,
+                                            region);
+        }
         while ((ioreq->blkdev->persistent_gnt_count < ioreq->blkdev->max_grants)
               && new_maps) {
             /* Go through the list of newly mapped grants and add as many
@@ -447,6 +488,7 @@ static int ioreq_map(struct ioreq *ioreq)
                           grant);
             ioreq->blkdev->persistent_gnt_count++;
         }
+        assert(!batch_maps || new_maps == 0);
     }
     for (i = 0; i < ioreq->v.niov; i++) {
         ioreq->v.iov[i].iov_base += (uintptr_t)page[i];
@@ -971,7 +1013,10 @@ static int blk_connect(struct XenDevice *xendev)
         blkdev->max_grants = max_requests * BLKIF_MAX_SEGMENTS_PER_REQUEST;
         blkdev->persistent_gnts = g_tree_new_full((GCompareDataFunc)int_cmp,
                                              NULL, NULL,
+                                             batch_maps ?
+                                             (GDestroyNotify)g_free :
                                              (GDestroyNotify)destroy_grant);
+        blkdev->persistent_regions = NULL;
         blkdev->persistent_gnt_count = 0;
     }
 
@@ -1000,6 +1045,26 @@ static void blk_disconnect(struct XenDevice *xendev)
         blkdev->cnt_map--;
         blkdev->sring = NULL;
     }
+
+    /*
+     * Unmap persistent grants before switching to the closed state
+     * so the frontend can free them.
+     *
+     * In the !batch_maps case g_tree_destroy will take care of unmapping
+     * the grant, but in the batch_maps case we need to iterate over every
+     * region in persistent_regions and unmap it.
+     */
+    if (blkdev->feature_persistent) {
+        g_tree_destroy(blkdev->persistent_gnts);
+        assert(batch_maps || blkdev->persistent_gnt_count == 0);
+        if (batch_maps) {
+            blkdev->persistent_gnt_count = 0;
+            g_slist_foreach(blkdev->persistent_regions,
+                            (GFunc)remove_persistent_region, blkdev);
+            g_slist_free(blkdev->persistent_regions);
+        }
+        blkdev->feature_persistent = false;
+    }
 }
 
 static int blk_free(struct XenDevice *xendev)
@@ -1011,11 +1076,6 @@ static int blk_free(struct XenDevice *xendev)
         blk_disconnect(xendev);
     }
 
-    /* Free persistent grants */
-    if (blkdev->feature_persistent) {
-        g_tree_destroy(blkdev->persistent_gnts);
-    }
-
     while (!QLIST_EMPTY(&blkdev->freelist)) {
         ioreq = QLIST_FIRST(&blkdev->freelist);
         QLIST_REMOVE(ioreq, list);

hw/core/loader.c

@@ -80,6 +80,13 @@ int load_image(const char *filename, uint8_t *addr)
     if (fd < 0)
         return -1;
     size = lseek(fd, 0, SEEK_END);
+    if (size == -1) {
+        fprintf(stderr, "file %-20s: get size error: %s\n",
+                filename, strerror(errno));
+        close(fd);
+        return -1;
+    }
+
     lseek(fd, 0, SEEK_SET);
     if (read(fd, addr, size) != size) {
         close(fd);
@@ -748,6 +755,12 @@ int rom_add_file(const char *file, const char *fw_dir,
     }
     rom->addr     = addr;
     rom->romsize  = lseek(fd, 0, SEEK_END);
+    if (rom->romsize == -1) {
+        fprintf(stderr, "rom: file %-20s: get size error: %s\n",
+                rom->name, strerror(errno));
+        goto err;
+    }
+
     rom->datasize = rom->romsize;
     rom->data     = g_malloc0(rom->datasize);
     lseek(fd, 0, SEEK_SET);
@@ -798,12 +811,12 @@ err:
     return -1;
 }
 
-void *rom_add_blob(const char *name, const void *blob, size_t len,
+ram_addr_t rom_add_blob(const char *name, const void *blob, size_t len,
                    hwaddr addr, const char *fw_file_name,
                    FWCfgReadCallback fw_callback, void *callback_opaque)
 {
     Rom *rom;
-    void *data = NULL;
+    ram_addr_t ret = RAM_ADDR_MAX;
 
     rom           = g_malloc0(sizeof(*rom));
     rom->name     = g_strdup(name);
@@ -815,11 +828,13 @@ void *rom_add_blob(const char *name, const void *blob, size_t len,
     rom_insert(rom);
     if (fw_file_name && fw_cfg) {
         char devpath[100];
+        void *data;
 
         snprintf(devpath, sizeof(devpath), "/rom@%s", fw_file_name);
 
         if (rom_file_has_mr) {
             data = rom_set_mr(rom, OBJECT(fw_cfg), devpath);
+            ret = memory_region_get_ram_addr(rom->mr);
         } else {
             data = rom->data;
         }
@@ -828,7 +843,7 @@ void *rom_add_blob(const char *name, const void *blob, size_t len,
                                  fw_callback, callback_opaque,
                                  data, rom->romsize);
     }
-    return data;
+    return ret;
 }
 
 /* This function is specific for elf program because we don't need to allocate

hw/core/qdev.c

@@ -935,7 +935,7 @@ void qdev_alias_all_properties(DeviceState *target, Object *source)
     } while (class != object_class_by_name(TYPE_DEVICE));
 }
 
-int qdev_build_hotpluggable_device_list(Object *obj, void *opaque)
+static int qdev_add_hotpluggable_device(Object *obj, void *opaque)
 {
     GSList **list = opaque;
     DeviceState *dev = DEVICE(obj);
@@ -944,10 +944,18 @@ int qdev_build_hotpluggable_device_list(Object *obj, void *opaque)
         *list = g_slist_append(*list, dev);
     }
 
-    object_child_foreach(obj, qdev_build_hotpluggable_device_list, opaque);
     return 0;
 }
 
+GSList *qdev_build_hotpluggable_device_list(Object *peripheral)
+{
+    GSList *list = NULL;
+
+    object_child_foreach(peripheral, qdev_add_hotpluggable_device, &list);
+
+    return list;
+}
+
 static bool device_get_realized(Object *obj, Error **errp)
 {
     DeviceState *dev = DEVICE(obj);

hw/cpu/icc_bus.c

@@ -73,11 +73,11 @@ typedef struct ICCBridgeState {
     MemoryRegion apic_container;
 } ICCBridgeState;
 
-#define ICC_BRIGDE(obj) OBJECT_CHECK(ICCBridgeState, (obj), TYPE_ICC_BRIDGE)
+#define ICC_BRIDGE(obj) OBJECT_CHECK(ICCBridgeState, (obj), TYPE_ICC_BRIDGE)
 
 static void icc_bridge_init(Object *obj)
 {
-    ICCBridgeState *s = ICC_BRIGDE(obj);
+    ICCBridgeState *s = ICC_BRIDGE(obj);
     SysBusDevice *sb = SYS_BUS_DEVICE(obj);
 
     qbus_create_inplace(&s->icc_bus, sizeof(s->icc_bus), TYPE_ICC_BUS,

hw/display/cirrus_vga.c

@@ -173,20 +173,6 @@
 
 #define CIRRUS_PNPMMIO_SIZE         0x1000
 
-#define BLTUNSAFE(s) \
-    ( \
-        ( /* check dst is within bounds */ \
-            (s)->cirrus_blt_height * ABS((s)->cirrus_blt_dstpitch) \
-                + ((s)->cirrus_blt_dstaddr & (s)->cirrus_addr_mask) > \
-                    (s)->vga.vram_size \
-        ) || \
-        ( /* check src is within bounds */ \
-            (s)->cirrus_blt_height * ABS((s)->cirrus_blt_srcpitch) \
-                + ((s)->cirrus_blt_srcaddr & (s)->cirrus_addr_mask) > \
-                    (s)->vga.vram_size \
-        ) \
-    )
-
 struct CirrusVGAState;
 typedef void (*cirrus_bitblt_rop_t) (struct CirrusVGAState *s,
                                      uint8_t * dst, const uint8_t * src,
@@ -279,6 +265,50 @@ static void cirrus_update_memory_access(CirrusVGAState *s);
  *
  ***************************************/
 
+static bool blit_region_is_unsafe(struct CirrusVGAState *s,
+                                  int32_t pitch, int32_t addr)
+{
+    if (pitch < 0) {
+        int64_t min = addr
+            + ((int64_t)s->cirrus_blt_height-1) * pitch;
+        int32_t max = addr
+            + s->cirrus_blt_width;
+        if (min < 0 || max >= s->vga.vram_size) {
+            return true;
+        }
+    } else {
+        int64_t max = addr
+            + ((int64_t)s->cirrus_blt_height-1) * pitch
+            + s->cirrus_blt_width;
+        if (max >= s->vga.vram_size) {
+            return true;
+        }
+    }
+    return false;
+}
+
+static bool blit_is_unsafe(struct CirrusVGAState *s)
+{
+    /* should be the case, see cirrus_bitblt_start */
+    assert(s->cirrus_blt_width > 0);
+    assert(s->cirrus_blt_height > 0);
+
+    if (s->cirrus_blt_width > CIRRUS_BLTBUFSIZE) {
+        return true;
+    }
+
+    if (blit_region_is_unsafe(s, s->cirrus_blt_dstpitch,
+                              s->cirrus_blt_dstaddr & s->cirrus_addr_mask)) {
+        return true;
+    }
+    if (blit_region_is_unsafe(s, s->cirrus_blt_srcpitch,
+                              s->cirrus_blt_srcaddr & s->cirrus_addr_mask)) {
+        return true;
+    }
+
+    return false;
+}
+
 static void cirrus_bitblt_rop_nop(CirrusVGAState *s,
                                   uint8_t *dst,const uint8_t *src,
                                   int dstpitch,int srcpitch,
@@ -636,7 +666,7 @@ static int cirrus_bitblt_common_patterncopy(CirrusVGAState * s,
 
     dst = s->vga.vram_ptr + (s->cirrus_blt_dstaddr & s->cirrus_addr_mask);
 
-    if (BLTUNSAFE(s))
+    if (blit_is_unsafe(s))
         return 0;
 
     (*s->cirrus_rop) (s, dst, src,
@@ -654,8 +684,9 @@ static int cirrus_bitblt_solidfill(CirrusVGAState *s, int blt_rop)
 {
     cirrus_fill_t rop_func;
 
-    if (BLTUNSAFE(s))
+    if (blit_is_unsafe(s)) {
         return 0;
+    }
     rop_func = cirrus_fill[rop_to_index[blt_rop]][s->cirrus_blt_pixelwidth - 1];
     rop_func(s, s->vga.vram_ptr + (s->cirrus_blt_dstaddr & s->cirrus_addr_mask),
              s->cirrus_blt_dstpitch,
@@ -752,7 +783,7 @@ static void cirrus_do_copy(CirrusVGAState *s, int dst, int src, int w, int h)
 
 static int cirrus_bitblt_videotovideo_copy(CirrusVGAState * s)
 {
-    if (BLTUNSAFE(s))
+    if (blit_is_unsafe(s))
         return 0;
 
     cirrus_do_copy(s, s->cirrus_blt_dstaddr - s->vga.start_addr,

hw/i386/acpi-build.c

@@ -56,6 +56,7 @@
 
 #include "qapi/qmp/qint.h"
 #include "qom/qom-qobject.h"
+#include "exec/ram_addr.h"
 
 /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
  * -M pc-i440fx-2.0.  Even if the actual amount of AML generated grows
@@ -1269,8 +1270,7 @@ acpi_build_srat_memory(AcpiSratMemoryAffinity *numamem, uint64_t base,
 }
 
 static void
-build_srat(GArray *table_data, GArray *linker,
-           AcpiCpuInfo *cpu, PcGuestInfo *guest_info)
+build_srat(GArray *table_data, GArray *linker, PcGuestInfo *guest_info)
 {
     AcpiSystemResourceAffinityTable *srat;
     AcpiSratProcessorAffinity *core;
@@ -1300,11 +1300,7 @@ build_srat(GArray *table_data, GArray *linker,
         core->proximity_lo = curnode;
         memset(core->proximity_hi, 0, 3);
         core->local_sapic_eid = 0;
-        if (test_bit(i, cpu->found_cpus)) {
-            core->flags = cpu_to_le32(1);
-        } else {
-            core->flags = cpu_to_le32(0);
-        }
+        core->flags = cpu_to_le32(1);
     }
 
 
@@ -1511,7 +1507,7 @@ static inline void acpi_build_tables_cleanup(AcpiBuildTables *tables, bool mfre)
 typedef
 struct AcpiBuildState {
     /* Copy of table in RAM (for patching). */
-    uint8_t *table_ram;
+    ram_addr_t table_ram;
     uint32_t table_size;
     /* Is table patched? */
     uint8_t patched;
@@ -1622,7 +1618,7 @@ void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
     }
     if (guest_info->numa_nodes) {
         acpi_add_table(table_offsets, tables->table_data);
-        build_srat(tables->table_data, tables->linker, &cpu, guest_info);
+        build_srat(tables->table_data, tables->linker, guest_info);
     }
     if (acpi_get_mcfg(&mcfg)) {
         acpi_add_table(table_offsets, tables->table_data);
@@ -1716,9 +1712,12 @@ static void acpi_build_update(void *build_opaque, uint32_t offset)
     acpi_build(build_state->guest_info, &tables);
 
     assert(acpi_data_len(tables.table_data) == build_state->table_size);
-    memcpy(build_state->table_ram, tables.table_data->data,
+    memcpy(qemu_get_ram_ptr(build_state->table_ram), tables.table_data->data,
            build_state->table_size);
 
+    cpu_physical_memory_set_dirty_range_nocode(build_state->table_ram,
+                                               build_state->table_size);
+
     acpi_build_tables_cleanup(&tables, true);
 }
 
@@ -1728,7 +1727,7 @@ static void acpi_build_reset(void *build_opaque)
     build_state->patched = 0;
 }
 
-static void *acpi_add_rom_blob(AcpiBuildState *build_state, GArray *blob,
+static ram_addr_t acpi_add_rom_blob(AcpiBuildState *build_state, GArray *blob,
                                const char *name)
 {
     return rom_add_blob(name, blob->data, acpi_data_len(blob), -1, name,
@@ -1777,6 +1776,7 @@ void acpi_setup(PcGuestInfo *guest_info)
     /* Now expose it all to Guest */
     build_state->table_ram = acpi_add_rom_blob(build_state, tables.table_data,
                                                ACPI_BUILD_TABLE_FILE);
+    assert(build_state->table_ram != RAM_ADDR_MAX);
     build_state->table_size = acpi_data_len(tables.table_data);
 
     acpi_add_rom_blob(NULL, tables.linker, "etc/table-loader");

hw/i386/acpi-dsdt-mem-hotplug.dsl

@@ -0,0 +1,176 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+    External(MEMORY_SLOT_NOTIFY_METHOD, MethodObj)
+
+    Scope(\_SB.PCI0) {
+        Device(MEMORY_HOTPLUG_DEVICE) {
+            Name(_HID, "PNP0A06")
+            Name(_UID, "Memory hotplug resources")
+            External(MEMORY_SLOTS_NUMBER, IntObj)
+
+            /* Memory hotplug IO registers */
+            OperationRegion(MEMORY_HOTPLUG_IO_REGION, SystemIO,
+                            ACPI_MEMORY_HOTPLUG_BASE,
+                            ACPI_MEMORY_HOTPLUG_IO_LEN)
+
+            Name(_CRS, ResourceTemplate() {
+                IO(Decode16, ACPI_MEMORY_HOTPLUG_BASE, ACPI_MEMORY_HOTPLUG_BASE,
+                   0, ACPI_MEMORY_HOTPLUG_IO_LEN, IO)
+            })
+
+            Method(_STA, 0) {
+                If (LEqual(MEMORY_SLOTS_NUMBER, Zero)) {
+                    Return(0x0)
+                }
+                /* present, functioning, decoding, not shown in UI */
+                Return(0xB)
+            }
+
+            Field(MEMORY_HOTPLUG_IO_REGION, DWordAcc, NoLock, Preserve) {
+                MEMORY_SLOT_ADDR_LOW, 32,  // read only
+                MEMORY_SLOT_ADDR_HIGH, 32, // read only
+                MEMORY_SLOT_SIZE_LOW, 32,  // read only
+                MEMORY_SLOT_SIZE_HIGH, 32, // read only
+                MEMORY_SLOT_PROXIMITY, 32, // read only
+            }
+            Field(MEMORY_HOTPLUG_IO_REGION, ByteAcc, NoLock, Preserve) {
+                Offset(20),
+                MEMORY_SLOT_ENABLED,  1, // 1 if enabled, read only
+                MEMORY_SLOT_INSERT_EVENT, 1, // (read) 1 if has a insert event. (write) 1 to clear event
+            }
+
+            Mutex (MEMORY_SLOT_LOCK, 0)
+            Field (MEMORY_HOTPLUG_IO_REGION, DWordAcc, NoLock, Preserve) {
+                MEMORY_SLOT_SLECTOR, 32,  // DIMM selector, write only
+                MEMORY_SLOT_OST_EVENT, 32,  // _OST event code, write only
+                MEMORY_SLOT_OST_STATUS, 32,  // _OST status code, write only
+            }
+
+            Method(MEMORY_SLOT_SCAN_METHOD, 0) {
+                If (LEqual(MEMORY_SLOTS_NUMBER, Zero)) {
+                     Return(Zero)
+                }
+
+                Store(Zero, Local0) // Mem devs iterrator
+                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
+                while (LLess(Local0, MEMORY_SLOTS_NUMBER)) {
+                    Store(Local0, MEMORY_SLOT_SLECTOR) // select Local0 DIMM
+                    If (LEqual(MEMORY_SLOT_INSERT_EVENT, One)) { // Memory device needs check
+                        MEMORY_SLOT_NOTIFY_METHOD(Local0, 1)
+                        Store(1, MEMORY_SLOT_INSERT_EVENT)
+                    }
+                    // TODO: handle memory eject request
+                    Add(Local0, One, Local0) // goto next DIMM
+                }
+                Release(MEMORY_SLOT_LOCK)
+                Return(One)
+            }
+
+            Method(MEMORY_SLOT_STATUS_METHOD, 1) {
+                Store(Zero, Local0)
+
+                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
+                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
+
+                If (LEqual(MEMORY_SLOT_ENABLED, One)) {
+                    Store(0xF, Local0)
+                }
+
+                Release(MEMORY_SLOT_LOCK)
+                Return(Local0)
+            }
+
+            Method(MEMORY_SLOT_CRS_METHOD, 1, Serialized) {
+                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
+                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
+
+                Name(MR64, ResourceTemplate() {
+                    QWordMemory(ResourceProducer, PosDecode, MinFixed, MaxFixed,
+                    Cacheable, ReadWrite,
+                    0x0000000000000000,        // Address Space Granularity
+                    0x0000000000000000,        // Address Range Minimum
+                    0xFFFFFFFFFFFFFFFE,        // Address Range Maximum
+                    0x0000000000000000,        // Address Translation Offset
+                    0xFFFFFFFFFFFFFFFF,        // Address Length
+                    ,, MW64, AddressRangeMemory, TypeStatic)
+                })
+
+                CreateDWordField(MR64, 14, MINL)
+                CreateDWordField(MR64, 18, MINH)
+                CreateDWordField(MR64, 38, LENL)
+                CreateDWordField(MR64, 42, LENH)
+                CreateDWordField(MR64, 22, MAXL)
+                CreateDWordField(MR64, 26, MAXH)
+
+                Store(MEMORY_SLOT_ADDR_HIGH, MINH)
+                Store(MEMORY_SLOT_ADDR_LOW, MINL)
+                Store(MEMORY_SLOT_SIZE_HIGH, LENH)
+                Store(MEMORY_SLOT_SIZE_LOW, LENL)
+
+                // 64-bit math: MAX = MIN + LEN - 1
+                Add(MINL, LENL, MAXL)
+                Add(MINH, LENH, MAXH)
+                If (LLess(MAXL, MINL)) {
+                    Add(MAXH, One, MAXH)
+                }
+                If (LLess(MAXL, One)) {
+                    Subtract(MAXH, One, MAXH)
+                }
+                Subtract(MAXL, One, MAXL)
+
+                If (LEqual(MAXH, Zero)){
+                    Name(MR32, ResourceTemplate() {
+                        DWordMemory(ResourceProducer, PosDecode, MinFixed, MaxFixed,
+                        Cacheable, ReadWrite,
+                        0x00000000,        // Address Space Granularity
+                        0x00000000,        // Address Range Minimum
+                        0xFFFFFFFE,        // Address Range Maximum
+                        0x00000000,        // Address Translation Offset
+                        0xFFFFFFFF,        // Address Length
+                        ,, MW32, AddressRangeMemory, TypeStatic)
+                    })
+                    CreateDWordField(MR32, MW32._MIN, MIN)
+                    CreateDWordField(MR32, MW32._MAX, MAX)
+                    CreateDWordField(MR32, MW32._LEN, LEN)
+                    Store(MINL, MIN)
+                    Store(MAXL, MAX)
+                    Store(LENL, LEN)
+
+                    Release(MEMORY_SLOT_LOCK)
+                    Return(MR32)
+                }
+
+                Release(MEMORY_SLOT_LOCK)
+                Return(MR64)
+            }
+
+            Method(MEMORY_SLOT_PROXIMITY_METHOD, 1) {
+                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
+                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
+                Store(MEMORY_SLOT_PROXIMITY, Local0)
+                Release(MEMORY_SLOT_LOCK)
+                Return(Local0)
+            }
+
+            Method(MEMORY_SLOT_OST_METHOD, 4) {
+                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
+                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
+                Store(Arg1, MEMORY_SLOT_OST_EVENT)
+                Store(Arg2, MEMORY_SLOT_OST_STATUS)
+                Release(MEMORY_SLOT_LOCK)
+            }
+        } // Device()
+    } // Scope()

