Update VERSION for 1.7.2 release

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>

VERSION

@@ -1 +1 @@
-1.7.0
+1.7.2

arch_init.c

@@ -857,64 +857,60 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
 {
     ram_addr_t addr;
     int flags, ret = 0;
-    int error;
     static uint64_t seq_iter;
 
     seq_iter++;
 
-    if (version_id < 4 || version_id > 4) {
+    if (version_id != 4) {
         return -EINVAL;
     }
 
-    do {
+    while (!ret) {
         addr = qemu_get_be64(f);
 
         flags = addr & ~TARGET_PAGE_MASK;
         addr &= TARGET_PAGE_MASK;
 
         if (flags & RAM_SAVE_FLAG_MEM_SIZE) {
-            if (version_id == 4) {
+            /* Synchronize RAM block list */
-                /* Synchronize RAM block list */
+            char id[256];
-                char id[256];
+            ram_addr_t length;
-                ram_addr_t length;
+            ram_addr_t total_ram_bytes = addr;
-                ram_addr_t total_ram_bytes = addr;
 
-                while (total_ram_bytes) {
+            while (total_ram_bytes) {
-                    RAMBlock *block;
+                RAMBlock *block;
-                    uint8_t len;
+                uint8_t len;
 
-                    len = qemu_get_byte(f);
+                len = qemu_get_byte(f);
-                    qemu_get_buffer(f, (uint8_t *)id, len);
+                qemu_get_buffer(f, (uint8_t *)id, len);
-                    id[len] = 0;
+                id[len] = 0;
-                    length = qemu_get_be64(f);
+                length = qemu_get_be64(f);
 
-                    QTAILQ_FOREACH(block, &ram_list.blocks, next) {
+                QTAILQ_FOREACH(block, &ram_list.blocks, next) {
-                        if (!strncmp(id, block->idstr, sizeof(id))) {
+                    if (!strncmp(id, block->idstr, sizeof(id))) {
-                            if (block->length != length) {
+                        if (block->length != length) {
-                                fprintf(stderr,
+                            fprintf(stderr,
-                                        "Length mismatch: %s: " RAM_ADDR_FMT
+                                    "Length mismatch: %s: " RAM_ADDR_FMT
-                                        " in != " RAM_ADDR_FMT "\n", id, length,
+                                    " in != " RAM_ADDR_FMT "\n", id, length,
-                                        block->length);
+                                    block->length);
-                                ret =  -EINVAL;
+                            ret =  -EINVAL;
-                                goto done;
-                            }
-                            break;
                         }
+                        break;
                     }
-
-                    if (!block) {
-                        fprintf(stderr, "Unknown ramblock \"%s\", cannot "
-                                "accept migration\n", id);
-                        ret = -EINVAL;
-                        goto done;
-                    }
-
-                    total_ram_bytes -= length;
                 }
-            }
-        }
 
-        if (flags & RAM_SAVE_FLAG_COMPRESS) {
+                if (!block) {
+                    fprintf(stderr, "Unknown ramblock \"%s\", cannot "
+                            "accept migration\n", id);
+                    ret = -EINVAL;
+                }
+                if (ret) {
+                    break;
+                }
+
+                total_ram_bytes -= length;
+            }
+        } else if (flags & RAM_SAVE_FLAG_COMPRESS) {
             void *host;
             uint8_t ch;
 
@@ -941,20 +937,24 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
             }
 
             if (load_xbzrle(f, addr, host) < 0) {
+                error_report("Failed to decompress XBZRLE page at "
+                             RAM_ADDR_FMT, addr);
                 ret = -EINVAL;
-                goto done;
+                break;
             }
         } else if (flags & RAM_SAVE_FLAG_HOOK) {
             ram_control_load_hook(f, flags);
+        } else if (flags & RAM_SAVE_FLAG_EOS) {
+            /* normal exit */
+            break;
+        } else {
+            error_report("Unknown migration flags: %#x", flags);
+            ret = -EINVAL;
+            break;
         }
-        error = qemu_file_get_error(f);
+        ret = qemu_file_get_error(f);
-        if (error) {
+    }
-            ret = error;
-            goto done;
-        }
-    } while (!(flags & RAM_SAVE_FLAG_EOS));
 
-done:
     DPRINTF("Completed load of VM with exit code %d seq iteration "
             "%" PRIu64 "\n", ret, seq_iter);
     return ret;

async.c

@@ -117,15 +117,21 @@ void qemu_bh_schedule_idle(QEMUBH *bh)
 
 void qemu_bh_schedule(QEMUBH *bh)
 {
+    AioContext *ctx;
+
     if (bh->scheduled)
         return;
+    ctx = bh->ctx;
     bh->idle = 0;
-    /* Make sure that idle & any writes needed by the callback are done
+    /* Make sure that:
-     * before the locations are read in the aio_bh_poll.
+     * 1. idle & any writes needed by the callback are done before the
+     *    locations are read in the aio_bh_poll.
+     * 2. ctx is loaded before scheduled is set and the callback has a chance
+     *    to execute.
      */
-    smp_wmb();
+    smp_mb();
     bh->scheduled = 1;
-    aio_notify(bh->ctx);
+    aio_notify(ctx);
 }
 
 

block.c

@@ -966,14 +966,14 @@ fail:
  */
 int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
 {
-    char backing_filename[PATH_MAX];
+    char *backing_filename = g_malloc0(PATH_MAX);
-    int back_flags, ret;
+    int back_flags, ret = 0;
     BlockDriver *back_drv = NULL;
     Error *local_err = NULL;
 
     if (bs->backing_hd != NULL) {
         QDECREF(options);
-        return 0;
+        goto free_exit;
     }
 
     /* NULL means an empty set of options */
@@ -986,10 +986,9 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         backing_filename[0] = '\0';
     } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
         QDECREF(options);
-        return 0;
+        goto free_exit;
     } else {
-        bdrv_get_full_backing_filename(bs, backing_filename,
+        bdrv_get_full_backing_filename(bs, backing_filename, PATH_MAX);
-                                       sizeof(backing_filename));
     }
 
     bs->backing_hd = bdrv_new("");
@@ -1012,11 +1011,14 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *options, Error **errp)
         error_setg(errp, "Could not open backing file: %s",
                    error_get_pretty(local_err));
         error_free(local_err);
-        return ret;
+        goto free_exit;
     }
     pstrcpy(bs->backing_file, sizeof(bs->backing_file),
             bs->backing_hd->file->filename);
-    return 0;
+    ret = 0;
+free_exit:
+    g_free(backing_filename);
+    return ret;
 }
 
 /*
@@ -1032,7 +1034,8 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
 {
     int ret;
     /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
-    char tmp_filename[PATH_MAX + 1];
+    char *backing_filename = NULL;
+    char *tmp_filename = g_malloc0(PATH_MAX + 1);
     BlockDriverState *file = NULL;
     QDict *file_options = NULL;
     const char *drvname;
@@ -1052,7 +1055,7 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
         int64_t total_size;
         BlockDriver *bdrv_qcow2;
         QEMUOptionParameter *create_options;
-        char backing_filename[PATH_MAX];
+        backing_filename = g_malloc0(PATH_MAX);
 
         if (qdict_size(options) != 0) {
             error_setg(errp, "Can't use snapshot=on with driver-specific options");
@@ -1064,9 +1067,9 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
         /* if snapshot, we create a temporary backing file and open it
            instead of opening 'filename' directly */
 
-        /* if there is a backing file, use it */
         bs1 = bdrv_new("");
-        ret = bdrv_open(bs1, filename, NULL, 0, drv, &local_err);
+        ret = bdrv_open(bs1, filename, NULL, BDRV_O_NO_BACKING, drv,
+                        &local_err);
         if (ret < 0) {
             bdrv_unref(bs1);
             goto fail;
@@ -1075,7 +1078,7 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
 
         bdrv_unref(bs1);
 
-        ret = get_tmp_filename(tmp_filename, sizeof(tmp_filename));
+        ret = get_tmp_filename(tmp_filename, PATH_MAX + 1);
         if (ret < 0) {
             error_setg_errno(errp, -ret, "Could not get temporary filename");
             goto fail;
@@ -1083,8 +1086,7 @@ int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
 
         /* Real path is meaningless for protocols */
         if (path_has_protocol(filename)) {
-            snprintf(backing_filename, sizeof(backing_filename),
+            snprintf(backing_filename, PATH_MAX, "%s", filename);
-                     "%s", filename);
         } else if (!realpath(filename, backing_filename)) {
             ret = -errno;
             error_setg_errno(errp, errno, "Could not resolve path '%s'", filename);
@@ -1206,6 +1208,8 @@ fail:
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
     }
+    g_free(tmp_filename);
+    g_free(backing_filename);
     return ret;
 
 close_and_fail:
@@ -1214,6 +1218,8 @@ close_and_fail:
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
     }
+    g_free(tmp_filename);
+    g_free(backing_filename);
     return ret;
 }
 
@@ -2271,6 +2277,10 @@ static int bdrv_check_byte_request(BlockDriverState *bs, int64_t offset,
 static int bdrv_check_request(BlockDriverState *bs, int64_t sector_num,
                               int nb_sectors)
 {
+    if (nb_sectors > INT_MAX / BDRV_SECTOR_SIZE) {
+        return -EIO;
+    }
+
     return bdrv_check_byte_request(bs, sector_num * BDRV_SECTOR_SIZE,
                                    nb_sectors * BDRV_SECTOR_SIZE);
 }

block/bochs.c

@@ -38,57 +38,42 @@
 
 // not allocated: 0xffffffff
 
-// always little-endian
-struct bochs_header_v1 {
-    char magic[32]; // "Bochs Virtual HD Image"
-    char type[16]; // "Redolog"
-    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
-    uint32_t version;
-    uint32_t header; // size of header
-
-    union {
-	struct {
-	    uint32_t catalog; // num of entries
-	    uint32_t bitmap; // bitmap size
-	    uint32_t extent; // extent size
-	    uint64_t disk; // disk size
-	    char padding[HEADER_SIZE - 64 - 8 - 20];
-	} redolog;
-	char padding[HEADER_SIZE - 64 - 8];
-    } extra;
-};
-
 // always little-endian
 struct bochs_header {
-    char magic[32]; // "Bochs Virtual HD Image"
+    char magic[32];     /* "Bochs Virtual HD Image" */
-    char type[16]; // "Redolog"
+    char type[16];      /* "Redolog" */
-    char subtype[16]; // "Undoable" / "Volatile" / "Growing"
+    char subtype[16];   /* "Undoable" / "Volatile" / "Growing" */
     uint32_t version;
-    uint32_t header; // size of header
+    uint32_t header;    /* size of header */
+
+    uint32_t catalog;   /* num of entries */
+    uint32_t bitmap;    /* bitmap size */
+    uint32_t extent;    /* extent size */
 
     union {
-	struct {
+        struct {
-	    uint32_t catalog; // num of entries
+            uint32_t reserved;  /* for ??? */
-	    uint32_t bitmap; // bitmap size
+            uint64_t disk;      /* disk size */
-	    uint32_t extent; // extent size
+            char padding[HEADER_SIZE - 64 - 20 - 12];
-	    uint32_t reserved; // for ???
+        } QEMU_PACKED redolog;
-	    uint64_t disk; // disk size
+        struct {
-	    char padding[HEADER_SIZE - 64 - 8 - 24];
+            uint64_t disk;      /* disk size */
-	} redolog;
+            char padding[HEADER_SIZE - 64 - 20 - 8];
-	char padding[HEADER_SIZE - 64 - 8];
+        } QEMU_PACKED redolog_v1;
+        char padding[HEADER_SIZE - 64 - 20];
     } extra;
-};
+} QEMU_PACKED;
 
 typedef struct BDRVBochsState {
     CoMutex lock;
     uint32_t *catalog_bitmap;
-    int catalog_size;
+    uint32_t catalog_size;
 
-    int data_offset;
+    uint32_t data_offset;
 
-    int bitmap_blocks;
+    uint32_t bitmap_blocks;
-    int extent_blocks;
+    uint32_t extent_blocks;
-    int extent_size;
+    uint32_t extent_size;
 } BDRVBochsState;
 
 static int bochs_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -112,9 +97,8 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
     BDRVBochsState *s = bs->opaque;
-    int i;
+    uint32_t i;
     struct bochs_header bochs;
-    struct bochs_header_v1 header_v1;
     int ret;
 
     bs->read_only = 1; // no write support yet
@@ -133,13 +117,19 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     if (le32_to_cpu(bochs.version) == HEADER_V1) {
-      memcpy(&header_v1, &bochs, sizeof(bochs));
+        bs->total_sectors = le64_to_cpu(bochs.extra.redolog_v1.disk) / 512;
-      bs->total_sectors = le64_to_cpu(header_v1.extra.redolog.disk) / 512;
     } else {
-      bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
+        bs->total_sectors = le64_to_cpu(bochs.extra.redolog.disk) / 512;
+    }
+
+    /* Limit to 1M entries to avoid unbounded allocation. This is what is
+     * needed for the largest image that bximage can create (~8 TB). */
+    s->catalog_size = le32_to_cpu(bochs.catalog);
+    if (s->catalog_size > 0x100000) {
+        error_setg(errp, "Catalog size is too large");
+        return -EFBIG;
     }
 
-    s->catalog_size = le32_to_cpu(bochs.extra.redolog.catalog);
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
@@ -153,10 +143,24 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->data_offset = le32_to_cpu(bochs.header) + (s->catalog_size * 4);
 
-    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.bitmap) - 1) / 512;
+    s->bitmap_blocks = 1 + (le32_to_cpu(bochs.bitmap) - 1) / 512;
-    s->extent_blocks = 1 + (le32_to_cpu(bochs.extra.redolog.extent) - 1) / 512;
+    s->extent_blocks = 1 + (le32_to_cpu(bochs.extent) - 1) / 512;
 
