Merge remote branch 'kwolf/for-stable-0.13' into stable-0.13

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>

Makefile.target

@@ -190,6 +190,9 @@ obj-$(CONFIG_USB_OHCI) += usb-ohci.o
 obj-y += rtl8139.o
 obj-y += e1000.o
 
+# Inter-VM PCI shared memory
+obj-$(CONFIG_KVM) += ivshmem.o
+
 # Hardware support
 obj-i386-y += vga.o
 obj-i386-y += mc146818rtc.o i8259.o pc.o

VERSION

@@ -1 +1 @@
-0.12.90
+0.12.92

block-migration.c

@@ -586,6 +586,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
         addr >>= BDRV_SECTOR_BITS;
 
         if (flags & BLK_MIG_FLAG_DEVICE_BLOCK) {
+            int ret;
             /* get device name */
             len = qemu_get_byte(f);
             qemu_get_buffer(f, (uint8_t *)device_name, len);
@@ -601,9 +602,12 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
             buf = qemu_malloc(BLOCK_SIZE);
 
             qemu_get_buffer(f, buf, BLOCK_SIZE);
-            bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);
+            ret = bdrv_write(bs, addr, buf, BDRV_SECTORS_PER_DIRTY_CHUNK);
 
             qemu_free(buf);
+            if (ret < 0) {
+                return ret;
+            }
         } else if (flags & BLK_MIG_FLAG_PROGRESS) {
             if (!banner_printed) {
                 printf("Receiving block device images\n");

block.c

@@ -330,7 +330,7 @@ BlockDriver *bdrv_find_protocol(const char *filename)
     return NULL;
 }
 
-static BlockDriver *find_image_format(const char *filename)
+static int find_image_format(const char *filename, BlockDriver **pdrv)
 {
     int ret, score, score_max;
     BlockDriver *drv1, *drv;
@@ -338,19 +338,27 @@ static BlockDriver *find_image_format(const char *filename)
     BlockDriverState *bs;
 
     ret = bdrv_file_open(&bs, filename, 0);
-    if (ret < 0)
-        return NULL;
+    if (ret < 0) {
+        *pdrv = NULL;
+        return ret;
+    }
 
     /* Return the raw BlockDriver * to scsi-generic devices or empty drives */
     if (bs->sg || !bdrv_is_inserted(bs)) {
         bdrv_delete(bs);
-        return bdrv_find_format("raw");
+        drv = bdrv_find_format("raw");
+        if (!drv) {
+            ret = -ENOENT;
+        }
+        *pdrv = drv;
+        return ret;
     }
 
     ret = bdrv_pread(bs, 0, buf, sizeof(buf));
     bdrv_delete(bs);
     if (ret < 0) {
-        return NULL;
+        *pdrv = NULL;
+        return ret;
     }
 
     score_max = 0;
@@ -364,7 +372,11 @@ static BlockDriver *find_image_format(const char *filename)
             }
         }
     }
-    return drv;
+    if (!drv) {
+        ret = -ENOENT;
+    }
+    *pdrv = drv;
+    return ret;
 }
 
 /**
@@ -571,12 +583,11 @@ int bdrv_open(BlockDriverState *bs, const char *filename, int flags,
 
     /* Find the right image format driver */
     if (!drv) {
-        drv = find_image_format(filename);
+        ret = find_image_format(filename, &drv);
         probed = 1;
     }
 
     if (!drv) {
-        ret = -ENOENT;
         goto unlink_and_fail;
     }
 
@@ -732,6 +743,7 @@ int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res)
 int bdrv_commit(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
+    BlockDriver *backing_drv;
     int64_t i, total_sectors;
     int n, j, ro, open_flags;
     int ret = 0, rw_ret = 0;
@@ -749,7 +761,8 @@ int bdrv_commit(BlockDriverState *bs)
     if (bs->backing_hd->keep_read_only) {
         return -EACCES;
     }
-    
+
+    backing_drv = bs->backing_hd->drv;
     ro = bs->backing_hd->read_only;
     strncpy(filename, bs->backing_hd->filename, sizeof(filename));
     open_flags =  bs->backing_hd->open_flags;
@@ -759,12 +772,14 @@ int bdrv_commit(BlockDriverState *bs)
         bdrv_delete(bs->backing_hd);
         bs->backing_hd = NULL;
         bs_rw = bdrv_new("");
-        rw_ret = bdrv_open(bs_rw, filename, open_flags | BDRV_O_RDWR, drv);
+        rw_ret = bdrv_open(bs_rw, filename, open_flags | BDRV_O_RDWR,
+            backing_drv);
         if (rw_ret < 0) {
             bdrv_delete(bs_rw);
             /* try to re-open read-only */
             bs_ro = bdrv_new("");
-            ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR, drv);
+            ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR,
+                backing_drv);
             if (ret < 0) {
                 bdrv_delete(bs_ro);
                 /* drive not functional anymore */
@@ -816,7 +831,8 @@ ro_cleanup:
         bdrv_delete(bs->backing_hd);
         bs->backing_hd = NULL;
         bs_ro = bdrv_new("");
-        ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR, drv);
+        ret = bdrv_open(bs_ro, filename, open_flags & ~BDRV_O_RDWR,
+            backing_drv);
         if (ret < 0) {
             bdrv_delete(bs_ro);
             /* drive not functional anymore */
@@ -1465,10 +1481,8 @@ int bdrv_has_zero_init(BlockDriverState *bs)
 {
     assert(bs->drv);
 
-    if (bs->drv->no_zero_init) {
-        return 0;
-    } else if (bs->file) {
-        return bdrv_has_zero_init(bs->file);
+    if (bs->drv->bdrv_has_zero_init) {
+        return bs->drv->bdrv_has_zero_init(bs);
     }
 
     return 1;
@@ -1800,6 +1814,11 @@ int bdrv_can_snapshot(BlockDriverState *bs)
     return 1;
 }
 
+int bdrv_is_snapshot(BlockDriverState *bs)
+{
+    return !!(bs->open_flags & BDRV_O_SNAPSHOT);
+}
+
 BlockDriverState *bdrv_snapshots(void)
 {
     BlockDriverState *bs;
@@ -2502,7 +2521,7 @@ int bdrv_is_inserted(BlockDriverState *bs)
     if (!drv)
         return 0;
     if (!drv->bdrv_is_inserted)
-        return 1;
+        return !bs->tray_open;
     ret = drv->bdrv_is_inserted(bs);
     return ret;
 }
@@ -2544,10 +2563,11 @@ int bdrv_eject(BlockDriverState *bs, int eject_flag)
         ret = drv->bdrv_eject(bs, eject_flag);
     }
     if (ret == -ENOTSUP) {
-        if (eject_flag)
-            bdrv_close(bs);
         ret = 0;
     }
+    if (ret >= 0) {
+        bs->tray_open = eject_flag;
+    }
 
     return ret;
 }

block.h

@@ -35,7 +35,7 @@ typedef struct QEMUSnapshotInfo {
 #define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
 #define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
 
-#define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB)
+#define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH)
 
 #define BDRV_SECTOR_BITS   9
 #define BDRV_SECTOR_SIZE   (1ULL << BDRV_SECTOR_BITS)
@@ -202,6 +202,7 @@ const char *bdrv_get_encrypted_filename(BlockDriverState *bs);
 void bdrv_get_backing_filename(BlockDriverState *bs,
                                char *filename, int filename_size);
 int bdrv_can_snapshot(BlockDriverState *bs);
+int bdrv_is_snapshot(BlockDriverState *bs);
 BlockDriverState *bdrv_snapshots(void);
 int bdrv_snapshot_create(BlockDriverState *bs,
                          QEMUSnapshotInfo *sn_info);

block/qcow2-cluster.c

@@ -655,7 +655,7 @@ static int write_l2_entries(BlockDriverState *bs, uint64_t *l2_table,
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_L2_UPDATE);
-    ret = bdrv_pwrite_sync(bs->file, l2_offset + start_offset,
+    ret = bdrv_pwrite(bs->file, l2_offset + start_offset,
         &l2_table[l2_start_index], len);
     if (ret < 0) {
         return ret;
@@ -718,9 +718,17 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
         goto err;
     }
 
-    for (i = 0; i < j; i++)
-        qcow2_free_any_clusters(bs,
-            be64_to_cpu(old_cluster[i]) & ~QCOW_OFLAG_COPIED, 1);
+    /*
+     * If this was a COW, we need to decrease the refcount of the old cluster.
+     * Also flush bs->file to get the right order for L2 and refcount update.
+     */
+    if (j != 0) {
+        bdrv_flush(bs->file);
+        for (i = 0; i < j; i++) {
+            qcow2_free_any_clusters(bs,
+                be64_to_cpu(old_cluster[i]) & ~QCOW_OFLAG_COPIED, 1);
+        }
+    }
 
     ret = 0;
 err:

block/raw-posix.c

@@ -993,6 +993,11 @@ static int hdev_create(const char *filename, QEMUOptionParameter *options)
     return ret;
 }
 
+static int hdev_has_zero_init(BlockDriverState *bs)
+{
+    return 0;
+}
+
 static BlockDriver bdrv_host_device = {
     .format_name        = "host_device",
     .protocol_name        = "host_device",
@@ -1002,7 +1007,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
-    .no_zero_init       = 1,
+    .bdrv_has_zero_init = hdev_has_zero_init,
     .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv	= raw_aio_readv,
@@ -1117,7 +1122,7 @@ static BlockDriver bdrv_host_floppy = {
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
-    .no_zero_init       = 1,
+    .bdrv_has_zero_init = hdev_has_zero_init,
     .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,
@@ -1149,9 +1154,6 @@ static int cdrom_probe_device(const char *filename)
     int fd, ret;
     int prio = 0;
 
-    if (strstart(filename, "/dev/cd", NULL))
-        prio = 50;
-
     fd = open(filename, O_RDONLY | O_NONBLOCK);
     if (fd < 0) {
         goto out;
@@ -1217,7 +1219,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
-    .no_zero_init       = 1,
+    .bdrv_has_zero_init = hdev_has_zero_init,
     .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,
@@ -1340,7 +1342,7 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_close         = raw_close,
     .bdrv_create        = hdev_create,
     .create_options     = raw_create_options,
-    .no_zero_init       = 1,
+    .bdrv_has_zero_init = hdev_has_zero_init,
     .bdrv_flush         = raw_flush,
 