hw/i386/acpi-dsdt.dsl

@@ -297,13 +297,12 @@ DefinitionBlock (
 #include "hw/acpi/pc-hotplug.h"
 #define CPU_STATUS_BASE PIIX4_CPU_HOTPLUG_IO_BASE
 #include "acpi-dsdt-cpu-hotplug.dsl"
+#include "acpi-dsdt-mem-hotplug.dsl"
 
 
 /****************************************************************
  * General purpose events
  ****************************************************************/
-    External(\_SB.PCI0.MEMORY_HOTPLUG_DEVICE.MEMORY_SLOT_SCAN_METHOD, MethodObj)
-
     Scope(\_GPE) {
         Name(_HID, "ACPI0006")
 

hw/i386/acpi-dsdt.hex.generated

@@ -3,12 +3,12 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x53,
 0x44,
 0x54,
-0xf7,
-0xa,
+0x8,
+0xe,
 0x0,
 0x0,
 0x1,
-0x1f,
+0xfc,
 0x42,
 0x58,
 0x50,
@@ -32,8 +32,8 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0x54,
 0x4c,
 0x28,
-0x5,
-0x10,
+0x8,
+0x14,
 0x20,
 0x10,
 0x49,
@@ -2593,6 +2593,791 @@ static unsigned char AcpiDsdtAmlCode[] = {
 0xa,
 0xb,
 0x10,
+0x40,
+0x31,
+0x2e,
+0x5f,
+0x53,
+0x42,
+0x5f,
+0x50,
+0x43,
+0x49,
+0x30,
+0x5b,
+0x82,
+0x43,
+0x30,
+0x4d,
+0x48,
+0x50,
+0x44,
+0x8,
+0x5f,
+0x48,
+0x49,
+0x44,
+0xd,
+0x50,
+0x4e,
+0x50,
+0x30,
+0x41,
+0x30,
+0x36,
+0x0,
+0x8,
+0x5f,
+0x55,
+0x49,
+0x44,
+0xd,
+0x4d,
+0x65,
+0x6d,
+0x6f,
+0x72,
+0x79,
+0x20,
+0x68,
+0x6f,
+0x74,
+0x70,
+0x6c,
+0x75,
+0x67,
+0x20,
+0x72,
+0x65,
+0x73,
+0x6f,
+0x75,
+0x72,
+0x63,
+0x65,
+0x73,
+0x0,
+0x5b,
+0x80,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x1,
+0xb,
+0x0,
+0xa,
+0xa,
+0x18,
+0x8,
+0x5f,
+0x43,
+0x52,
+0x53,
+0x11,
+0xd,
+0xa,
+0xa,
+0x47,
+0x1,
+0x0,
+0xa,
+0x0,
+0xa,
+0x0,
+0x18,
+0x79,
+0x0,
+0x14,
+0x13,
+0x5f,
+0x53,
+0x54,
+0x41,
+0x0,
+0xa0,
+0x9,
+0x93,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x0,
+0xa4,
+0x0,
+0xa4,
+0xa,
+0xb,
+0x5b,
+0x81,
+0x1f,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x3,
+0x4d,
+0x52,
+0x42,
+0x4c,
+0x20,
+0x4d,
+0x52,
+0x42,
+0x48,
+0x20,
+0x4d,
+0x52,
+0x4c,
+0x4c,
+0x20,
+0x4d,
+0x52,
+0x4c,
+0x48,
+0x20,
+0x4d,
+0x50,
+0x58,
+0x5f,
+0x20,
+0x5b,
+0x81,
+0x13,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x1,
+0x0,
+0x40,
+0xa,
+0x4d,
+0x45,
+0x53,
+0x5f,
+0x1,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x1,
+0x5b,
+0x1,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0x0,
+0x5b,
+0x81,
+0x15,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x3,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x20,
+0x4d,
+0x4f,
+0x45,
+0x56,
+0x20,
+0x4d,
+0x4f,
+0x53,
+0x43,
+0x20,
+0x14,
+0x4a,
+0x4,
+0x4d,
+0x53,
+0x43,
+0x4e,
+0x0,
+0xa0,
+0x9,
+0x93,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x0,
+0xa4,
+0x0,
+0x70,
+0x0,
+0x60,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0xa2,
+0x25,
+0x95,
+0x60,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x70,
+0x60,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0xa0,
+0x13,
+0x93,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x1,
+0x4d,
+0x54,
+0x46,
+0x59,
+0x60,
+0x1,
+0x70,
+0x1,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x72,
+0x60,
+0x1,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x1,
+0x14,
+0x2d,
+0x4d,
+0x52,
+0x53,
+0x54,
+0x1,
+0x70,
+0x0,
+0x60,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0xa0,
+0xb,
+0x93,
+0x4d,
+0x45,
+0x53,
+0x5f,
+0x1,
+0x70,
+0xa,
+0xf,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x60,
+0x14,
+0x41,
+0x18,
+0x4d,
+0x43,
+0x52,
+0x53,
+0x9,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x8,
+0x4d,
+0x52,
+0x36,
+0x34,
+0x11,
+0x33,
+0xa,
+0x30,
+0x8a,
+0x2b,
+0x0,
+0x0,
+0xc,
+0x3,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xfe,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0x79,
+0x0,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0xe,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x12,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x26,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x2a,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x16,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x1a,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x42,
+0x48,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x42,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x70,
+0x4d,
+0x52,
+0x4c,
+0x48,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x4c,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x72,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x72,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x4d,
+0x41,
+0x58,
+0x48,
+0xa0,
+0x14,
+0x95,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x72,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x48,
+0xa0,
+0x11,
+0x95,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x1,
+0x74,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x74,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0xa0,
+0x44,
+0x7,
+0x93,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x0,
+0x8,
+0x4d,
+0x52,
+0x33,
+0x32,
+0x11,
+0x1f,
+0xa,
+0x1c,
+0x87,
+0x17,
+0x0,
+0x0,
+0xc,
+0x3,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xfe,
+0xff,
+0xff,
+0xff,
+0x0,
+0x0,
+0x0,
+0x0,
+0xff,
+0xff,
+0xff,
+0xff,
+0x79,
+0x0,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0xa,
+0x4d,
+0x49,
+0x4e,
+0x5f,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0xe,
+0x4d,
+0x41,
+0x58,
+0x5f,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0x16,
+0x4c,
+0x45,
+0x4e,
+0x5f,
+0x70,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x5f,
+0x70,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x4d,
+0x41,
+0x58,
+0x5f,
+0x70,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x5f,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x4d,
+0x52,
+0x33,
+0x32,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x4d,
+0x52,
+0x36,
+0x34,
+0x14,
+0x24,
+0x4d,
+0x50,
+0x58,
+0x4d,
+0x1,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x70,
+0x4d,
+0x50,
+0x58,
+0x5f,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x60,
+0x14,
+0x28,
+0x4d,
+0x4f,
+0x53,
+0x54,
+0x4,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x70,
+0x69,
+0x4d,
+0x4f,
+0x45,
+0x56,
+0x70,
+0x6a,
+0x4d,
+0x4f,
+0x53,
+0x43,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0x10,
 0x45,
 0xd,
 0x5f,

hw/i386/kvm/apic.c

@@ -175,6 +175,9 @@ static void kvm_apic_realize(DeviceState *dev, Error **errp)
 {
     APICCommonState *s = APIC_COMMON(dev);
 
+    /* Not used by KVM, which uses the CPU mp_state instead.  */
+    s->wait_for_sipi = 0;
+
     memory_region_init_io(&s->io_memory, NULL, &kvm_apic_io_ops, s, "kvm-apic-msi",
                           APIC_SPACE_SIZE);
 

hw/i386/kvm/clock.c

@@ -127,7 +127,21 @@ static void kvmclock_vm_state_change(void *opaque, int running,
         }
 
         cpu_synchronize_all_states();
+        /* In theory, the cpu_synchronize_all_states() call above wouldn't
+         * affect the rest of the code, as the VCPU state inside CPUState
+         * is supposed to always match the VCPU state on the kernel side.
+         *
+         * In practice, calling cpu_synchronize_state() too soon will load the
+         * kernel-side APIC state into X86CPU.apic_state too early, APIC state
+         * won't be reloaded later because CPUState.vcpu_dirty==true, and
+         * outdated APIC state may be migrated to another host.
+         *
+         * The real fix would be to make sure outdated APIC state is read
+         * from the kernel again when necessary. While this is not fixed, we
+         * need the cpu_clean_all_dirty() call below.
+         */
         cpu_clean_all_dirty();
+
         ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
         if (ret < 0) {
             fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));

hw/i386/pc.c

@@ -61,6 +61,7 @@
 #include "hw/mem/pc-dimm.h"
 #include "trace.h"
 #include "qapi/visitor.h"
+#include "qapi-visit.h"
 
 /* debug PC/ISA interrupts */
 //#define DEBUG_IRQ
@@ -1247,6 +1248,11 @@ FWCfgState *pc_memory_init(MachineState *machine,
         pcms->hotplug_memory_base =
             ROUND_UP(0x100000000ULL + above_4g_mem_size, 1ULL << 30);
 
+        if (pcms->enforce_aligned_dimm) {
+            /* size hotplug region assuming 1G page max alignment per slot */
+            hotplug_mem_size += (1ULL << 30) * machine->ram_slots;
+        }
+
         if ((pcms->hotplug_memory_base + hotplug_mem_size) <
             hotplug_mem_size) {
             error_report("unsupported amount of maximum memory: " RAM_ADDR_FMT,
@@ -1545,6 +1551,37 @@ void qemu_register_pc_machine(QEMUMachine *m)
     g_free(name);
 }
 
+static int pc_dimm_count(Object *obj, void *opaque)
+{
+    int *count = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_PC_DIMM)) {
+        (*count)++;
+    }
+
+    object_child_foreach(obj, pc_dimm_count, opaque);
+    return 0;
+}
+
+static int pc_existing_dimms_capacity(Object *obj, void *opaque)
+{
+    Error *local_err = NULL;
+    uint64_t *size = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_PC_DIMM)) {
+        (*size) += object_property_get_int(obj, PC_DIMM_SIZE_PROP, &local_err);
+
+        if (local_err) {
+            qerror_report_err(local_err);
+            error_free(local_err);
+            return 1;
+        }
+    }
+
+    object_child_foreach(obj, pc_dimm_count, opaque);
+    return 0;
+}
+
 static void pc_dimm_plug(HotplugHandler *hotplug_dev,
                          DeviceState *dev, Error **errp)
 {
@@ -1556,20 +1593,40 @@ static void pc_dimm_plug(HotplugHandler *hotplug_dev,
     PCDIMMDevice *dimm = PC_DIMM(dev);
     PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
     MemoryRegion *mr = ddc->get_memory_region(dimm);
-    uint64_t addr = object_property_get_int(OBJECT(dimm), PC_DIMM_ADDR_PROP,
-                                            &local_err);
+    uint64_t existing_dimms_capacity = 0;
+    uint64_t align = TARGET_PAGE_SIZE;
+    uint64_t addr;
+
+    addr = object_property_get_int(OBJECT(dimm), PC_DIMM_ADDR_PROP, &local_err);
     if (local_err) {
         goto out;
     }
 
+    if (memory_region_get_alignment(mr) && pcms->enforce_aligned_dimm) {
+        align = memory_region_get_alignment(mr);
+    }
+
     addr = pc_dimm_get_free_addr(pcms->hotplug_memory_base,
                                  memory_region_size(&pcms->hotplug_memory),
-                                 !addr ? NULL : &addr,
+                                 !addr ? NULL : &addr, align,
                                  memory_region_size(mr), &local_err);
     if (local_err) {
         goto out;
     }
 
+    if (pc_existing_dimms_capacity(OBJECT(machine), &existing_dimms_capacity)) {
+        error_setg(&local_err, "failed to get total size of existing DIMMs");
+        goto out;
+    }
+
+    if (existing_dimms_capacity + memory_region_size(mr) >
+        machine->maxram_size - machine->ram_size) {
+        error_setg(&local_err, "not enough space, currently 0x%" PRIx64
+                   " in use of total 0x" RAM_ADDR_FMT,
+                   existing_dimms_capacity, machine->maxram_size);
+        goto out;
+    }
+
     object_property_set_int(OBJECT(dev), addr, PC_DIMM_ADDR_PROP, &local_err);
     if (local_err) {
         goto out;
@@ -1598,6 +1655,11 @@ static void pc_dimm_plug(HotplugHandler *hotplug_dev,
         goto out;
     }
 
+    if (kvm_enabled() && !kvm_has_free_slot(machine)) {
+        error_setg(&local_err, "hypervisor has no free memory slots left");
+        goto out;
+    }
+
     memory_region_add_subregion(&pcms->hotplug_memory,
                                 addr - pcms->hotplug_memory_base, mr);
     vmstate_register_ram(mr, dev);
@@ -1711,18 +1773,28 @@ static void pc_machine_set_max_ram_below_4g(Object *obj, Visitor *v,
     pcms->max_ram_below_4g = value;
 }
 
-static bool pc_machine_get_vmport(Object *obj, Error **errp)
+static void pc_machine_get_vmport(Object *obj, Visitor *v, void *opaque,
+                                  const char *name, Error **errp)
 {
     PCMachineState *pcms = PC_MACHINE(obj);
+    OnOffAuto vmport = pcms->vmport;
 
-    return pcms->vmport;
+    visit_type_OnOffAuto(v, &vmport, name, errp);
 }
 
-static void pc_machine_set_vmport(Object *obj, bool value, Error **errp)
+static void pc_machine_set_vmport(Object *obj, Visitor *v, void *opaque,
+                                  const char *name, Error **errp)
 {
     PCMachineState *pcms = PC_MACHINE(obj);
 
-    pcms->vmport = value;
+    visit_type_OnOffAuto(v, &pcms->vmport, name, errp);
+}
+
+static bool pc_machine_get_aligned_dimm(Object *obj, Error **errp)
+{
+    PCMachineState *pcms = PC_MACHINE(obj);
+
+    return pcms->enforce_aligned_dimm;
 }
 
 static void pc_machine_initfn(Object *obj)
@@ -1737,11 +1809,17 @@ static void pc_machine_initfn(Object *obj)
                         pc_machine_get_max_ram_below_4g,
                         pc_machine_set_max_ram_below_4g,
                         NULL, NULL, NULL);
-    pcms->vmport = !xen_enabled();
-    object_property_add_bool(obj, PC_MACHINE_VMPORT,
-                             pc_machine_get_vmport,
-                             pc_machine_set_vmport,
-                             NULL);
+
+    pcms->vmport = ON_OFF_AUTO_AUTO;
+    object_property_add(obj, PC_MACHINE_VMPORT, "OnOffAuto",
+                        pc_machine_get_vmport,
+                        pc_machine_set_vmport,
+                        NULL, NULL, NULL);
+
+    pcms->enforce_aligned_dimm = true;
+    object_property_add_bool(obj, PC_MACHINE_ENFORCE_ALIGNED_DIMM,
+                             pc_machine_get_aligned_dimm,
+                             NULL, NULL);
 }
 
 static void pc_machine_class_init(ObjectClass *oc, void *data)

hw/i386/pc_piix.c

@@ -234,9 +234,14 @@ static void pc_init1(MachineState *machine,
 
     pc_vga_init(isa_bus, pci_enabled ? pci_bus : NULL);
 