-    s->extent_size = le32_to_cpu(bochs.extra.redolog.extent);
+    s->extent_size = le32_to_cpu(bochs.extent);
+    if (s->extent_size == 0) {
+        error_setg(errp, "Extent size may not be zero");
+        return -EINVAL;
+    } else if (s->extent_size > 0x800000) {
+        error_setg(errp, "Extent size %" PRIu32 " is too large",
+                   s->extent_size);
+        return -EINVAL;
+    }
+
+    if (s->catalog_size < bs->total_sectors / s->extent_size) {
+        error_setg(errp, "Catalog size is too small for this disk size");
+        ret = -EINVAL;
+        goto fail;
+    }
 
     qemu_co_mutex_init(&s->lock);
     return 0;
@@ -169,8 +173,8 @@ fail:
 static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 {
     BDRVBochsState *s = bs->opaque;
-    int64_t offset = sector_num * 512;
+    uint64_t offset = sector_num * 512;
-    int64_t extent_index, extent_offset, bitmap_offset;
+    uint64_t extent_index, extent_offset, bitmap_offset;
     char bitmap_entry;
 
     // seek to sector
@@ -181,8 +185,9 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
 	return -1; /* not allocated */
     }
 
-    bitmap_offset = s->data_offset + (512 * s->catalog_bitmap[extent_index] *
+    bitmap_offset = s->data_offset +
-	(s->extent_blocks + s->bitmap_blocks));
+        (512 * (uint64_t) s->catalog_bitmap[extent_index] *
+        (s->extent_blocks + s->bitmap_blocks));
 
     /* read in bitmap for current extent */
     if (bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),

block/cloop.c

@@ -26,6 +26,9 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
+/* Maximum compressed block size */
+#define MAX_BLOCK_SIZE (64 * 1024 * 1024)
+
 typedef struct BDRVCloopState {
     CoMutex lock;
     uint32_t block_size;
@@ -68,6 +71,26 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return ret;
     }
     s->block_size = be32_to_cpu(s->block_size);
+    if (s->block_size % 512) {
+        error_setg(errp, "block_size %u must be a multiple of 512",
+                   s->block_size);
+        return -EINVAL;
+    }
+    if (s->block_size == 0) {
+        error_setg(errp, "block_size cannot be zero");
+        return -EINVAL;
+    }
+
+    /* cloop's create_compressed_fs.c warns about block sizes beyond 256 KB but
+     * we can accept more.  Prevent ridiculous values like 4 GB - 1 since we
+     * need a buffer this big.
+     */
+    if (s->block_size > MAX_BLOCK_SIZE) {
+        error_setg(errp, "block_size %u must be %u MB or less",
+                   s->block_size,
+                   MAX_BLOCK_SIZE / (1024 * 1024));
+        return -EINVAL;
+    }
 
     ret = bdrv_pread(bs->file, 128 + 4, &s->n_blocks, 4);
     if (ret < 0) {
@@ -76,7 +99,23 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
     s->n_blocks = be32_to_cpu(s->n_blocks);
 
     /* read offsets */
-    offsets_size = s->n_blocks * sizeof(uint64_t);
+    if (s->n_blocks > (UINT32_MAX - 1) / sizeof(uint64_t)) {
+        /* Prevent integer overflow */
+        error_setg(errp, "n_blocks %u must be %zu or less",
+                   s->n_blocks,
+                   (UINT32_MAX - 1) / sizeof(uint64_t));
+        return -EINVAL;
+    }
+    offsets_size = (s->n_blocks + 1) * sizeof(uint64_t);
+    if (offsets_size > 512 * 1024 * 1024) {
+        /* Prevent ridiculous offsets_size which causes memory allocation to
+         * fail or overflows bdrv_pread() size.  In practice the 512 MB
+         * offsets[] limit supports 16 TB images at 256 KB block size.
+         */
+        error_setg(errp, "image requires too many offsets, "
+                   "try increasing block size");
+        return -EINVAL;
+    }
     s->offsets = g_malloc(offsets_size);
 
     ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
@@ -84,13 +123,37 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    for(i=0;i<s->n_blocks;i++) {
+    for (i = 0; i < s->n_blocks + 1; i++) {
+        uint64_t size;
+
         s->offsets[i] = be64_to_cpu(s->offsets[i]);
-        if (i > 0) {
+        if (i == 0) {
-            uint32_t size = s->offsets[i] - s->offsets[i - 1];
+            continue;
-            if (size > max_compressed_block_size) {
+        }
-                max_compressed_block_size = size;
+
-            }
+        if (s->offsets[i] < s->offsets[i - 1]) {
+            error_setg(errp, "offsets not monotonically increasing at "
+                       "index %u, image file is corrupt", i);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        size = s->offsets[i] - s->offsets[i - 1];
+
+        /* Compressed blocks should be smaller than the uncompressed block size
+         * but maybe compression performed poorly so the compressed block is
+         * actually bigger.  Clamp down on unrealistic values to prevent
+         * ridiculous s->compressed_block allocation.
+         */
+        if (size > 2 * MAX_BLOCK_SIZE) {
+            error_setg(errp, "invalid compressed block size at index %u, "
+                       "image file is corrupt", i);
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        if (size > max_compressed_block_size) {
+            max_compressed_block_size = size;
         }
     }
 
@@ -180,9 +243,7 @@ static coroutine_fn int cloop_co_read(BlockDriverState *bs, int64_t sector_num,
 static void cloop_close(BlockDriverState *bs)
 {
     BDRVCloopState *s = bs->opaque;
-    if (s->n_blocks > 0) {
+    g_free(s->offsets);
-        g_free(s->offsets);
-    }
     g_free(s->compressed_block);
     g_free(s->uncompressed_block);
     inflateEnd(&s->zstream);

block/curl.c

@@ -34,6 +34,11 @@
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
+#if LIBCURL_VERSION_NUM >= 0x071000
+/* The multi interface timer callback was introduced in 7.16.0 */
+#define NEED_CURL_TIMER_CALLBACK
+#endif
+
 #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
                    CURLPROTO_FTP | CURLPROTO_FTPS | \
                    CURLPROTO_TFTP)
@@ -77,6 +82,7 @@ typedef struct CURLState
 
 typedef struct BDRVCURLState {
     CURLM *multi;
+    QEMUTimer timer;
     size_t len;
     CURLState states[CURL_NUM_STATES];
     char *url;
@@ -87,6 +93,23 @@ typedef struct BDRVCURLState {
 static void curl_clean_state(CURLState *s);
 static void curl_multi_do(void *arg);
 
+#ifdef NEED_CURL_TIMER_CALLBACK
+static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
+{
+    BDRVCURLState *s = opaque;
+
+    DPRINTF("CURL: timer callback timeout_ms %ld\n", timeout_ms);
+    if (timeout_ms == -1) {
+        timer_del(&s->timer);
+    } else {
+        int64_t timeout_ns = (int64_t)timeout_ms * 1000 * 1000;
+        timer_mod(&s->timer,
+                  qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + timeout_ns);
+    }
+    return 0;
+}
+#endif
+
 static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
                         void *s, void *sp)
 {
@@ -134,6 +157,11 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
     if (!s || !s->orig_buf)
         goto read_end;
 
+    if (s->buf_off >= s->buf_len) {
+        /* buffer full, read nothing */
+        return 0;
+    }
+    realsize = MIN(realsize, s->buf_len - s->buf_off);
     memcpy(s->orig_buf + s->buf_off, ptr, realsize);
     s->buf_off += realsize;
 
@@ -209,20 +237,10 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
     return FIND_RET_NONE;
 }
 
-static void curl_multi_do(void *arg)
+static void curl_multi_read(BDRVCURLState *s)
 {
-    BDRVCURLState *s = (BDRVCURLState *)arg;
-    int running;
-    int r;
     int msgs_in_queue;
 
-    if (!s->multi)
-        return;
-
-    do {
-        r = curl_multi_socket_all(s->multi, &running);
-    } while(r == CURLM_CALL_MULTI_PERFORM);
-
     /* Try to find done transfers, so we can free the easy
      * handle again. */
     do {
@@ -266,6 +284,41 @@ static void curl_multi_do(void *arg)
     } while(msgs_in_queue);
 }
 
+static void curl_multi_do(void *arg)
+{
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+    int r;
+
+    if (!s->multi) {
+        return;
+    }
+
+    do {
+        r = curl_multi_socket_all(s->multi, &running);
+    } while(r == CURLM_CALL_MULTI_PERFORM);
+
+    curl_multi_read(s);
+}
+
+static void curl_multi_timeout_do(void *arg)
+{
+#ifdef NEED_CURL_TIMER_CALLBACK
+    BDRVCURLState *s = (BDRVCURLState *)arg;
+    int running;
+
+    if (!s->multi) {
+        return;
+    }
+
+    curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
+
+    curl_multi_read(s);
+#else
+    abort();
+#endif
+}
+
 static CURLState *curl_init_state(BDRVCURLState *s)
 {
     CURLState *state = NULL;
@@ -473,12 +526,20 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
     curl_easy_cleanup(state->curl);
     state->curl = NULL;
 
+    aio_timer_init(bdrv_get_aio_context(bs), &s->timer,
+                   QEMU_CLOCK_REALTIME, SCALE_NS,
+                   curl_multi_timeout_do, s);
+
     // Now we know the file exists and its size, so let's
     // initialize the multi interface!
 
     s->multi = curl_multi_init();
     curl_multi_setopt(s->multi, CURLMOPT_SOCKETDATA, s);
     curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
+#ifdef NEED_CURL_TIMER_CALLBACK
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
+    curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
+#endif
     curl_multi_do(s);
 
     qemu_opts_del(opts);
@@ -597,6 +658,9 @@ static void curl_close(BlockDriverState *bs)
     }
     if (s->multi)
         curl_multi_cleanup(s->multi);
+
+    timer_del(&s->timer);
+
     g_free(s->url);
 }
 

block/dmg.c

@@ -27,6 +27,14 @@
 #include "qemu/module.h"
 #include <zlib.h>
 
+enum {
+    /* Limit chunk sizes to prevent unreasonable amounts of memory being used
+     * or truncating when converting to 32-bit types
+     */
+    DMG_LENGTHS_MAX = 64 * 1024 * 1024, /* 64 MB */
+    DMG_SECTORCOUNTS_MAX = DMG_LENGTHS_MAX / 512,
+};
+
 typedef struct BDRVDMGState {
     CoMutex lock;
     /* each chunk contains a certain number of sectors,
@@ -92,13 +100,44 @@ static int read_uint32(BlockDriverState *bs, int64_t offset, uint32_t *result)
     return 0;
 }
 
+/* Increase max chunk sizes, if necessary.  This function is used to calculate
+ * the buffer sizes needed for compressed/uncompressed chunk I/O.
+ */
+static void update_max_chunk_size(BDRVDMGState *s, uint32_t chunk,
+                                  uint32_t *max_compressed_size,
+                                  uint32_t *max_sectors_per_chunk)
+{
+    uint32_t compressed_size = 0;
+    uint32_t uncompressed_sectors = 0;
+
+    switch (s->types[chunk]) {
+    case 0x80000005: /* zlib compressed */
+        compressed_size = s->lengths[chunk];
+        uncompressed_sectors = s->sectorcounts[chunk];
+        break;
+    case 1: /* copy */
+        uncompressed_sectors = (s->lengths[chunk] + 511) / 512;
+        break;
+    case 2: /* zero */
+        uncompressed_sectors = s->sectorcounts[chunk];
+        break;
+    }
+
+    if (compressed_size > *max_compressed_size) {
+        *max_compressed_size = compressed_size;
+    }
+    if (uncompressed_sectors > *max_sectors_per_chunk) {
+        *max_sectors_per_chunk = uncompressed_sectors;
+    }
+}
+
 static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
     BDRVDMGState *s = bs->opaque;
-    uint64_t info_begin,info_end,last_in_offset,last_out_offset;
+    uint64_t info_begin, info_end, last_in_offset, last_out_offset;
     uint32_t count, tmp;
-    uint32_t max_compressed_size=1,max_sectors_per_chunk=1,i;
+    uint32_t max_compressed_size = 1, max_sectors_per_chunk = 1, i;
     int64_t offset;
     int ret;
 
@@ -160,37 +199,40 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
             goto fail;
         }
 
-	if (type == 0x6d697368 && count >= 244) {
+        if (type == 0x6d697368 && count >= 244) {
-	    int new_size, chunk_count;
+            size_t new_size;
+            uint32_t chunk_count;
 
             offset += 4;
             offset += 200;
 
-	    chunk_count = (count-204)/40;
+            chunk_count = (count - 204) / 40;
-	    new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
+            new_size = sizeof(uint64_t) * (s->n_chunks + chunk_count);
-	    s->types = g_realloc(s->types, new_size/2);
+            s->types = g_realloc(s->types, new_size / 2);
-	    s->offsets = g_realloc(s->offsets, new_size);
+            s->offsets = g_realloc(s->offsets, new_size);
-	    s->lengths = g_realloc(s->lengths, new_size);
+            s->lengths = g_realloc(s->lengths, new_size);
-	    s->sectors = g_realloc(s->sectors, new_size);
+            s->sectors = g_realloc(s->sectors, new_size);
-	    s->sectorcounts = g_realloc(s->sectorcounts, new_size);
+            s->sectorcounts = g_realloc(s->sectorcounts, new_size);
 
             for (i = s->n_chunks; i < s->n_chunks + chunk_count; i++) {
                 ret = read_uint32(bs, offset, &s->types[i]);
                 if (ret < 0) {
                     goto fail;
                 }
-		offset += 4;
+                offset += 4;
-		if(s->types[i]!=0x80000005 && s->types[i]!=1 && s->types[i]!=2) {
+                if (s->types[i] != 0x80000005 && s->types[i] != 1 &&
-		    if(s->types[i]==0xffffffff) {
+                    s->types[i] != 2) {
-			last_in_offset = s->offsets[i-1]+s->lengths[i-1];
+                    if (s->types[i] == 0xffffffff && i > 0) {
-			last_out_offset = s->sectors[i-1]+s->sectorcounts[i-1];
+                        last_in_offset = s->offsets[i - 1] + s->lengths[i - 1];
-		    }
+                        last_out_offset = s->sectors[i - 1] +
-		    chunk_count--;
+                                          s->sectorcounts[i - 1];
-		    i--;
+                    }
-		    offset += 36;
+                    chunk_count--;
-		    continue;
+                    i--;
-		}
+                    offset += 36;
-		offset += 4;
+                    continue;
+                }
+                offset += 4;
 
                 ret = read_uint64(bs, offset, &s->sectors[i]);
                 if (ret < 0) {
@@ -205,6 +247,14 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                 }
                 offset += 8;
 