     .bdrv_aio_readv     = raw_aio_readv,

block/raw-win32.c

@@ -394,6 +394,11 @@ static int raw_set_locked(BlockDriverState *bs, int locked)
 }
 #endif
 
+static int hdev_has_zero_init(BlockDriverState *bs)
+{
+    return 0;
+}
+
 static BlockDriver bdrv_host_device = {
     .format_name	= "host_device",
     .protocol_name	= "host_device",
@@ -402,6 +407,7 @@ static BlockDriver bdrv_host_device = {
     .bdrv_file_open	= hdev_open,
     .bdrv_close		= raw_close,
     .bdrv_flush		= raw_flush,
+    .bdrv_has_zero_init = hdev_has_zero_init,
 
     .bdrv_read		= raw_read,
     .bdrv_write	        = raw_write,

block/raw.c

@@ -237,6 +237,11 @@ static QEMUOptionParameter raw_create_options[] = {
     { NULL }
 };
 
+static int raw_has_zero_init(BlockDriverState *bs)
+{
+    return bdrv_has_zero_init(bs->file);
+}
+
 static BlockDriver bdrv_raw = {
     .format_name        = "raw",
 
@@ -264,6 +269,7 @@ static BlockDriver bdrv_raw = {
 
     .bdrv_create        = raw_create,
     .create_options     = raw_create_options,
+    .bdrv_has_zero_init = raw_has_zero_init,
 };
 
 static void bdrv_raw_init(void)

block/vvfat.c

@@ -512,7 +512,7 @@ static inline uint8_t fat_chksum(const direntry_t* entry)
     for(i=0;i<11;i++) {
         unsigned char c;
 
-        c = (i <= 8) ? entry->name[i] : entry->extension[i-8];
+        c = (i < 8) ? entry->name[i] : entry->extension[i-8];
         chksum=(((chksum&0xfe)>>1)|((chksum&0x01)?0x80:0)) + c;
     }
 
@@ -2665,6 +2665,11 @@ static int vvfat_write(BlockDriverState *bs, int64_t sector_num,
 
 DLOG(checkpoint());
 
+    /* Check if we're operating in read-only mode */
+    if (s->qcow == NULL) {
+        return -EACCES;
+    }
+
     vvfat_close_current_file(s);
 
     /*
@@ -2763,12 +2768,12 @@ static int vvfat_is_allocated(BlockDriverState *bs,
 
 static int write_target_commit(BlockDriverState *bs, int64_t sector_num,
 	const uint8_t* buffer, int nb_sectors) {
-    BDRVVVFATState* s = bs->opaque;
+    BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque);
     return try_commit(s);
 }
 
 static void write_target_close(BlockDriverState *bs) {
-    BDRVVVFATState* s = bs->opaque;
+    BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque);
     bdrv_delete(s->qcow);
     free(s->qcow_filename);
 }
@@ -2783,6 +2788,7 @@ static int enable_write_target(BDRVVVFATState *s)
 {
     BlockDriver *bdrv_qcow;
     QEMUOptionParameter *options;
+    int ret;
     int size = sector2cluster(s, s->sector_count);
     s->used_clusters = calloc(size, 1);
 
@@ -2798,11 +2804,16 @@ static int enable_write_target(BDRVVVFATState *s)
 
     if (bdrv_create(bdrv_qcow, s->qcow_filename, options) < 0)
 	return -1;
+
     s->qcow = bdrv_new("");
-    if (s->qcow == NULL ||
-        bdrv_open(s->qcow, s->qcow_filename, BDRV_O_RDWR, bdrv_qcow) < 0)
-    {
-	return -1;
+    if (s->qcow == NULL) {
+        return -1;
+    }
+
+    ret = bdrv_open(s->qcow, s->qcow_filename,
+            BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, bdrv_qcow);
+    if (ret < 0) {
+	return ret;
     }
 
 #ifndef _WIN32
@@ -2811,7 +2822,8 @@ static int enable_write_target(BDRVVVFATState *s)
 
     s->bs->backing_hd = calloc(sizeof(BlockDriverState), 1);
     s->bs->backing_hd->drv = &vvfat_write_target;
-    s->bs->backing_hd->opaque = s;
+    s->bs->backing_hd->opaque = qemu_malloc(sizeof(void*));
+    *(void**)s->bs->backing_hd->opaque = s;
 
     return 0;
 }

block_int.h

@@ -127,8 +127,11 @@ struct BlockDriver {
 
     void (*bdrv_debug_event)(BlockDriverState *bs, BlkDebugEvent event);
 
-    /* Set if newly created images are not guaranteed to contain only zeros */
-    int no_zero_init;
+    /*
+     * Returns 1 if newly created images are guaranteed to contain only
+     * zeros, 0 otherwise.
+     */
+    int (*bdrv_has_zero_init)(BlockDriverState *bs);
 
     QLIST_ENTRY(BlockDriver) list;
 };
@@ -141,6 +144,7 @@ struct BlockDriverState {
     int open_flags; /* flags used to open the file, re-used for re-open */
     int removable; /* if true, the media can be removed */
     int locked;    /* if true, the media cannot temporarily be ejected */
+    int tray_open; /* if true, the virtual tray is open */
     int encrypted; /* if true, the media is encrypted */
     int valid_key; /* if true, a valid encryption key has been set */
     int sg;        /* if true, the device is a /dev/sg* */
@@ -243,7 +247,7 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf)
                        _conf.logical_block_size, 512),                  \
     DEFINE_PROP_UINT16("physical_block_size", _state,                   \
                        _conf.physical_block_size, 512),                 \
-    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 512),  \
-    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 512)
+    DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0),  \
+    DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0)
 
 #endif /* BLOCK_INT_H */

blockdev.c

@@ -590,6 +590,7 @@ int do_change_block(Monitor *mon, const char *device,
         return -1;
     }
     bdrv_flags = bdrv_is_read_only(bs) ? 0 : BDRV_O_RDWR;
+    bdrv_flags |= bdrv_is_snapshot(bs) ? BDRV_O_SNAPSHOT : 0;
     if (bdrv_open(bs, filename, bdrv_flags, drv) < 0) {
         qerror_report(QERR_OPEN_FILE_FAILED, filename);
         return -1;

cpu-all.h

@@ -629,8 +629,10 @@ extern unsigned long guest_base;
 extern int have_guest_base;
 extern unsigned long reserved_va;
 #define GUEST_BASE guest_base
+#define RESERVED_VA reserved_va
 #else
 #define GUEST_BASE 0ul
+#define RESERVED_VA 0ul
 #endif
 
 /* All direct uses of g2h and h2g need to go away for usermode softmmu.  */

cpu-common.h

@@ -40,6 +40,8 @@ static inline void cpu_register_physical_memory(target_phys_addr_t start_addr,
 }
 
 ram_addr_t cpu_get_physical_page_desc(target_phys_addr_t addr);
+ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
+                        ram_addr_t size, void *host);
 ram_addr_t qemu_ram_alloc(DeviceState *dev, const char *name, ram_addr_t size);
 void qemu_ram_free(ram_addr_t addr);
 /* This should only be used for ram local to a device.  */

docs/specs/ivshmem_device_spec.txt

@@ -0,0 +1,96 @@
+
+Device Specification for Inter-VM shared memory device
+------------------------------------------------------
+
+The Inter-VM shared memory device is designed to share a region of memory to
+userspace in multiple virtual guests.  The memory region does not belong to any
+guest, but is a POSIX memory object on the host.  Optionally, the device may
+support sending interrupts to other guests sharing the same memory region.
+
+
+The Inter-VM PCI device
+-----------------------
+
+*BARs*
+
+The device supports three BARs.  BAR0 is a 1 Kbyte MMIO region to support
+registers.  BAR1 is used for MSI-X when it is enabled in the device.  BAR2 is
+used to map the shared memory object from the host.  The size of BAR2 is
+specified when the guest is started and must be a power of 2 in size.
+
+*Registers*
+
+The device currently supports 4 registers of 32-bits each.  Registers
+are used for synchronization between guests sharing the same memory object when
+interrupts are supported (this requires using the shared memory server).
+
+The server assigns each VM an ID number and sends this ID number to the Qemu
+process when the guest starts.
+
+enum ivshmem_registers {
+    IntrMask = 0,
+    IntrStatus = 4,
+    IVPosition = 8,
+    Doorbell = 12
+};
+
+The first two registers are the interrupt mask and status registers.  Mask and
+status are only used with pin-based interrupts.  They are unused with MSI
+interrupts.
+
+Status Register: The status register is set to 1 when an interrupt occurs.
+
+Mask Register: The mask register is bitwise ANDed with the interrupt status
+and the result will raise an interrupt if it is non-zero.  However, since 1 is
+the only value the status will be set to, it is only the first bit of the mask
+that has any effect.  Therefore interrupts can be masked by setting the first
+bit to 0 and unmasked by setting the first bit to 1.
+
+IVPosition Register: The IVPosition register is read-only and reports the
+guest's ID number.  The guest IDs are non-negative integers.  When using the
+server, since the server is a separate process, the VM ID will only be set when
+the device is ready (shared memory is received from the server and accessible via
+the device).  If the device is not ready, the IVPosition will return -1.
+Applications should ensure that they have a valid VM ID before accessing the
+shared memory.
+
+Doorbell Register:  To interrupt another guest, a guest must write to the
+Doorbell register.  The doorbell register is 32-bits, logically divided into
+two 16-bit fields.  The high 16-bits are the guest ID to interrupt and the low
+16-bits are the interrupt vector to trigger.  The semantics of the value
+written to the doorbell depends on whether the device is using MSI or a regular
+pin-based interrupt.  In short, MSI uses vectors while regular interrupts set the
+status register.
+
+Regular Interrupts
+
+If regular interrupts are used (due to either a guest not supporting MSI or the
+user specifying not to use them on startup) then the value written to the lower
+16-bits of the Doorbell register results is arbitrary and will trigger an
+interrupt in the destination guest.
+
+Message Signalled Interrupts
+
+A ivshmem device may support multiple MSI vectors.  If so, the lower 16-bits
+written to the Doorbell register must be between 0 and the maximum number of
+vectors the guest supports.  The lower 16 bits written to the doorbell is the
+MSI vector that will be raised in the destination guest.  The number of MSI
+vectors is configurable but it is set when the VM is started.
+
+The important thing to remember with MSI is that it is only a signal, no status
+is set (since MSI interrupts are not shared).  All information other than the
+interrupt itself should be communicated via the shared memory region.  Devices
+supporting multiple MSI vectors can use different vectors to indicate different
+events have occurred.  The semantics of interrupt vectors are left to the
+user's discretion.
+
+
+Usage in the Guest
+------------------
+
+The shared memory device is intended to be used with the provided UIO driver.
+Very little configuration is needed.  The guest should map BAR0 to access the
+registers (an array of 32-bit ints allows simple writing) and map BAR2 to
+access the shared memory region itself.  The size of the shared memory region
+is specified when the guest (or shared memory server) is started.  A guest may
+map the whole shared memory region or only part of it.