+    assert(pc_machine->vmport != ON_OFF_AUTO_MAX);
+    if (pc_machine->vmport == ON_OFF_AUTO_AUTO) {
+        pc_machine->vmport = xen_enabled() ? ON_OFF_AUTO_OFF : ON_OFF_AUTO_ON;
+    }
+
     /* init basic PC hardware */
     pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy,
-                         !pc_machine->vmport, 0x4);
+                         (pc_machine->vmport != ON_OFF_AUTO_ON), 0x4);
 
     pc_nic_init(isa_bus, pci_bus);
 
@@ -305,10 +310,12 @@ static void pc_init_pci(MachineState *machine)
 
 static void pc_compat_2_1(MachineState *machine)
 {
+    PCMachineState *pcms = PC_MACHINE(machine);
     smbios_uuid_encoded = false;
     x86_cpu_compat_set_features("coreduo", FEAT_1_ECX, CPUID_EXT_VMX, 0);
     x86_cpu_compat_set_features("core2duo", FEAT_1_ECX, CPUID_EXT_VMX, 0);
     x86_cpu_compat_kvm_no_autodisable(FEAT_8000_0001_ECX, CPUID_EXT3_SVM);
+    pcms->enforce_aligned_dimm = false;
 }
 
 static void pc_compat_2_0(MachineState *machine)
@@ -916,17 +923,6 @@ static QEMUMachine xenfv_machine = {
     .max_cpus = HVM_MAX_VCPUS,
     .default_machine_opts = "accel=xen",
     .hot_add_cpu = pc_hot_add_cpu,
-    .compat_props = (GlobalProperty[]) {
-        /* xenfv has no fwcfg and so does not load acpi from QEMU.
-         * as such new acpi features don't work.
-         */
-        {
-            .driver   = "PIIX4_PM",
-            .property = "acpi-pci-hotplug-with-bridge-support",
-            .value    = "off",
-        },
-        { /* end of list */ }
-    },
 };
 #endif
 

hw/i386/pc_q35.c

@@ -242,9 +242,14 @@ static void pc_q35_init(MachineState *machine)
 
     pc_register_ferr_irq(gsi[13]);
 
+    assert(pc_machine->vmport != ON_OFF_AUTO_MAX);
+    if (pc_machine->vmport == ON_OFF_AUTO_AUTO) {
+        pc_machine->vmport = xen_enabled() ? ON_OFF_AUTO_OFF : ON_OFF_AUTO_ON;
+    }
+
     /* init basic PC hardware */
     pc_basic_device_init(isa_bus, gsi, &rtc_state, &floppy,
-                         !pc_machine->vmport, 0xff0104);
+                         (pc_machine->vmport != ON_OFF_AUTO_ON), 0xff0104);
 
     /* connect pm stuff to lpc */
     ich9_lpc_pm_init(lpc);
@@ -284,6 +289,9 @@ static void pc_q35_init(MachineState *machine)
 
 static void pc_compat_2_1(MachineState *machine)
 {
+    PCMachineState *pcms = PC_MACHINE(machine);
+
+    pcms->enforce_aligned_dimm = false;
     smbios_uuid_encoded = false;
     x86_cpu_compat_set_features("coreduo", FEAT_1_ECX, CPUID_EXT_VMX, 0);
     x86_cpu_compat_set_features("core2duo", FEAT_1_ECX, CPUID_EXT_VMX, 0);

hw/i386/q35-acpi-dsdt.dsl

@@ -405,13 +405,12 @@ DefinitionBlock (
 #include "hw/acpi/pc-hotplug.h"
 #define CPU_STATUS_BASE ICH9_CPU_HOTPLUG_IO_BASE
 #include "acpi-dsdt-cpu-hotplug.dsl"
+#include "acpi-dsdt-mem-hotplug.dsl"
 
 
 /****************************************************************
  * General purpose events
  ****************************************************************/
-    External(\_SB.PCI0.MEMORY_HOTPLUG_DEVICE.MEMORY_SLOT_SCAN_METHOD, MethodObj)
-
     Scope(\_GPE) {
         Name(_HID, "ACPI0006")
 

hw/i386/q35-acpi-dsdt.hex.generated

@@ -3,12 +3,12 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x53,
 0x44,
 0x54,
-0xe5,
-0x1c,
+0xf6,
+0x1f,
 0x0,
 0x0,
 0x1,
-0xb7,
+0x91,
 0x42,
 0x58,
 0x50,
@@ -31,9 +31,9 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0x4e,
 0x54,
 0x4c,
-0x15,
-0x11,
-0x13,
+0x28,
+0x8,
+0x14,
 0x20,
 0x10,
 0x49,
@@ -7234,6 +7234,791 @@ static unsigned char Q35AcpiDsdtAmlCode[] = {
 0xa,
 0xb,
 0x10,
+0x40,
+0x31,
+0x2e,
+0x5f,
+0x53,
+0x42,
+0x5f,
+0x50,
+0x43,
+0x49,
+0x30,
+0x5b,
+0x82,
+0x43,
+0x30,
+0x4d,
+0x48,
+0x50,
+0x44,
+0x8,
+0x5f,
+0x48,
+0x49,
+0x44,
+0xd,
+0x50,
+0x4e,
+0x50,
+0x30,
+0x41,
+0x30,
+0x36,
+0x0,
+0x8,
+0x5f,
+0x55,
+0x49,
+0x44,
+0xd,
+0x4d,
+0x65,
+0x6d,
+0x6f,
+0x72,
+0x79,
+0x20,
+0x68,
+0x6f,
+0x74,
+0x70,
+0x6c,
+0x75,
+0x67,
+0x20,
+0x72,
+0x65,
+0x73,
+0x6f,
+0x75,
+0x72,
+0x63,
+0x65,
+0x73,
+0x0,
+0x5b,
+0x80,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x1,
+0xb,
+0x0,
+0xa,
+0xa,
+0x18,
+0x8,
+0x5f,
+0x43,
+0x52,
+0x53,
+0x11,
+0xd,
+0xa,
+0xa,
+0x47,
+0x1,
+0x0,
+0xa,
+0x0,
+0xa,
+0x0,
+0x18,
+0x79,
+0x0,
+0x14,
+0x13,
+0x5f,
+0x53,
+0x54,
+0x41,
+0x0,
+0xa0,
+0x9,
+0x93,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x0,
+0xa4,
+0x0,
+0xa4,
+0xa,
+0xb,
+0x5b,
+0x81,
+0x1f,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x3,
+0x4d,
+0x52,
+0x42,
+0x4c,
+0x20,
+0x4d,
+0x52,
+0x42,
+0x48,
+0x20,
+0x4d,
+0x52,
+0x4c,
+0x4c,
+0x20,
+0x4d,
+0x52,
+0x4c,
+0x48,
+0x20,
+0x4d,
+0x50,
+0x58,
+0x5f,
+0x20,
+0x5b,
+0x81,
+0x13,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x1,
+0x0,
+0x40,
+0xa,
+0x4d,
+0x45,
+0x53,
+0x5f,
+0x1,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x1,
+0x5b,
+0x1,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0x0,
+0x5b,
+0x81,
+0x15,
+0x48,
+0x50,
+0x4d,
+0x52,
+0x3,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x20,
+0x4d,
+0x4f,
+0x45,
+0x56,
+0x20,
+0x4d,
+0x4f,
+0x53,
+0x43,
+0x20,
+0x14,
+0x4a,
+0x4,
+0x4d,
+0x53,
+0x43,
+0x4e,
+0x0,
+0xa0,
+0x9,
+0x93,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x0,
+0xa4,
+0x0,
+0x70,
+0x0,
+0x60,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0xa2,
+0x25,
+0x95,
+0x60,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0x70,
+0x60,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0xa0,
+0x13,
+0x93,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x1,
+0x4d,
+0x54,
+0x46,
+0x59,
+0x60,
+0x1,
+0x70,
+0x1,
+0x4d,
+0x49,
+0x4e,
+0x53,
+0x72,
+0x60,
+0x1,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x1,
+0x14,
+0x2d,
+0x4d,
+0x52,
+0x53,
+0x54,
+0x1,
+0x70,
+0x0,
+0x60,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0xa0,
+0xb,
+0x93,
+0x4d,
+0x45,
+0x53,
+0x5f,
+0x1,
+0x70,
+0xa,
+0xf,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x60,
+0x14,
+0x41,
+0x18,
+0x4d,
+0x43,
+0x52,
+0x53,
+0x9,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x8,
+0x4d,
+0x52,
+0x36,
+0x34,
+0x11,
+0x33,
+0xa,
+0x30,
+0x8a,
+0x2b,
+0x0,
+0x0,
+0xc,
+0x3,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xfe,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0xff,
+0x79,
+0x0,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0xe,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x12,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x26,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x2a,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x16,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x8a,
+0x4d,
+0x52,
+0x36,
+0x34,
+0xa,
+0x1a,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x42,
+0x48,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x42,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x70,
+0x4d,
+0x52,
+0x4c,
+0x48,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x70,
+0x4d,
+0x52,
+0x4c,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x72,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x72,
+0x4d,
+0x49,
+0x4e,
+0x48,
+0x4c,
+0x45,
+0x4e,
+0x48,
+0x4d,
+0x41,
+0x58,
+0x48,
+0xa0,
+0x14,
+0x95,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x72,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x48,
+0xa0,
+0x11,
+0x95,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x1,
+0x74,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x74,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x1,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0xa0,
+0x44,
+0x7,
+0x93,
+0x4d,
+0x41,
+0x58,
+0x48,
+0x0,
+0x8,
+0x4d,
+0x52,
+0x33,
+0x32,
+0x11,
+0x1f,
+0xa,
+0x1c,
+0x87,
+0x17,
+0x0,
+0x0,
+0xc,
+0x3,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0x0,
+0xfe,
+0xff,
+0xff,
+0xff,
+0x0,
+0x0,
+0x0,
+0x0,
+0xff,
+0xff,
+0xff,
+0xff,
+0x79,
+0x0,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0xa,
+0x4d,
+0x49,
+0x4e,
+0x5f,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0xe,
+0x4d,
+0x41,
+0x58,
+0x5f,
+0x8a,
+0x4d,
+0x52,
+0x33,
+0x32,
+0xa,
+0x16,
+0x4c,
+0x45,
+0x4e,
+0x5f,
+0x70,
+0x4d,
+0x49,
+0x4e,
+0x4c,
+0x4d,
+0x49,
+0x4e,
+0x5f,
+0x70,
+0x4d,
+0x41,
+0x58,
+0x4c,
+0x4d,
+0x41,
+0x58,
+0x5f,
+0x70,
+0x4c,
+0x45,
+0x4e,
+0x4c,
+0x4c,
+0x45,
+0x4e,
+0x5f,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x4d,
+0x52,
+0x33,
+0x32,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x4d,
+0x52,
+0x36,
+0x34,
+0x14,
+0x24,
+0x4d,
+0x50,
+0x58,
+0x4d,
+0x1,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x70,
+0x4d,
+0x50,
+0x58,
+0x5f,
+0x60,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xa4,
+0x60,
+0x14,
+0x28,
+0x4d,
+0x4f,
+0x53,
+0x54,
+0x4,
+0x5b,
+0x23,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0xff,
+0xff,
+0x70,
+0x99,
+0x68,
+0x0,
+0x4d,
+0x53,
+0x45,
+0x4c,
+0x70,
+0x69,
+0x4d,
+0x4f,
+0x45,
+0x56,
+0x70,
+0x6a,
+0x4d,
+0x4f,
+0x53,
+0x43,
+0x5b,
+0x27,
+0x4d,
+0x4c,
+0x43,
+0x4b,
+0x10,
 0x42,
 0xa,
 0x5f,

hw/i386/smbios.c

@@ -645,7 +645,7 @@ static void smbios_build_type_4_table(unsigned instance)
 
 static void smbios_build_type_16_table(unsigned dimm_cnt)
 {
-    ram_addr_t size_kb;
+    uint64_t size_kb;
 
     SMBIOS_BUILD_TABLE_PRE(16, 0x1000, true); /* required */
 
@@ -669,10 +669,10 @@ static void smbios_build_type_16_table(unsigned dimm_cnt)
 #define MAX_T17_STD_SZ 0x7FFF /* (32G - 1M), in Megabytes */
 #define MAX_T17_EXT_SZ 0x80000000 /* 2P, in Megabytes */
 
-static void smbios_build_type_17_table(unsigned instance, ram_addr_t size)
+static void smbios_build_type_17_table(unsigned instance, uint64_t size)
 {
     char loc_str[128];
-    ram_addr_t size_mb;
+    uint64_t size_mb;
 
     SMBIOS_BUILD_TABLE_PRE(17, 0x1100 + instance, true); /* required */
 
@@ -711,9 +711,9 @@ static void smbios_build_type_17_table(unsigned instance, ram_addr_t size)
 }
 
 static void smbios_build_type_19_table(unsigned instance,
-                                       ram_addr_t start, ram_addr_t size)
+                                       uint64_t start, uint64_t size)
 {
-    ram_addr_t end, start_kb, end_kb;
+    uint64_t end, start_kb, end_kb;
 
     SMBIOS_BUILD_TABLE_PRE(19, 0x1300 + instance, true); /* required */
 

hw/i386/ssdt-mem.hex.generated

@@ -11,7 +11,7 @@ static unsigned char ssdm_mem_aml[] = {
 0x0,
 0x0,
 0x2,
-0x71,
+0x66,
 0x42,
 0x58,
 0x50,
@@ -34,9 +34,9 @@ static unsigned char ssdm_mem_aml[] = {
 0x4e,
 0x54,
 0x4c,
-0x15,
-0x11,
-0x13,
+0x28,
+0x8,
+0x14,
 0x20,
 0x10,
 0x42,

hw/i386/ssdt-misc.dsl

@@ -36,6 +36,8 @@ DefinitionBlock ("ssdt-misc.aml", "SSDT", 0x01, "BXPC", "BXSSDTSUSP", 0x1)
        Name(P1E, Buffer() { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 })
        ACPI_EXTRACT_NAME_BUFFER8 acpi_pci64_length
        Name(P1L, Buffer() { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 })
+       ACPI_EXTRACT_NAME_DWORD_CONST ssdt_mctrl_nr_slots
+       Name(MEMORY_SLOTS_NUMBER, 0x12345678)
     }
 
 
@@ -117,167 +119,4 @@ DefinitionBlock ("ssdt-misc.aml", "SSDT", 0x01, "BXPC", "BXSSDTSUSP", 0x1)
             }
         }
     }
-
-    External(MEMORY_SLOT_NOTIFY_METHOD, MethodObj)
-    Scope(\_SB.PCI0) {
-        Device(MEMORY_HOTPLUG_DEVICE) {
-            Name(_HID, "PNP0A06")
-            Name(_UID, "Memory hotplug resources")
-
-            ACPI_EXTRACT_NAME_DWORD_CONST ssdt_mctrl_nr_slots
-            Name(MEMORY_SLOTS_NUMBER, 0x12345678)
-
-            /* Memory hotplug IO registers */
-            OperationRegion(MEMORY_HOTPLUG_IO_REGION, SystemIO,
-                            ACPI_MEMORY_HOTPLUG_BASE,
-                            ACPI_MEMORY_HOTPLUG_IO_LEN)
-
-            Name(_CRS, ResourceTemplate() {
-                IO(Decode16, ACPI_MEMORY_HOTPLUG_BASE, ACPI_MEMORY_HOTPLUG_BASE,
-                   0, ACPI_MEMORY_HOTPLUG_IO_LEN, IO)
-            })
-
-            Method(_STA, 0) {
-                If (LEqual(MEMORY_SLOTS_NUMBER, Zero)) {
-                    Return(0x0)
-                }
-                /* present, functioning, decoding, not shown in UI */
-                Return(0xB)
-            }
-
-            Field(MEMORY_HOTPLUG_IO_REGION, DWordAcc, NoLock, Preserve) {
-                MEMORY_SLOT_ADDR_LOW, 32,  // read only
-                MEMORY_SLOT_ADDR_HIGH, 32, // read only
-                MEMORY_SLOT_SIZE_LOW, 32,  // read only
-                MEMORY_SLOT_SIZE_HIGH, 32, // read only
-                MEMORY_SLOT_PROXIMITY, 32, // read only
-            }
-            Field(MEMORY_HOTPLUG_IO_REGION, ByteAcc, NoLock, Preserve) {
-                Offset(20),
-                MEMORY_SLOT_ENABLED,  1, // 1 if enabled, read only
-                MEMORY_SLOT_INSERT_EVENT, 1, // (read) 1 if has a insert event. (write) 1 to clear event
-            }
-
-            Mutex (MEMORY_SLOT_LOCK, 0)
-            Field (MEMORY_HOTPLUG_IO_REGION, DWordAcc, NoLock, Preserve) {
-                MEMORY_SLOT_SLECTOR, 32,  // DIMM selector, write only
-                MEMORY_SLOT_OST_EVENT, 32,  // _OST event code, write only
-                MEMORY_SLOT_OST_STATUS, 32,  // _OST status code, write only
-            }
-
-            Method(MEMORY_SLOT_SCAN_METHOD, 0) {
-                If (LEqual(MEMORY_SLOTS_NUMBER, Zero)) {
-                     Return(Zero)
-                }
-
-                Store(Zero, Local0) // Mem devs iterrator
-                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
-                while (LLess(Local0, MEMORY_SLOTS_NUMBER)) {
-                    Store(Local0, MEMORY_SLOT_SLECTOR) // select Local0 DIMM
-                    If (LEqual(MEMORY_SLOT_INSERT_EVENT, One)) { // Memory device needs check
-                        MEMORY_SLOT_NOTIFY_METHOD(Local0, 1)
-                        Store(1, MEMORY_SLOT_INSERT_EVENT)
-                    }
-                    // TODO: handle memory eject request
-                    Add(Local0, One, Local0) // goto next DIMM
-                }
-                Release(MEMORY_SLOT_LOCK)
-                Return(One)
-            }
-
-            Method(MEMORY_SLOT_STATUS_METHOD, 1) {
-                Store(Zero, Local0)
-
-                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
-                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
-
-                If (LEqual(MEMORY_SLOT_ENABLED, One)) {
-                    Store(0xF, Local0)
-                }
-
-                Release(MEMORY_SLOT_LOCK)
-                Return(Local0)
-            }
-
-            Method(MEMORY_SLOT_CRS_METHOD, 1, Serialized) {
-                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
-                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
-
-                Name(MR64, ResourceTemplate() {
-                    QWordMemory(ResourceProducer, PosDecode, MinFixed, MaxFixed,
-                    Cacheable, ReadWrite,
-                    0x0000000000000000,        // Address Space Granularity
-                    0x0000000000000000,        // Address Range Minimum
-                    0xFFFFFFFFFFFFFFFE,        // Address Range Maximum
-                    0x0000000000000000,        // Address Translation Offset
-                    0xFFFFFFFFFFFFFFFF,        // Address Length
-                    ,, MW64, AddressRangeMemory, TypeStatic)
-                })
-
-                CreateDWordField(MR64, 14, MINL)
-                CreateDWordField(MR64, 18, MINH)
-                CreateDWordField(MR64, 38, LENL)
-                CreateDWordField(MR64, 42, LENH)
-                CreateDWordField(MR64, 22, MAXL)
-                CreateDWordField(MR64, 26, MAXH)
-
-                Store(MEMORY_SLOT_ADDR_HIGH, MINH)
-                Store(MEMORY_SLOT_ADDR_LOW, MINL)
-                Store(MEMORY_SLOT_SIZE_HIGH, LENH)
-                Store(MEMORY_SLOT_SIZE_LOW, LENL)
-
-                // 64-bit math: MAX = MIN + LEN - 1
-                Add(MINL, LENL, MAXL)
-                Add(MINH, LENH, MAXH)
-                If (LLess(MAXL, MINL)) {
-                    Add(MAXH, One, MAXH)
-                }
-                If (LLess(MAXL, One)) {
-                    Subtract(MAXH, One, MAXH)
-                }
-                Subtract(MAXL, One, MAXL)
-
-                If (LEqual(MAXH, Zero)){
-                    Name(MR32, ResourceTemplate() {
-                        DWordMemory(ResourceProducer, PosDecode, MinFixed, MaxFixed,
-                        Cacheable, ReadWrite,
-                        0x00000000,        // Address Space Granularity
-                        0x00000000,        // Address Range Minimum
-                        0xFFFFFFFE,        // Address Range Maximum
-                        0x00000000,        // Address Translation Offset
-                        0xFFFFFFFF,        // Address Length
-                        ,, MW32, AddressRangeMemory, TypeStatic)
-                    })
-                    CreateDWordField(MR32, MW32._MIN, MIN)
-                    CreateDWordField(MR32, MW32._MAX, MAX)
-                    CreateDWordField(MR32, MW32._LEN, LEN)
-                    Store(MINL, MIN)
-                    Store(MAXL, MAX)
-                    Store(LENL, LEN)
-
-                    Release(MEMORY_SLOT_LOCK)
-                    Return(MR32)
-                }
-
-                Release(MEMORY_SLOT_LOCK)
-                Return(MR64)
-            }
-
-            Method(MEMORY_SLOT_PROXIMITY_METHOD, 1) {
-                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
-                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
-                Store(MEMORY_SLOT_PROXIMITY, Local0)
-                Release(MEMORY_SLOT_LOCK)
-                Return(Local0)
-            }
-
-            Method(MEMORY_SLOT_OST_METHOD, 4) {
-                Acquire(MEMORY_SLOT_LOCK, 0xFFFF)
-                Store(ToInteger(Arg0), MEMORY_SLOT_SLECTOR) // select DIMM
-                Store(Arg1, MEMORY_SLOT_OST_EVENT)
-                Store(Arg2, MEMORY_SLOT_OST_STATUS)
-                Release(MEMORY_SLOT_LOCK)
-            }
-        } // Device()
-    } // Scope()
 }