+                if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
+                    error_report("sector count %" PRIu64 " for chunk %u is "
+                                 "larger than max (%u)",
+                                 s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
+                    ret = -EINVAL;
+                    goto fail;
+                }
+
                 ret = read_uint64(bs, offset, &s->offsets[i]);
                 if (ret < 0) {
                     goto fail;
@@ -218,19 +268,25 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
                 }
                 offset += 8;
 
-		if(s->lengths[i]>max_compressed_size)
+                if (s->lengths[i] > DMG_LENGTHS_MAX) {
-		    max_compressed_size = s->lengths[i];
+                    error_report("length %" PRIu64 " for chunk %u is larger "
-		if(s->sectorcounts[i]>max_sectors_per_chunk)
+                                 "than max (%u)",
-		    max_sectors_per_chunk = s->sectorcounts[i];
+                                 s->lengths[i], i, DMG_LENGTHS_MAX);
-	    }
+                    ret = -EINVAL;
-	    s->n_chunks+=chunk_count;
+                    goto fail;
-	}
+                }
+
+                update_max_chunk_size(s, i, &max_compressed_size,
+                                      &max_sectors_per_chunk);
+            }
+            s->n_chunks += chunk_count;
+        }
     }
 
     /* initialize zlib engine */
-    s->compressed_chunk = g_malloc(max_compressed_size+1);
+    s->compressed_chunk = g_malloc(max_compressed_size + 1);
-    s->uncompressed_chunk = g_malloc(512*max_sectors_per_chunk);
+    s->uncompressed_chunk = g_malloc(512 * max_sectors_per_chunk);
-    if(inflateInit(&s->zstream) != Z_OK) {
+    if (inflateInit(&s->zstream) != Z_OK) {
         ret = -EINVAL;
         goto fail;
     }
@@ -252,83 +308,82 @@ fail:
 }
 
 static inline int is_sector_in_chunk(BDRVDMGState* s,
-		uint32_t chunk_num,int sector_num)
+                uint32_t chunk_num, uint64_t sector_num)
 {
-    if(chunk_num>=s->n_chunks || s->sectors[chunk_num]>sector_num ||
+    if (chunk_num >= s->n_chunks || s->sectors[chunk_num] > sector_num ||
-	    s->sectors[chunk_num]+s->sectorcounts[chunk_num]<=sector_num)
+            s->sectors[chunk_num] + s->sectorcounts[chunk_num] <= sector_num) {
-	return 0;
+        return 0;
-    else
+    } else {
-	return -1;
+        return -1;
+    }
 }
 
-static inline uint32_t search_chunk(BDRVDMGState* s,int sector_num)
+static inline uint32_t search_chunk(BDRVDMGState *s, uint64_t sector_num)
 {
     /* binary search */
-    uint32_t chunk1=0,chunk2=s->n_chunks,chunk3;
+    uint32_t chunk1 = 0, chunk2 = s->n_chunks, chunk3;
-    while(chunk1!=chunk2) {
+    while (chunk1 != chunk2) {
-	chunk3 = (chunk1+chunk2)/2;
+        chunk3 = (chunk1 + chunk2) / 2;
-	if(s->sectors[chunk3]>sector_num)
+        if (s->sectors[chunk3] > sector_num) {
-	    chunk2 = chunk3;
+            chunk2 = chunk3;
-	else if(s->sectors[chunk3]+s->sectorcounts[chunk3]>sector_num)
+        } else if (s->sectors[chunk3] + s->sectorcounts[chunk3] > sector_num) {
-	    return chunk3;
+            return chunk3;
-	else
+        } else {
-	    chunk1 = chunk3;
+            chunk1 = chunk3;
+        }
     }
     return s->n_chunks; /* error */
 }
 
-static inline int dmg_read_chunk(BlockDriverState *bs, int sector_num)
+static inline int dmg_read_chunk(BlockDriverState *bs, uint64_t sector_num)
 {
     BDRVDMGState *s = bs->opaque;
 
-    if(!is_sector_in_chunk(s,s->current_chunk,sector_num)) {
+    if (!is_sector_in_chunk(s, s->current_chunk, sector_num)) {
-	int ret;
+        int ret;
-	uint32_t chunk = search_chunk(s,sector_num);
+        uint32_t chunk = search_chunk(s, sector_num);
 
-	if(chunk>=s->n_chunks)
+        if (chunk >= s->n_chunks) {
-	    return -1;
+            return -1;
+        }
 
-	s->current_chunk = s->n_chunks;
+        s->current_chunk = s->n_chunks;
-	switch(s->types[chunk]) {
+        switch (s->types[chunk]) {
-	case 0x80000005: { /* zlib compressed */
+        case 0x80000005: { /* zlib compressed */
-	    int i;
+            /* we need to buffer, because only the chunk as whole can be
+             * inflated. */
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
+                             s->compressed_chunk, s->lengths[chunk]);
+            if (ret != s->lengths[chunk]) {
+                return -1;
+            }
 
-	    /* we need to buffer, because only the chunk as whole can be
+            s->zstream.next_in = s->compressed_chunk;
-	     * inflated. */
+            s->zstream.avail_in = s->lengths[chunk];
-	    i=0;
+            s->zstream.next_out = s->uncompressed_chunk;
-	    do {
+            s->zstream.avail_out = 512 * s->sectorcounts[chunk];
-                ret = bdrv_pread(bs->file, s->offsets[chunk] + i,
+            ret = inflateReset(&s->zstream);
-                                 s->compressed_chunk+i, s->lengths[chunk]-i);
+            if (ret != Z_OK) {
-		if(ret<0 && errno==EINTR)
+                return -1;
-		    ret=0;
+            }
-		i+=ret;
+            ret = inflate(&s->zstream, Z_FINISH);
-	    } while(ret>=0 && ret+i<s->lengths[chunk]);
+            if (ret != Z_STREAM_END ||
-
+                s->zstream.total_out != 512 * s->sectorcounts[chunk]) {
-	    if (ret != s->lengths[chunk])
+                return -1;
-		return -1;
+            }
-
+            break; }
-	    s->zstream.next_in = s->compressed_chunk;
+        case 1: /* copy */
-	    s->zstream.avail_in = s->lengths[chunk];
+            ret = bdrv_pread(bs->file, s->offsets[chunk],
-	    s->zstream.next_out = s->uncompressed_chunk;
-	    s->zstream.avail_out = 512*s->sectorcounts[chunk];
-	    ret = inflateReset(&s->zstream);
-	    if(ret != Z_OK)
-		return -1;
-	    ret = inflate(&s->zstream, Z_FINISH);
-	    if(ret != Z_STREAM_END || s->zstream.total_out != 512*s->sectorcounts[chunk])
-		return -1;
-	    break; }
-	case 1: /* copy */
-	    ret = bdrv_pread(bs->file, s->offsets[chunk],
                              s->uncompressed_chunk, s->lengths[chunk]);
-	    if (ret != s->lengths[chunk])
+            if (ret != s->lengths[chunk]) {
-		return -1;
+                return -1;
-	    break;
+            }
-	case 2: /* zero */
+            break;
-	    memset(s->uncompressed_chunk, 0, 512*s->sectorcounts[chunk]);
+        case 2: /* zero */
-	    break;
+            memset(s->uncompressed_chunk, 0, 512 * s->sectorcounts[chunk]);
-	}
+            break;
-	s->current_chunk = chunk;
+        }
+        s->current_chunk = chunk;
     }
     return 0;
 }
@@ -339,12 +394,14 @@ static int dmg_read(BlockDriverState *bs, int64_t sector_num,
     BDRVDMGState *s = bs->opaque;
     int i;
 
-    for(i=0;i<nb_sectors;i++) {
+    for (i = 0; i < nb_sectors; i++) {
-	uint32_t sector_offset_in_chunk;
+        uint32_t sector_offset_in_chunk;
-	if(dmg_read_chunk(bs, sector_num+i) != 0)
+        if (dmg_read_chunk(bs, sector_num + i) != 0) {
-	    return -1;
+            return -1;
-	sector_offset_in_chunk = sector_num+i-s->sectors[s->current_chunk];
+        }
-	memcpy(buf+i*512,s->uncompressed_chunk+sector_offset_in_chunk*512,512);
+        sector_offset_in_chunk = sector_num + i - s->sectors[s->current_chunk];
+        memcpy(buf + i * 512,
+               s->uncompressed_chunk + sector_offset_in_chunk * 512, 512);
     }
     return 0;
 }
@@ -376,12 +433,12 @@ static void dmg_close(BlockDriverState *bs)
 }
 
 static BlockDriver bdrv_dmg = {
-    .format_name	= "dmg",
+    .format_name    = "dmg",
-    .instance_size	= sizeof(BDRVDMGState),
+    .instance_size  = sizeof(BDRVDMGState),
-    .bdrv_probe		= dmg_probe,
+    .bdrv_probe     = dmg_probe,
-    .bdrv_open		= dmg_open,
+    .bdrv_open      = dmg_open,
-    .bdrv_read          = dmg_co_read,
+    .bdrv_read      = dmg_co_read,
-    .bdrv_close		= dmg_close,
+    .bdrv_close     = dmg_close,
 };
 
 static void bdrv_dmg_init(void)

block/iscsi.c

@@ -65,6 +65,7 @@ typedef struct IscsiTask {
     int do_retry;
     struct scsi_task *task;
     Coroutine *co;
+    QEMUBH *bh;
 } IscsiTask;
 
 typedef struct IscsiAIOCB {
@@ -121,6 +122,13 @@ iscsi_schedule_bh(IscsiAIOCB *acb)
     qemu_bh_schedule(acb->bh);
 }
 
+static void iscsi_co_generic_bh_cb(void *opaque)
+{
+    struct IscsiTask *iTask = opaque;
+    qemu_bh_delete(iTask->bh);
+    qemu_coroutine_enter(iTask->co, NULL);
+}
+
 static void
 iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
                         void *command_data, void *opaque)
@@ -135,17 +143,19 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
 
     if (iTask->retries-- > 0 && status == SCSI_STATUS_CHECK_CONDITION
         && task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
+        error_report("iSCSI CheckCondition: %s", iscsi_get_error(iscsi));
         iTask->do_retry = 1;
         goto out;
     }
 
     if (status != SCSI_STATUS_GOOD) {
-        error_report("iSCSI: Failure. %s", iscsi_get_error(iscsi));
+        error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
     }
 
 out:
     if (iTask->co) {
-        qemu_coroutine_enter(iTask->co, NULL);
+        iTask->bh = qemu_bh_new(iscsi_co_generic_bh_cb, iTask);
+        qemu_bh_schedule(iTask->bh);
     }
 }
 
@@ -859,6 +869,7 @@ retry:
             scsi_free_scsi_task(iTask.task);
             iTask.task = NULL;
         }
+        iTask.complete = 0;
         goto retry;
     }
 
@@ -955,6 +966,7 @@ retry:
         }
 
         if (iTask.do_retry) {
+            iTask.complete = 0;
             goto retry;
         }
 

block/mirror.c

@@ -95,7 +95,14 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
     }
 
     g_slice_free(MirrorOp, op);
-    qemu_coroutine_enter(s->common.co, NULL);
+
+    /* Enter coroutine when it is not sleeping.  The coroutine sleeps to
+     * rate-limit itself.  The coroutine will eventually resume since there is
+     * a sleep timeout so don't wake it early.
+     */
+    if (s->common.busy) {
+        qemu_coroutine_enter(s->common.co, NULL);
+    }
 }
 
 static void mirror_write_complete(void *opaque, int ret)
@@ -136,11 +143,12 @@ static void mirror_read_complete(void *opaque, int ret)
                     mirror_write_complete, op);
 }
 
-static void coroutine_fn mirror_iteration(MirrorBlockJob *s)
+static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
 {
     BlockDriverState *source = s->common.bs;
     int nb_sectors, sectors_per_chunk, nb_chunks;
     int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
+    uint64_t delay_ns;
     MirrorOp *op;
 
     s->sector_num = hbitmap_iter_next(&s->hbi);
@@ -227,7 +235,12 @@ static void coroutine_fn mirror_iteration(MirrorBlockJob *s)
         nb_chunks += added_chunks;
         next_sector += added_sectors;
         next_chunk += added_chunks;
-    } while (next_sector < end);
+        if (!s->synced && s->common.speed) {
+            delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
+        } else {
+            delay_ns = 0;
+        }
+    } while (delay_ns == 0 && next_sector < end);
 
     /* Allocate a MirrorOp that is used as an AIO callback.  */
     op = g_slice_new(MirrorOp);
@@ -263,6 +276,7 @@ static void coroutine_fn mirror_iteration(MirrorBlockJob *s)
     trace_mirror_one_iteration(s, sector_num, nb_sectors);
     bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
                    mirror_read_complete, op);
+    return delay_ns;
 }
 
 static void mirror_free_init(MirrorBlockJob *s)
@@ -358,7 +372,7 @@ static void coroutine_fn mirror_run(void *opaque)
     bdrv_dirty_iter_init(bs, &s->hbi);
     last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
     for (;;) {
-        uint64_t delay_ns;
+        uint64_t delay_ns = 0;
         int64_t cnt;
         bool should_complete;
 
@@ -382,8 +396,10 @@ static void coroutine_fn mirror_run(void *opaque)
                 qemu_coroutine_yield();
                 continue;
             } else if (cnt != 0) {
-                mirror_iteration(s);
+                delay_ns = mirror_iteration(s);
-                continue;
+                if (delay_ns == 0) {
+                    continue;
+                }
             }
         }
 
@@ -428,17 +444,10 @@ static void coroutine_fn mirror_run(void *opaque)
         }
 
         ret = 0;
-        trace_mirror_before_sleep(s, cnt, s->synced);
+        trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
         if (!s->synced) {
             /* Publish progress */
             s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
-
-            if (s->common.speed) {
-                delay_ns = ratelimit_calculate_delay(&s->limit, sectors_per_chunk);
-            } else {
-                delay_ns = 0;
-            }
-
             block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
             if (block_job_is_cancelled(&s->common)) {
                 break;

block/parallels.c

@@ -49,9 +49,9 @@ typedef struct BDRVParallelsState {
     CoMutex lock;
 
     uint32_t *catalog_bitmap;
-    int catalog_size;
+    unsigned int catalog_size;
 