exec.c

@@ -2808,6 +2808,49 @@ static ram_addr_t last_ram_offset(void)
     return last;
 }
 
+ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
+                        ram_addr_t size, void *host)
+{
+    RAMBlock *new_block, *block;
+
+    size = TARGET_PAGE_ALIGN(size);
+    new_block = qemu_mallocz(sizeof(*new_block));
+
+    if (dev && dev->parent_bus && dev->parent_bus->info->get_dev_path) {
+        char *id = dev->parent_bus->info->get_dev_path(dev);
+        if (id) {
+            snprintf(new_block->idstr, sizeof(new_block->idstr), "%s/", id);
+            qemu_free(id);
+        }
+    }
+    pstrcat(new_block->idstr, sizeof(new_block->idstr), name);
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        if (!strcmp(block->idstr, new_block->idstr)) {
+            fprintf(stderr, "RAMBlock \"%s\" already registered, abort!\n",
+                    new_block->idstr);
+            abort();
+        }
+    }
+
+    new_block->host = host;
+
+    new_block->offset = find_ram_offset(size);
+    new_block->length = size;
+
+    QLIST_INSERT_HEAD(&ram_list.blocks, new_block, next);
+
+    ram_list.phys_dirty = qemu_realloc(ram_list.phys_dirty,
+                                       last_ram_offset() >> TARGET_PAGE_BITS);
+    memset(ram_list.phys_dirty + (new_block->offset >> TARGET_PAGE_BITS),
+           0xff, size >> TARGET_PAGE_BITS);
+
+    if (kvm_enabled())
+        kvm_setup_guest_memory(new_block->host, size);
+
+    return new_block->offset;
+}
+
 ram_addr_t qemu_ram_alloc(DeviceState *dev, const char *name, ram_addr_t size)
 {
     RAMBlock *new_block, *block;

hw/hw.h

@@ -264,6 +264,8 @@ int register_savevm_live(DeviceState *dev,
                          void *opaque);
 
 void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque);
+void register_device_unmigratable(DeviceState *dev, const char *idstr,
+                                                                void *opaque);
 
 typedef void QEMUResetHandler(void *opaque);
 

hw/ide/core.c

@@ -1643,6 +1643,21 @@ static void ide_atapi_cmd(IDEState *s)
             ide_atapi_cmd_reply(s, len, max_len);
             break;
         }
+    case GPCMD_GET_EVENT_STATUS_NOTIFICATION:
+        max_len = ube16_to_cpu(packet + 7);
+
+        if (packet[1] & 0x01) { /* polling */
+            /* We don't support any event class (yet). */
+            cpu_to_ube16(buf, 0x00); /* No event descriptor returned */
+            buf[2] = 0x80;           /* No Event Available (NEA) */
+            buf[3] = 0x00;           /* Empty supported event classes */
+            ide_atapi_cmd_reply(s, 4, max_len);
+        } else { /* asynchronous mode */
+            /* Only polling is supported, asynchronous mode is not. */
+            ide_atapi_cmd_error(s, SENSE_ILLEGAL_REQUEST,
+                                ASC_INV_FIELD_IN_CMD_PACKET);
+        }
+        break;
     default:
         ide_atapi_cmd_error(s, SENSE_ILLEGAL_REQUEST,
                             ASC_ILLEGAL_OPCODE);

hw/ide/pci.c

@@ -40,8 +40,27 @@ void bmdma_cmd_writeb(void *opaque, uint32_t addr, uint32_t val)
     printf("%s: 0x%08x\n", __func__, val);
 #endif
     if (!(val & BM_CMD_START)) {
-        /* XXX: do it better */
-        ide_dma_cancel(bm);
+        /*
+         * We can't cancel Scatter Gather DMA in the middle of the
+         * operation or a partial (not full) DMA transfer would reach
+         * the storage so we wait for completion instead (we beahve
+         * like if the DMA was completed by the time the guest trying
+         * to cancel dma with bmdma_cmd_writeb with BM_CMD_START not
+         * set).
+         *
+         * In the future we'll be able to safely cancel the I/O if the
+         * whole DMA operation will be submitted to disk with a single
+         * aio operation with preadv/pwritev.
+         */
+        if (bm->aiocb) {
+            qemu_aio_flush();
+#ifdef DEBUG_IDE
+            if (bm->aiocb)
+                printf("ide_dma_cancel: aiocb still pending");
+            if (bm->status & BM_STATUS_DMAING)
+                printf("ide_dma_cancel: BM_STATUS_DMAING still pending");
+#endif
+        }
         bm->cmd = val & 0x09;
     } else {
         if (!(bm->status & BM_STATUS_DMAING)) {