hw/i386/ssdt-misc.hex.generated

@@ -2,13 +2,13 @@ static unsigned char acpi_pci64_length[] = {
 0x6f
 };
 static unsigned char acpi_s4_pkg[] = {
-0x8f
+0x99
 };
-static unsigned short ssdt_mctrl_nr_slots[] = {
-0x1aa
+static unsigned char ssdt_mctrl_nr_slots[] = {
+0x7d
 };
 static unsigned char acpi_s3_name[] = {
-0x7c
+0x86
 };
 static unsigned char acpi_pci32_start[] = {
 0x2f
@@ -21,12 +21,12 @@ static unsigned char ssdp_misc_aml[] = {
 0x53,
 0x44,
 0x54,
-0x7e,
-0x4,
+0x6c,
+0x1,
 0x0,
 0x0,
 0x1,
-0x8b,
+0x3,
 0x42,
 0x58,
 0x50,
@@ -49,12 +49,12 @@ static unsigned char ssdp_misc_aml[] = {
 0x4e,
 0x54,
 0x4c,
-0x15,
-0x11,
-0x13,
+0x28,
+0x8,
+0x14,
 0x20,
 0x10,
-0x42,
+0x4c,
 0x5,
 0x5c,
 0x0,
@@ -136,6 +136,16 @@ static unsigned char ssdp_misc_aml[] = {
 0x0,
 0x0,
 0x0,
+0x8,
+0x4d,
+0x44,
+0x4e,
+0x52,
+0xc,
+0x78,
+0x56,
+0x34,
+0x12,
 0x10,
 0x29,
 0x5c,
@@ -370,809 +380,13 @@ static unsigned char ssdp_misc_aml[] = {
 0x49,
 0x4f,
 0x4d,
-0x58,
-0x10,
-0x4b,
-0x31,
-0x5c,
-0x2e,
-0x5f,
-0x53,
-0x42,
-0x5f,
-0x50,
-0x43,
-0x49,
-0x30,
-0x5b,
-0x82,
-0x4d,
-0x30,
-0x4d,
-0x48,
-0x50,
-0x44,
-0x8,
-0x5f,
-0x48,
-0x49,
-0x44,
-0xd,
-0x50,
-0x4e,
-0x50,
-0x30,
-0x41,
-0x30,
-0x36,
-0x0,
-0x8,
-0x5f,
-0x55,
-0x49,
-0x44,
-0xd,
-0x4d,
-0x65,
-0x6d,
-0x6f,
-0x72,
-0x79,
-0x20,
-0x68,
-0x6f,
-0x74,
-0x70,
-0x6c,
-0x75,
-0x67,
-0x20,
-0x72,
-0x65,
-0x73,
-0x6f,
-0x75,
-0x72,
-0x63,
-0x65,
-0x73,
-0x0,
-0x8,
-0x4d,
-0x44,
-0x4e,
-0x52,
-0xc,
-0x78,
-0x56,
-0x34,
-0x12,
-0x5b,
-0x80,
-0x48,
-0x50,
-0x4d,
-0x52,
-0x1,
-0xb,
-0x0,
-0xa,
-0xa,
-0x18,
-0x8,
-0x5f,
-0x43,
-0x52,
-0x53,
-0x11,
-0xd,
-0xa,
-0xa,
-0x47,
-0x1,
-0x0,
-0xa,
-0x0,
-0xa,
-0x0,
-0x18,
-0x79,
-0x0,
-0x14,
-0x13,
-0x5f,
-0x53,
-0x54,
-0x41,
-0x0,
-0xa0,
-0x9,
-0x93,
-0x4d,
-0x44,
-0x4e,
-0x52,
-0x0,
-0xa4,
-0x0,
-0xa4,
-0xa,
-0xb,
-0x5b,
-0x81,
-0x1f,
-0x48,
-0x50,
-0x4d,
-0x52,
-0x3,
-0x4d,
-0x52,
-0x42,
-0x4c,
-0x20,
-0x4d,
-0x52,
-0x42,
-0x48,
-0x20,
-0x4d,
-0x52,
-0x4c,
-0x4c,
-0x20,
-0x4d,
-0x52,
-0x4c,
-0x48,
-0x20,
-0x4d,
-0x50,
-0x58,
-0x5f,
-0x20,
-0x5b,
-0x81,
-0x13,
-0x48,
-0x50,
-0x4d,
-0x52,
-0x1,
-0x0,
-0x40,
-0xa,
-0x4d,
-0x45,
-0x53,
-0x5f,
-0x1,
-0x4d,
-0x49,
-0x4e,
-0x53,
-0x1,
-0x5b,
-0x1,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0x0,
-0x5b,
-0x81,
-0x15,
-0x48,
-0x50,
-0x4d,
-0x52,
-0x3,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0x20,
-0x4d,
-0x4f,
-0x45,
-0x56,
-0x20,
-0x4d,
-0x4f,
-0x53,
-0x43,
-0x20,
-0x14,
-0x4a,
-0x4,
-0x4d,
-0x53,
-0x43,
-0x4e,
-0x0,
-0xa0,
-0x9,
-0x93,
-0x4d,
-0x44,
-0x4e,
-0x52,
-0x0,
-0xa4,
-0x0,
-0x70,
-0x0,
-0x60,
-0x5b,
-0x23,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xff,
-0xff,
-0xa2,
-0x25,
-0x95,
-0x60,
-0x4d,
-0x44,
-0x4e,
-0x52,
-0x70,
-0x60,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0xa0,
-0x13,
-0x93,
-0x4d,
-0x49,
-0x4e,
-0x53,
-0x1,
-0x4d,
-0x54,
-0x46,
-0x59,
-0x60,
-0x1,
-0x70,
-0x1,
-0x4d,
-0x49,
-0x4e,
-0x53,
-0x72,
-0x60,
-0x1,
-0x60,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xa4,
-0x1,
-0x14,
-0x2d,
-0x4d,
-0x52,
-0x53,
-0x54,
-0x1,
-0x70,
-0x0,
-0x60,
-0x5b,
-0x23,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xff,
-0xff,
-0x70,
-0x99,
-0x68,
-0x0,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0xa0,
-0xb,
-0x93,
-0x4d,
-0x45,
-0x53,
-0x5f,
-0x1,
-0x70,
-0xa,
-0xf,
-0x60,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xa4,
-0x60,
-0x14,
-0x41,
-0x18,
-0x4d,
-0x43,
-0x52,
-0x53,
-0x9,
-0x5b,
-0x23,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xff,
-0xff,
-0x70,
-0x99,
-0x68,
-0x0,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0x8,
-0x4d,
-0x52,
-0x36,
-0x34,
-0x11,
-0x33,
-0xa,
-0x30,
-0x8a,
-0x2b,
-0x0,
-0x0,
-0xc,
-0x3,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0xfe,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0xff,
-0x79,
-0x0,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0xe,
-0x4d,
-0x49,
-0x4e,
-0x4c,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0x12,
-0x4d,
-0x49,
-0x4e,
-0x48,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0x26,
-0x4c,
-0x45,
-0x4e,
-0x4c,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0x2a,
-0x4c,
-0x45,
-0x4e,
-0x48,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0x16,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x8a,
-0x4d,
-0x52,
-0x36,
-0x34,
-0xa,
-0x1a,
-0x4d,
-0x41,
-0x58,
-0x48,
-0x70,
-0x4d,
-0x52,
-0x42,
-0x48,
-0x4d,
-0x49,
-0x4e,
-0x48,
-0x70,
-0x4d,
-0x52,
-0x42,
-0x4c,
-0x4d,
-0x49,
-0x4e,
-0x4c,
-0x70,
-0x4d,
-0x52,
-0x4c,
-0x48,
-0x4c,
-0x45,
-0x4e,
-0x48,
-0x70,
-0x4d,
-0x52,
-0x4c,
-0x4c,
-0x4c,
-0x45,
-0x4e,
-0x4c,
-0x72,
-0x4d,
-0x49,
-0x4e,
-0x4c,
-0x4c,
-0x45,
-0x4e,
-0x4c,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x72,
-0x4d,
-0x49,
-0x4e,
-0x48,
-0x4c,
-0x45,
-0x4e,
-0x48,
-0x4d,
-0x41,
-0x58,
-0x48,
-0xa0,
-0x14,
-0x95,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x4d,
-0x49,
-0x4e,
-0x4c,
-0x72,
-0x4d,
-0x41,
-0x58,
-0x48,
-0x1,
-0x4d,
-0x41,
-0x58,
-0x48,
-0xa0,
-0x11,
-0x95,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x1,
-0x74,
-0x4d,
-0x41,
-0x58,
-0x48,
-0x1,
-0x4d,
-0x41,
-0x58,
-0x48,
-0x74,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x1,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0xa0,
-0x44,
-0x7,
-0x93,
-0x4d,
-0x41,
-0x58,
-0x48,
-0x0,
-0x8,
-0x4d,
-0x52,
-0x33,
-0x32,
-0x11,
-0x1f,
-0xa,
-0x1c,
-0x87,
-0x17,
-0x0,
-0x0,
-0xc,
-0x3,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0x0,
-0xfe,
-0xff,
-0xff,
-0xff,
-0x0,
-0x0,
-0x0,
-0x0,
-0xff,
-0xff,
-0xff,
-0xff,
-0x79,
-0x0,
-0x8a,
-0x4d,
-0x52,
-0x33,
-0x32,
-0xa,
-0xa,
-0x4d,
-0x49,
-0x4e,
-0x5f,
-0x8a,
-0x4d,
-0x52,
-0x33,
-0x32,
-0xa,
-0xe,
-0x4d,
-0x41,
-0x58,
-0x5f,
-0x8a,
-0x4d,
-0x52,
-0x33,
-0x32,
-0xa,
-0x16,
-0x4c,
-0x45,
-0x4e,
-0x5f,
-0x70,
-0x4d,
-0x49,
-0x4e,
-0x4c,
-0x4d,
-0x49,
-0x4e,
-0x5f,
-0x70,
-0x4d,
-0x41,
-0x58,
-0x4c,
-0x4d,
-0x41,
-0x58,
-0x5f,
-0x70,
-0x4c,
-0x45,
-0x4e,
-0x4c,
-0x4c,
-0x45,
-0x4e,
-0x5f,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xa4,
-0x4d,
-0x52,
-0x33,
-0x32,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xa4,
-0x4d,
-0x52,
-0x36,
-0x34,
-0x14,
-0x24,
-0x4d,
-0x50,
-0x58,
-0x4d,
-0x1,
-0x5b,
-0x23,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xff,
-0xff,
-0x70,
-0x99,
-0x68,
-0x0,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0x70,
-0x4d,
-0x50,
-0x58,
-0x5f,
-0x60,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xa4,
-0x60,
-0x14,
-0x28,
-0x4d,
-0x4f,
-0x53,
-0x54,
-0x4,
-0x5b,
-0x23,
-0x4d,
-0x4c,
-0x43,
-0x4b,
-0xff,
-0xff,
-0x70,
-0x99,
-0x68,
-0x0,
-0x4d,
-0x53,
-0x45,
-0x4c,
-0x70,
-0x69,
-0x4d,
-0x4f,
-0x45,
-0x56,
-0x70,
-0x6a,
-0x4d,
-0x4f,
-0x53,
-0x43,
-0x5b,
-0x27,
-0x4d,
-0x4c,
-0x43,
-0x4b
+0x58
 };
 static unsigned char ssdt_isa_pest[] = {
-0xd0
+0xda
 };
 static unsigned char acpi_s4_name[] = {
-0x88
+0x92
 };
 static unsigned char acpi_pci64_start[] = {
 0x4d

hw/ide/ahci.c

@@ -730,7 +730,8 @@ static int prdt_tbl_entry_size(const AHCI_SG *tbl)
     return (le32_to_cpu(tbl->flags_size) & AHCI_PRDT_SIZE_MASK) + 1;
 }
 
-static int ahci_populate_sglist(AHCIDevice *ad, QEMUSGList *sglist, int offset)
+static int ahci_populate_sglist(AHCIDevice *ad, QEMUSGList *sglist,
+                                int32_t offset)
 {
     AHCICmdHdr *cmd = ad->cur_cmd;
     uint32_t opts = le32_to_cpu(cmd->opts);
@@ -741,13 +742,21 @@ static int ahci_populate_sglist(AHCIDevice *ad, QEMUSGList *sglist, int offset)
     uint8_t *prdt;
     int i;
     int r = 0;
-    int sum = 0;
+    uint64_t sum = 0;
     int off_idx = -1;
-    int off_pos = -1;
+    int64_t off_pos = -1;
     int tbl_entry_size;
     IDEBus *bus = &ad->port;
     BusState *qbus = BUS(bus);
 
+    /*
+     * Note: AHCI PRDT can describe up to 256GiB. SATA/ATA only support
+     * transactions of up to 32MiB as of ATA8-ACS3 rev 1b, assuming a
+     * 512 byte sector size. We limit the PRDT in this implementation to
+     * a reasonably large 2GiB, which can accommodate the maximum transfer
+     * request for sector sizes up to 32K.
+     */
+
     if (!sglist_alloc_hint) {
         DPRINTF(ad->port_no, "no sg list given by guest: 0x%08x\n", opts);
         return -1;
@@ -782,7 +791,7 @@ static int ahci_populate_sglist(AHCIDevice *ad, QEMUSGList *sglist, int offset)
         }
         if ((off_idx == -1) || (off_pos < 0) || (off_pos > tbl_entry_size)) {
             DPRINTF(ad->port_no, "%s: Incorrect offset! "
-                            "off_idx: %d, off_pos: %d\n",
+                            "off_idx: %d, off_pos: %"PRId64"\n",
                             __func__, off_idx, off_pos);
             r = -1;
             goto out;
@@ -797,6 +806,13 @@ static int ahci_populate_sglist(AHCIDevice *ad, QEMUSGList *sglist, int offset)
             /* flags_size is zero-based */
             qemu_sglist_add(sglist, le64_to_cpu(tbl[i].addr),
                             prdt_tbl_entry_size(&tbl[i]));
+            if (sglist->size > INT32_MAX) {
+                error_report("AHCI Physical Region Descriptor Table describes "
+                             "more than 2 GiB.\n");
+                qemu_sglist_destroy(sglist);
+                r = -1;
+                goto out;
+            }
         }
     }
 
@@ -838,6 +854,21 @@ static void ncq_cb(void *opaque, int ret)
     ncq_tfs->used = 0;
 }
 
+static int is_ncq(uint8_t ata_cmd)
+{
+    /* Based on SATA 3.2 section 13.6.3.2 */
+    switch (ata_cmd) {
+    case READ_FPDMA_QUEUED:
+    case WRITE_FPDMA_QUEUED:
+    case NCQ_NON_DATA:
+    case RECEIVE_FPDMA_QUEUED:
+    case SEND_FPDMA_QUEUED:
+        return 1;
+    default:
+        return 0;
+    }
+}
+
 static void process_ncq_command(AHCIState *s, int port, uint8_t *cmd_fis,
                                 int slot)
 {
@@ -903,16 +934,106 @@ static void process_ncq_command(AHCIState *s, int port, uint8_t *cmd_fis,
                                            ncq_cb, ncq_tfs);
             break;
         default:
-            DPRINTF(port, "error: tried to process non-NCQ command as NCQ\n");
+            if (is_ncq(cmd_fis[2])) {
+                DPRINTF(port,
+                        "error: unsupported NCQ command (0x%02x) received\n",
+                        cmd_fis[2]);
+            } else {
+                DPRINTF(port,
+                        "error: tried to process non-NCQ command as NCQ\n");
+            }
             qemu_sglist_destroy(&ncq_tfs->sglist);
-            break;
     }
 }
 