-    int tracks;
+    unsigned int tracks;
 } BDRVParallelsState;
 
 static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -92,8 +92,18 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
     bs->total_sectors = le32_to_cpu(ph.nb_sectors);
 
     s->tracks = le32_to_cpu(ph.tracks);
+    if (s->tracks == 0) {
+        error_setg(errp, "Invalid image: Zero sectors per track");
+        ret = -EINVAL;
+        goto fail;
+    }
 
     s->catalog_size = le32_to_cpu(ph.catalog_entries);
+    if (s->catalog_size > INT_MAX / 4) {
+        error_setg(errp, "Catalog too large");
+        ret = -EFBIG;
+        goto fail;
+    }
     s->catalog_bitmap = g_malloc(s->catalog_size * 4);
 
     ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);

block/qapi.c

@@ -471,6 +471,7 @@ static void dump_qobject(fprintf_function func_fprintf, void *f,
         case QTYPE_QERROR: {
             QString *value = qerror_human((QError *)obj);
             func_fprintf(f, "%s", qstring_get_str(value));
+            QDECREF(value);
             break;
         }
         case QTYPE_NONE:

block/qcow.c

@@ -48,9 +48,10 @@ typedef struct QCowHeader {
     uint64_t size; /* in bytes */
     uint8_t cluster_bits;
     uint8_t l2_bits;
+    uint16_t padding;
     uint32_t crypt_method;
     uint64_t l1_table_offset;
-} QCowHeader;
+} QEMU_PACKED QCowHeader;
 
 #define L2_CACHE_SIZE 16
 
@@ -60,7 +61,7 @@ typedef struct BDRVQcowState {
     int cluster_sectors;
     int l2_bits;
     int l2_size;
-    int l1_size;
+    unsigned int l1_size;
     uint64_t cluster_offset_mask;
     uint64_t l1_table_offset;
     uint64_t *l1_table;
@@ -96,7 +97,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
                      Error **errp)
 {
     BDRVQcowState *s = bs->opaque;
-    int len, i, shift, ret;
+    unsigned int len, i, shift;
+    int ret;
     QCowHeader header;
 
     ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
@@ -125,10 +127,25 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
         goto fail;
     }
 
-    if (header.size <= 1 || header.cluster_bits < 9) {
+    if (header.size <= 1) {
+        error_setg(errp, "Image size is too small (must be at least 2 bytes)");
         ret = -EINVAL;
         goto fail;
     }
+    if (header.cluster_bits < 9 || header.cluster_bits > 16) {
+        error_setg(errp, "Cluster size must be between 512 and 64k");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    /* l2_bits specifies number of entries; storing a uint64_t in each entry,
+     * so bytes = num_entries << 3. */
+    if (header.l2_bits < 9 - 3 || header.l2_bits > 16 - 3) {
+        error_setg(errp, "L2 table size must be between 512 and 64k");
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (header.crypt_method > QCOW_CRYPT_AES) {
         ret = -EINVAL;
         goto fail;
@@ -147,7 +164,19 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
 
     /* read the level 1 table */
     shift = s->cluster_bits + s->l2_bits;
-    s->l1_size = (header.size + (1LL << shift) - 1) >> shift;
+    if (header.size > UINT64_MAX - (1LL << shift)) {
+        error_setg(errp, "Image too large");
+        ret = -EINVAL;
+        goto fail;
+    } else {
+        uint64_t l1_size = (header.size + (1LL << shift) - 1) >> shift;
+        if (l1_size > INT_MAX / sizeof(uint64_t)) {
+            error_setg(errp, "Image too large");
+            ret = -EINVAL;
+            goto fail;
+        }
+        s->l1_size = l1_size;
+    }
 
     s->l1_table_offset = header.l1_table_offset;
     s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
@@ -171,7 +200,9 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
         if (len > 1023) {
-            len = 1023;
+            error_setg(errp, "Backing file name too long");
+            ret = -EINVAL;
+            goto fail;
         }
         ret = bdrv_pread(bs->file, header.backing_file_offset,
                    bs->backing_file, len);

block/qcow2-cluster.c

@@ -55,7 +55,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
         }
     }
 
-    if (new_l1_size > INT_MAX) {
+    if (new_l1_size > INT_MAX / sizeof(uint64_t)) {
         return -EFBIG;
     }
 
@@ -359,15 +359,6 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
     struct iovec iov;
     int n, ret;
 
-    /*
-     * If this is the last cluster and it is only partially used, we must only
-     * copy until the end of the image, or bdrv_check_request will fail for the
-     * bdrv_read/write calls below.
-     */
-    if (start_sect + n_end > bs->total_sectors) {
-        n_end = bs->total_sectors - start_sect;
-    }
-
     n = n_end - n_start;
     if (n <= 0) {
         return 0;

block/qcow2-refcount.c

@@ -28,7 +28,7 @@
 #include "qemu/range.h"
 #include "qapi/qmp/types.h"
 
-static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size);
+static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size);
 static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
                             int64_t offset, int64_t length,
                             int addend, enum qcow2_discard_type type);
@@ -40,8 +40,10 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs,
 int qcow2_refcount_init(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
-    int ret, refcount_table_size2, i;
+    unsigned int refcount_table_size2, i;
+    int ret;
 
+    assert(s->refcount_table_size <= INT_MAX / sizeof(uint64_t));
     refcount_table_size2 = s->refcount_table_size * sizeof(uint64_t);
     s->refcount_table = g_malloc(refcount_table_size2);
     if (s->refcount_table_size > 0) {
@@ -87,7 +89,7 @@ static int load_refcount_block(BlockDriverState *bs,
 static int get_refcount(BlockDriverState *bs, int64_t cluster_index)
 {
     BDRVQcowState *s = bs->opaque;
-    int refcount_table_index, block_index;
+    uint64_t refcount_table_index, block_index;
     int64_t refcount_block_offset;
     int ret;
     uint16_t *refcount_block;
@@ -191,10 +193,11 @@ static int alloc_refcount_block(BlockDriverState *bs,
      *   they can describe them themselves.
      *
      * - We need to consider that at this point we are inside update_refcounts
-     *   and doing the initial refcount increase. This means that some clusters
+     *   and potentially doing an initial refcount increase. This means that
-     *   have already been allocated by the caller, but their refcount isn't
+     *   some clusters have already been allocated by the caller, but their
-     *   accurate yet. free_cluster_index tells us where this allocation ends
+     *   refcount isn't accurate yet. If we allocate clusters for metadata, we
-     *   as long as we don't overwrite it by freeing clusters.
+     *   need to return -EAGAIN to signal the caller that it needs to restart
+     *   the search for free clusters.
      *
      * - alloc_clusters_noref and qcow2_free_clusters may load a different
      *   refcount block into the cache
@@ -279,7 +282,10 @@ static int alloc_refcount_block(BlockDriverState *bs,
         }
 
         s->refcount_table[refcount_table_index] = new_block;
-        return 0;
+
+        /* The new refcount block may be where the caller intended to put its
+         * data, so let it restart the search. */
+        return -EAGAIN;
     }
 
     ret = qcow2_cache_put(bs, s->refcount_block_cache, (void**) refcount_block);
@@ -302,8 +308,11 @@ static int alloc_refcount_block(BlockDriverState *bs,
 
     /* Calculate the number of refcount blocks needed so far */
     uint64_t refcount_block_clusters = 1 << (s->cluster_bits - REFCOUNT_SHIFT);
-    uint64_t blocks_used = (s->free_cluster_index +
+    uint64_t blocks_used = DIV_ROUND_UP(cluster_index, refcount_block_clusters);
-        refcount_block_clusters - 1) / refcount_block_clusters;
+
+    if (blocks_used > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
+        return -EFBIG;
+    }
 
     /* And now we need at least one block more for the new metadata */
     uint64_t table_size = next_refcount_table_size(s, blocks_used + 1);
@@ -336,8 +345,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
     uint16_t *new_blocks = g_malloc0(blocks_clusters * s->cluster_size);
     uint64_t *new_table = g_malloc0(table_size * sizeof(uint64_t));
 
-    assert(meta_offset >= (s->free_cluster_index * s->cluster_size));
-
     /* Fill the new refcount table */
     memcpy(new_table, s->refcount_table,
         s->refcount_table_size * sizeof(uint64_t));
@@ -400,18 +407,19 @@ static int alloc_refcount_block(BlockDriverState *bs,
     s->refcount_table_size = table_size;
     s->refcount_table_offset = table_offset;
 
-    /* Free old table. Remember, we must not change free_cluster_index */
+    /* Free old table. */
-    uint64_t old_free_cluster_index = s->free_cluster_index;
     qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
                         QCOW2_DISCARD_OTHER);
-    s->free_cluster_index = old_free_cluster_index;
 
     ret = load_refcount_block(bs, new_block, (void**) refcount_block);
     if (ret < 0) {
         return ret;
     }
 
-    return 0;
+    /* If we were trying to do the initial refcount update for some cluster
+     * allocation, we might have used the same clusters to store newly
+     * allocated metadata. Make the caller search some new space. */
+    return -EAGAIN;
 
 fail_table:
     g_free(new_table);
@@ -626,15 +634,16 @@ int qcow2_update_cluster_refcount(BlockDriverState *bs,
 
 
 /* return < 0 if error */
-static int64_t alloc_clusters_noref(BlockDriverState *bs, int64_t size)
+static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size)
 {
     BDRVQcowState *s = bs->opaque;
-    int i, nb_clusters, refcount;
+    uint64_t i, nb_clusters;
+    int refcount;
 
     nb_clusters = size_to_clusters(s, size);
 retry:
     for(i = 0; i < nb_clusters; i++) {
-        int64_t next_cluster_index = s->free_cluster_index++;
+        uint64_t next_cluster_index = s->free_cluster_index++;
         refcount = get_refcount(bs, next_cluster_index);
 
         if (refcount < 0) {
@@ -651,18 +660,21 @@ retry:
     return (s->free_cluster_index - nb_clusters) << s->cluster_bits;
 }
 
-int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size)
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size)
 {
     int64_t offset;
     int ret;
 
     BLKDBG_EVENT(bs->file, BLKDBG_CLUSTER_ALLOC);
-    offset = alloc_clusters_noref(bs, size);
+    do {
-    if (offset < 0) {
+        offset = alloc_clusters_noref(bs, size);
-        return offset;
+        if (offset < 0) {
-    }
+            return offset;
+        }
+
+        ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
+    } while (ret == -EAGAIN);
 
-    ret = update_refcount(bs, offset, size, 1, QCOW2_DISCARD_NEVER);
     if (ret < 0) {
         return ret;
     }
@@ -675,33 +687,36 @@ int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
 {
     BDRVQcowState *s = bs->opaque;
     uint64_t cluster_index;
-    uint64_t old_free_cluster_index;
+    uint64_t i;
-    int i, refcount, ret;
+    int refcount, ret;
 
-    /* Check how many clusters there are free */
+    assert(nb_clusters >= 0);
-    cluster_index = offset >> s->cluster_bits;
+    if (nb_clusters == 0) {
-    for(i = 0; i < nb_clusters; i++) {
+        return 0;
-        refcount = get_refcount(bs, cluster_index++);
-
-        if (refcount < 0) {
-            return refcount;
-        } else if (refcount != 0) {
-            break;
-        }
     }
 
-    /* And then allocate them */
+    do {
-    old_free_cluster_index = s->free_cluster_index;
+        /* Check how many clusters there are free */
-    s->free_cluster_index = cluster_index + i;
+        cluster_index = offset >> s->cluster_bits;
+        for(i = 0; i < nb_clusters; i++) {
+            refcount = get_refcount(bs, cluster_index++);
+
+            if (refcount < 0) {
+                return refcount;
+            } else if (refcount != 0) {
+                break;
+            }
+        }
+
+        /* And then allocate them */
+        ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
+                              QCOW2_DISCARD_NEVER);
+    } while (ret == -EAGAIN);
 
-    ret = update_refcount(bs, offset, i << s->cluster_bits, 1,
-                          QCOW2_DISCARD_NEVER);
     if (ret < 0) {
         return ret;
     }
 
-    s->free_cluster_index = old_free_cluster_index;
-
     return i;
 }
 
@@ -1004,8 +1019,7 @@ static void inc_refcounts(BlockDriverState *bs,
                           int64_t offset, int64_t size)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t start, last, cluster_offset;
+    uint64_t start, last, cluster_offset, k;
-    int k;
 
     if (size <= 0)
         return;
@@ -1015,11 +1029,7 @@ static void inc_refcounts(BlockDriverState *bs,
     for(cluster_offset = start; cluster_offset <= last;
         cluster_offset += s->cluster_size) {
         k = cluster_offset >> s->cluster_bits;
-        if (k < 0) {
+        if (k >= refcount_table_size) {
-            fprintf(stderr, "ERROR: invalid cluster offset=0x%" PRIx64 "\n",
-                cluster_offset);
-            res->corruptions++;
-        } else if (k >= refcount_table_size) {
             fprintf(stderr, "Warning: cluster offset=0x%" PRIx64 " is after "
                 "the end of the image file, can't properly check refcounts.\n",
                 cluster_offset);
@@ -1460,14 +1470,19 @@ int qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res,
                           BdrvCheckMode fix)
 {
     BDRVQcowState *s = bs->opaque;
-    int64_t size, i, highest_cluster;
+    int64_t size, i, highest_cluster, nb_clusters;
-    int nb_clusters, refcount1, refcount2;
+    int refcount1, refcount2;
     QCowSnapshot *sn;
     uint16_t *refcount_table;
     int ret;
 
     size = bdrv_getlength(bs->file);
     nb_clusters = size_to_clusters(s, size);
+    if (nb_clusters > INT_MAX) {
+        res->check_errors++;
+        return -EFBIG;
+    }
+
     refcount_table = g_malloc0(nb_clusters * sizeof(uint16_t));
 
     res->bfi.total_clusters =

block/qcow2-snapshot.c

@@ -26,31 +26,6 @@
 #include "block/block_int.h"
 #include "block/qcow2.h"
 