hw/ivshmem.c

@@ -0,0 +1,829 @@
+/*
+ * Inter-VM Shared Memory PCI device.
+ *
+ * Author:
+ *      Cam Macdonell <cam@cs.ualberta.ca>
+ *
+ * Based On: cirrus_vga.c
+ *          Copyright (c) 2004 Fabrice Bellard
+ *          Copyright (c) 2004 Makoto Suzuki (suzu)
+ *
+ *      and rtl8139.c
+ *          Copyright (c) 2006 Igor Kovalenko
+ *
+ * This code is licensed under the GNU GPL v2.
+ */
+#include "hw.h"
+#include "pc.h"
+#include "pci.h"
+#include "msix.h"
+#include "kvm.h"
+
+#include <sys/mman.h>
+#include <sys/types.h>
+
+#define IVSHMEM_IOEVENTFD   0
+#define IVSHMEM_MSI     1
+
+#define IVSHMEM_PEER    0
+#define IVSHMEM_MASTER  1
+
+#define IVSHMEM_REG_BAR_SIZE 0x100
+
+//#define DEBUG_IVSHMEM
+#ifdef DEBUG_IVSHMEM
+#define IVSHMEM_DPRINTF(fmt, ...)        \
+    do {printf("IVSHMEM: " fmt, ## __VA_ARGS__); } while (0)
+#else
+#define IVSHMEM_DPRINTF(fmt, ...)
+#endif
+
+typedef struct Peer {
+    int nb_eventfds;
+    int *eventfds;
+} Peer;
+
+typedef struct EventfdEntry {
+    PCIDevice *pdev;
+    int vector;
+} EventfdEntry;
+
+typedef struct IVShmemState {
+    PCIDevice dev;
+    uint32_t intrmask;
+    uint32_t intrstatus;
+    uint32_t doorbell;
+
+    CharDriverState **eventfd_chr;
+    CharDriverState *server_chr;
+    int ivshmem_mmio_io_addr;
+
+    pcibus_t mmio_addr;
+    pcibus_t shm_pci_addr;
+    uint64_t ivshmem_offset;
+    uint64_t ivshmem_size; /* size of shared memory region */
+    int shm_fd; /* shared memory file descriptor */
+
+    Peer *peers;
+    int nb_peers; /* how many guests we have space for */
+    int max_peer; /* maximum numbered peer */
+
+    int vm_id;
+    uint32_t vectors;
+    uint32_t features;
+    EventfdEntry *eventfd_table;
+
+    char * shmobj;
+    char * sizearg;
+    char * role;
+    int role_val;   /* scalar to avoid multiple string comparisons */
+} IVShmemState;
+
+/* registers for the Inter-VM shared memory device */
+enum ivshmem_registers {
+    INTRMASK = 0,
+    INTRSTATUS = 4,
+    IVPOSITION = 8,
+    DOORBELL = 12,
+};
+
+static inline uint32_t ivshmem_has_feature(IVShmemState *ivs,
+                                                    unsigned int feature) {
+    return (ivs->features & (1 << feature));
+}
+
+static inline bool is_power_of_two(uint64_t x) {
+    return (x & (x - 1)) == 0;
+}
+
+static void ivshmem_map(PCIDevice *pci_dev, int region_num,
+                    pcibus_t addr, pcibus_t size, int type)
+{
+    IVShmemState *s = DO_UPCAST(IVShmemState, dev, pci_dev);
+
+    s->shm_pci_addr = addr;
+
+    if (s->ivshmem_offset > 0) {
+        cpu_register_physical_memory(s->shm_pci_addr, s->ivshmem_size,
+                                                            s->ivshmem_offset);
+    }
+
+    IVSHMEM_DPRINTF("guest pci addr = %" FMT_PCIBUS ", guest h/w addr = %"
+        PRIu64 ", size = %" FMT_PCIBUS "\n", addr, s->ivshmem_offset, size);
+
+}
+
+/* accessing registers - based on rtl8139 */
+static void ivshmem_update_irq(IVShmemState *s, int val)
+{
+    int isr;
+    isr = (s->intrstatus & s->intrmask) & 0xffffffff;
+
+    /* don't print ISR resets */
+    if (isr) {
+        IVSHMEM_DPRINTF("Set IRQ to %d (%04x %04x)\n",
+           isr ? 1 : 0, s->intrstatus, s->intrmask);
+    }
+
+    qemu_set_irq(s->dev.irq[0], (isr != 0));
+}
+
+static void ivshmem_IntrMask_write(IVShmemState *s, uint32_t val)
+{
+    IVSHMEM_DPRINTF("IntrMask write(w) val = 0x%04x\n", val);
+
+    s->intrmask = val;
+
+    ivshmem_update_irq(s, val);
+}
+
+static uint32_t ivshmem_IntrMask_read(IVShmemState *s)
+{
+    uint32_t ret = s->intrmask;
+
+    IVSHMEM_DPRINTF("intrmask read(w) val = 0x%04x\n", ret);
+
+    return ret;
+}
+
+static void ivshmem_IntrStatus_write(IVShmemState *s, uint32_t val)
+{
+    IVSHMEM_DPRINTF("IntrStatus write(w) val = 0x%04x\n", val);
+
+    s->intrstatus = val;
+
+    ivshmem_update_irq(s, val);
+    return;
+}
+
+static uint32_t ivshmem_IntrStatus_read(IVShmemState *s)
+{
+    uint32_t ret = s->intrstatus;
+
+    /* reading ISR clears all interrupts */
+    s->intrstatus = 0;
+
+    ivshmem_update_irq(s, 0);
+
+    return ret;
+}
+
+static void ivshmem_io_writew(void *opaque, target_phys_addr_t addr,
+                                                            uint32_t val)
+{
+
+    IVSHMEM_DPRINTF("We shouldn't be writing words\n");
+}
+
+static void ivshmem_io_writel(void *opaque, target_phys_addr_t addr,
+                                                            uint32_t val)
+{
+    IVShmemState *s = opaque;
+
+    uint64_t write_one = 1;
+    uint16_t dest = val >> 16;
+    uint16_t vector = val & 0xff;
+
+    addr &= 0xfc;
+
+    IVSHMEM_DPRINTF("writing to addr " TARGET_FMT_plx "\n", addr);
+    switch (addr)
+    {
+        case INTRMASK:
+            ivshmem_IntrMask_write(s, val);
+            break;
+
+        case INTRSTATUS:
+            ivshmem_IntrStatus_write(s, val);
+            break;
+
+        case DOORBELL:
+            /* check that dest VM ID is reasonable */
+            if (dest > s->max_peer) {
+                IVSHMEM_DPRINTF("Invalid destination VM ID (%d)\n", dest);
+                break;
+            }
+
+            /* check doorbell range */
+            if (vector < s->peers[dest].nb_eventfds) {
+                IVSHMEM_DPRINTF("Writing %" PRId64 " to VM %d on vector %d\n",
+                                                    write_one, dest, vector);
+                if (write(s->peers[dest].eventfds[vector],
+                                                    &(write_one), 8) != 8) {
+                    IVSHMEM_DPRINTF("error writing to eventfd\n");
+                }
+            }
+            break;
+        default:
+            IVSHMEM_DPRINTF("Invalid VM Doorbell VM %d\n", dest);
+    }
+}
+
+static void ivshmem_io_writeb(void *opaque, target_phys_addr_t addr,
+                                                                uint32_t val)
+{
+    IVSHMEM_DPRINTF("We shouldn't be writing bytes\n");
+}
+
+static uint32_t ivshmem_io_readw(void *opaque, target_phys_addr_t addr)
+{
+
+    IVSHMEM_DPRINTF("We shouldn't be reading words\n");
+    return 0;
+}
+
+static uint32_t ivshmem_io_readl(void *opaque, target_phys_addr_t addr)
+{
+
+    IVShmemState *s = opaque;
+    uint32_t ret;
+
+    switch (addr)
+    {
+        case INTRMASK:
+            ret = ivshmem_IntrMask_read(s);
+            break;
+
+        case INTRSTATUS:
+            ret = ivshmem_IntrStatus_read(s);
+            break;
+
+        case IVPOSITION:
+            /* return my VM ID if the memory is mapped */
+            if (s->shm_fd > 0) {
+                ret = s->vm_id;
+            } else {
+                ret = -1;
+            }
+            break;
+
+        default:
+            IVSHMEM_DPRINTF("why are we reading " TARGET_FMT_plx "\n", addr);
+            ret = 0;
+    }
+
+    return ret;
+}
+
+static uint32_t ivshmem_io_readb(void *opaque, target_phys_addr_t addr)
+{
+    IVSHMEM_DPRINTF("We shouldn't be reading bytes\n");
+
+    return 0;
+}
+
+static CPUReadMemoryFunc * const ivshmem_mmio_read[3] = {
+    ivshmem_io_readb,
+    ivshmem_io_readw,
+    ivshmem_io_readl,
+};
+
+static CPUWriteMemoryFunc * const ivshmem_mmio_write[3] = {
+    ivshmem_io_writeb,
+    ivshmem_io_writew,
+    ivshmem_io_writel,
+};
+
+static void ivshmem_receive(void *opaque, const uint8_t *buf, int size)
+{
+    IVShmemState *s = opaque;
+
+    ivshmem_IntrStatus_write(s, *buf);
+
+    IVSHMEM_DPRINTF("ivshmem_receive 0x%02x\n", *buf);
+}
+
+static int ivshmem_can_receive(void * opaque)
+{
+    return 8;
+}
+
+static void ivshmem_event(void *opaque, int event)
+{
+    IVSHMEM_DPRINTF("ivshmem_event %d\n", event);
+}
+
+static void fake_irqfd(void *opaque, const uint8_t *buf, int size) {
+
+    EventfdEntry *entry = opaque;
+    PCIDevice *pdev = entry->pdev;
+
+    IVSHMEM_DPRINTF("interrupt on vector %p %d\n", pdev, entry->vector);
+    msix_notify(pdev, entry->vector);
+}
+
+static CharDriverState* create_eventfd_chr_device(void * opaque, int eventfd,
+                                                                    int vector)
+{
+    /* create a event character device based on the passed eventfd */
+    IVShmemState *s = opaque;
+    CharDriverState * chr;
+
+    chr = qemu_chr_open_eventfd(eventfd);
+
+    if (chr == NULL) {
+        fprintf(stderr, "creating eventfd for eventfd %d failed\n", eventfd);
+        exit(-1);
+    }
+
+    /* if MSI is supported we need multiple interrupts */
+    if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+        s->eventfd_table[vector].pdev = &s->dev;
+        s->eventfd_table[vector].vector = vector;
+
+        qemu_chr_add_handlers(chr, ivshmem_can_receive, fake_irqfd,
+                      ivshmem_event, &s->eventfd_table[vector]);
+    } else {
+        qemu_chr_add_handlers(chr, ivshmem_can_receive, ivshmem_receive,
+                      ivshmem_event, s);
+    }
+
+    return chr;
+
+}
+
+static int check_shm_size(IVShmemState *s, int fd) {
+    /* check that the guest isn't going to try and map more memory than the
+     * the object has allocated return -1 to indicate error */
+
+    struct stat buf;
+
+    fstat(fd, &buf);
+
+    if (s->ivshmem_size > buf.st_size) {
+        fprintf(stderr,
+                "IVSHMEM ERROR: Requested memory size greater"
+                " than shared object size (%" PRIu64 " > %" PRIu64")\n",
+                s->ivshmem_size, (uint64_t)buf.st_size);
+        return -1;
+    } else {
+        return 0;
+    }
+}
+
+/* create the shared memory BAR when we are not using the server, so we can
+ * create the BAR and map the memory immediately */
+static void create_shared_memory_BAR(IVShmemState *s, int fd) {
+
+    void * ptr;
+
+    s->shm_fd = fd;
+
+    ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
+
+    s->ivshmem_offset = qemu_ram_alloc_from_ptr(&s->dev.qdev, "ivshmem.bar2",
+                                                        s->ivshmem_size, ptr);
+
+    /* region for shared memory */
+    pci_register_bar(&s->dev, 2, s->ivshmem_size,
+                                PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_map);
+}
+
+static void close_guest_eventfds(IVShmemState *s, int posn)
+{
+    int i, guest_curr_max;
+
+    guest_curr_max = s->peers[posn].nb_eventfds;
+
+    for (i = 0; i < guest_curr_max; i++) {
+        kvm_set_ioeventfd_mmio_long(s->peers[posn].eventfds[i],
+                    s->mmio_addr + DOORBELL, (posn << 16) | i, 0);
+        close(s->peers[posn].eventfds[i]);
+    }
+
+    qemu_free(s->peers[posn].eventfds);
+    s->peers[posn].nb_eventfds = 0;
+}
+
+static void setup_ioeventfds(IVShmemState *s) {
+
+    int i, j;
+
+    for (i = 0; i <= s->max_peer; i++) {
+        for (j = 0; j < s->peers[i].nb_eventfds; j++) {
+            kvm_set_ioeventfd_mmio_long(s->peers[i].eventfds[j],
+                    s->mmio_addr + DOORBELL, (i << 16) | j, 1);
+        }
+    }
+}
+
+/* this function increase the dynamic storage need to store data about other
+ * guests */
+static void increase_dynamic_storage(IVShmemState *s, int new_min_size) {
+
+    int j, old_nb_alloc;
+
+    old_nb_alloc = s->nb_peers;
+
+    while (new_min_size >= s->nb_peers)
+        s->nb_peers = s->nb_peers * 2;
+
+    IVSHMEM_DPRINTF("bumping storage to %d guests\n", s->nb_peers);
+    s->peers = qemu_realloc(s->peers, s->nb_peers * sizeof(Peer));
+
+    /* zero out new pointers */
+    for (j = old_nb_alloc; j < s->nb_peers; j++) {
+        s->peers[j].eventfds = NULL;
+        s->peers[j].nb_eventfds = 0;
+    }
+}
+
+static void ivshmem_read(void *opaque, const uint8_t * buf, int flags)
+{
+    IVShmemState *s = opaque;
+    int incoming_fd, tmp_fd;
+    int guest_max_eventfd;
+    long incoming_posn;
+
+    memcpy(&incoming_posn, buf, sizeof(long));
+    /* pick off s->server_chr->msgfd and store it, posn should accompany msg */
+    tmp_fd = qemu_chr_get_msgfd(s->server_chr);
+    IVSHMEM_DPRINTF("posn is %ld, fd is %d\n", incoming_posn, tmp_fd);
+
+    /* make sure we have enough space for this guest */
+    if (incoming_posn >= s->nb_peers) {
+        increase_dynamic_storage(s, incoming_posn);
+    }
+
+    if (tmp_fd == -1) {
+        /* if posn is positive and unseen before then this is our posn*/