+static void handle_reg_h2d_fis(AHCIState *s, int port,
+                               int slot, uint8_t *cmd_fis)
+{
+    IDEState *ide_state = &s->dev[port].port.ifs[0];
+    AHCICmdHdr *cmd = s->dev[port].cur_cmd;
+    uint32_t opts = le32_to_cpu(cmd->opts);
+
+    if (cmd_fis[1] & 0x0F) {
+        DPRINTF(port, "Port Multiplier not supported."
+                " cmd_fis[0]=%02x cmd_fis[1]=%02x cmd_fis[2]=%02x\n",
+                cmd_fis[0], cmd_fis[1], cmd_fis[2]);
+        return;
+    }
+
+    if (cmd_fis[1] & 0x70) {
+        DPRINTF(port, "Reserved flags set in H2D Register FIS."
+                " cmd_fis[0]=%02x cmd_fis[1]=%02x cmd_fis[2]=%02x\n",
+                cmd_fis[0], cmd_fis[1], cmd_fis[2]);
+        return;
+    }
+
+    if (!(cmd_fis[1] & SATA_FIS_REG_H2D_UPDATE_COMMAND_REGISTER)) {
+        switch (s->dev[port].port_state) {
+        case STATE_RUN:
+            if (cmd_fis[15] & ATA_SRST) {
+                s->dev[port].port_state = STATE_RESET;
+            }
+            break;
+        case STATE_RESET:
+            if (!(cmd_fis[15] & ATA_SRST)) {
+                ahci_reset_port(s, port);
+            }
+            break;
+        }
+        return;
+    }
+
+    /* Check for NCQ command */
+    if (is_ncq(cmd_fis[2])) {
+        process_ncq_command(s, port, cmd_fis, slot);
+        return;
+    }
+
+    /* Decompose the FIS:
+     * AHCI does not interpret FIS packets, it only forwards them.
+     * SATA 1.0 describes how to decode LBA28 and CHS FIS packets.
+     * Later specifications, e.g, SATA 3.2, describe LBA48 FIS packets.
+     *
+     * ATA4 describes sector number for LBA28/CHS commands.
+     * ATA6 describes sector number for LBA48 commands.
+     * ATA8 deprecates CHS fully, describing only LBA28/48.
+     *
+     * We dutifully convert the FIS into IDE registers, and allow the
+     * core layer to interpret them as needed. */
+    ide_state->feature = cmd_fis[3];
+    ide_state->sector = cmd_fis[4];      /* LBA 7:0 */
+    ide_state->lcyl = cmd_fis[5];        /* LBA 15:8  */
+    ide_state->hcyl = cmd_fis[6];        /* LBA 23:16 */
+    ide_state->select = cmd_fis[7];      /* LBA 27:24 (LBA28) */
+    ide_state->hob_sector = cmd_fis[8];  /* LBA 31:24 */
+    ide_state->hob_lcyl = cmd_fis[9];    /* LBA 39:32 */
+    ide_state->hob_hcyl = cmd_fis[10];   /* LBA 47:40 */
+    ide_state->hob_feature = cmd_fis[11];
+    ide_state->nsector = (int64_t)((cmd_fis[13] << 8) | cmd_fis[12]);
+    /* 14, 16, 17, 18, 19: Reserved (SATA 1.0) */
+    /* 15: Only valid when UPDATE_COMMAND not set. */
+
+    /* Copy the ACMD field (ATAPI packet, if any) from the AHCI command
+     * table to ide_state->io_buffer */
+    if (opts & AHCI_CMD_ATAPI) {
+        memcpy(ide_state->io_buffer, &cmd_fis[AHCI_COMMAND_TABLE_ACMD], 0x10);
+        debug_print_fis(ide_state->io_buffer, 0x10);
+        s->dev[port].done_atapi_packet = false;
+        /* XXX send PIO setup FIS */
+    }
+
+    ide_state->error = 0;
+
+    /* Reset transferred byte counter */
+    cmd->status = 0;
+
+    /* We're ready to process the command in FIS byte 2. */
+    ide_exec_cmd(&s->dev[port].port, cmd_fis[2]);
+}
+
 static int handle_cmd(AHCIState *s, int port, int slot)
 {
     IDEState *ide_state;
-    uint32_t opts;
     uint64_t tbl_addr;
     AHCICmdHdr *cmd;
     uint8_t *cmd_fis;
@@ -924,142 +1045,48 @@ static int handle_cmd(AHCIState *s, int port, int slot)
         return -1;
     }
 
-    cmd = &((AHCICmdHdr *)s->dev[port].lst)[slot];
-
     if (!s->dev[port].lst) {
         DPRINTF(port, "error: lst not given but cmd handled");
         return -1;
     }
-
+    cmd = &((AHCICmdHdr *)s->dev[port].lst)[slot];
     /* remember current slot handle for later */
     s->dev[port].cur_cmd = cmd;
 
-    opts = le32_to_cpu(cmd->opts);
-    tbl_addr = le64_to_cpu(cmd->tbl_addr);
-
-    cmd_len = 0x80;
-    cmd_fis = dma_memory_map(s->as, tbl_addr, &cmd_len,
-                             DMA_DIRECTION_FROM_DEVICE);
-
-    if (!cmd_fis) {
-        DPRINTF(port, "error: guest passed us an invalid cmd fis\n");
+    /* The device we are working for */
+    ide_state = &s->dev[port].port.ifs[0];
+    if (!ide_state->blk) {
+        DPRINTF(port, "error: guest accessed unused port");
         return -1;
     }
 
-    /* The device we are working for */
-    ide_state = &s->dev[port].port.ifs[0];
-
-    if (!ide_state->blk) {
-        DPRINTF(port, "error: guest accessed unused port");
+    tbl_addr = le64_to_cpu(cmd->tbl_addr);
+    cmd_len = 0x80;
+    cmd_fis = dma_memory_map(s->as, tbl_addr, &cmd_len,
+                             DMA_DIRECTION_FROM_DEVICE);
+    if (!cmd_fis) {
+        DPRINTF(port, "error: guest passed us an invalid cmd fis\n");
+        return -1;
+    } else if (cmd_len != 0x80) {
+        ahci_trigger_irq(s, &s->dev[port], PORT_IRQ_HBUS_ERR);
+        DPRINTF(port, "error: dma_memory_map failed: "
+                "(len(%02"PRIx64") != 0x80)\n",
+                cmd_len);
         goto out;
     }
-
-    debug_print_fis(cmd_fis, 0x90);
-    //debug_print_fis(cmd_fis, (opts & AHCI_CMD_HDR_CMD_FIS_LEN) * 4);
+    debug_print_fis(cmd_fis, 0x80);
 
     switch (cmd_fis[0]) {
         case SATA_FIS_TYPE_REGISTER_H2D:
+            handle_reg_h2d_fis(s, port, slot, cmd_fis);
             break;
         default:
             DPRINTF(port, "unknown command cmd_fis[0]=%02x cmd_fis[1]=%02x "
                           "cmd_fis[2]=%02x\n", cmd_fis[0], cmd_fis[1],
                           cmd_fis[2]);
-            goto out;
             break;
     }
 
-    switch (cmd_fis[1]) {
-        case SATA_FIS_REG_H2D_UPDATE_COMMAND_REGISTER:
-            break;
-        case 0:
-            break;
-        default:
-            DPRINTF(port, "unknown command cmd_fis[0]=%02x cmd_fis[1]=%02x "
-                          "cmd_fis[2]=%02x\n", cmd_fis[0], cmd_fis[1],
-                          cmd_fis[2]);
-            goto out;
-            break;
-    }
-
-    switch (s->dev[port].port_state) {
-        case STATE_RUN:
-            if (cmd_fis[15] & ATA_SRST) {
-                s->dev[port].port_state = STATE_RESET;
-            }
-            break;
-        case STATE_RESET:
-            if (!(cmd_fis[15] & ATA_SRST)) {
-                ahci_reset_port(s, port);
-            }
-            break;
-    }
-
-    if (cmd_fis[1] == SATA_FIS_REG_H2D_UPDATE_COMMAND_REGISTER) {
-
-        /* Check for NCQ command */
-        if ((cmd_fis[2] == READ_FPDMA_QUEUED) ||
-            (cmd_fis[2] == WRITE_FPDMA_QUEUED)) {
-            process_ncq_command(s, port, cmd_fis, slot);
-            goto out;
-        }
-
-        /* Decompose the FIS  */
-        ide_state->nsector = (int64_t)((cmd_fis[13] << 8) | cmd_fis[12]);
-        ide_state->feature = cmd_fis[3];
-        if (!ide_state->nsector) {
-            ide_state->nsector = 256;
-        }
-
-        if (ide_state->drive_kind != IDE_CD) {
-            /*
-             * We set the sector depending on the sector defined in the FIS.
-             * Unfortunately, the spec isn't exactly obvious on this one.
-             *
-             * Apparently LBA48 commands set fis bytes 10,9,8,6,5,4 to the
-             * 48 bit sector number. ATA_CMD_READ_DMA_EXT is an example for
-             * such a command.
-             *
-             * Non-LBA48 commands however use 7[lower 4 bits],6,5,4 to define a
-             * 28-bit sector number. ATA_CMD_READ_DMA is an example for such
-             * a command.
-             *
-             * Since the spec doesn't explicitly state what each field should
-             * do, I simply assume non-used fields as reserved and OR everything
-             * together, independent of the command.
-             */
-            ide_set_sector(ide_state, ((uint64_t)cmd_fis[10] << 40)
-                                    | ((uint64_t)cmd_fis[9] << 32)
-                                    /* This is used for LBA48 commands */
-                                    | ((uint64_t)cmd_fis[8] << 24)
-                                    /* This is used for non-LBA48 commands */
-                                    | ((uint64_t)(cmd_fis[7] & 0xf) << 24)
-                                    | ((uint64_t)cmd_fis[6] << 16)
-                                    | ((uint64_t)cmd_fis[5] << 8)
-                                    | cmd_fis[4]);
-        }
-
-        /* Copy the ACMD field (ATAPI packet, if any) from the AHCI command
-         * table to ide_state->io_buffer
-         */
-        if (opts & AHCI_CMD_ATAPI) {
-            memcpy(ide_state->io_buffer, &cmd_fis[AHCI_COMMAND_TABLE_ACMD], 0x10);
-            ide_state->lcyl = 0x14;
-            ide_state->hcyl = 0xeb;
-            debug_print_fis(ide_state->io_buffer, 0x10);
-            ide_state->feature = IDE_FEATURE_DMA;
-            s->dev[port].done_atapi_packet = false;
-            /* XXX send PIO setup FIS */
-        }
-
-        ide_state->error = 0;
-
-        /* Reset transferred byte counter */
-        cmd->status = 0;
-
-        /* We're ready to process the command in FIS byte 2. */
-        ide_exec_cmd(&s->dev[port].port, cmd_fis[2]);
-    }
-
 out:
     dma_memory_unmap(s->as, cmd_fis, cmd_len, DMA_DIRECTION_FROM_DEVICE,
                      cmd_len);
@@ -1089,10 +1116,11 @@ static void ahci_start_transfer(IDEDMA *dma)
     if (is_atapi && !ad->done_atapi_packet) {
         /* already prepopulated iobuffer */
         ad->done_atapi_packet = true;
+        size = 0;
         goto out;
     }
 
-    if (!ahci_populate_sglist(ad, &s->sg, 0)) {
+    if (ahci_dma_prepare_buf(dma, is_write)) {
         has_sglist = 1;
     }
 
@@ -1139,16 +1167,19 @@ static void ahci_start_dma(IDEDMA *dma, IDEState *s,
  * Not currently invoked by PIO R/W chains,
  * which invoke ahci_populate_sglist via ahci_start_transfer.
  */
-static int ahci_dma_prepare_buf(IDEDMA *dma, int is_write)
+static int32_t ahci_dma_prepare_buf(IDEDMA *dma, int is_write)
 {
     AHCIDevice *ad = DO_UPCAST(AHCIDevice, dma, dma);
     IDEState *s = &ad->port.ifs[0];
 
-    ahci_populate_sglist(ad, &s->sg, 0);
+    if (ahci_populate_sglist(ad, &s->sg, s->io_buffer_offset) == -1) {
+        DPRINTF(ad->port_no, "ahci_dma_prepare_buf failed.\n");
+        return -1;
+    }
     s->io_buffer_size = s->sg.size;
 
     DPRINTF(ad->port_no, "len=%#x\n", s->io_buffer_size);
-    return s->io_buffer_size != 0;
+    return s->io_buffer_size;
 }
 
 /**

hw/ide/ahci.h

@@ -186,6 +186,9 @@
 
 #define READ_FPDMA_QUEUED                  0x60
 #define WRITE_FPDMA_QUEUED                 0x61
+#define NCQ_NON_DATA                       0x63
+#define RECEIVE_FPDMA_QUEUED               0x65
+#define SEND_FPDMA_QUEUED                  0x64
 
 #define RES_FIS_DSFIS                      0x00
 #define RES_FIS_PSFIS                      0x20

hw/ide/core.c

@@ -592,6 +592,7 @@ static void ide_sector_read_cb(void *opaque, int ret)
 
     ide_set_sector(s, ide_get_sector(s) + n);
     s->nsector -= n;
+    s->io_buffer_offset += 512 * n;
 }
 
 void ide_sector_read(IDEState *s)
@@ -730,10 +731,11 @@ void ide_dma_cb(void *opaque, int ret)
     n = s->nsector;
     s->io_buffer_index = 0;
     s->io_buffer_size = n * 512;
-    if (s->bus->dma->ops->prepare_buf(s->bus->dma, ide_cmd_is_read(s)) == 0) {
+    if (s->bus->dma->ops->prepare_buf(s->bus->dma, ide_cmd_is_read(s)) < 512) {
         /* The PRDs were too short. Reset the Active bit, but don't raise an
          * interrupt. */
         s->status = READY_STAT | SEEK_STAT;
+        dma_buf_commit(s, 0);
         goto eot;
     }
 
@@ -832,6 +834,8 @@ static void ide_sector_write_cb(void *opaque, int ret)
         n = s->req_nb_sectors;
     }
     s->nsector -= n;
+    s->io_buffer_offset += 512 * n;
+
     if (s->nsector == 0) {
         /* no more sectors to write */
         ide_transfer_stop(s);
@@ -1824,6 +1828,7 @@ void ide_exec_cmd(IDEBus *bus, uint32_t val)
 
     s->status = READY_STAT | BUSY_STAT;
     s->error = 0;
+    s->io_buffer_offset = 0;
 
     complete = ide_cmd_table[val].handler(s, val);
     if (complete) {
@@ -2309,12 +2314,17 @@ static int ide_nop_int(IDEDMA *dma, int x)
     return 0;
 }
 
+static int32_t ide_nop_int32(IDEDMA *dma, int x)
+{
+    return 0;
+}
+
 static void ide_nop_restart(void *opaque, int x, RunState y)
 {
 }
 
 static const IDEDMAOps ide_dma_nop_ops = {
-    .prepare_buf    = ide_nop_int,
+    .prepare_buf    = ide_nop_int32,
     .rw_buf         = ide_nop_int,
     .set_unit       = ide_nop_int,
     .restart_cb     = ide_nop_restart,
@@ -2391,7 +2401,7 @@ static int ide_drive_post_load(void *opaque, int version_id)
 {
     IDEState *s = opaque;
 
-    if (s->identify_set) {
+    if (s->blk && s->identify_set) {
         blk_set_enable_write_cache(s->blk, !!(s->identify_data[85] & (1 << 5)));
     }
     return 0;

hw/ide/internal.h

@@ -322,6 +322,7 @@ typedef void EndTransferFunc(IDEState *);
 typedef void DMAStartFunc(IDEDMA *, IDEState *, BlockCompletionFunc *);
 typedef void DMAVoidFunc(IDEDMA *);
 typedef int DMAIntFunc(IDEDMA *, int);
+typedef int32_t DMAInt32Func(IDEDMA *, int);
 typedef void DMAu32Func(IDEDMA *, uint32_t);
 typedef void DMAStopFunc(IDEDMA *, bool);
 typedef void DMARestartFunc(void *, int, RunState);
@@ -385,7 +386,7 @@ struct IDEState {
     uint8_t cdrom_changed;
     int packet_transfer_size;
     int elementary_transfer_size;
-    int io_buffer_index;
+    int32_t io_buffer_index;
     int lba;
     int cd_sector_size;
     int atapi_dma; /* true if dma is requested for the packet cmd */
@@ -394,8 +395,8 @@ struct IDEState {
     struct iovec iov;
     QEMUIOVector qiov;
     /* ATA DMA state */
-    int io_buffer_offset;
-    int io_buffer_size;
+    int32_t io_buffer_offset;
+    int32_t io_buffer_size;
     QEMUSGList sg;
     /* PIO transfer handling */
     int req_nb_sectors; /* number of sectors per interrupt */
@@ -405,8 +406,8 @@ struct IDEState {
     uint8_t *io_buffer;
     /* PIO save/restore */
     int32_t io_buffer_total_len;
-    int cur_io_buffer_offset;
-    int cur_io_buffer_len;
+    int32_t cur_io_buffer_offset;
+    int32_t cur_io_buffer_len;
     uint8_t end_transfer_fn_idx;
     QEMUTimer *sector_write_timer; /* only used for win2k install hack */
     uint32_t irq_count; /* counts IRQs when using win2k install hack */
@@ -430,7 +431,7 @@ struct IDEState {
 struct IDEDMAOps {
     DMAStartFunc *start_dma;
     DMAVoidFunc *start_transfer;
-    DMAIntFunc *prepare_buf;
+    DMAInt32Func *prepare_buf;
     DMAu32Func *commit_buf;
     DMAIntFunc *rw_buf;
     DMAIntFunc *set_unit;

hw/ide/macio.c

@@ -553,6 +553,11 @@ static int ide_nop_int(IDEDMA *dma, int x)
     return 0;
 }
 
+static int32_t ide_nop_int32(IDEDMA *dma, int x)
+{
+    return 0;
+}
+
 static void ide_nop_restart(void *opaque, int x, RunState y)
 {
 }
@@ -569,7 +574,7 @@ static void ide_dbdma_start(IDEDMA *dma, IDEState *s,
 
 static const IDEDMAOps dbdma_ops = {
     .start_dma      = ide_dbdma_start,
-    .prepare_buf    = ide_nop_int,
+    .prepare_buf    = ide_nop_int32,
     .rw_buf         = ide_nop_int,
     .set_unit       = ide_nop_int,
     .restart_cb     = ide_nop_restart,

hw/ide/pci.c

@@ -28,7 +28,7 @@
 #include <hw/isa/isa.h>
 #include "sysemu/block-backend.h"
 #include "sysemu/dma.h"
-
+#include "qemu/error-report.h"
 #include <hw/ide/pci.h>
 