-typedef struct QEMU_PACKED QCowSnapshotHeader {
-    /* header is 8 byte aligned */
-    uint64_t l1_table_offset;
-
-    uint32_t l1_size;
-    uint16_t id_str_size;
-    uint16_t name_size;
-
-    uint32_t date_sec;
-    uint32_t date_nsec;
-
-    uint64_t vm_clock_nsec;
-
-    uint32_t vm_state_size;
-    uint32_t extra_data_size; /* for extension */
-    /* extra data follows */
-    /* id_str follows */
-    /* name follows  */
-} QCowSnapshotHeader;
-
-typedef struct QEMU_PACKED QCowSnapshotExtraData {
-    uint64_t vm_state_size_large;
-    uint64_t disk_size;
-} QCowSnapshotExtraData;
-
 void qcow2_free_snapshots(BlockDriverState *bs)
 {
     BDRVQcowState *s = bs->opaque;
@@ -357,6 +332,10 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     uint64_t *l1_table = NULL;
     int64_t l1_table_offset;
 
+    if (s->nb_snapshots >= QCOW_MAX_SNAPSHOTS) {
+        return -EFBIG;
+    }
+
     memset(sn, 0, sizeof(*sn));
 
     /* Generate an ID if it wasn't passed */
@@ -694,7 +673,11 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_name)
     sn = &s->snapshots[snapshot_index];
 
     /* Allocate and read in the snapshot's L1 table */
-    new_l1_bytes = s->l1_size * sizeof(uint64_t);
+    if (sn->l1_size > QCOW_MAX_L1_SIZE) {
+        error_report("Snapshot L1 table too large");
+        return -EFBIG;
+    }
+    new_l1_bytes = sn->l1_size * sizeof(uint64_t);
     new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
 
     ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);

block/qcow2.c

@@ -269,12 +269,15 @@ static int qcow2_mark_clean(BlockDriverState *bs)
     BDRVQcowState *s = bs->opaque;
 
     if (s->incompatible_features & QCOW2_INCOMPAT_DIRTY) {
-        int ret = bdrv_flush(bs);
+        int ret;
+
+        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
+
+        ret = bdrv_flush(bs);
         if (ret < 0) {
             return ret;
         }
 
-        s->incompatible_features &= ~QCOW2_INCOMPAT_DIRTY;
         return qcow2_update_header(bs);
     }
     return 0;
@@ -329,6 +332,32 @@ static int qcow2_check(BlockDriverState *bs, BdrvCheckResult *result,
     return ret;
 }
 
+static int validate_table_offset(BlockDriverState *bs, uint64_t offset,
+                                 uint64_t entries, size_t entry_len)
+{
+    BDRVQcowState *s = bs->opaque;
+    uint64_t size;
+
+    /* Use signed INT64_MAX as the maximum even for uint64_t header fields,
+     * because values will be passed to qemu functions taking int64_t. */
+    if (entries > INT64_MAX / entry_len) {
+        return -EINVAL;
+    }
+
+    size = entries * entry_len;
+
+    if (INT64_MAX - size < offset) {
+        return -EINVAL;
+    }
+
+    /* Tables must be cluster aligned */
+    if (offset & (s->cluster_size - 1)) {
+        return -EINVAL;
+    }
+
+    return 0;
+}
+
 static QemuOptsList qcow2_runtime_opts = {
     .name = "qcow2",
     .head = QTAILQ_HEAD_INITIALIZER(qcow2_runtime_opts.head),
@@ -419,7 +448,8 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
                       Error **errp)
 {
     BDRVQcowState *s = bs->opaque;
-    int len, i, ret = 0;
+    unsigned int len, i;
+    int ret = 0;
     QCowHeader header;
     QemuOpts *opts;
     Error *local_err = NULL;
@@ -460,6 +490,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->qcow_version = header.version;
 
+    /* Initialise cluster size */
+    if (header.cluster_bits < MIN_CLUSTER_BITS ||
+        header.cluster_bits > MAX_CLUSTER_BITS) {
+        error_setg(errp, "Unsupported cluster size: 2^%i", header.cluster_bits);
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    s->cluster_bits = header.cluster_bits;
+    s->cluster_size = 1 << s->cluster_bits;
+    s->cluster_sectors = 1 << (s->cluster_bits - 9);
+
     /* Initialise version 3 header fields */
     if (header.version == 2) {
         header.incompatible_features    = 0;
@@ -473,6 +515,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         be64_to_cpus(&header.autoclear_features);
         be32_to_cpus(&header.refcount_order);
         be32_to_cpus(&header.header_length);
+
+        if (header.header_length < 104) {
+            error_setg(errp, "qcow2 header too short");
+            ret = -EINVAL;
+            goto fail;
+        }
+    }
+
+    if (header.header_length > s->cluster_size) {
+        error_setg(errp, "qcow2 header exceeds cluster size");
+        ret = -EINVAL;
+        goto fail;
     }
 
     if (header.header_length > sizeof(header)) {
@@ -487,6 +541,12 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         }
     }
 
+    if (header.backing_file_offset > s->cluster_size) {
+        error_setg(errp, "Invalid backing file offset");
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (header.backing_file_offset) {
         ext_end = header.backing_file_offset;
     } else {
@@ -529,12 +589,6 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     }
     s->refcount_order = header.refcount_order;
 
-    if (header.cluster_bits < MIN_CLUSTER_BITS ||
-        header.cluster_bits > MAX_CLUSTER_BITS) {
-        error_setg(errp, "Unsupported cluster size: 2^%i", header.cluster_bits);
-        ret = -EINVAL;
-        goto fail;
-    }
     if (header.crypt_method > QCOW_CRYPT_AES) {
         error_setg(errp, "Unsupported encryption method: %i",
                    header.crypt_method);
@@ -545,23 +599,52 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     if (s->crypt_method_header) {
         bs->encrypted = 1;
     }
-    s->cluster_bits = header.cluster_bits;
+
-    s->cluster_size = 1 << s->cluster_bits;
-    s->cluster_sectors = 1 << (s->cluster_bits - 9);
     s->l2_bits = s->cluster_bits - 3; /* L2 is always one cluster */
     s->l2_size = 1 << s->l2_bits;
     bs->total_sectors = header.size / 512;
     s->csize_shift = (62 - (s->cluster_bits - 8));
     s->csize_mask = (1 << (s->cluster_bits - 8)) - 1;
     s->cluster_offset_mask = (1LL << s->csize_shift) - 1;
+
     s->refcount_table_offset = header.refcount_table_offset;
     s->refcount_table_size =
         header.refcount_table_clusters << (s->cluster_bits - 3);
 
-    s->snapshots_offset = header.snapshots_offset;
+    if (header.refcount_table_clusters > qcow2_max_refcount_clusters(s)) {
-    s->nb_snapshots = header.nb_snapshots;
+        error_setg(errp, "Reference count table too large");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = validate_table_offset(bs, s->refcount_table_offset,
+                                s->refcount_table_size, sizeof(uint64_t));
+    if (ret < 0) {
+        error_setg(errp, "Invalid reference count table offset");
+        goto fail;
+    }
+
+    /* Snapshot table offset/length */
+    if (header.nb_snapshots > QCOW_MAX_SNAPSHOTS) {
+        error_setg(errp, "Too many snapshots");
+        ret = -EINVAL;
+        goto fail;
+    }
+
+    ret = validate_table_offset(bs, header.snapshots_offset,
+                                header.nb_snapshots,
+                                sizeof(QCowSnapshotHeader));
+    if (ret < 0) {
+        error_setg(errp, "Invalid snapshot table offset");
+        goto fail;
+    }
 
     /* read the level 1 table */
+    if (header.l1_size > QCOW_MAX_L1_SIZE) {
+        error_setg(errp, "Active L1 table too large");
+        ret = -EFBIG;
+        goto fail;
+    }
     s->l1_size = header.l1_size;
 
     l1_vm_state_index = size_to_l1(s, header.size);
@@ -579,7 +662,16 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         ret = -EINVAL;
         goto fail;
     }
+
+    ret = validate_table_offset(bs, header.l1_table_offset,
+                                header.l1_size, sizeof(uint64_t));
+    if (ret < 0) {
+        error_setg(errp, "Invalid L1 table offset");
+        goto fail;
+    }
     s->l1_table_offset = header.l1_table_offset;
+
+
     if (s->l1_size > 0) {
         s->l1_table = g_malloc0(
             align_offset(s->l1_size * sizeof(uint64_t), 512));
@@ -625,8 +717,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
     /* read the backing file name */
     if (header.backing_file_offset != 0) {
         len = header.backing_file_size;
-        if (len > 1023) {
+        if (len > MIN(1023, s->cluster_size - header.backing_file_offset)) {
-            len = 1023;
+            error_setg(errp, "Backing file name too long");
+            ret = -EINVAL;
+            goto fail;
         }
         ret = bdrv_pread(bs->file, header.backing_file_offset,
                          bs->backing_file, len);
@@ -637,6 +731,10 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
         bs->backing_file[len] = '\0';
     }
 
+    /* Internal snapshots */
+    s->snapshots_offset = header.snapshots_offset;
+    s->nb_snapshots = header.nb_snapshots;
+
     ret = qcow2_read_snapshots(bs);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not read snapshots");
@@ -792,11 +890,25 @@ static int qcow2_set_key(BlockDriverState *bs, const char *key)
     return 0;
 }
 
-/* We have nothing to do for QCOW2 reopen, stubs just return
+/* We have no actual commit/abort logic for qcow2, but we need to write out any
- * success */
+ * unwritten data if we reopen read-only. */
 static int qcow2_reopen_prepare(BDRVReopenState *state,
                                 BlockReopenQueue *queue, Error **errp)
 {
+    int ret;
+
+    if ((state->flags & BDRV_O_RDWR) == 0) {
+        ret = bdrv_flush(state->bs);
+        if (ret < 0) {
+            return ret;
+        }
+
+        ret = qcow2_mark_clean(state->bs);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 
@@ -1471,8 +1583,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
      * size for any qcow2 image.
      */
     BlockDriverState* bs;
-    QCowHeader header;
+    QCowHeader *header;
-    uint8_t* refcount_table;
+    uint64_t* refcount_table;
     Error *local_err = NULL;
     int ret;
 
@@ -1489,38 +1601,43 @@ static int qcow2_create2(const char *filename, int64_t total_size,
     }
 
     /* Write the header */
-    memset(&header, 0, sizeof(header));
+    QEMU_BUILD_BUG_ON((1 << MIN_CLUSTER_BITS) < sizeof(*header));
-    header.magic = cpu_to_be32(QCOW_MAGIC);
+    header = g_malloc0(cluster_size);
-    header.version = cpu_to_be32(version);
+    *header = (QCowHeader) {
-    header.cluster_bits = cpu_to_be32(cluster_bits);
+        .magic                      = cpu_to_be32(QCOW_MAGIC),
-    header.size = cpu_to_be64(0);
+        .version                    = cpu_to_be32(version),
-    header.l1_table_offset = cpu_to_be64(0);
+        .cluster_bits               = cpu_to_be32(cluster_bits),
-    header.l1_size = cpu_to_be32(0);
+        .size                       = cpu_to_be64(0),
-    header.refcount_table_offset = cpu_to_be64(cluster_size);
+        .l1_table_offset            = cpu_to_be64(0),
-    header.refcount_table_clusters = cpu_to_be32(1);
+        .l1_size                    = cpu_to_be32(0),
-    header.refcount_order = cpu_to_be32(3 + REFCOUNT_SHIFT);
+        .refcount_table_offset      = cpu_to_be64(cluster_size),
-    header.header_length = cpu_to_be32(sizeof(header));
+        .refcount_table_clusters    = cpu_to_be32(1),
+        .refcount_order             = cpu_to_be32(3 + REFCOUNT_SHIFT),
+        .header_length              = cpu_to_be32(sizeof(*header)),
+    };
 
     if (flags & BLOCK_FLAG_ENCRYPT) {
-        header.crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
+        header->crypt_method = cpu_to_be32(QCOW_CRYPT_AES);
     } else {
-        header.crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
+        header->crypt_method = cpu_to_be32(QCOW_CRYPT_NONE);
     }
 
     if (flags & BLOCK_FLAG_LAZY_REFCOUNTS) {
-        header.compatible_features |=
+        header->compatible_features |=
             cpu_to_be64(QCOW2_COMPAT_LAZY_REFCOUNTS);
     }
 
-    ret = bdrv_pwrite(bs, 0, &header, sizeof(header));
+    ret = bdrv_pwrite(bs, 0, header, cluster_size);
+    g_free(header);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not write qcow2 header");
         goto out;
     }
 
-    /* Write an empty refcount table */
+    /* Write a refcount table with one refcount block */
-    refcount_table = g_malloc0(cluster_size);
+    refcount_table = g_malloc0(2 * cluster_size);
-    ret = bdrv_pwrite(bs, cluster_size, refcount_table, cluster_size);
+    refcount_table[0] = cpu_to_be64(2 * cluster_size);
+    ret = bdrv_pwrite(bs, cluster_size, refcount_table, 2 * cluster_size);
     g_free(refcount_table);
 
     if (ret < 0) {
@@ -1544,7 +1661,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
         goto out;
     }
 
-    ret = qcow2_alloc_clusters(bs, 2 * cluster_size);
+    ret = qcow2_alloc_clusters(bs, 3 * cluster_size);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "Could not allocate clusters for qcow2 "
                          "header and refcount table");
@@ -1588,7 +1705,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
 
     /* Reopen the image without BDRV_O_NO_FLUSH to flush it before returning */
     ret = bdrv_open(bs, filename, NULL,
-                    BDRV_O_RDWR | BDRV_O_CACHE_WB, drv, &local_err);
+                    BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
+                    drv, &local_err);
     if (error_is_set(&local_err)) {
         error_propagate(errp, local_err);
         goto out;

block/qcow2.h

@@ -38,6 +38,15 @@
 #define QCOW_CRYPT_AES  1
 
 #define QCOW_MAX_CRYPT_CLUSTERS 32
+#define QCOW_MAX_SNAPSHOTS 65536
+
+/* 8 MB refcount table is enough for 2 PB images at 64k cluster size
+ * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
+#define QCOW_MAX_REFTABLE_SIZE 0x800000
+
+/* 32 MB L1 table is enough for 2 PB images at 64k cluster size
+ * (128 GB for 512 byte clusters, 2 EB for 2 MB clusters) */
+#define QCOW_MAX_L1_SIZE 0x2000000
 
 /* indicate that the refcount of the referenced cluster is exactly one. */
 #define QCOW_OFLAG_COPIED     (1ULL << 63)
@@ -97,6 +106,32 @@ typedef struct QCowHeader {
     uint32_t header_length;
 } QEMU_PACKED QCowHeader;
 