+        if ((incoming_posn >= 0) &&
+                            (s->peers[incoming_posn].eventfds == NULL)) {
+            /* receive our posn */
+            s->vm_id = incoming_posn;
+            return;
+        } else {
+            /* otherwise an fd == -1 means an existing guest has gone away */
+            IVSHMEM_DPRINTF("posn %ld has gone away\n", incoming_posn);
+            close_guest_eventfds(s, incoming_posn);
+            return;
+        }
+    }
+
+    /* because of the implementation of get_msgfd, we need a dup */
+    incoming_fd = dup(tmp_fd);
+
+    if (incoming_fd == -1) {
+        fprintf(stderr, "could not allocate file descriptor %s\n",
+                                                            strerror(errno));
+        return;
+    }
+
+    /* if the position is -1, then it's shared memory region fd */
+    if (incoming_posn == -1) {
+
+        void * map_ptr;
+
+        s->max_peer = 0;
+
+        if (check_shm_size(s, incoming_fd) == -1) {
+            exit(-1);
+        }
+
+        /* mmap the region and map into the BAR2 */
+        map_ptr = mmap(0, s->ivshmem_size, PROT_READ|PROT_WRITE, MAP_SHARED,
+                                                            incoming_fd, 0);
+        s->ivshmem_offset = qemu_ram_alloc_from_ptr(&s->dev.qdev,
+                                    "ivshmem.bar2", s->ivshmem_size, map_ptr);
+
+        IVSHMEM_DPRINTF("guest pci addr = %" FMT_PCIBUS ", guest h/w addr = %"
+                         PRIu64 ", size = %" PRIu64 "\n", s->shm_pci_addr,
+                         s->ivshmem_offset, s->ivshmem_size);
+
+        if (s->shm_pci_addr > 0) {
+            /* map memory into BAR2 */
+            cpu_register_physical_memory(s->shm_pci_addr, s->ivshmem_size,
+                                                            s->ivshmem_offset);
+        }
+
+        /* only store the fd if it is successfully mapped */
+        s->shm_fd = incoming_fd;
+
+        return;
+    }
+
+    /* each guest has an array of eventfds, and we keep track of how many
+     * guests for each VM */
+    guest_max_eventfd = s->peers[incoming_posn].nb_eventfds;
+
+    if (guest_max_eventfd == 0) {
+        /* one eventfd per MSI vector */
+        s->peers[incoming_posn].eventfds = (int *) qemu_malloc(s->vectors *
+                                                                sizeof(int));
+    }
+
+    /* this is an eventfd for a particular guest VM */
+    IVSHMEM_DPRINTF("eventfds[%ld][%d] = %d\n", incoming_posn,
+                                            guest_max_eventfd, incoming_fd);
+    s->peers[incoming_posn].eventfds[guest_max_eventfd] = incoming_fd;
+
+    /* increment count for particular guest */
+    s->peers[incoming_posn].nb_eventfds++;
+
+    /* keep track of the maximum VM ID */
+    if (incoming_posn > s->max_peer) {
+        s->max_peer = incoming_posn;
+    }
+
+    if (incoming_posn == s->vm_id) {
+        s->eventfd_chr[guest_max_eventfd] = create_eventfd_chr_device(s,
+                   s->peers[s->vm_id].eventfds[guest_max_eventfd],
+                   guest_max_eventfd);
+    }
+
+    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
+        if (kvm_set_ioeventfd_mmio_long(incoming_fd, s->mmio_addr + DOORBELL,
+                        (incoming_posn << 16) | guest_max_eventfd, 1) < 0) {
+            fprintf(stderr, "ivshmem: ioeventfd not available\n");
+        }
+    }
+
+    return;
+}
+
+static void ivshmem_reset(DeviceState *d)
+{
+    IVShmemState *s = DO_UPCAST(IVShmemState, dev.qdev, d);
+
+    s->intrstatus = 0;
+    return;
+}
+
+static void ivshmem_mmio_map(PCIDevice *pci_dev, int region_num,
+                       pcibus_t addr, pcibus_t size, int type)
+{
+    IVShmemState *s = DO_UPCAST(IVShmemState, dev, pci_dev);
+
+    s->mmio_addr = addr;
+    cpu_register_physical_memory(addr + 0, IVSHMEM_REG_BAR_SIZE,
+                                                s->ivshmem_mmio_io_addr);
+
+    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD)) {
+        setup_ioeventfds(s);
+    }
+}
+
+static uint64_t ivshmem_get_size(IVShmemState * s) {
+
+    uint64_t value;
+    char *ptr;
+
+    value = strtoull(s->sizearg, &ptr, 10);
+    switch (*ptr) {
+        case 0: case 'M': case 'm':
+            value <<= 20;
+            break;
+        case 'G': case 'g':
+            value <<= 30;
+            break;
+        default:
+            fprintf(stderr, "qemu: invalid ram size: %s\n", s->sizearg);
+            exit(1);
+    }
+
+    /* BARs must be a power of 2 */
+    if (!is_power_of_two(value)) {
+        fprintf(stderr, "ivshmem: size must be power of 2\n");
+        exit(1);
+    }
+
+    return value;
+}
+
+static void ivshmem_setup_msi(IVShmemState * s) {
+
+    int i;
+
+    /* allocate the MSI-X vectors */
+
+    if (!msix_init(&s->dev, s->vectors, 1, 0)) {
+        pci_register_bar(&s->dev, 1,
+                         msix_bar_size(&s->dev),
+                         PCI_BASE_ADDRESS_SPACE_MEMORY,
+                         msix_mmio_map);
+        IVSHMEM_DPRINTF("msix initialized (%d vectors)\n", s->vectors);
+    } else {
+        IVSHMEM_DPRINTF("msix initialization failed\n");
+        exit(1);
+    }
+
+    /* 'activate' the vectors */
+    for (i = 0; i < s->vectors; i++) {
+        msix_vector_use(&s->dev, i);
+    }
+
+    /* allocate Qemu char devices for receiving interrupts */
+    s->eventfd_table = qemu_mallocz(s->vectors * sizeof(EventfdEntry));
+}
+
+static void ivshmem_save(QEMUFile* f, void *opaque)
+{
+    IVShmemState *proxy = opaque;
+
+    IVSHMEM_DPRINTF("ivshmem_save\n");
+    pci_device_save(&proxy->dev, f);
+
+    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
+        msix_save(&proxy->dev, f);
+    } else {
+        qemu_put_be32(f, proxy->intrstatus);
+        qemu_put_be32(f, proxy->intrmask);
+    }
+
+}
+
+static int ivshmem_load(QEMUFile* f, void *opaque, int version_id)
+{
+    IVSHMEM_DPRINTF("ivshmem_load\n");
+
+    IVShmemState *proxy = opaque;
+    int ret, i;
+
+    if (version_id > 0) {
+        return -EINVAL;
+    }
+
+    if (proxy->role_val == IVSHMEM_PEER) {
+        fprintf(stderr, "ivshmem: 'peer' devices are not migratable\n");
+        return -EINVAL;
+    }
+
+    ret = pci_device_load(&proxy->dev, f);
+    if (ret) {
+        return ret;
+    }
+
+    if (ivshmem_has_feature(proxy, IVSHMEM_MSI)) {
+        msix_load(&proxy->dev, f);
+        for (i = 0; i < proxy->vectors; i++) {
+            msix_vector_use(&proxy->dev, i);
+        }
+    } else {
+        proxy->intrstatus = qemu_get_be32(f);
+        proxy->intrmask = qemu_get_be32(f);
+    }
+
+    return 0;
+}
+
+static int pci_ivshmem_init(PCIDevice *dev)
+{
+    IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev);
+    uint8_t *pci_conf;
+
+    if (s->sizearg == NULL)
+        s->ivshmem_size = 4 << 20; /* 4 MB default */
+    else {
+        s->ivshmem_size = ivshmem_get_size(s);
+    }
+
+    register_savevm(&s->dev.qdev, "ivshmem", 0, 0, ivshmem_save, ivshmem_load,
+                                                                        dev);
+
+    /* IRQFD requires MSI */
+    if (ivshmem_has_feature(s, IVSHMEM_IOEVENTFD) &&
+        !ivshmem_has_feature(s, IVSHMEM_MSI)) {
+        fprintf(stderr, "ivshmem: ioeventfd/irqfd requires MSI\n");
+        exit(1);
+    }
+
+    /* check that role is reasonable */
+    if (s->role) {
+        if (strncmp(s->role, "peer", 5) == 0) {
+            s->role_val = IVSHMEM_PEER;
+        } else if (strncmp(s->role, "master", 7) == 0) {
+            s->role_val = IVSHMEM_MASTER;
+        } else {
+            fprintf(stderr, "ivshmem: 'role' must be 'peer' or 'master'\n");
+            exit(1);
+        }
+    } else {
+        s->role_val = IVSHMEM_MASTER; /* default */
+    }
+
+    if (s->role_val == IVSHMEM_PEER) {
+        register_device_unmigratable(&s->dev.qdev, "ivshmem", s);
+    }
+
+    pci_conf = s->dev.config;
+    pci_config_set_vendor_id(pci_conf, PCI_VENDOR_ID_REDHAT_QUMRANET);
+    pci_conf[0x02] = 0x10;
+    pci_conf[0x03] = 0x11;
+    pci_conf[PCI_COMMAND] = PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
+    pci_config_set_class(pci_conf, PCI_CLASS_MEMORY_RAM);
+    pci_conf[PCI_HEADER_TYPE] = PCI_HEADER_TYPE_NORMAL;
+
+    pci_config_set_interrupt_pin(pci_conf, 1);
+
+    s->shm_pci_addr = 0;
+    s->ivshmem_offset = 0;
+    s->shm_fd = 0;
+
+    s->ivshmem_mmio_io_addr = cpu_register_io_memory(ivshmem_mmio_read,
+                                    ivshmem_mmio_write, s);
+    /* region for registers*/
+    pci_register_bar(&s->dev, 0, IVSHMEM_REG_BAR_SIZE,
+                           PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_mmio_map);
+
+    if ((s->server_chr != NULL) &&
+                        (strncmp(s->server_chr->filename, "unix:", 5) == 0)) {
+        /* if we get a UNIX socket as the parameter we will talk
+         * to the ivshmem server to receive the memory region */
+
+        if (s->shmobj != NULL) {
+            fprintf(stderr, "WARNING: do not specify both 'chardev' "
+                                                "and 'shm' with ivshmem\n");
+        }
+
+        IVSHMEM_DPRINTF("using shared memory server (socket = %s)\n",
+                                                    s->server_chr->filename);
+
+        if (ivshmem_has_feature(s, IVSHMEM_MSI)) {
+            ivshmem_setup_msi(s);
+        }
+
+        /* we allocate enough space for 16 guests and grow as needed */
+        s->nb_peers = 16;
+        s->vm_id = -1;
+
+        /* allocate/initialize space for interrupt handling */
+        s->peers = qemu_mallocz(s->nb_peers * sizeof(Peer));
+
+        pci_register_bar(&s->dev, 2, s->ivshmem_size,
+                                PCI_BASE_ADDRESS_SPACE_MEMORY, ivshmem_map);
+
+        s->eventfd_chr = qemu_mallocz(s->vectors * sizeof(CharDriverState *));
+
+        qemu_chr_add_handlers(s->server_chr, ivshmem_can_receive, ivshmem_read,
+                     ivshmem_event, s);
+    } else {
+        /* just map the file immediately, we're not using a server */
+        int fd;
+
+        if (s->shmobj == NULL) {
+            fprintf(stderr, "Must specify 'chardev' or 'shm' to ivshmem\n");
+        }
+
+        IVSHMEM_DPRINTF("using shm_open (shm object = %s)\n", s->shmobj);
+
+        /* try opening with O_EXCL and if it succeeds zero the memory
+         * by truncating to 0 */
+        if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR|O_EXCL,
+                        S_IRWXU|S_IRWXG|S_IRWXO)) > 0) {
+           /* truncate file to length PCI device's memory */
+            if (ftruncate(fd, s->ivshmem_size) != 0) {
+                fprintf(stderr, "ivshmem: could not truncate shared file\n");
+            }
+
+        } else if ((fd = shm_open(s->shmobj, O_CREAT|O_RDWR,
+                        S_IRWXU|S_IRWXG|S_IRWXO)) < 0) {
+            fprintf(stderr, "ivshmem: could not open shared file\n");
+            exit(-1);
+
+        }
+
+        if (check_shm_size(s, fd) == -1) {
+            exit(-1);
+        }
+
+        create_shared_memory_BAR(s, fd);
+
+    }
+
+    return 0;
+}
+
+static int pci_ivshmem_uninit(PCIDevice *dev)
+{
+    IVShmemState *s = DO_UPCAST(IVShmemState, dev, dev);
+
+    cpu_unregister_io_memory(s->ivshmem_mmio_io_addr);
+    unregister_savevm(&dev->qdev, "ivshmem", s);
+
+    return 0;
+}
+
+static PCIDeviceInfo ivshmem_info = {
+    .qdev.name  = "ivshmem",
+    .qdev.size  = sizeof(IVShmemState),
+    .qdev.reset = ivshmem_reset,
+    .init       = pci_ivshmem_init,
+    .exit       = pci_ivshmem_uninit,
+    .qdev.props = (Property[]) {
+        DEFINE_PROP_CHR("chardev", IVShmemState, server_chr),
+        DEFINE_PROP_STRING("size", IVShmemState, sizearg),
+        DEFINE_PROP_UINT32("vectors", IVShmemState, vectors, 1),
+        DEFINE_PROP_BIT("ioeventfd", IVShmemState, features, IVSHMEM_IOEVENTFD, false),
+        DEFINE_PROP_BIT("msi", IVShmemState, features, IVSHMEM_MSI, true),
+        DEFINE_PROP_STRING("shm", IVShmemState, shmobj),
+        DEFINE_PROP_STRING("role", IVShmemState, role),
+        DEFINE_PROP_END_OF_LIST(),
+    }
+};
+
+static void ivshmem_register_devices(void)
+{
+    pci_qdev_register(&ivshmem_info);
+}
+
+device_init(ivshmem_register_devices)