 #define BMDMA_PAGE_SIZE 4096
@@ -55,8 +55,11 @@ static void bmdma_start_dma(IDEDMA *dma, IDEState *s,
     }
 }
 
-/* return 0 if buffer completed */
-static int bmdma_prepare_buf(IDEDMA *dma, int is_write)
+/**
+ * Return the number of bytes successfully prepared.
+ * -1 on error.
+ */
+static int32_t bmdma_prepare_buf(IDEDMA *dma, int is_write)
 {
     BMDMAState *bm = DO_UPCAST(BMDMAState, dma, dma);
     IDEState *s = bmdma_active_if(bm);
@@ -74,8 +77,9 @@ static int bmdma_prepare_buf(IDEDMA *dma, int is_write)
         if (bm->cur_prd_len == 0) {
             /* end of table (with a fail safe of one page) */
             if (bm->cur_prd_last ||
-                (bm->cur_addr - bm->addr) >= BMDMA_PAGE_SIZE)
-                return s->io_buffer_size != 0;
+                (bm->cur_addr - bm->addr) >= BMDMA_PAGE_SIZE) {
+                return s->io_buffer_size;
+            }
             pci_dma_read(pci_dev, bm->cur_addr, &prd, 8);
             bm->cur_addr += 8;
             prd.addr = le32_to_cpu(prd.addr);
@@ -90,12 +94,23 @@ static int bmdma_prepare_buf(IDEDMA *dma, int is_write)
         l = bm->cur_prd_len;
         if (l > 0) {
             qemu_sglist_add(&s->sg, bm->cur_prd_addr, l);
+
+            /* Note: We limit the max transfer to be 2GiB.
+             * This should accommodate the largest ATA transaction
+             * for LBA48 (65,536 sectors) and 32K sector sizes. */
+            if (s->sg.size > INT32_MAX) {
+                error_report("IDE: sglist describes more than 2GiB.\n");
+                break;
+            }
             bm->cur_prd_addr += l;
             bm->cur_prd_len -= l;
             s->io_buffer_size += l;
         }
     }
-    return 1;
+
+    qemu_sglist_destroy(&s->sg);
+    s->io_buffer_size = 0;
+    return -1;
 }
 
 /* return 0 if buffer completed */

hw/intc/apic.c

@@ -188,7 +188,7 @@ void apic_deliver_pic_intr(DeviceState *dev, int level)
             apic_reset_bit(s->irr, lvt & 0xff);
             /* fall through */
         case APIC_DM_EXTINT:
-            cpu_reset_interrupt(CPU(s->cpu), CPU_INTERRUPT_HARD);
+            apic_update_irq(s);
             break;
         }
     }
@@ -349,6 +349,11 @@ static int apic_get_arb_pri(APICCommonState *s)
 static int apic_irq_pending(APICCommonState *s)
 {
     int irrv, ppr;
+
+    if (!(s->spurious_vec & APIC_SV_ENABLE)) {
+        return 0;
+    }
+
     irrv = get_highest_priority_int(s->irr);
     if (irrv < 0) {
         return 0;
@@ -366,14 +371,13 @@ static void apic_update_irq(APICCommonState *s)
 {
     CPUState *cpu;
 
-    if (!(s->spurious_vec & APIC_SV_ENABLE)) {
-        return;
-    }
     cpu = CPU(s->cpu);
     if (!qemu_cpu_is_self(cpu)) {
         cpu_interrupt(cpu, CPU_INTERRUPT_POLL);
     } else if (apic_irq_pending(s) > 0) {
         cpu_interrupt(cpu, CPU_INTERRUPT_HARD);
+    } else if (!apic_accept_pic_intr(&s->busdev.qdev) || !pic_get_output(isa_pic)) {
+        cpu_reset_interrupt(cpu, CPU_INTERRUPT_HARD);
     }
 }
 
@@ -567,7 +571,10 @@ int apic_get_interrupt(DeviceState *dev)
     apic_sync_vapic(s, SYNC_FROM_VAPIC);
     intno = apic_irq_pending(s);
 
-    if (intno == 0) {
+    /* if there is an interrupt from the 8259, let the caller handle
+     * that first since ExtINT interrupts ignore the priority.
+     */
+    if (intno == 0 || apic_check_pic(s)) {
         apic_sync_vapic(s, SYNC_TO_VAPIC);
         return -1;
     } else if (intno < 0) {
@@ -578,9 +585,6 @@ int apic_get_interrupt(DeviceState *dev)
     apic_set_bit(s->isr, intno);
     apic_sync_vapic(s, SYNC_TO_VAPIC);
 
-    /* re-inject if there is still a pending PIC interrupt */
-    apic_check_pic(s);
-
     apic_update_irq(s);
 
     return intno;

hw/intc/apic_common.c

@@ -324,6 +324,19 @@ static void apic_common_realize(DeviceState *dev, Error **errp)
 
 }
 
+static int apic_pre_load(void *opaque)
+{
+    APICCommonState *s = APIC_COMMON(opaque);
+
+    /* The default is !cpu_is_bsp(s->cpu), but the common value is 0
+     * so that's what apic_common_sipi_needed checks for.  Reset to
+     * the value that is assumed when the apic_sipi subsection is
+     * absent.
+     */
+    s->wait_for_sipi = 0;
+    return 0;
+}
+
 static void apic_dispatch_pre_save(void *opaque)
 {
     APICCommonState *s = APIC_COMMON(opaque);
@@ -345,12 +358,30 @@ static int apic_dispatch_post_load(void *opaque, int version_id)
     return 0;
 }
 
+static bool apic_common_sipi_needed(void *opaque)
+{
+    APICCommonState *s = APIC_COMMON(opaque);
+    return s->wait_for_sipi != 0;
+}
+
+static const VMStateDescription vmstate_apic_common_sipi = {
+    .name = "apic_sipi",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32(sipi_vector, APICCommonState),
+        VMSTATE_INT32(wait_for_sipi, APICCommonState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static const VMStateDescription vmstate_apic_common = {
     .name = "apic",
     .version_id = 3,
     .minimum_version_id = 3,
     .minimum_version_id_old = 1,
     .load_state_old = apic_load_old,
+    .pre_load = apic_pre_load,
     .pre_save = apic_dispatch_pre_save,
     .post_load = apic_dispatch_post_load,
     .fields = (VMStateField[]) {
@@ -375,6 +406,13 @@ static const VMStateDescription vmstate_apic_common = {
         VMSTATE_INT64(timer_expiry,
                       APICCommonState), /* open-coded timer state */
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (VMStateSubsection[]) {
+        {
+            .vmsd = &vmstate_apic_common_sipi,
+            .needed = apic_common_sipi_needed,
+        },
+        VMSTATE_END_OF_LIST()
     }
 };
 

hw/mem/pc-dimm.c

@@ -139,19 +139,34 @@ static int pc_dimm_built_list(Object *obj, void *opaque)
 
 uint64_t pc_dimm_get_free_addr(uint64_t address_space_start,
                                uint64_t address_space_size,
-                               uint64_t *hint, uint64_t size,
+                               uint64_t *hint, uint64_t align, uint64_t size,
                                Error **errp)
 {
     GSList *list = NULL, *item;
     uint64_t new_addr, ret = 0;
     uint64_t address_space_end = address_space_start + address_space_size;
 
+    g_assert(QEMU_ALIGN_UP(address_space_start, align) == address_space_start);
+    g_assert(QEMU_ALIGN_UP(address_space_size, align) == address_space_size);
+
     if (!address_space_size) {
         error_setg(errp, "memory hotplug is not enabled, "
                          "please add maxmem option");
         goto out;
     }
 
+    if (hint && QEMU_ALIGN_UP(*hint, align) != *hint) {
+        error_setg(errp, "address must be aligned to 0x%" PRIx64 " bytes",
+                   align);
+        goto out;
+    }
+
+    if (QEMU_ALIGN_UP(size, align) != size) {
+        error_setg(errp, "backend memory size must be multiple of 0x%"
+                   PRIx64, align);
+        goto out;
+    }
+
     assert(address_space_end > address_space_start);
     object_child_foreach(qdev_get_machine(), pc_dimm_built_list, &list);
 
@@ -177,7 +192,7 @@ uint64_t pc_dimm_get_free_addr(uint64_t address_space_start,
                 error_setg(errp, "address range conflicts with '%s'", d->id);
                 goto out;
             }
-            new_addr = dimm->addr + dimm_size;
+            new_addr = QEMU_ALIGN_UP(dimm->addr + dimm_size, align);
         }
     }
     ret = new_addr;

hw/mips/mips_mipssim.c

@@ -197,7 +197,7 @@ mips_mipssim_init(MachineState *machine)
         !kernel_filename && !qtest_enabled()) {
         /* Bail out if we have neither a kernel image nor boot vector code. */
         error_report("Could not load MIPS bios '%s', and no "
-                     "-kernel argument was specified", filename);
+                     "-kernel argument was specified", bios_name);
         exit(1);
     } else {
         /* We have a boot vector start address. */

hw/net/pcnet.c

@@ -1212,7 +1212,7 @@ static void pcnet_transmit(PCNetState *s)
     hwaddr xmit_cxda = 0;
     int count = CSR_XMTRL(s)-1;
     int add_crc = 0;
-
+    int bcnt;
     s->xmit_pos = -1;
 
     if (!CSR_TXON(s)) {
@@ -1247,35 +1247,40 @@ static void pcnet_transmit(PCNetState *s)
             s->xmit_pos = -1;
             goto txdone;
         }
-        if (!GET_FIELD(tmd.status, TMDS, ENP)) {
-            int bcnt = 4096 - GET_FIELD(tmd.length, TMDL, BCNT);
-            s->phys_mem_read(s->dma_opaque, PHYSADDR(s, tmd.tbadr),
-                             s->buffer + s->xmit_pos, bcnt, CSR_BSWP(s));
-            s->xmit_pos += bcnt;
-        } else if (s->xmit_pos >= 0) {
-            int bcnt = 4096 - GET_FIELD(tmd.length, TMDL, BCNT);
-            s->phys_mem_read(s->dma_opaque, PHYSADDR(s, tmd.tbadr),
-                             s->buffer + s->xmit_pos, bcnt, CSR_BSWP(s));
-            s->xmit_pos += bcnt;
-#ifdef PCNET_DEBUG
-            printf("pcnet_transmit size=%d\n", s->xmit_pos);
-#endif
-            if (CSR_LOOP(s)) {
-                if (BCR_SWSTYLE(s) == 1)
-                    add_crc = !GET_FIELD(tmd.status, TMDS, NOFCS);
-                s->looptest = add_crc ? PCNET_LOOPTEST_CRC : PCNET_LOOPTEST_NOCRC;
-                pcnet_receive(qemu_get_queue(s->nic), s->buffer, s->xmit_pos);
-                s->looptest = 0;
-            } else
-                if (s->nic)
-                    qemu_send_packet(qemu_get_queue(s->nic), s->buffer,
-                                     s->xmit_pos);
 
-            s->csr[0] &= ~0x0008;   /* clear TDMD */
-            s->csr[4] |= 0x0004;    /* set TXSTRT */
-            s->xmit_pos = -1;
+        if (s->xmit_pos < 0) {
+            goto txdone;
         }
 
+        bcnt = 4096 - GET_FIELD(tmd.length, TMDL, BCNT);
+        s->phys_mem_read(s->dma_opaque, PHYSADDR(s, tmd.tbadr),
+                         s->buffer + s->xmit_pos, bcnt, CSR_BSWP(s));
+        s->xmit_pos += bcnt;
+        
+        if (!GET_FIELD(tmd.status, TMDS, ENP)) {
+            goto txdone;
+        }
+
+#ifdef PCNET_DEBUG
+        printf("pcnet_transmit size=%d\n", s->xmit_pos);
+#endif
+        if (CSR_LOOP(s)) {
+            if (BCR_SWSTYLE(s) == 1)
+                add_crc = !GET_FIELD(tmd.status, TMDS, NOFCS);
+            s->looptest = add_crc ? PCNET_LOOPTEST_CRC : PCNET_LOOPTEST_NOCRC;
+            pcnet_receive(qemu_get_queue(s->nic), s->buffer, s->xmit_pos);
+            s->looptest = 0;
+        } else {
+            if (s->nic) {
+                qemu_send_packet(qemu_get_queue(s->nic), s->buffer,
+                                 s->xmit_pos);
+            }
+        }
+
+        s->csr[0] &= ~0x0008;   /* clear TDMD */
+        s->csr[4] |= 0x0004;    /* set TXSTRT */
+        s->xmit_pos = -1;
+
     txdone:
         SET_FIELD(&tmd.status, TMDS, OWN, 0);
         TMDSTORE(&tmd, PHYSADDR(s,CSR_CXDA(s)));

hw/net/rtl8139.c

@@ -1775,6 +1775,7 @@ static void rtl8139_transfer_frame(RTL8139State *s, uint8_t *buf, int size,
     int do_interrupt, const uint8_t *dot1q_buf)
 {
     struct iovec *iov = NULL;
+    struct iovec vlan_iov[3];
 
     if (!size)
     {
@@ -1789,6 +1790,9 @@ static void rtl8139_transfer_frame(RTL8139State *s, uint8_t *buf, int size,
             { .iov_base = buf + ETHER_ADDR_LEN * 2,
                 .iov_len = size - ETHER_ADDR_LEN * 2 },
         };
+
+        memcpy(vlan_iov, iov, sizeof(vlan_iov));
+        iov = vlan_iov;
     }
 
     if (TxLoopBack == (s->TxConfig & TxLoopBack))

hw/net/virtio-net.c

@@ -798,7 +798,7 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
     virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
     VirtQueueElement elem;
     size_t s;
-    struct iovec *iov;
+    struct iovec *iov, *iov2;
     unsigned int iov_cnt;
 
     while (virtqueue_pop(vq, &elem)) {
@@ -808,8 +808,8 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
             exit(1);
         }
 
-        iov = elem.out_sg;
         iov_cnt = elem.out_num;
+        iov2 = iov = g_memdup(elem.out_sg, sizeof(struct iovec) * elem.out_num);
         s = iov_to_buf(iov, iov_cnt, 0, &ctrl, sizeof(ctrl));
         iov_discard_front(&iov, &iov_cnt, sizeof(ctrl));
         if (s != sizeof(ctrl)) {
@@ -833,6 +833,7 @@ static void virtio_net_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
 
         virtqueue_push(vq, &elem, sizeof(status));
         virtio_notify(vdev, vq);
+        g_free(iov2);
     }
 }
 

hw/nvram/fw_cfg.c

@@ -523,6 +523,7 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
                         void *data, size_t len)
 {
     int i, index;
+    void *ptr = NULL;
 
     assert(s->files);
 
@@ -531,8 +532,10 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
 
     for (i = 0; i < index; i++) {
         if (strcmp(filename, s->files->f[i].name) == 0) {
-            return fw_cfg_modify_bytes_read(s, FW_CFG_FILE_FIRST + i,
-                                     data, len);
+            ptr = fw_cfg_modify_bytes_read(s, FW_CFG_FILE_FIRST + i,
+                                           data, len);
+            s->files->f[i].size   = cpu_to_be32(len);
+            return ptr;
         }
     }
     /* add new one */

hw/pci/pcie.c

@@ -145,7 +145,7 @@ void pcie_cap_deverr_init(PCIDevice *dev)
                                PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE);
     pci_long_test_and_set_mask(dev->w1cmask + pos + PCI_EXP_DEVSTA,
                                PCI_EXP_DEVSTA_CED | PCI_EXP_DEVSTA_NFED |
-                               PCI_EXP_DEVSTA_URD | PCI_EXP_DEVSTA_URD);
+                               PCI_EXP_DEVSTA_FED | PCI_EXP_DEVSTA_URD);
 }
 
 void pcie_cap_deverr_reset(PCIDevice *dev)
@@ -229,7 +229,7 @@ static void pcie_cap_slot_hotplug_common(PCIDevice *hotplug_dev,
         /* the slot is electromechanically locked.
          * This error is propagated up to qdev and then to HMP/QMP.
          */
-        error_setg_errno(errp, -EBUSY, "slot is electromechanically locked");
+        error_setg_errno(errp, EBUSY, "slot is electromechanically locked");
     }
 }
 

hw/pci/shpc.c

@@ -559,8 +559,9 @@ void shpc_device_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
     uint8_t led;
     int slot;
 
-    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, errp);
+    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
     if (local_err) {
+        error_propagate(errp, local_err);
         return;
     }
 
@@ -662,6 +663,7 @@ void shpc_cleanup(PCIDevice *d, MemoryRegion *bar)
     SHPCDevice *shpc = d->shpc;
     d->cap_present &= ~QEMU_PCI_CAP_SHPC;
     memory_region_del_subregion(bar, &shpc->mmio);
+    object_unparent(OBJECT(&shpc->mmio));
     /* TODO: cleanup config space changes? */
     g_free(shpc->config);
     g_free(shpc->cmask);

hw/scsi/esp-pci.c

@@ -268,6 +268,9 @@ static void esp_pci_dma_memory_rw(PCIESPState *pci, uint8_t *buf, int len,
     /* update status registers */
     pci->dma_regs[DMA_WBC] -= len;
     pci->dma_regs[DMA_WAC] += len;
+    if (pci->dma_regs[DMA_WBC] == 0) {
+        pci->dma_regs[DMA_STAT] |= DMA_STAT_DONE;
+    }
 }
 
 static void esp_pci_dma_memory_read(void *opaque, uint8_t *buf, int len)

hw/scsi/esp.c

@@ -364,7 +364,7 @@ void esp_hard_reset(ESPState *s)
 {
     memset(s->rregs, 0, ESP_REGS);
     memset(s->wregs, 0, ESP_REGS);
-    s->rregs[ESP_TCHI] = s->chip_id;
+    s->tchi_written = 0;
     s->ti_size = 0;
     s->ti_rptr = 0;
     s->ti_wptr = 0;
@@ -422,6 +422,11 @@ uint64_t esp_reg_read(ESPState *s, uint32_t saddr)
         esp_lower_irq(s);
 
         return old_val;
+    case ESP_TCHI:
+        /* Return the unique id if the value has never been written */
+        if (!s->tchi_written) {
+            return s->chip_id;
+        }
     default:
         break;
     }
@@ -432,9 +437,11 @@ void esp_reg_write(ESPState *s, uint32_t saddr, uint64_t val)
 {
     trace_esp_mem_writeb(saddr, s->wregs[saddr], val);
     switch (saddr) {
+    case ESP_TCHI:
+        s->tchi_written = true;
+        /* fall through */
     case ESP_TCLO:
     case ESP_TCMID:
-    case ESP_TCHI:
         s->rregs[ESP_RSTAT] &= ~STAT_TC;
         break;
     case ESP_FIFO:

hw/scsi/vhost-scsi.c

@@ -233,6 +233,7 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp)
                                vhost_dummy_handle_output);
     if (err != NULL) {
         error_propagate(errp, err);
+        close(vhostfd);
         return;
     }
 

hw/scsi/virtio-scsi-dataplane.c

@@ -92,9 +92,14 @@ VirtIOSCSIReq *virtio_scsi_pop_req_vring(VirtIOSCSI *s,
 
 void virtio_scsi_vring_push_notify(VirtIOSCSIReq *req)
 {
+    VirtIODevice *vdev = VIRTIO_DEVICE(req->vring->parent);
+
     vring_push(&req->vring->vring, &req->elem,
                req->qsgl.size + req->resp_iov.size);
-    event_notifier_set(&req->vring->guest_notifier);
+
+    if (vring_should_notify(vdev, &req->vring->vring)) {
+        event_notifier_set(&req->vring->guest_notifier);
+    }
 }
 
 static void virtio_scsi_iothread_handle_ctrl(EventNotifier *notifier)
@@ -230,7 +235,7 @@ void virtio_scsi_dataplane_start(VirtIOSCSI *s)
     if (!s->event_vring) {
         goto fail_vrings;
     }
-    s->cmd_vrings = g_malloc0(sizeof(VirtIOSCSIVring) * vs->conf.num_queues);
+    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],

hw/scsi/virtio-scsi.c

@@ -118,6 +118,7 @@ static size_t qemu_sgl_concat(VirtIOSCSIReq *req, struct iovec *iov,
 static int virtio_scsi_parse_req(VirtIOSCSIReq *req,
                                  unsigned req_size, unsigned resp_size)
 {
+    VirtIODevice *vdev = (VirtIODevice *) req->dev;
     size_t in_size, out_size;
 
     if (iov_to_buf(req->elem.out_sg, req->elem.out_num, 0,
@@ -130,8 +131,24 @@ static int virtio_scsi_parse_req(VirtIOSCSIReq *req,
                               resp_size) < resp_size) {
         return -EINVAL;
     }
+
     req->resp_size = resp_size;
 