+typedef struct QEMU_PACKED QCowSnapshotHeader {
+    /* header is 8 byte aligned */
+    uint64_t l1_table_offset;
+
+    uint32_t l1_size;
+    uint16_t id_str_size;
+    uint16_t name_size;
+
+    uint32_t date_sec;
+    uint32_t date_nsec;
+
+    uint64_t vm_clock_nsec;
+
+    uint32_t vm_state_size;
+    uint32_t extra_data_size; /* for extension */
+    /* extra data follows */
+    /* id_str follows */
+    /* name follows  */
+} QCowSnapshotHeader;
+
+typedef struct QEMU_PACKED QCowSnapshotExtraData {
+    uint64_t vm_state_size_large;
+    uint64_t disk_size;
+} QCowSnapshotExtraData;
+
+
 typedef struct QCowSnapshot {
     uint64_t l1_table_offset;
     uint32_t l1_size;
@@ -191,8 +226,8 @@ typedef struct BDRVQcowState {
     uint64_t *refcount_table;
     uint64_t refcount_table_offset;
     uint32_t refcount_table_size;
-    int64_t free_cluster_index;
+    uint64_t free_cluster_index;
-    int64_t free_byte_offset;
+    uint64_t free_byte_offset;
 
     CoMutex lock;
 
@@ -202,7 +237,7 @@ typedef struct BDRVQcowState {
     AES_KEY aes_decrypt_key;
     uint64_t snapshots_offset;
     int snapshots_size;
-    int nb_snapshots;
+    unsigned int nb_snapshots;
     QCowSnapshot *snapshots;
 
     int flags;
@@ -383,6 +418,11 @@ static inline int64_t qcow2_vm_state_offset(BDRVQcowState *s)
     return (int64_t)s->l1_vm_state_index << (s->cluster_bits + s->l2_bits);
 }
 
+static inline uint64_t qcow2_max_refcount_clusters(BDRVQcowState *s)
+{
+    return QCOW_MAX_REFTABLE_SIZE >> s->cluster_bits;
+}
+
 static inline int qcow2_get_cluster_type(uint64_t l2_entry)
 {
     if (l2_entry & QCOW_OFLAG_COMPRESSED) {
@@ -431,7 +471,7 @@ void qcow2_refcount_close(BlockDriverState *bs);
 int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
                                   int addend, enum qcow2_discard_type type);
 
-int64_t qcow2_alloc_clusters(BlockDriverState *bs, int64_t size);
+int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size);
 int qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset,
     int nb_clusters);
 int64_t qcow2_alloc_bytes(BlockDriverState *bs, int size);

block/sheepdog.c

@@ -2082,6 +2082,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
     strncpy(s->inode.tag, sn_info->name, sizeof(s->inode.tag));
     /* we don't need to update entire object */
     datalen = SD_INODE_SIZE - sizeof(s->inode.data_vdi_id);
+    inode = g_malloc(datalen);
 
     /* refresh inode. */
     fd = connect_to_sdog(s);
@@ -2105,8 +2106,6 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
         goto cleanup;
     }
 
-    inode = (SheepdogInode *)g_malloc(datalen);
-
     ret = read_object(fd, (char *)inode, vid_to_vdi_oid(new_vid),
                       s->inode.nr_copies, datalen, 0, s->cache_flags);
 
@@ -2120,6 +2119,7 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
             s->inode.name, s->inode.snap_id, s->inode.vdi_id);
 
 cleanup:
+    g_free(inode);
     closesocket(fd);
     return ret;
 }

block/vdi.c

@@ -120,6 +120,11 @@ typedef unsigned char uuid_t[16];
 
 #define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
 
+/* max blocks in image is (0xffffffff / 4) */
+#define VDI_BLOCKS_IN_IMAGE_MAX  0x3fffffff
+#define VDI_DISK_SIZE_MAX        ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \
+                                  (uint64_t)DEFAULT_CLUSTER_SIZE)
+
 #if !defined(CONFIG_UUID)
 static inline void uuid_generate(uuid_t out)
 {
@@ -384,6 +389,13 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
     vdi_header_print(&header);
 #endif
 
+    if (header.disk_size > VDI_DISK_SIZE_MAX) {
+        logout("disk size is 0x%" PRIx64 ", max supported is 0x%" PRIx64,
+               header.disk_size, VDI_DISK_SIZE_MAX);
+        ret = -ENOTSUP;
+        goto fail;
+    }
+
     if (header.disk_size % SECTOR_SIZE != 0) {
         /* 'VBoxManage convertfromraw' can create images with odd disk sizes.
            We accept them but round the disk size to the next multiple of
@@ -416,7 +428,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
         logout("unsupported sector size %u B\n", header.sector_size);
         ret = -ENOTSUP;
         goto fail;
-    } else if (header.block_size != 1 * MiB) {
+    } else if (header.block_size != DEFAULT_CLUSTER_SIZE) {
         logout("unsupported block size %u B\n", header.block_size);
         ret = -ENOTSUP;
         goto fail;
@@ -433,6 +445,11 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
         logout("parent uuid != 0, unsupported\n");
         ret = -ENOTSUP;
         goto fail;
+    } else if (header.blocks_in_image > VDI_BLOCKS_IN_IMAGE_MAX) {
+        logout("too many blocks %u, max is %u)",
+               header.blocks_in_image, VDI_BLOCKS_IN_IMAGE_MAX);
+        ret = -ENOTSUP;
+        goto fail;
     }
 
     bs->total_sectors = header.disk_size / SECTOR_SIZE;
@@ -681,11 +698,20 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
         options++;
     }
 
+    if (bytes > VDI_DISK_SIZE_MAX) {
+        result = -ENOTSUP;
+        logout("image size (size is 0x%" PRIx64
+               ", max supported is 0x%" PRIx64 ")",
+               bytes, VDI_DISK_SIZE_MAX);
+        goto exit;
+    }
+
     fd = qemu_open(filename,
                    O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
                    0644);
     if (fd < 0) {
-        return -errno;
+        result = -errno;
+        goto exit;
     }
 
     /* We need enough blocks to store the given disk size,
@@ -746,6 +772,7 @@ static int vdi_create(const char *filename, QEMUOptionParameter *options,
         result = -errno;
     }
 
+exit:
     return result;
 }
 

block/vhdx.c

@@ -785,12 +785,20 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
     le32_to_cpus(&s->logical_sector_size);
     le32_to_cpus(&s->physical_sector_size);
 
-    if (s->logical_sector_size == 0 || s->params.block_size == 0) {
+    if (s->params.block_size < VHDX_BLOCK_SIZE_MIN ||
+        s->params.block_size > VHDX_BLOCK_SIZE_MAX) {
         ret = -EINVAL;
         goto exit;
     }
 
-    /* both block_size and sector_size are guaranteed powers of 2 */
+    /* only 2 supported sector sizes */
+    if (s->logical_sector_size != 512 && s->logical_sector_size != 4096) {
+        ret = -EINVAL;
+        goto exit;
+    }
+
+    /* Both block_size and sector_size are guaranteed powers of 2, below.
+       Due to range checks above, s->sectors_per_block can never be < 256 */
     s->sectors_per_block = s->params.block_size / s->logical_sector_size;
     s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
                      (uint64_t)s->logical_sector_size /

block/vmdk.c

@@ -1689,7 +1689,7 @@ static int vmdk_create(const char *filename, QEMUOptionParameter *options,
     }
     if (backing_file) {
         BlockDriverState *bs = bdrv_new("");
-        ret = bdrv_open(bs, backing_file, NULL, 0, NULL, errp);
+        ret = bdrv_open(bs, backing_file, NULL, BDRV_O_NO_BACKING, NULL, errp);
         if (ret != 0) {
             bdrv_unref(bs);
             return ret;

block/vpc.c

@@ -45,6 +45,8 @@ enum vhd_type {
 // Seconds since Jan 1, 2000 0:00:00 (UTC)
 #define VHD_TIMESTAMP_BASE 946684800
 
+#define VHD_MAX_SECTORS       (65535LL * 255 * 255)
+
 // always big-endian
 typedef struct vhd_footer {
     char        creator[8]; // "conectix"
@@ -164,6 +166,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     VHDDynDiskHeader *dyndisk_header;
     uint8_t buf[HEADER_SIZE];
     uint32_t checksum;
+    uint64_t computed_size;
     int disk_type = VHD_DYNAMIC;
     int ret;
 
@@ -221,7 +224,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* Allow a maximum disk size of approximately 2 TB */
-    if (bs->total_sectors >= 65535LL * 255 * 255) {
+    if (bs->total_sectors >= VHD_MAX_SECTORS) {
         ret = -EFBIG;
         goto fail;
     }
@@ -241,10 +244,31 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
         }
 
         s->block_size = be32_to_cpu(dyndisk_header->block_size);
+        if (!is_power_of_2(s->block_size) || s->block_size < BDRV_SECTOR_SIZE) {
+            error_setg(errp, "Invalid block size %" PRIu32, s->block_size);
+            ret = -EINVAL;
+            goto fail;
+        }
         s->bitmap_size = ((s->block_size / (8 * 512)) + 511) & ~511;
 
         s->max_table_entries = be32_to_cpu(dyndisk_header->max_table_entries);
-        s->pagetable = g_malloc(s->max_table_entries * 4);
+
+        if ((bs->total_sectors * 512) / s->block_size > 0xffffffffU) {
+            ret = -EINVAL;
+            goto fail;
+        }
+        if (s->max_table_entries > (VHD_MAX_SECTORS * 512) / s->block_size) {
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        computed_size = (uint64_t) s->max_table_entries * s->block_size;
+        if (computed_size < bs->total_sectors * 512) {
+            ret = -EINVAL;
+            goto fail;
+        }
+
+        s->pagetable = qemu_blockalign(bs, s->max_table_entries * 4);
 
         s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
 
@@ -297,7 +321,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
     return 0;
 
 fail:
-    g_free(s->pagetable);
+    qemu_vfree(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif
@@ -819,7 +843,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
 static void vpc_close(BlockDriverState *bs)
 {
     BDRVVPCState *s = bs->opaque;
-    g_free(s->pagetable);
+    qemu_vfree(s->pagetable);
 #ifdef CACHE
     g_free(s->pageentry_u8);
 #endif

block/vvfat.c

@@ -788,7 +788,9 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
 	    s->current_mapping->path=buffer;
 	    s->current_mapping->read_only =
 		(st.st_mode & (S_IWUSR | S_IWGRP | S_IWOTH)) == 0;
-	}
+        } else {
+            g_free(buffer);
+        }
     }
     closedir(dir);
 
@@ -1866,7 +1868,7 @@ static int check_directory_consistency(BDRVVVFATState *s,
 
 	if (s->used_clusters[cluster_num] & USED_ANY) {
 	    fprintf(stderr, "cluster %d used more than once\n", (int)cluster_num);
-	    return 0;
+            goto fail;
 	}
 	s->used_clusters[cluster_num] = USED_DIRECTORY;
 

blockdev-nbd.c

@@ -27,8 +27,9 @@ static void nbd_accept(void *opaque)
     socklen_t addr_len = sizeof(addr);
 
     int fd = accept(server_fd, (struct sockaddr *)&addr, &addr_len);
-    if (fd >= 0) {
+    if (fd >= 0 && !nbd_client_new(NULL, fd, nbd_client_put)) {
-        nbd_client_new(NULL, fd, nbd_client_put);
+        shutdown(fd, 2);
+        close(fd);
     }
 }
 
@@ -91,6 +92,10 @@ void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
         error_set(errp, QERR_DEVICE_NOT_FOUND, device);
         return;
     }
+    if (!bdrv_is_inserted(bs)) {
+        error_set(errp, QERR_DEVICE_HAS_NO_MEDIUM, device);
+        return;
+    }
 
     if (!has_writable) {
         writable = false;

blockdev.c

@@ -334,7 +334,7 @@ static DriveInfo *blockdev_init(QDict *bs_opts,
     opts = qemu_opts_create(&qemu_common_drive_opts, id, 1, &error);
     if (error_is_set(&error)) {
         error_propagate(errp, error);
-        return NULL;
+        goto err_no_opts;
     }
 
     qemu_opts_absorb_qdict(opts, bs_opts, &error);
@@ -535,8 +535,9 @@ err:
     QTAILQ_REMOVE(&drives, dinfo, next);
     g_free(dinfo);
 early_err:
-    QDECREF(bs_opts);
     qemu_opts_del(opts);
+err_no_opts:
+    QDECREF(bs_opts);
     return NULL;
 }
 
@@ -867,6 +868,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
     /* Actual block device init: Functionality shared with blockdev-add */
     dinfo = blockdev_init(bs_opts, type, &local_err);
+    bs_opts = NULL;
     if (dinfo == NULL) {
         if (error_is_set(&local_err)) {
             qerror_report_err(local_err);
@@ -903,6 +905,7 @@ DriveInfo *drive_init(QemuOpts *all_opts, BlockInterfaceType block_default_type)
 
 fail:
     qemu_opts_del(legacy_opts);
+    QDECREF(bs_opts);
     return dinfo;
 }
 
@@ -1786,6 +1789,10 @@ void qmp_block_commit(const char *device,
      */
     BlockdevOnError on_error = BLOCKDEV_ON_ERROR_REPORT;
 
+    if (!has_speed) {
+        speed = 0;
+    }
+
     /* drain all i/o before commits */
     bdrv_drain_all();
 

configure

@@ -1357,6 +1357,11 @@ EOF
       pie="no"
     fi
   fi
+
+  if compile_prog "-fno-pie" "-nopie"; then
+    CFLAGS_NOPIE="-fno-pie"
+    LDFLAGS_NOPIE="-nopie"
+  fi
 fi
 