hw/scsi-disk.c

@@ -485,16 +485,26 @@ static int scsi_disk_emulate_inquiry(SCSIRequest *req, uint8_t *outbuf)
     return buflen;
 }
 
-static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p)
+static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p,
+                           int page_control)
 {
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev);
     BlockDriverState *bdrv = s->bs;
     int cylinders, heads, secs;
 
+    /*
+     * If Changeable Values are requested, a mask denoting those mode parameters
+     * that are changeable shall be returned. As we currently don't support
+     * parameter changes via MODE_SELECT all bits are returned set to zero.
+     * The buffer was already menset to zero by the caller of this function.
+     */
     switch (page) {
     case 4: /* Rigid disk device geometry page. */
         p[0] = 4;
         p[1] = 0x16;
+        if (page_control == 1) { /* Changeable Values */
+            return p[1] + 2;
+        }
         /* if a geometry hint is available, use it */
         bdrv_get_geometry_hint(bdrv, &cylinders, &heads, &secs);
         p[2] = (cylinders >> 16) & 0xff;
@@ -519,11 +529,14 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p)
         /* Medium rotation rate [rpm], 5400 rpm */
         p[20] = (5400 >> 8) & 0xff;
         p[21] = 5400 & 0xff;
-        return 0x16;
+        return p[1] + 2;
 
     case 5: /* Flexible disk device geometry page. */
         p[0] = 5;
         p[1] = 0x1e;
+        if (page_control == 1) { /* Changeable Values */
+            return p[1] + 2;
+        }
         /* Transfer rate [kbit/s], 5Mbit/s */
         p[2] = 5000 >> 8;
         p[3] = 5000 & 0xff;
@@ -555,21 +568,27 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p)
         /* Medium rotation rate [rpm], 5400 rpm */
         p[28] = (5400 >> 8) & 0xff;
         p[29] = 5400 & 0xff;
-        return 0x1e;
+        return p[1] + 2;
 
     case 8: /* Caching page.  */
         p[0] = 8;
         p[1] = 0x12;
+        if (page_control == 1) { /* Changeable Values */
+            return p[1] + 2;
+        }
         if (bdrv_enable_write_cache(s->bs)) {
             p[2] = 4; /* WCE */
         }
-        return 20;
+        return p[1] + 2;
 
     case 0x2a: /* CD Capabilities and Mechanical Status page. */
         if (bdrv_get_type_hint(bdrv) != BDRV_TYPE_CDROM)
             return 0;
         p[0] = 0x2a;
         p[1] = 0x14;
+        if (page_control == 1) { /* Changeable Values */
+            return p[1] + 2;
+        }
         p[2] = 3; // CD-R & CD-RW read
         p[3] = 0; // Writing not supported
         p[4] = 0x7f; /* Audio, composite, digital out,
@@ -593,7 +612,7 @@ static int mode_sense_page(SCSIRequest *req, int page, uint8_t *p)
         p[19] = (16 * 176) & 0xff;
         p[20] = (16 * 176) >> 8; // 16x write speed current
         p[21] = (16 * 176) & 0xff;
-        return 22;
+        return p[1] + 2;
 
     default:
         return 0;
@@ -604,29 +623,46 @@ static int scsi_disk_emulate_mode_sense(SCSIRequest *req, uint8_t *outbuf)
 {
     SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev);
     uint64_t nb_sectors;
-    int page, dbd, buflen;
+    int page, dbd, buflen, page_control;
     uint8_t *p;
+    uint8_t dev_specific_param;
 
     dbd = req->cmd.buf[1]  & 0x8;
     page = req->cmd.buf[2] & 0x3f;
-    DPRINTF("Mode Sense (page %d, len %zd)\n", page, req->cmd.xfer);
+    page_control = (req->cmd.buf[2] & 0xc0) >> 6;
+    DPRINTF("Mode Sense(%d) (page %d, len %d, page_control %d)\n",
+        (req->cmd.buf[0] == MODE_SENSE) ? 6 : 10, page, len, page_control);
     memset(outbuf, 0, req->cmd.xfer);
     p = outbuf;
 
-    p[1] = 0; /* Default media type.  */
-    p[3] = 0; /* Block descriptor length.  */
     if (bdrv_is_read_only(s->bs)) {
-        p[2] = 0x80; /* Readonly.  */
+        dev_specific_param = 0x80; /* Readonly.  */
+    } else {
+        dev_specific_param = 0x00;
+    }
+
+    if (req->cmd.buf[0] == MODE_SENSE) {
+        p[1] = 0; /* Default media type.  */
+        p[2] = dev_specific_param;
+        p[3] = 0; /* Block descriptor length.  */
+        p += 4;
+    } else { /* MODE_SENSE_10 */
+        p[2] = 0; /* Default media type.  */
+        p[3] = dev_specific_param;
+        p[6] = p[7] = 0; /* Block descriptor length.  */
+        p += 8;
     }
-    p += 4;
 
     bdrv_get_geometry(s->bs, &nb_sectors);
-    if ((~dbd) & nb_sectors) {
-        outbuf[3] = 8; /* Block descriptor length  */
+    if (!dbd && nb_sectors) {
+        if (req->cmd.buf[0] == MODE_SENSE) {
+            outbuf[3] = 8; /* Block descriptor length  */
+        } else { /* MODE_SENSE_10 */
+            outbuf[7] = 8; /* Block descriptor length  */
+        }
         nb_sectors /= s->cluster_size;
-        nb_sectors--;
         if (nb_sectors > 0xffffff)
-            nb_sectors = 0xffffff;
+            nb_sectors = 0;
         p[0] = 0; /* media density code */
         p[1] = (nb_sectors >> 16) & 0xff;
         p[2] = (nb_sectors >> 8) & 0xff;
@@ -638,21 +674,37 @@ static int scsi_disk_emulate_mode_sense(SCSIRequest *req, uint8_t *outbuf)
         p += 8;
     }
 