+    /* Old BIOSes left some padding by mistake after the req_size/resp_size.
+     * As a workaround, always consider the first buffer as the virtio-scsi
+     * request/response, making the payload start at the second element
+     * of the iovec.
+     *
+     * The actual length of the response header, stored in req->resp_size,
+     * does not change.
+     *
+     * TODO: always disable this workaround for virtio 1.0 devices.
+     */
+    if ((vdev->guest_features & VIRTIO_F_ANY_LAYOUT) == 0) {
+        req_size = req->elem.out_sg[0].iov_len;
+        resp_size = req->elem.in_sg[0].iov_len;
+    }
+
     out_size = qemu_sgl_concat(req, req->elem.out_sg,
                                &req->elem.out_addr[0], req->elem.out_num,
                                req_size);

hw/usb/hcd-musb.c

@@ -608,6 +608,7 @@ static void musb_packet(MUSBState *s, MUSBEndPoint *ep,
     USBDevice *dev;
     USBEndpoint *uep;
     int idx = epnum && dir;
+    int id;
     int ttype;
 
     /* ep->type[0,1] contains:
@@ -625,8 +626,11 @@ static void musb_packet(MUSBState *s, MUSBEndPoint *ep,
     /* A wild guess on the FADDR semantics... */
     dev = usb_find_device(&s->port, ep->faddr[idx]);
     uep = usb_ep_get(dev, pid, ep->type[idx] & 0xf);
-    usb_packet_setup(&ep->packey[dir].p, pid, uep, 0,
-                     (dev->addr << 16) | (uep->nr << 8) | pid, false, true);
+    id = pid;
+    if (uep) {
+        id |= (dev->addr << 16) | (uep->nr << 8);
+    }
+    usb_packet_setup(&ep->packey[dir].p, pid, uep, 0, id, false, true);
     usb_packet_addbuf(&ep->packey[dir].p, ep->buf[idx], len);
     ep->packey[dir].ep = ep;
     ep->packey[dir].dir = dir;

hw/usb/hcd-xhci.c

@@ -2262,6 +2262,9 @@ static USBPort *xhci_lookup_uport(XHCIState *xhci, uint32_t *slot_ctx)
     int i, pos, port;
 
     port = (slot_ctx[1]>>16) & 0xFF;
+    if (port < 1 || port > xhci->numports) {
+        return NULL;
+    }
     port = xhci->ports[port-1].uport->index+1;
     pos = snprintf(path, sizeof(path), "%d", port);
     for (i = 0; i < 5; i++) {
@@ -3706,6 +3709,12 @@ static int usb_xhci_post_load(void *opaque, int version_id)
             xhci_mask64(ldq_le_pci_dma(pci_dev, dcbaap + 8 * slotid));
         xhci_dma_read_u32s(xhci, slot->ctx, slot_ctx, sizeof(slot_ctx));
         slot->uport = xhci_lookup_uport(xhci, slot_ctx);
+        if (!slot->uport) {
+            /* should not happen, but may trigger on guest bugs */
+            slot->enabled = 0;
+            slot->addressed = 0;
+            continue;
+        }
         assert(slot->uport && slot->uport->dev);
 
         for (epid = 1; epid <= 31; epid++) {

hw/usb/host-libusb.c

@@ -143,6 +143,12 @@ static void usb_host_attach_kernel(USBHostDevice *s);
 
 /* ------------------------------------------------------------------------ */
 
+#ifndef LIBUSB_LOG_LEVEL_WARNING /* older libusb didn't define these */
+#define LIBUSB_LOG_LEVEL_WARNING 2
+#endif
+
+/* ------------------------------------------------------------------------ */
+
 #define CONTROL_TIMEOUT  10000        /* 10 sec    */
 #define BULK_TIMEOUT         0        /* unlimited */
 #define INTR_TIMEOUT         0        /* unlimited */
@@ -743,13 +749,13 @@ static void usb_host_speed_compat(USBHostDevice *s)
 
     udev->speedmask = (1 << udev->speed);
     if (udev->speed == USB_SPEED_SUPER && compat_high) {
-        udev->speedmask |= USB_SPEED_HIGH;
+        udev->speedmask |= USB_SPEED_MASK_HIGH;
     }
     if (udev->speed == USB_SPEED_SUPER && compat_full) {
-        udev->speedmask |= USB_SPEED_FULL;
+        udev->speedmask |= USB_SPEED_MASK_FULL;
     }
     if (udev->speed == USB_SPEED_HIGH && compat_full) {
-        udev->speedmask |= USB_SPEED_FULL;
+        udev->speedmask |= USB_SPEED_MASK_FULL;
     }
 }
 

hw/virtio/vhost.c

@@ -817,10 +817,12 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
     int i, r;
 
     if (vhost_set_backend_type(hdev, backend_type) < 0) {
+        close((uintptr_t)opaque);
         return -1;
     }
 
     if (hdev->vhost_ops->vhost_backend_init(hdev, opaque) < 0) {
+        close((uintptr_t)opaque);
         return -errno;
     }
 

hw/virtio/virtio-rng.c

@@ -113,20 +113,22 @@ static void virtio_rng_save(QEMUFile *f, void *opaque)
 
 static int virtio_rng_load(QEMUFile *f, void *opaque, int version_id)
 {
+    VirtIORNG *vrng = opaque;
+    int ret;
+
     if (version_id != 1) {
         return -EINVAL;
     }
-    return virtio_load(VIRTIO_DEVICE(opaque), f, version_id);
-}
+    ret = virtio_load(VIRTIO_DEVICE(vrng), f, version_id);
+    if (ret != 0) {
+        return ret;
+    }
 
-static int virtio_rng_load_device(VirtIODevice *vdev, QEMUFile *f,
-                                  int version_id)
-{
     /* We may have an element ready but couldn't process it due to a quota
      * limit.  Make sure to try again after live migration when the quota may
      * have been reset.
      */
-    virtio_rng_process(VIRTIO_RNG(vdev));
+    virtio_rng_process(vrng);
 
     return 0;
 }
@@ -231,7 +233,6 @@ static void virtio_rng_class_init(ObjectClass *klass, void *data)
     vdc->realize = virtio_rng_device_realize;
     vdc->unrealize = virtio_rng_device_unrealize;
     vdc->get_features = get_features;
-    vdc->load = virtio_rng_load_device;
 }
 
 static void virtio_rng_initfn(Object *obj)

include/block/block.h

@@ -83,7 +83,9 @@ typedef enum {
 #define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
 #define BDRV_SECTOR_MASK   ~(BDRV_SECTOR_SIZE - 1)
 
-/* BDRV_BLOCK_DATA: data is read from bs->file or another file
+/*
+ * Allocation status flags
+ * BDRV_BLOCK_DATA: data is read from bs->file or another file
  * BDRV_BLOCK_ZERO: sectors read as zero
  * BDRV_BLOCK_OFFSET_VALID: sector stored in bs->file as raw data
  * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this

include/exec/exec-all.h

@@ -333,7 +333,7 @@ extern uintptr_t tci_tb_ptr;
 
 #if !defined(CONFIG_USER_ONLY)
 
-void phys_mem_set_alloc(void *(*alloc)(size_t));
+void phys_mem_set_alloc(void *(*alloc)(size_t, uint64_t *align));
 
 struct MemoryRegion *iotlb_to_region(AddressSpace *as, hwaddr index);
 bool io_mem_read(struct MemoryRegion *mr, hwaddr addr,

include/exec/memory.h

@@ -146,6 +146,7 @@ struct MemoryRegion {
     hwaddr addr;
     void (*destructor)(MemoryRegion *mr);
     ram_addr_t ram_addr;
+    uint64_t align;
     bool subpage;
     bool terminates;
     bool romd_mode;
@@ -838,6 +839,7 @@ void memory_region_add_subregion_overlap(MemoryRegion *mr,
  */
 ram_addr_t memory_region_get_ram_addr(MemoryRegion *mr);
 
+uint64_t memory_region_get_alignment(const MemoryRegion *mr);
 /**
  * memory_region_del_subregion: Remove a subregion.
  *

include/exec/ram_addr.h

@@ -49,6 +49,21 @@ static inline bool cpu_physical_memory_get_dirty(ram_addr_t start,
     return next < end;
 }
 
+static inline bool cpu_physical_memory_get_clean(ram_addr_t start,
+                                                 ram_addr_t length,
+                                                 unsigned client)
+{
+    unsigned long end, page, next;
+
+    assert(client < DIRTY_MEMORY_NUM);
+
+    end = TARGET_PAGE_ALIGN(start + length) >> TARGET_PAGE_BITS;
+    page = start >> TARGET_PAGE_BITS;
+    next = find_next_zero_bit(ram_list.dirty_memory[client], end, page);
+
+    return next < end;
+}
+
 static inline bool cpu_physical_memory_get_dirty_flag(ram_addr_t addr,
                                                       unsigned client)
 {
@@ -64,6 +79,16 @@ static inline bool cpu_physical_memory_is_clean(ram_addr_t addr)
     return !(vga && code && migration);
 }
 
+static inline bool cpu_physical_memory_range_includes_clean(ram_addr_t start,
+                                                            ram_addr_t length)
+{
+    bool vga = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_VGA);
+    bool code = cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_CODE);
+    bool migration =
+        cpu_physical_memory_get_clean(start, length, DIRTY_MEMORY_MIGRATION);
+    return vga || code || migration;
+}
+
 static inline void cpu_physical_memory_set_dirty_flag(ram_addr_t addr,
                                                       unsigned client)
 {

include/hw/i386/pc.h

@@ -24,6 +24,8 @@
  * address space begins.
  * @hotplug_memory: hotplug memory addess space container
  * @acpi_dev: link to ACPI PM device that performs ACPI hotplug handling
+ * @enforce_aligned_dimm: check that DIMM's address/size is aligned by
+ *                        backend's alignment value if provided
  */
 struct PCMachineState {
     /*< private >*/
@@ -37,13 +39,15 @@ struct PCMachineState {
     ISADevice *rtc;
 
     uint64_t max_ram_below_4g;
-    bool vmport;
+    OnOffAuto vmport;
+    bool enforce_aligned_dimm;
 };
 
 #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"
 #define PC_MACHINE_MEMHP_REGION_SIZE "hotplug-memory-region-size"
 #define PC_MACHINE_MAX_RAM_BELOW_4G "max-ram-below-4g"
 #define PC_MACHINE_VMPORT           "vmport"
+#define PC_MACHINE_ENFORCE_ALIGNED_DIMM "enforce-aligned-dimm"
 
 /**
  * PCMachineClass:

include/hw/loader.h

@@ -59,7 +59,7 @@ extern bool rom_file_has_mr;
 int rom_add_file(const char *file, const char *fw_dir,
                  hwaddr addr, int32_t bootindex,
                  bool option_rom);
-void *rom_add_blob(const char *name, const void *blob, size_t len,
+ram_addr_t rom_add_blob(const char *name, const void *blob, size_t len,
                    hwaddr addr, const char *fw_file_name,
                    FWCfgReadCallback fw_callback, void *callback_opaque);
 int rom_add_elf_program(const char *name, void *data, size_t datasize,

include/hw/mem/pc-dimm.h

@@ -72,7 +72,7 @@ typedef struct PCDIMMDeviceClass {
 
 uint64_t pc_dimm_get_free_addr(uint64_t address_space_start,
                                uint64_t address_space_size,
-                               uint64_t *hint, uint64_t size,
+                               uint64_t *hint, uint64_t align, uint64_t size,
                                Error **errp);
 
 int pc_dimm_get_free_slot(const int *hint, int max_slots, Error **errp);

include/hw/qdev-core.h

@@ -365,7 +365,7 @@ extern int qdev_hotplug;
 
 char *qdev_get_dev_path(DeviceState *dev);
 
-int qdev_build_hotpluggable_device_list(Object *obj, void *opaque);
+GSList *qdev_build_hotpluggable_device_list(Object *peripheral);
 
 void qbus_set_hotplug_handler(BusState *bus, DeviceState *handler,
                               Error **errp);

include/hw/scsi/esp.h

@@ -22,6 +22,7 @@ struct ESPState {
     uint8_t wregs[ESP_REGS];
     qemu_irq irq;
     uint8_t chip_id;
+    bool tchi_written;
     int32_t ti_size;
     uint32_t ti_rptr, ti_wptr;
     uint32_t status;

include/hw/sysbus.h

@@ -10,7 +10,7 @@
 #define QDEV_MAX_PIO 32
 
 #define TYPE_SYSTEM_BUS "System"
-#define SYSTEM_BUS(obj) OBJECT_CHECK(IDEBus, (obj), TYPE_IDE_BUS)
+#define SYSTEM_BUS(obj) OBJECT_CHECK(BusState, (obj), TYPE_SYSTEM_BUS)
 
 typedef struct SysBusDevice SysBusDevice;
 

include/hw/virtio/virtio-scsi.h

@@ -209,7 +209,8 @@ typedef struct VirtIOSCSIReq {
     /* Note:
      * - fields before elem are initialized by virtio_scsi_init_req;
      * - elem is uninitialized at the time of allocation.
-     * - fields after elem are zeroed by virtio_scsi_init_req.
+     * - fields after elem (except the ending cdb[]) are zeroed by
+     *   virtio_scsi_init_req.
      * */
 
     VirtQueueElement elem;

include/qemu/osdep.h

@@ -5,6 +5,7 @@
 #include <stdarg.h>
 #include <stddef.h>
 #include <stdbool.h>
+#include <stdint.h>
 #include <sys/types.h>
 #ifdef __OpenBSD__
 #include <sys/signal.h>
@@ -103,7 +104,7 @@ typedef signed int              int_fast16_t;
 int qemu_daemon(int nochdir, int noclose);
 void *qemu_try_memalign(size_t alignment, size_t size);
 void *qemu_memalign(size_t alignment, size_t size);
-void *qemu_anon_ram_alloc(size_t size);
+void *qemu_anon_ram_alloc(size_t size, uint64_t *align);
 void qemu_vfree(void *ptr);
 void qemu_anon_ram_free(void *ptr, size_t size);
 

include/sysemu/kvm.h

@@ -163,6 +163,7 @@ extern KVMState *kvm_state;
 
 /* external API */
 
+bool kvm_has_free_slot(MachineState *ms);
 int kvm_has_sync_mmu(void);
 int kvm_has_vcpu_events(void);
 int kvm_has_robust_singlestep(void);

include/sysemu/sysemu.h

@@ -161,6 +161,7 @@ typedef struct node_info {
 extern NodeInfo numa_info[MAX_NODES];
 void set_numa_nodes(void);
 void set_numa_modes(void);
+void query_numa_node_mem(uint64_t node_mem[]);
 extern QemuOptsList qemu_numa_opts;
 int numa_init_func(QemuOpts *opts, void *opaque);
 

kvm-all.c

@@ -132,7 +132,7 @@ static const KVMCapabilityInfo kvm_required_capabilites[] = {
     KVM_CAP_LAST_INFO
 };
 
-static KVMSlot *kvm_alloc_slot(KVMState *s)
+static KVMSlot *kvm_get_free_slot(KVMState *s)
 {
     int i;
 
@@ -142,6 +142,22 @@ static KVMSlot *kvm_alloc_slot(KVMState *s)
         }
     }
 
+    return NULL;
+}
+
+bool kvm_has_free_slot(MachineState *ms)
+{
+    return kvm_get_free_slot(KVM_STATE(ms->accelerator));
+}
+
+static KVMSlot *kvm_alloc_slot(KVMState *s)
+{
+    KVMSlot *slot = kvm_get_free_slot(s);
+
+    if (slot) {
+        return slot;
+    }
+
     fprintf(stderr, "%s: no free slot available\n", __func__);
     abort();
 }
@@ -634,8 +650,10 @@ static void kvm_set_phys_mem(MemoryRegionSection *section, bool add)
     unsigned delta;
 