 ##########################################
@@ -3515,6 +3520,11 @@ fi
 
 int128=no
 cat > $TMPC << EOF
+#if defined(__clang_major__) && defined(__clang_minor__)
+# if ((__clang_major__ < 3) || (__clang_major__ == 3) && (__clang_minor__ < 2))
+#  error __int128_t does not work in CLANG before 3.2
+# endif
+#endif
 __int128_t a;
 __uint128_t b;
 int main (void) {
@@ -4288,6 +4298,7 @@ echo "LD=$ld" >> $config_host_mak
 echo "WINDRES=$windres" >> $config_host_mak
 echo "LIBTOOL=$libtool" >> $config_host_mak
 echo "CFLAGS=$CFLAGS" >> $config_host_mak
+echo "CFLAGS_NOPIE=$CFLAGS_NOPIE" >> $config_host_mak
 echo "QEMU_CFLAGS=$QEMU_CFLAGS" >> $config_host_mak
 echo "QEMU_INCLUDES=$QEMU_INCLUDES" >> $config_host_mak
 if test "$sparse" = "yes" ; then
@@ -4301,6 +4312,7 @@ else
   echo "AUTOCONF_HOST := "                             >> $config_host_mak
 fi
 echo "LDFLAGS=$LDFLAGS" >> $config_host_mak
+echo "LDFLAGS_NOPIE=$LDFLAGS_NOPIE" >> $config_host_mak
 echo "LIBTOOLFLAGS=$LIBTOOLFLAGS" >> $config_host_mak
 echo "LIBS+=$LIBS" >> $config_host_mak
 echo "LIBS_TOOLS+=$libs_tools" >> $config_host_mak

coroutine-win32.c

@@ -36,8 +36,17 @@ typedef struct
 static __thread CoroutineWin32 leader;
 static __thread Coroutine *current;
 
-CoroutineAction qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
+/* This function is marked noinline to prevent GCC from inlining it
-                                      CoroutineAction action)
+ * into coroutine_trampoline(). If we allow it to do that then it
+ * hoists the code to get the address of the TLS variable "current"
+ * out of the while() loop. This is an invalid transformation because
+ * the SwitchToFiber() call may be called when running thread A but
+ * return in thread B, and so we might be in a different thread
+ * context each time round the loop.
+ */
+CoroutineAction __attribute__((noinline))
+qemu_coroutine_switch(Coroutine *from_, Coroutine *to_,
+                      CoroutineAction action)
 {
     CoroutineWin32 *from = DO_UPCAST(CoroutineWin32, base, from_);
     CoroutineWin32 *to = DO_UPCAST(CoroutineWin32, base, to_);

cputlb.c

@@ -344,8 +344,10 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env1, target_ulong addr)
 }
 
 #define MMUSUFFIX _cmmu
-#undef GETPC
+#undef GETPC_ADJ
-#define GETPC() ((uintptr_t)0)
+#define GETPC_ADJ 0
+#undef GETRA
+#define GETRA() ((uintptr_t)0)
 #define SOFTMMU_CODE_ACCESS
 
 #define SHIFT 0

docs/migration.txt

@@ -139,7 +139,6 @@ static const VMStateDescription vmstate_kbd = {
     .name = "pckbd",
     .version_id = 3,
     .minimum_version_id = 3,
-    .minimum_version_id_old = 3,
     .fields      = (VMStateField []) {
         VMSTATE_UINT8(write_cmd, KBDState),
         VMSTATE_UINT8(status, KBDState),
@@ -168,12 +167,13 @@ You can see that there are several version fields:
 - minimum_version_id: the minimum version_id that VMState is able to understand
   for that device.
 - minimum_version_id_old: For devices that were not able to port to vmstate, we can
-  assign a function that knows how to read this old state.
+  assign a function that knows how to read this old state. This field is
+  ignored if there is no load_state_old handler.
 
 So, VMState is able to read versions from minimum_version_id to
-version_id.  And the function load_state_old() is able to load state
+version_id.  And the function load_state_old() (if present) is able to
-from minimum_version_id_old to minimum_version_id.  This function is
+load state from minimum_version_id_old to minimum_version_id.  This
-deprecated and will be removed when no more users are left.
+function is deprecated and will be removed when no more users are left.
 
 ===  Massaging functions ===
 
@@ -255,7 +255,6 @@ const VMStateDescription vmstate_ide_drive_pio_state = {
     .name = "ide_drive/pio_state",
     .version_id = 1,
     .minimum_version_id = 1,
-    .minimum_version_id_old = 1,
     .pre_save = ide_drive_pio_pre_save,
     .post_load = ide_drive_pio_post_load,
     .fields      = (VMStateField []) {
@@ -275,7 +274,6 @@ const VMStateDescription vmstate_ide_drive = {
     .name = "ide_drive",
     .version_id = 3,
     .minimum_version_id = 0,
-    .minimum_version_id_old = 0,
     .post_load = ide_drive_post_load,
     .fields      = (VMStateField []) {
         .... several fields ....

exec.c

@@ -83,20 +83,37 @@ int use_icount;
 typedef struct PhysPageEntry PhysPageEntry;
 
 struct PhysPageEntry {
-    uint16_t is_leaf : 1;
+    /* How many bits skip to next level (in units of L2_SIZE). 0 for a leaf. */
-     /* index into phys_sections (is_leaf) or phys_map_nodes (!is_leaf) */
+    uint16_t skip : 1;
+     /* index into phys_sections (!skip) or phys_map_nodes (skip) */
     uint16_t ptr : 15;
 };
 
-typedef PhysPageEntry Node[L2_SIZE];
+/* Size of the L2 (and L3, etc) page tables.  */
+#define ADDR_SPACE_BITS TARGET_PHYS_ADDR_SPACE_BITS
+
+#define P_L2_BITS 10
+#define P_L2_SIZE (1 << P_L2_BITS)
+
+#define P_L2_LEVELS (((ADDR_SPACE_BITS - TARGET_PAGE_BITS - 1) / P_L2_BITS) + 1)
+
+typedef PhysPageEntry Node[P_L2_SIZE];
+
+typedef struct PhysPageMap {
+    unsigned sections_nb;
+    unsigned sections_nb_alloc;
+    unsigned nodes_nb;
+    unsigned nodes_nb_alloc;
+    Node *nodes;
+    MemoryRegionSection *sections;
+} PhysPageMap;
 
 struct AddressSpaceDispatch {
     /* This is a multi-level map on the physical address space.
      * The bottom level has pointers to MemoryRegionSections.
      */
     PhysPageEntry phys_map;
-    Node *nodes;
+    PhysPageMap map;
-    MemoryRegionSection *sections;
     AddressSpace *as;
 };
 
@@ -113,18 +130,6 @@ typedef struct subpage_t {
 #define PHYS_SECTION_ROM 2
 #define PHYS_SECTION_WATCH 3
 
-typedef struct PhysPageMap {
-    unsigned sections_nb;
-    unsigned sections_nb_alloc;
-    unsigned nodes_nb;
-    unsigned nodes_nb_alloc;
-    Node *nodes;
-    MemoryRegionSection *sections;
-} PhysPageMap;
-
-static PhysPageMap *prev_map;
-static PhysPageMap next_map;
-
 #define PHYS_MAP_NODE_NIL (((uint16_t)~0) >> 1)
 
 static void io_mem_init(void);
@@ -135,63 +140,60 @@ static MemoryRegion io_mem_watch;
 
 #if !defined(CONFIG_USER_ONLY)
 
-static void phys_map_node_reserve(unsigned nodes)
+static void phys_map_node_reserve(PhysPageMap *map, unsigned nodes)
 {
-    if (next_map.nodes_nb + nodes > next_map.nodes_nb_alloc) {
+    if (map->nodes_nb + nodes > map->nodes_nb_alloc) {
-        next_map.nodes_nb_alloc = MAX(next_map.nodes_nb_alloc * 2,
+        map->nodes_nb_alloc = MAX(map->nodes_nb_alloc * 2, 16);
-                                            16);
+        map->nodes_nb_alloc = MAX(map->nodes_nb_alloc, map->nodes_nb + nodes);
-        next_map.nodes_nb_alloc = MAX(next_map.nodes_nb_alloc,
+        map->nodes = g_renew(Node, map->nodes, map->nodes_nb_alloc);
-                                      next_map.nodes_nb + nodes);
-        next_map.nodes = g_renew(Node, next_map.nodes,
-                                 next_map.nodes_nb_alloc);
     }
 }
 
-static uint16_t phys_map_node_alloc(void)
+static uint16_t phys_map_node_alloc(PhysPageMap *map)
 {
     unsigned i;
     uint16_t ret;
 
-    ret = next_map.nodes_nb++;
+    ret = map->nodes_nb++;
     assert(ret != PHYS_MAP_NODE_NIL);
-    assert(ret != next_map.nodes_nb_alloc);
+    assert(ret != map->nodes_nb_alloc);
-    for (i = 0; i < L2_SIZE; ++i) {
+    for (i = 0; i < P_L2_SIZE; ++i) {
-        next_map.nodes[ret][i].is_leaf = 0;
+        map->nodes[ret][i].skip = 1;
-        next_map.nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
+        map->nodes[ret][i].ptr = PHYS_MAP_NODE_NIL;
     }
     return ret;
 }
 
-static void phys_page_set_level(PhysPageEntry *lp, hwaddr *index,
+static void phys_page_set_level(PhysPageMap *map, PhysPageEntry *lp,
-                                hwaddr *nb, uint16_t leaf,
+                                hwaddr *index, hwaddr *nb, uint16_t leaf,
                                 int level)
 {
     PhysPageEntry *p;
     int i;
-    hwaddr step = (hwaddr)1 << (level * L2_BITS);
+    hwaddr step = (hwaddr)1 << (level * P_L2_BITS);
 
-    if (!lp->is_leaf && lp->ptr == PHYS_MAP_NODE_NIL) {
+    if (lp->skip && lp->ptr == PHYS_MAP_NODE_NIL) {
-        lp->ptr = phys_map_node_alloc();
+        lp->ptr = phys_map_node_alloc(map);
-        p = next_map.nodes[lp->ptr];
+        p = map->nodes[lp->ptr];
         if (level == 0) {
-            for (i = 0; i < L2_SIZE; i++) {
+            for (i = 0; i < P_L2_SIZE; i++) {
-                p[i].is_leaf = 1;
+                p[i].skip = 0;
                 p[i].ptr = PHYS_SECTION_UNASSIGNED;
             }
         }
     } else {
-        p = next_map.nodes[lp->ptr];
+        p = map->nodes[lp->ptr];
     }
-    lp = &p[(*index >> (level * L2_BITS)) & (L2_SIZE - 1)];
+    lp = &p[(*index >> (level * P_L2_BITS)) & (P_L2_SIZE - 1)];
 
-    while (*nb && lp < &p[L2_SIZE]) {
+    while (*nb && lp < &p[P_L2_SIZE]) {
         if ((*index & (step - 1)) == 0 && *nb >= step) {
-            lp->is_leaf = true;
+            lp->skip = 0;
             lp->ptr = leaf;
             *index += step;
             *nb -= step;
         } else {
-            phys_page_set_level(lp, index, nb, leaf, level - 1);
+            phys_page_set_level(map, lp, index, nb, leaf, level - 1);
         }
         ++lp;
     }
@@ -202,23 +204,24 @@ static void phys_page_set(AddressSpaceDispatch *d,
                           uint16_t leaf)
 {
     /* Wildly overreserve - it doesn't matter much. */
-    phys_map_node_reserve(3 * P_L2_LEVELS);
+    phys_map_node_reserve(&d->map, 3 * P_L2_LEVELS);
 
-    phys_page_set_level(&d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
+    phys_page_set_level(&d->map, &d->phys_map, &index, &nb, leaf, P_L2_LEVELS - 1);
 }
 
-static MemoryRegionSection *phys_page_find(PhysPageEntry lp, hwaddr index,
+static MemoryRegionSection *phys_page_find(PhysPageEntry lp, hwaddr addr,
                                            Node *nodes, MemoryRegionSection *sections)
 {
     PhysPageEntry *p;
+    hwaddr index = addr >> TARGET_PAGE_BITS;
     int i;
 
-    for (i = P_L2_LEVELS - 1; i >= 0 && !lp.is_leaf; i--) {
+    for (i = P_L2_LEVELS; lp.skip && (i -= lp.skip) >= 0;) {
         if (lp.ptr == PHYS_MAP_NODE_NIL) {
             return &sections[PHYS_SECTION_UNASSIGNED];
         }
         p = nodes[lp.ptr];
-        lp = p[(index >> (i * L2_BITS)) & (L2_SIZE - 1)];
+        lp = p[(index >> (i * P_L2_BITS)) & (P_L2_SIZE - 1)];
     }
     return &sections[lp.ptr];
 }
@@ -236,11 +239,10 @@ static MemoryRegionSection *address_space_lookup_region(AddressSpaceDispatch *d,
     MemoryRegionSection *section;
     subpage_t *subpage;
 
-    section = phys_page_find(d->phys_map, addr >> TARGET_PAGE_BITS,
+    section = phys_page_find(d->phys_map, addr, d->map.nodes, d->map.sections);
-                             d->nodes, d->sections);
     if (resolve_subpage && section->mr->subpage) {
         subpage = container_of(section->mr, subpage_t, iomem);
-        section = &d->sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
+        section = &d->map.sections[subpage->sub_section[SUBPAGE_IDX(addr)]];
     }
     return section;
 }
@@ -264,6 +266,18 @@ address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *x
     return section;
 }
 
+static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
+{
+    if (memory_region_is_ram(mr)) {
+        return !(is_write && mr->readonly);
+    }
+    if (memory_region_is_romd(mr)) {
+        return !is_write;
+    }
+
+    return false;
+}
+
 MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
                                       hwaddr *xlat, hwaddr *plen,
                                       bool is_write)
@@ -293,6 +307,11 @@ MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr,
         as = iotlb.target_as;
     }
 
+    if (memory_access_is_direct(mr, is_write)) {
+        hwaddr page = ((addr & TARGET_PAGE_MASK) + TARGET_PAGE_SIZE) - addr;
+        len = MIN(page, len);
+    }
+
     *plen = len;
     *xlat = addr;
     return mr;
@@ -708,7 +727,7 @@ hwaddr memory_region_section_get_iotlb(CPUArchState *env,
             iotlb |= PHYS_SECTION_ROM;
         }
     } else {
-        iotlb = section - address_space_memory.dispatch->sections;
+        iotlb = section - address_space_memory.dispatch->map.sections;
         iotlb += xlat;
     }
 
@@ -747,23 +766,23 @@ void phys_mem_set_alloc(void *(*alloc)(size_t))
     phys_mem_alloc = alloc;
 }
 