+    if (page_control == 3) { /* Saved Values */
+        return -1; /* ILLEGAL_REQUEST */
+    }
+
     switch (page) {
     case 0x04:
     case 0x05:
     case 0x08:
     case 0x2a:
-        p += mode_sense_page(req, page, p);
+        p += mode_sense_page(req, page, p, page_control);
         break;
     case 0x3f:
-        p += mode_sense_page(req, 0x08, p);
-        p += mode_sense_page(req, 0x2a, p);
+        p += mode_sense_page(req, 0x08, p, page_control);
+        p += mode_sense_page(req, 0x2a, p, page_control);
         break;
+    default:
+        return -1; /* ILLEGAL_REQUEST */
     }
 
     buflen = p - outbuf;
-    outbuf[0] = buflen - 4;
+    /*
+     * The mode data length field specifies the length in bytes of the
+     * following data that is available to be transferred. The mode data
+     * length does not include itself.
+     */
+    if (req->cmd.buf[0] == MODE_SENSE) {
+        outbuf[0] = buflen - 1;
+    } else { /* MODE_SENSE_10 */
+        outbuf[0] = ((buflen - 2) >> 8) & 0xff;
+        outbuf[1] = (buflen - 2) & 0xff;
+    }
     if (buflen > req->cmd.xfer)
         buflen = req->cmd.xfer;
     return buflen;

hw/virtio-blk.c

@@ -28,6 +28,7 @@ typedef struct VirtIOBlock
     BlockConf *conf;
     unsigned short sector_mask;
     char sn[BLOCK_SERIAL_STRLEN];
+    DeviceState *qdev;
 } VirtIOBlock;
 
 static VirtIOBlock *to_virtio_blk(VirtIODevice *vdev)
@@ -479,6 +480,11 @@ static int virtio_blk_load(QEMUFile *f, void *opaque, int version_id)
         qemu_get_buffer(f, (unsigned char*)&req->elem, sizeof(req->elem));
         req->next = s->rq;
         s->rq = req;
+
+        virtqueue_map_sg(req->elem.in_sg, req->elem.in_addr,
+            req->elem.in_num, 1);
+        virtqueue_map_sg(req->elem.out_sg, req->elem.out_addr,
+            req->elem.out_num, 0);
     }
 
     return 0;
@@ -522,9 +528,16 @@ VirtIODevice *virtio_blk_init(DeviceState *dev, BlockConf *conf)
     s->vq = virtio_add_queue(&s->vdev, 128, virtio_blk_handle_output);
 
     qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
+    s->qdev = dev;
     register_savevm(dev, "virtio-blk", virtio_blk_id++, 2,
                     virtio_blk_save, virtio_blk_load, s);
     bdrv_set_removable(s->bs, 0);
 
     return &s->vdev;
 }
+
+void virtio_blk_exit(VirtIODevice *vdev)
+{
+    VirtIOBlock *s = to_virtio_blk(vdev);
+    unregister_savevm(s->qdev, "virtio-blk", s);
+}

hw/virtio-pci.c

@@ -569,6 +569,7 @@ static int virtio_blk_exit_pci(PCIDevice *pci_dev)
 {
     VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
 
+    virtio_blk_exit(proxy->vdev);
     blockdev_mark_auto_del(proxy->block.bs);
     return virtio_exit_pci(pci_dev);
 }

hw/virtio.c

@@ -360,11 +360,26 @@ int virtqueue_avail_bytes(VirtQueue *vq, int in_bytes, int out_bytes)
     return 0;
 }
 
+void virtqueue_map_sg(struct iovec *sg, target_phys_addr_t *addr,
+    size_t num_sg, int is_write)
+{
+    unsigned int i;
+    target_phys_addr_t len;
+
+    for (i = 0; i < num_sg; i++) {
+        len = sg[i].iov_len;
+        sg[i].iov_base = cpu_physical_memory_map(addr[i], &len, is_write);
+        if (sg[i].iov_base == NULL || len != sg[i].iov_len) {
+            fprintf(stderr, "virtio: trying to map MMIO memory\n");
+            exit(1);
+        }
+    }
+}
+
 int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
 {
     unsigned int i, head, max;
     target_phys_addr_t desc_pa = vq->vring.desc;
-    target_phys_addr_t len;
 
     if (!virtqueue_num_heads(vq, vq->last_avail_idx))
         return 0;
@@ -388,29 +403,20 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
         i = 0;
     }
 
+    /* Collect all the descriptors */
     do {
         struct iovec *sg;
-        int is_write = 0;
 
         if (vring_desc_flags(desc_pa, i) & VRING_DESC_F_WRITE) {
             elem->in_addr[elem->in_num] = vring_desc_addr(desc_pa, i);
             sg = &elem->in_sg[elem->in_num++];
-            is_write = 1;
-        } else
+        } else {
+            elem->out_addr[elem->out_num] = vring_desc_addr(desc_pa, i);
             sg = &elem->out_sg[elem->out_num++];
-
-        /* Grab the first descriptor, and check it's OK. */
-        sg->iov_len = vring_desc_len(desc_pa, i);
-        len = sg->iov_len;
-
-        sg->iov_base = cpu_physical_memory_map(vring_desc_addr(desc_pa, i),
-                                               &len, is_write);
-
-        if (sg->iov_base == NULL || len != sg->iov_len) {
-            fprintf(stderr, "virtio: trying to map MMIO memory\n");
-            exit(1);
         }
 
+        sg->iov_len = vring_desc_len(desc_pa, i);
+
         /* If we've got too many, that implies a descriptor loop. */
         if ((elem->in_num + elem->out_num) > max) {
             fprintf(stderr, "Looped descriptor");
@@ -418,6 +424,10 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem)
         }
     } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max);
 
+    /* Now map what we have collected */
+    virtqueue_map_sg(elem->in_sg, elem->in_addr, elem->in_num, 1);
+    virtqueue_map_sg(elem->out_sg, elem->out_addr, elem->out_num, 0);
+
     elem->index = head;
 
     vq->inuse++;

hw/virtio.h

@@ -81,6 +81,7 @@ typedef struct VirtQueueElement
     unsigned int out_num;
     unsigned int in_num;
     target_phys_addr_t in_addr[VIRTQUEUE_MAX_SIZE];
+    target_phys_addr_t out_addr[VIRTQUEUE_MAX_SIZE];
     struct iovec in_sg[VIRTQUEUE_MAX_SIZE];
     struct iovec out_sg[VIRTQUEUE_MAX_SIZE];
 } VirtQueueElement;
@@ -142,6 +143,8 @@ void virtqueue_flush(VirtQueue *vq, unsigned int count);
 void virtqueue_fill(VirtQueue *vq, const VirtQueueElement *elem,
                     unsigned int len, unsigned int idx);
 
+void virtqueue_map_sg(struct iovec *sg, target_phys_addr_t *addr,
+    size_t num_sg, int is_write);
 int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem);
 int virtqueue_avail_bytes(VirtQueue *vq, int in_bytes, int out_bytes);
 
@@ -194,6 +197,7 @@ VirtIODevice *virtio_9p_init(DeviceState *dev, V9fsConf *conf);
 
 
 void virtio_net_exit(VirtIODevice *vdev);
+void virtio_blk_exit(VirtIODevice *vdev);
 
 #define DEFINE_VIRTIO_COMMON_FEATURES(_state, _field) \
 	DEFINE_PROP_BIT("indirect_desc", _state, _field, \

kvm-all.c

@@ -1241,6 +1241,38 @@ int kvm_set_signal_mask(CPUState *env, const sigset_t *sigset)
     return r;
 }
 
+int kvm_set_ioeventfd_mmio_long(int fd, uint32_t addr, uint32_t val, bool assign)
+{
+#ifdef KVM_IOEVENTFD
+    int ret;
+    struct kvm_ioeventfd iofd;
+
+    iofd.datamatch = val;
+    iofd.addr = addr;
+    iofd.len = 4;
+    iofd.flags = KVM_IOEVENTFD_FLAG_DATAMATCH;
+    iofd.fd = fd;
+
+    if (!kvm_enabled()) {
+        return -ENOSYS;
+    }
+
+    if (!assign) {
+        iofd.flags |= KVM_IOEVENTFD_FLAG_DEASSIGN;
+    }
+
+    ret = kvm_vm_ioctl(kvm_state, KVM_IOEVENTFD, &iofd);
+
+    if (ret < 0) {
+        return -errno;
+    }
+
+    return 0;
+#else
+    return -ENOSYS;
+#endif
+}
+
 int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
 {
 #ifdef KVM_IOEVENTFD

kvm-stub.c

@@ -136,3 +136,8 @@ int kvm_set_ioeventfd_pio_word(int fd, uint16_t addr, uint16_t val, bool assign)
 {
     return -ENOSYS;
 }
+
+int kvm_set_ioeventfd_mmio_long(int fd, uint32_t adr, uint32_t val, bool assign)
+{
+    return -ENOSYS;
+}

kvm.h

@@ -175,6 +175,7 @@ static inline void cpu_synchronize_post_init(CPUState *env)
 }
 
 #endif
+int kvm_set_ioeventfd_mmio_long(int fd, uint32_t adr, uint32_t val, bool assign);
 
 int kvm_set_ioeventfd_pio_word(int fd, uint16_t adr, uint16_t val, bool assign);
 #endif

linux-user/mmap.c

@@ -225,13 +225,13 @@ static abi_ulong mmap_find_vma_reserved(abi_ulong start, abi_ulong size)
     int prot;
     int looped = 0;
 
-    if (size > reserved_va) {
+    if (size > RESERVED_VA) {
         return (abi_ulong)-1;
     }
 
     last_addr = start;
     for (addr = start; last_addr + size != addr; addr += qemu_host_page_size) {
-        if (last_addr + size >= reserved_va
+        if (last_addr + size >= RESERVED_VA
             || (abi_ulong)(last_addr + size) < last_addr) {
             if (looped) {
                 return (abi_ulong)-1;
@@ -271,7 +271,7 @@ abi_ulong mmap_find_vma(abi_ulong start, abi_ulong size)
 
     size = HOST_PAGE_ALIGN(size);
 
-    if (reserved_va) {
+    if (RESERVED_VA) {
         return mmap_find_vma_reserved(start, size);
     }
 