     /* kvm works in page size chunks, but the function may be called
-       with sub-page size and unaligned start address. */
-    delta = TARGET_PAGE_ALIGN(size) - size;
+       with sub-page size and unaligned start address. Pad the start
+       address to next and truncate size to previous page boundary. */
+    delta = (TARGET_PAGE_SIZE - (start_addr & ~TARGET_PAGE_MASK));
+    delta &= ~TARGET_PAGE_MASK;
     if (delta > size) {
         return;
     }

kvm-stub.c

@@ -147,4 +147,9 @@ int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq)
 {
     return -ENOSYS;
 }
+
+bool kvm_has_free_slot(MachineState *ms)
+{
+    return false;
+}
 #endif

libcacard/vscclient.c

@@ -597,7 +597,7 @@ connect_to_qemu(
     const char *port
 ) {
     struct addrinfo hints;
-    struct addrinfo *server;
+    struct addrinfo *server = NULL;
     int ret, sock;
 
     sock = socket(AF_INET, SOCK_STREAM, 0);
@@ -629,9 +629,14 @@ connect_to_qemu(
     if (verbose) {
         printf("Connected (sizeof Header=%zd)!\n", sizeof(VSCMsgHeader));
     }
+
+    freeaddrinfo(server);
     return sock;
 
 cleanup_socket:
+    if (server) {
+        freeaddrinfo(server);
+    }
     closesocket(sock);
     return -1;
 }

linux-headers/asm-arm/kvm.h

@@ -25,6 +25,7 @@
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -173,6 +174,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24

linux-headers/asm-arm64/kvm.h

@@ -37,6 +37,7 @@
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -159,6 +160,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24

linux-headers/asm-powerpc/kvm.h

@@ -476,6 +476,11 @@ struct kvm_get_htab_header {
 
 /* FP and vector status/control registers */
 #define KVM_REG_PPC_FPSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x80)
+/*
+ * VSCR register is documented as a 32-bit register in the ISA, but it can
+ * only be accesses via a vector register. Expose VSCR as a 32-bit register
+ * even though the kernel represents it as a 128-bit vector.
+ */
 #define KVM_REG_PPC_VSCR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0x81)
 
 /* Virtual processor areas */
@@ -557,6 +562,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_DABRX	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xb8)
 #define KVM_REG_PPC_WORT	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xb9)
 #define KVM_REG_PPC_SPRG9	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
+#define KVM_REG_PPC_DBSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
 
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs

linux-headers/asm-s390/kvm.h

@@ -111,12 +111,22 @@ struct kvm_guest_debug_arch {
 #define KVM_SYNC_GPRS   (1UL << 1)
 #define KVM_SYNC_ACRS   (1UL << 2)
 #define KVM_SYNC_CRS    (1UL << 3)
+#define KVM_SYNC_ARCH0  (1UL << 4)
+#define KVM_SYNC_PFAULT (1UL << 5)
 /* definition of registers in kvm_run */
 struct kvm_sync_regs {
 	__u64 prefix;	/* prefix register */
 	__u64 gprs[16];	/* general purpose registers */
 	__u32 acrs[16];	/* access registers */
 	__u64 crs[16];	/* control registers */
+	__u64 todpr;	/* tod programmable register [ARCH0] */
+	__u64 cputm;	/* cpu timer [ARCH0] */
+	__u64 ckc;	/* clock comparator [ARCH0] */
+	__u64 pp;	/* program parameter [ARCH0] */
+	__u64 gbea;	/* guest breaking-event address [ARCH0] */
+	__u64 pft;	/* pfault token [PFAULT] */
+	__u64 pfs;	/* pfault select [PFAULT] */
+	__u64 pfc;	/* pfault compare [PFAULT] */
 };
 
 #define KVM_REG_S390_TODPR	(KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1)

linux-headers/linux/kvm.h

@@ -654,9 +654,7 @@ struct kvm_ppc_smmu_info {
 #endif
 /* Bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_DESTROY_MEMORY_REGION_WORKS 21
-#ifdef __KVM_HAVE_USER_NMI
 #define KVM_CAP_USER_NMI 22
-#endif
 #ifdef __KVM_HAVE_GUEST_DEBUG
 #define KVM_CAP_SET_GUEST_DEBUG 23
 #endif
@@ -738,9 +736,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
-#ifdef __KVM_HAVE_READONLY_MEM
 #define KVM_CAP_READONLY_MEM 81
-#endif
 #define KVM_CAP_IRQFD_RESAMPLE 82
 #define KVM_CAP_PPC_BOOKE_WATCHDOG 83
 #define KVM_CAP_PPC_HTAB_FD 84
@@ -947,15 +943,25 @@ struct kvm_device_attr {
 	__u64	addr;		/* userspace address of attr data */
 };
 
-#define KVM_DEV_TYPE_FSL_MPIC_20	1
-#define KVM_DEV_TYPE_FSL_MPIC_42	2
-#define KVM_DEV_TYPE_XICS		3
-#define KVM_DEV_TYPE_VFIO		4
 #define  KVM_DEV_VFIO_GROUP			1
 #define   KVM_DEV_VFIO_GROUP_ADD			1
 #define   KVM_DEV_VFIO_GROUP_DEL			2
-#define KVM_DEV_TYPE_ARM_VGIC_V2	5
-#define KVM_DEV_TYPE_FLIC		6
+
+enum kvm_device_type {
+	KVM_DEV_TYPE_FSL_MPIC_20	= 1,
+#define KVM_DEV_TYPE_FSL_MPIC_20	KVM_DEV_TYPE_FSL_MPIC_20
+	KVM_DEV_TYPE_FSL_MPIC_42,
+#define KVM_DEV_TYPE_FSL_MPIC_42	KVM_DEV_TYPE_FSL_MPIC_42
+	KVM_DEV_TYPE_XICS,
+#define KVM_DEV_TYPE_XICS		KVM_DEV_TYPE_XICS
+	KVM_DEV_TYPE_VFIO,
+#define KVM_DEV_TYPE_VFIO		KVM_DEV_TYPE_VFIO
+	KVM_DEV_TYPE_ARM_VGIC_V2,
+#define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
+	KVM_DEV_TYPE_FLIC,
+#define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_MAX,
+};
 
 /*
  * ioctls for VM fds
@@ -1093,7 +1099,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_S390_INITIAL_RESET    _IO(KVMIO,   0x97)
 #define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
 #define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
-/* Available with KVM_CAP_NMI */
+/* Available with KVM_CAP_USER_NMI */
 #define KVM_NMI                   _IO(KVMIO,   0x9a)
 /* Available with KVM_CAP_SET_GUEST_DEBUG */
 #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)

linux-headers/linux/vfio.h

@@ -33,6 +33,9 @@
 /* Check if EEH is supported */
 #define VFIO_EEH			5
 
+/* Two-stage IOMMU */
+#define VFIO_TYPE1_NESTING_IOMMU	6	/* Implies v2 */
+
 /*
  * The IOCTL interface is designed for extensibility by embedding the
  * structure length (argsz) and flags into structures passed between

linux-user/elfload.c

@@ -1824,7 +1824,7 @@ static void load_elf_image(const char *image_name, int image_fd,
             if (a < loaddr) {
                 loaddr = a;
             }
-            a += phdr[i].p_memsz;
+            a = phdr[i].p_vaddr + phdr[i].p_memsz;
             if (a > hiaddr) {
                 hiaddr = a;
             }

linux-user/syscall.c

@@ -5473,6 +5473,27 @@ static int do_openat(void *cpu_env, int dirfd, const char *pathname, int flags,
     return get_errno(sys_openat(dirfd, path(pathname), flags, mode));
 }
 
+#define TIMER_MAGIC 0x0caf0000
+#define TIMER_MAGIC_MASK 0xffff0000
+
+/* Convert QEMU provided timer ID back to internal 16bit index format */
+static target_timer_t get_timer_id(abi_long arg)
+{
+    target_timer_t timerid = arg;
+
+    if ((timerid & TIMER_MAGIC_MASK) != TIMER_MAGIC) {
+        return -TARGET_EINVAL;
+    }
+
+    timerid &= 0xffff;
+
+    if (timerid >= ARRAY_SIZE(g_posix_timers)) {
+        return -TARGET_EINVAL;
+    }
+
+    return timerid;
+}
+
 /* do_syscall() should always have a single exit point at the end so
    that actions, such as logging of syscall results, can be performed.
    All errnos that do_syscall() returns must be -TARGET_<errcode>. */
@@ -9579,7 +9600,6 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
         /* args: clockid_t clockid, struct sigevent *sevp, timer_t *timerid */
 
         struct sigevent host_sevp = { {0}, }, *phost_sevp = NULL;
-        struct target_timer_t *ptarget_timer;
 
         int clkid = arg1;
         int timer_index = next_free_host_timer();
@@ -9601,11 +9621,9 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
             if (ret) {
                 phtimer = NULL;
             } else {
-                if (!lock_user_struct(VERIFY_WRITE, ptarget_timer, arg3, 1)) {
+                if (put_user(TIMER_MAGIC | timer_index, arg3, target_timer_t)) {
                     goto efault;
                 }
-                ptarget_timer->ptr = tswap32(0xcafe0000 | timer_index);
-                unlock_user_struct(ptarget_timer, arg3, 1);
             }
         }
         break;
@@ -9617,9 +9635,11 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
     {
         /* args: timer_t timerid, int flags, const struct itimerspec *new_value,
          * struct itimerspec * old_value */
-        target_ulong timerid = arg1;
+        target_timer_t timerid = get_timer_id(arg1);
 
-        if (arg3 == 0 || timerid >= ARRAY_SIZE(g_posix_timers)) {
+        if (timerid < 0) {
+            ret = timerid;
+        } else if (arg3 == 0) {
             ret = -TARGET_EINVAL;
         } else {
             timer_t htimer = g_posix_timers[timerid];
@@ -9638,12 +9658,12 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
     case TARGET_NR_timer_gettime:
     {
         /* args: timer_t timerid, struct itimerspec *curr_value */
-        target_ulong timerid = arg1;
+        target_timer_t timerid = get_timer_id(arg1);
 
-        if (!arg2) {
-            return -TARGET_EFAULT;
-        } else if (timerid >= ARRAY_SIZE(g_posix_timers)) {
-            ret = -TARGET_EINVAL;
+        if (timerid < 0) {
+            ret = timerid;
+        } else if (!arg2) {
+            ret = -TARGET_EFAULT;
         } else {
             timer_t htimer = g_posix_timers[timerid];
             struct itimerspec hspec;
@@ -9661,10 +9681,10 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
     case TARGET_NR_timer_getoverrun:
     {
         /* args: timer_t timerid */
-        target_ulong timerid = arg1;
+        target_timer_t timerid = get_timer_id(arg1);
 
-        if (timerid >= ARRAY_SIZE(g_posix_timers)) {
-            ret = -TARGET_EINVAL;
+        if (timerid < 0) {
+            ret = timerid;
         } else {
             timer_t htimer = g_posix_timers[timerid];
             ret = get_errno(timer_getoverrun(htimer));
@@ -9677,10 +9697,10 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
     case TARGET_NR_timer_delete:
     {
         /* args: timer_t timerid */
-        target_ulong timerid = arg1;
+        target_timer_t timerid = get_timer_id(arg1);
 
-        if (timerid >= ARRAY_SIZE(g_posix_timers)) {
-            ret = -TARGET_EINVAL;
+        if (timerid < 0) {
+            ret = timerid;
         } else {
             timer_t htimer = g_posix_timers[timerid];
             ret = get_errno(timer_delete(htimer));

linux-user/syscall_defs.h

@@ -2564,10 +2564,7 @@ struct target_ucred {
 
 #endif
 
-
-struct target_timer_t {
-    abi_ulong ptr;
-};
+typedef int32_t target_timer_t;
 
 #define TARGET_SIGEV_MAX_SIZE 64
 

memory.c

@@ -1749,6 +1749,11 @@ ram_addr_t memory_region_get_ram_addr(MemoryRegion *mr)
     return mr->ram_addr;
 }
 
+uint64_t memory_region_get_alignment(const MemoryRegion *mr)
+{
+    return mr->align;
+}
+
 static int cmp_flatrange_addr(const void *addr_, const void *fr_)
 {
     const AddrRange *addr = addr_;

monitor.c

@@ -1948,7 +1948,10 @@ static void do_info_numa(Monitor *mon, const QDict *qdict)
 {
     int i;
     CPUState *cpu;
+    uint64_t *node_mem;
 
+    node_mem = g_new0(uint64_t, nb_numa_nodes);
+    query_numa_node_mem(node_mem);
     monitor_printf(mon, "%d nodes\n", nb_numa_nodes);
     for (i = 0; i < nb_numa_nodes; i++) {
         monitor_printf(mon, "node %d cpus:", i);
@@ -1959,8 +1962,9 @@ static void do_info_numa(Monitor *mon, const QDict *qdict)
         }
         monitor_printf(mon, "\n");
         monitor_printf(mon, "node %d size: %" PRId64 " MB\n", i,
-            numa_info[i].node_mem >> 20);
+                       node_mem[i] >> 20);
     }
+    g_free(node_mem);
 }
 
 #ifdef CONFIG_PROFILER
@@ -4317,17 +4321,14 @@ void object_add_completion(ReadLineState *rs, int nb_args, const char *str)
 static void peripheral_device_del_completion(ReadLineState *rs,
                                              const char *str, size_t len)
 {
-    Object *peripheral;
-    GSList *list = NULL, *item;
+    Object *peripheral = container_get(qdev_get_machine(), "/peripheral");
+    GSList *list, *item;
 
-    peripheral = object_resolve_path("/machine/peripheral/", NULL);
-    if (peripheral == NULL) {
+    list = qdev_build_hotpluggable_device_list(peripheral);
+    if (!list) {
         return;
     }
 
-    object_child_foreach(peripheral, qdev_build_hotpluggable_device_list,
-                         &list);
-
     for (item = list; item; item = g_slist_next(item)) {
         DeviceState *dev = item->data;
 

net/l2tpv3.c

@@ -516,7 +516,7 @@ static void net_l2tpv3_cleanup(NetClientState *nc)
     qemu_purge_queued_packets(nc);
     l2tpv3_read_poll(s, false);
     l2tpv3_write_poll(s, false);
-    if (s->fd > 0) {
+    if (s->fd >= 0) {
         close(s->fd);
     }
     destroy_vector(s->msgvec, MAX_L2TPV3_MSGCNT, IOVSIZE);
@@ -660,7 +660,6 @@ int net_init_l2tpv3(const NetClientOptions *opts,
     if (fd == -1) {
         fd = -errno;
         error_report("l2tpv3_open : socket creation failed, errno = %d", -fd);
-        freeaddrinfo(result);
         goto outerr;
     }
     if (bind(fd, (struct sockaddr *) result->ai_addr, result->ai_addrlen)) {
@@ -746,7 +745,7 @@ int net_init_l2tpv3(const NetClientOptions *opts,
     return 0;
 outerr:
     qemu_del_net_client(nc);
-    if (fd > 0) {
+    if (fd >= 0) {
         close(fd);
     }
     if (result) {

net/slirp.c

@@ -523,15 +523,21 @@ static int slirp_smb(SlirpState* s, const char *exported_dir,
     fprintf(f,
             "[global]\n"
             "private dir=%s\n"
-            "socket address=127.0.0.1\n"
+            "interfaces=127.0.0.1\n"
+            "bind interfaces only=yes\n"
             "pid directory=%s\n"
             "lock directory=%s\n"
             "state directory=%s\n"
+            "cache directory=%s\n"
             "ncalrpc dir=%s/ncalrpc\n"
             "log file=%s/log.smbd\n"
             "smb passwd file=%s/smbpasswd\n"
             "security = user\n"
             "map to guest = Bad User\n"
+            "load printers = no\n"
+            "printing = bsd\n"
+            "disable spoolss = yes\n"
+            "usershare max shares = 0\n"
             "[qemu]\n"
             "path=%s\n"
             "read only=no\n"
@@ -544,6 +550,7 @@ static int slirp_smb(SlirpState* s, const char *exported_dir,
             s->smb_dir,
             s->smb_dir,
             s->smb_dir,
+            s->smb_dir,
             exported_dir,
             passwd->pw_name
             );
@@ -636,17 +643,16 @@ static int slirp_guestfwd(SlirpState *s, const char *config_str,
         goto fail_syntax;
     }
 
-    fwd = g_malloc(sizeof(struct GuestFwd));
     snprintf(buf, sizeof(buf), "guestfwd.tcp.%d", port);
 
     if ((strlen(p) > 4) && !strncmp(p, "cmd:", 4)) {
         if (slirp_add_exec(s->slirp, 0, &p[4], &server, port) < 0) {
             error_report("conflicting/invalid host:port in guest forwarding "
                          "rule '%s'", config_str);
-            g_free(fwd);
             return -1;
         }
     } else {
+        fwd = g_malloc(sizeof(struct GuestFwd));
         fwd->hd = qemu_chr_new(buf, p, NULL);
         if (!fwd->hd) {
             error_report("could not open guest forwarding device '%s'", buf);

net/socket.c

@@ -352,7 +352,7 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
 {
     struct sockaddr_in saddr;
     int newfd;
-    socklen_t saddr_len;
+    socklen_t saddr_len = sizeof(saddr);
     NetClientState *nc;
     NetSocketState *s;
 
@@ -389,11 +389,6 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
 
     nc = qemu_new_net_client(&net_dgram_socket_info, peer, model, name);
 
-    snprintf(nc->info_str, sizeof(nc->info_str),
-            "socket: fd=%d (%s mcast=%s:%d)",
-            fd, is_connected ? "cloned" : "",
-            inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
-
     s = DO_UPCAST(NetSocketState, nc, nc);
 
     s->fd = fd;
@@ -404,6 +399,12 @@ static NetSocketState *net_socket_fd_init_dgram(NetClientState *peer,
     /* mcast: save bound address as dst */
     if (is_connected) {
         s->dgram_dst = saddr;
+        snprintf(nc->info_str, sizeof(nc->info_str),
+                 "socket: fd=%d (cloned mcast=%s:%d)",
+                 fd, inet_ntoa(saddr.sin_addr), ntohs(saddr.sin_port));
+    } else {
+        snprintf(nc->info_str, sizeof(nc->info_str),
+                 "socket: fd=%d", fd);
     }
 
     return s;

numa.c

@@ -35,6 +35,7 @@
 #include "hw/boards.h"
 #include "sysemu/hostmem.h"
 #include "qmp-commands.h"
+#include "hw/mem/pc-dimm.h"
 
 QemuOptsList qemu_numa_opts = {
     .name = "numa",
@@ -315,6 +316,43 @@ void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner,
     }
 }
 
+static void numa_stat_memory_devices(uint64_t node_mem[])
+{
+    MemoryDeviceInfoList *info_list = NULL;
+    MemoryDeviceInfoList **prev = &info_list;
+    MemoryDeviceInfoList *info;
+
+    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->kind) {
+            case MEMORY_DEVICE_INFO_KIND_DIMM:
+                node_mem[value->dimm->node] += value->dimm->size;
+                break;
+            default:
+                break;
+            }
+        }
+    }
+    qapi_free_MemoryDeviceInfoList(info_list);
+}
+
+void query_numa_node_mem(uint64_t node_mem[])
+{
+    int i;
+
+    if (nb_numa_nodes <= 0) {
+        return;
+    }
+
+    numa_stat_memory_devices(node_mem);
+    for (i = 0; i < nb_numa_nodes; i++) {
+        node_mem[i] += numa_info[i].node_mem;
+    }
+}
+
 static int query_memdev(Object *obj, void *opaque)
 {
     MemdevList **list = opaque;