@@ -651,7 +651,7 @@ int target_munmap(abi_ulong start, abi_ulong len)
     ret = 0;
     /* unmap what we can */
     if (real_start < real_end) {
-        if (reserved_va) {
+        if (RESERVED_VA) {
             mmap_reserve(real_start, real_end - real_start);
         } else {
             ret = munmap(g2h(real_start), real_end - real_start);
@@ -679,7 +679,7 @@ abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
                                      flags,
                                      g2h(new_addr));
 
-        if (reserved_va && host_addr != MAP_FAILED) {
+        if (RESERVED_VA && host_addr != MAP_FAILED) {
             /* If new and old addresses overlap then the above mremap will
                already have failed with EINVAL.  */
             mmap_reserve(old_addr, old_size);
@@ -701,7 +701,7 @@ abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
         }
     } else {
         int prot = 0;
-        if (reserved_va && old_size < new_size) {
+        if (RESERVED_VA && old_size < new_size) {
             abi_ulong addr;
             for (addr = old_addr + old_size;
                  addr < old_addr + new_size;
@@ -711,7 +711,7 @@ abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size,
         }
         if (prot == 0) {
             host_addr = mremap(g2h(old_addr), old_size, new_size, flags);
-            if (host_addr != MAP_FAILED && reserved_va && old_size > new_size) {
+            if (host_addr != MAP_FAILED && RESERVED_VA && old_size > new_size) {
                 mmap_reserve(old_addr + old_size, new_size - old_size);
             }
         } else {

posix-aio-compat.c

@@ -599,6 +599,7 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
     acb->aio_type = QEMU_AIO_IOCTL;
     acb->aio_fildes = fd;
     acb->ev_signo = SIGUSR2;
+    acb->async_context_id = get_async_context_id();
     acb->aio_offset = 0;
     acb->aio_ioctl_buf = buf;
     acb->aio_ioctl_cmd = req;

qemu-char.c

@@ -2087,6 +2087,12 @@ static void tcp_chr_read(void *opaque)
     }
 }
 
+CharDriverState *qemu_chr_open_eventfd(int eventfd){
+
+    return qemu_chr_open_fd(eventfd, eventfd);
+
+}
+
 static void tcp_chr_connect(void *opaque)
 {
     CharDriverState *chr = opaque;

qemu-char.h

@@ -94,6 +94,9 @@ void qemu_chr_info_print(Monitor *mon, const QObject *ret_data);
 void qemu_chr_info(Monitor *mon, QObject **ret_data);
 CharDriverState *qemu_chr_find(const char *name);
 
+/* add an eventfd to the qemu devices that are polled */
+CharDriverState *qemu_chr_open_eventfd(int eventfd);
+
 extern int term_escape_char;
 
 /* async I/O support */

qemu-doc.texi

@@ -706,6 +706,49 @@ Using the @option{-net socket} option, it is possible to make VLANs
 that span several QEMU instances. See @ref{sec_invocation} to have a
 basic example.
 
+@section Other Devices
+
+@subsection Inter-VM Shared Memory device
+
+With KVM enabled on a Linux host, a shared memory device is available.  Guests
+map a POSIX shared memory region into the guest as a PCI device that enables
+zero-copy communication to the application level of the guests.  The basic
+syntax is:
+
+@example
+qemu -device ivshmem,size=<size in format accepted by -m>[,shm=<shm name>]
+@end example
+
+If desired, interrupts can be sent between guest VMs accessing the same shared
+memory region.  Interrupt support requires using a shared memory server and
+using a chardev socket to connect to it.  The code for the shared memory server
+is qemu.git/contrib/ivshmem-server.  An example syntax when using the shared
+memory server is:
+
+@example
+qemu -device ivshmem,size=<size in format accepted by -m>[,chardev=<id>]
+                        [,msi=on][,ioeventfd=on][,vectors=n][,role=peer|master]
+qemu -chardev socket,path=<path>,id=<id>
+@end example
+
+When using the server, the guest will be assigned a VM ID (>=0) that allows guests
+using the same server to communicate via interrupts.  Guests can read their
+VM ID from a device register (see example code).  Since receiving the shared
+memory region from the server is asynchronous, there is a (small) chance the
+guest may boot before the shared memory is attached.  To allow an application
+to ensure shared memory is attached, the VM ID register will return -1 (an
+invalid VM ID) until the memory is attached.  Once the shared memory is
+attached, the VM ID will return the guest's valid VM ID.  With these semantics,
+the guest application can check to ensure the shared memory is attached to the
+guest before proceeding.
+
+The @option{role} argument can be set to either master or peer and will affect
+how the shared memory is migrated.  With @option{role=master}, the guest will
+copy the shared memory on migration to the destination host.  With
+@option{role=peer}, the guest will not be able to migrate with the device attached.
+With the @option{peer} case, the device should be detached and then reattached
+after migration using the PCI hotplug support.
+
 @node direct_linux_boot
 @section Direct Linux Boot
 

qemu-img.c

@@ -783,7 +783,8 @@ static int img_convert(int argc, char **argv)
         goto out;
     }
 
-    out_bs = bdrv_new_open(out_filename, out_fmt, BDRV_O_FLAGS | BDRV_O_RDWR);
+    out_bs = bdrv_new_open(out_filename, out_fmt,
+        BDRV_O_FLAGS | BDRV_O_RDWR | BDRV_O_NO_FLUSH);
     if (!out_bs) {
         ret = -1;
         goto out;
@@ -1286,7 +1287,7 @@ static int img_rebase(int argc, char **argv)
         }
 
         bs_new_backing = bdrv_new("new_backing");
-        ret = bdrv_open(bs_new_backing, out_baseimg, BDRV_O_FLAGS | BDRV_O_RDWR,
+        ret = bdrv_open(bs_new_backing, out_baseimg, BDRV_O_FLAGS,
                         new_backing_drv);
         if (ret) {
             error("Could not open new backing file '%s'", out_baseimg);

qemu-options.hx

@@ -118,7 +118,7 @@ ETEXI
 DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n"
     "       [,cyls=c,heads=h,secs=s[,trans=t]][,snapshot=on|off]\n"
-    "       [,cache=writethrough|writeback|unsafe|none][,format=f]\n"
+    "       [,cache=writethrough|writeback|none|unsafe][,format=f]\n"
     "       [,serial=s][,addr=A][,id=name][,aio=threads|native]\n"
     "       [,readonly=on|off]\n"
     "                use 'file' as a drive image\n", QEMU_ARCH_ALL)

savevm.c

@@ -1018,6 +1018,7 @@ typedef struct SaveStateEntry {
     const VMStateDescription *vmsd;
     void *opaque;
     CompatEntry *compat;
+    int no_migrate;
 } SaveStateEntry;
 
 
@@ -1081,6 +1082,7 @@ int register_savevm_live(DeviceState *dev,
     se->load_state = load_state;
     se->opaque = opaque;
     se->vmsd = NULL;
+    se->no_migrate = 0;
 
     if (dev && dev->parent_bus && dev->parent_bus->info->get_dev_path) {
         char *id = dev->parent_bus->info->get_dev_path(dev);
@@ -1139,11 +1141,39 @@ void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque)
     QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) {
         if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) {
             QTAILQ_REMOVE(&savevm_handlers, se, entry);
+            if (se->compat) {
+                qemu_free(se->compat);
+            }
             qemu_free(se);
         }
     }
 }
 
+/* mark a device as not to be migrated, that is the device should be
+   unplugged before migration */
+void register_device_unmigratable(DeviceState *dev, const char *idstr,
+                                                            void *opaque)
+{
+    SaveStateEntry *se;
+    char id[256] = "";
+
+    if (dev && dev->parent_bus && dev->parent_bus->info->get_dev_path) {
+        char *path = dev->parent_bus->info->get_dev_path(dev);
+        if (path) {
+            pstrcpy(id, sizeof(id), path);
+            pstrcat(id, sizeof(id), "/");
+            qemu_free(path);
+        }
+    }
+    pstrcat(id, sizeof(id), idstr);
+
+    QTAILQ_FOREACH(se, &savevm_handlers, entry) {
+        if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) {
+            se->no_migrate = 1;
+        }
+    }
+}
+
 int vmstate_register_with_alias_id(DeviceState *dev, int instance_id,
                                    const VMStateDescription *vmsd,
                                    void *opaque, int alias_id,
@@ -1206,6 +1236,9 @@ void vmstate_unregister(DeviceState *dev, const VMStateDescription *vmsd,
     QTAILQ_FOREACH_SAFE(se, &savevm_handlers, entry, new_se) {
         if (se->vmsd == vmsd && se->opaque == opaque) {
             QTAILQ_REMOVE(&savevm_handlers, se, entry);
+            if (se->compat) {
+                qemu_free(se->compat);
+            }
             qemu_free(se);
         }
     }
@@ -1347,13 +1380,19 @@ static int vmstate_load(QEMUFile *f, SaveStateEntry *se, int version_id)
     return vmstate_load_state(f, se->vmsd, se->opaque, version_id);
 }
 
-static void vmstate_save(QEMUFile *f, SaveStateEntry *se)
+static int vmstate_save(QEMUFile *f, SaveStateEntry *se)
 {
+    if (se->no_migrate) {
+        return -1;
+    }
+
     if (!se->vmsd) {         /* Old style */
         se->save_state(f, se->opaque);
-        return;
+        return 0;
     }
     vmstate_save_state(f,se->vmsd, se->opaque);
+
+    return 0;
 }
 
 #define QEMU_VM_FILE_MAGIC           0x5145564d
@@ -1448,6 +1487,7 @@ int qemu_savevm_state_iterate(Monitor *mon, QEMUFile *f)
 int qemu_savevm_state_complete(Monitor *mon, QEMUFile *f)
 {
     SaveStateEntry *se;
+    int r;
 
     cpu_synchronize_all_states();
 
@@ -1480,7 +1520,11 @@ int qemu_savevm_state_complete(Monitor *mon, QEMUFile *f)
         qemu_put_be32(f, se->instance_id);
         qemu_put_be32(f, se->version_id);
 
-        vmstate_save(f, se);
+        r = vmstate_save(f, se);
+        if (r < 0) {
+            monitor_printf(mon, "cannot migrate with device '%s'\n", se->idstr);
+            return r;
+        }
     }
 
     qemu_put_byte(f, QEMU_VM_EOF);