-static uint16_t phys_section_add(MemoryRegionSection *section)
+static uint16_t phys_section_add(PhysPageMap *map,
+                                 MemoryRegionSection *section)
 {
     /* The physical section number is ORed with a page-aligned
      * pointer to produce the iotlb entries.  Thus it should
      * never overflow into the page-aligned value.
      */
-    assert(next_map.sections_nb < TARGET_PAGE_SIZE);
+    assert(map->sections_nb < TARGET_PAGE_SIZE);
 
-    if (next_map.sections_nb == next_map.sections_nb_alloc) {
+    if (map->sections_nb == map->sections_nb_alloc) {
-        next_map.sections_nb_alloc = MAX(next_map.sections_nb_alloc * 2,
+        map->sections_nb_alloc = MAX(map->sections_nb_alloc * 2, 16);
-                                         16);
+        map->sections = g_renew(MemoryRegionSection, map->sections,
-        next_map.sections = g_renew(MemoryRegionSection, next_map.sections,
+                                map->sections_nb_alloc);
-                                    next_map.sections_nb_alloc);
     }
-    next_map.sections[next_map.sections_nb] = *section;
+    map->sections[map->sections_nb] = *section;
     memory_region_ref(section->mr);
-    return next_map.sections_nb++;
+    return map->sections_nb++;
 }
 
 static void phys_section_destroy(MemoryRegion *mr)
@@ -785,7 +804,6 @@ static void phys_sections_free(PhysPageMap *map)
     }
     g_free(map->sections);
     g_free(map->nodes);
-    g_free(map);
 }
 
 static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *section)
@@ -793,8 +811,8 @@ static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *secti
     subpage_t *subpage;
     hwaddr base = section->offset_within_address_space
         & TARGET_PAGE_MASK;
-    MemoryRegionSection *existing = phys_page_find(d->phys_map, base >> TARGET_PAGE_BITS,
+    MemoryRegionSection *existing = phys_page_find(d->phys_map, base,
-                                                   next_map.nodes, next_map.sections);
+                                                   d->map.nodes, d->map.sections);
     MemoryRegionSection subsection = {
         .offset_within_address_space = base,
         .size = int128_make64(TARGET_PAGE_SIZE),
@@ -807,13 +825,14 @@ static void register_subpage(AddressSpaceDispatch *d, MemoryRegionSection *secti
         subpage = subpage_init(d->as, base);
         subsection.mr = &subpage->iomem;
         phys_page_set(d, base >> TARGET_PAGE_BITS, 1,
-                      phys_section_add(&subsection));
+                      phys_section_add(&d->map, &subsection));
     } else {
         subpage = container_of(existing->mr, subpage_t, iomem);
     }
     start = section->offset_within_address_space & ~TARGET_PAGE_MASK;
     end = start + int128_get64(section->size) - 1;
-    subpage_register(subpage, start, end, phys_section_add(section));
+    subpage_register(subpage, start, end,
+                     phys_section_add(&d->map, section));
 }
 
 
@@ -821,7 +840,7 @@ static void register_multipage(AddressSpaceDispatch *d,
                                MemoryRegionSection *section)
 {
     hwaddr start_addr = section->offset_within_address_space;
-    uint16_t section_index = phys_section_add(section);
+    uint16_t section_index = phys_section_add(&d->map, section);
     uint64_t num_pages = int128_get64(int128_rshift(section->size,
                                                     TARGET_PAGE_BITS));
 
@@ -1605,7 +1624,7 @@ static subpage_t *subpage_init(AddressSpace *as, hwaddr base)
     return mmio;
 }
 
-static uint16_t dummy_section(MemoryRegion *mr)
+static uint16_t dummy_section(PhysPageMap *map, MemoryRegion *mr)
 {
     MemoryRegionSection section = {
         .mr = mr,
@@ -1614,12 +1633,13 @@ static uint16_t dummy_section(MemoryRegion *mr)
         .size = int128_2_64(),
     };
 
-    return phys_section_add(&section);
+    return phys_section_add(map, &section);
 }
 
 MemoryRegion *iotlb_to_region(hwaddr index)
 {
-    return address_space_memory.dispatch->sections[index & ~TARGET_PAGE_MASK].mr;
+    return address_space_memory.dispatch->map.sections[
+           index & ~TARGET_PAGE_MASK].mr;
 }
 
 static void io_mem_init(void)
@@ -1636,9 +1656,19 @@ static void io_mem_init(void)
 static void mem_begin(MemoryListener *listener)
 {
     AddressSpace *as = container_of(listener, AddressSpace, dispatch_listener);
-    AddressSpaceDispatch *d = g_new(AddressSpaceDispatch, 1);
+    AddressSpaceDispatch *d = g_new0(AddressSpaceDispatch, 1);
+    uint16_t n;
 
-    d->phys_map  = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .is_leaf = 0 };
+    n = dummy_section(&d->map, &io_mem_unassigned);
+    assert(n == PHYS_SECTION_UNASSIGNED);
+    n = dummy_section(&d->map, &io_mem_notdirty);
+    assert(n == PHYS_SECTION_NOTDIRTY);
+    n = dummy_section(&d->map, &io_mem_rom);
+    assert(n == PHYS_SECTION_ROM);
+    n = dummy_section(&d->map, &io_mem_watch);
+    assert(n == PHYS_SECTION_WATCH);
+
+    d->phys_map  = (PhysPageEntry) { .ptr = PHYS_MAP_NODE_NIL, .skip = 1 };
     d->as = as;
     as->next_dispatch = d;
 }
@@ -1649,37 +1679,12 @@ static void mem_commit(MemoryListener *listener)
     AddressSpaceDispatch *cur = as->dispatch;
     AddressSpaceDispatch *next = as->next_dispatch;
 
-    next->nodes = next_map.nodes;
-    next->sections = next_map.sections;
-
     as->dispatch = next;
-    g_free(cur);
-}
 
-static void core_begin(MemoryListener *listener)
+    if (cur) {
-{
+        phys_sections_free(&cur->map);
-    uint16_t n;
+        g_free(cur);
-
+    }
-    prev_map = g_new(PhysPageMap, 1);
-    *prev_map = next_map;
-
-    memset(&next_map, 0, sizeof(next_map));
-    n = dummy_section(&io_mem_unassigned);
-    assert(n == PHYS_SECTION_UNASSIGNED);
-    n = dummy_section(&io_mem_notdirty);
-    assert(n == PHYS_SECTION_NOTDIRTY);
-    n = dummy_section(&io_mem_rom);
-    assert(n == PHYS_SECTION_ROM);
-    n = dummy_section(&io_mem_watch);
-    assert(n == PHYS_SECTION_WATCH);
-}
-
-/* This listener's commit run after the other AddressSpaceDispatch listeners'.
- * All AddressSpaceDispatch instances have switched to the next map.
- */
-static void core_commit(MemoryListener *listener)
-{
-    phys_sections_free(prev_map);
 }
 
 static void tcg_commit(MemoryListener *listener)
@@ -1707,8 +1712,6 @@ static void core_log_global_stop(MemoryListener *listener)
 }
 
 static MemoryListener core_memory_listener = {
-    .begin = core_begin,
-    .commit = core_commit,
     .log_global_start = core_log_global_start,
     .log_global_stop = core_log_global_stop,
     .priority = 1,
@@ -1743,7 +1746,12 @@ void address_space_destroy_dispatch(AddressSpace *as)
 static void memory_map_init(void)
 {
     system_memory = g_malloc(sizeof(*system_memory));
-    memory_region_init(system_memory, NULL, "system", INT64_MAX);
+
+    assert(ADDR_SPACE_BITS <= 64);
+
+    memory_region_init(system_memory, NULL, "system",
+                       ADDR_SPACE_BITS == 64 ?
+                       UINT64_MAX : (0x1ULL << ADDR_SPACE_BITS));
     address_space_init(&address_space_memory, system_memory, "memory");
 
     system_io = g_malloc(sizeof(*system_io));
@@ -1824,18 +1832,6 @@ static void invalidate_and_set_dirty(hwaddr addr,
     xen_modified_memory(addr, length);
 }
 
-static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
-{
-    if (memory_region_is_ram(mr)) {
-        return !(is_write && mr->readonly);
-    }
-    if (memory_region_is_romd(mr)) {
-        return !is_write;
-    }
-
-    return false;
-}
-
 static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
 {
     unsigned access_size_max = mr->ops->valid.max_access_size;

hw/arm/mainstone.c

@@ -75,9 +75,18 @@ static struct keymap map[0xE0] = {
     [0x2c] = {4,3}, /* z */
     [0xc7] = {5,0}, /* Home */
     [0x2a] = {5,1}, /* shift */
-    [0x39] = {5,2}, /* space */
+    /*
+     * There are two matrix positions which map to space,
+     * but QEMU can only use one of them for the reverse
+     * mapping, so simply use the second one.
+     */
+    /* [0x39] = {5,2}, space */
     [0x39] = {5,3}, /* space */
-    [0x1c] = {5,5}, /*  enter */
+    /*
+     * Matrix position {5,4} and other keys are missing here.
+     * TODO: Compare with Linux code and test real hardware.
+     */
+    [0x1c] = {5,5}, /* enter (TODO: might be wrong) */
     [0xc8] = {6,0}, /* up */
     [0xd0] = {6,1}, /* down */
     [0xcb] = {6,2}, /* left */

hw/arm/musicpal.c

@@ -92,8 +92,6 @@
 #define MP_ETH_CRDP3            0x4AC
 #define MP_ETH_CTDP0            0x4E0
 #define MP_ETH_CTDP1            0x4E4
-#define MP_ETH_CTDP2            0x4E8
-#define MP_ETH_CTDP3            0x4EC
 
 /* MII PHY access */
 #define MP_ETH_SMIR_DATA        0x0000FFFF
@@ -308,7 +306,7 @@ static uint64_t mv88w8618_eth_read(void *opaque, hwaddr offset,
     case MP_ETH_CRDP0 ... MP_ETH_CRDP3:
         return s->rx_queue[(offset - MP_ETH_CRDP0)/4];
 
-    case MP_ETH_CTDP0 ... MP_ETH_CTDP3:
+    case MP_ETH_CTDP0 ... MP_ETH_CTDP1:
         return s->tx_queue[(offset - MP_ETH_CTDP0)/4];
 
     default:
@@ -362,7 +360,7 @@ static void mv88w8618_eth_write(void *opaque, hwaddr offset,
             s->cur_rx[(offset - MP_ETH_CRDP0)/4] = value;
         break;
 
-    case MP_ETH_CTDP0 ... MP_ETH_CTDP3:
+    case MP_ETH_CTDP0 ... MP_ETH_CTDP1:
         s->tx_queue[(offset - MP_ETH_CTDP0)/4] = value;
         break;
     }

hw/arm/omap1.c

@@ -172,7 +172,7 @@ static void omap_timer_clk_update(void *opaque, int line, int on)
 static void omap_timer_clk_setup(struct omap_mpu_timer_s *timer)
 {
     omap_clk_adduser(timer->clk,
-                    qemu_allocate_irqs(omap_timer_clk_update, timer, 1)[0]);
+                    qemu_allocate_irq(omap_timer_clk_update, timer, 0));
     timer->rate = omap_clk_getrate(timer->clk);
 }
 
@@ -2094,7 +2094,7 @@ static struct omap_mpuio_s *omap_mpuio_init(MemoryRegion *memory,
                           "omap-mpuio", 0x800);
     memory_region_add_subregion(memory, base, &s->iomem);
 
-    omap_clk_adduser(clk, qemu_allocate_irqs(omap_mpuio_onoff, s, 1)[0]);
+    omap_clk_adduser(clk, qemu_allocate_irq(omap_mpuio_onoff, s, 0));
 
     return s;
 }
@@ -2397,7 +2397,7 @@ static struct omap_pwl_s *omap_pwl_init(MemoryRegion *system_memory,
                           "omap-pwl", 0x800);
     memory_region_add_subregion(system_memory, base, &s->iomem);
 
-    omap_clk_adduser(clk, qemu_allocate_irqs(omap_pwl_clk_update, s, 1)[0]);
+    omap_clk_adduser(clk, qemu_allocate_irq(omap_pwl_clk_update, s, 0));
     return s;
 }
 
@@ -3481,8 +3481,8 @@ static void omap_mcbsp_i2s_start(void *opaque, int line, int level)
 void omap_mcbsp_i2s_attach(struct omap_mcbsp_s *s, I2SCodec *slave)
 {
     s->codec = slave;
-    slave->rx_swallow = qemu_allocate_irqs(omap_mcbsp_i2s_swallow, s, 1)[0];
+    slave->rx_swallow = qemu_allocate_irq(omap_mcbsp_i2s_swallow, s, 0);
-    slave->tx_start = qemu_allocate_irqs(omap_mcbsp_i2s_start, s, 1)[0];
+    slave->tx_start = qemu_allocate_irq(omap_mcbsp_i2s_start, s, 0);
 }
 
 /* LED Pulse Generators */
@@ -3630,7 +3630,7 @@ static struct omap_lpg_s *omap_lpg_init(MemoryRegion *system_memory,
     memory_region_init_io(&s->iomem, NULL, &omap_lpg_ops, s, "omap-lpg", 0x800);
     memory_region_add_subregion(system_memory, base, &s->iomem);
 
-    omap_clk_adduser(clk, qemu_allocate_irqs(omap_lpg_clk_update, s, 1)[0]);
+    omap_clk_adduser(clk, qemu_allocate_irq(omap_lpg_clk_update, s, 0));
 
     return s;
 }
@@ -3844,7 +3844,7 @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory,
     s->sdram_size = sdram_size;
     s->sram_size = OMAP15XX_SRAM_SIZE;
 
-    s->wakeup = qemu_allocate_irqs(omap_mpu_wakeup, s, 1)[0];
+    s->wakeup = qemu_allocate_irq(omap_mpu_wakeup, s, 0);
 
     /* Clocks */
     omap_clk_init(s);

hw/arm/omap2.c

@@ -2260,7 +2260,7 @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem,
     s->sdram_size = sdram_size;
     s->sram_size = OMAP242X_SRAM_SIZE;
 
-    s->wakeup = qemu_allocate_irqs(omap_mpu_wakeup, s, 1)[0];
+    s->wakeup = qemu_allocate_irq(omap_mpu_wakeup, s, 0);
 
     /* Clocks */
     omap_clk_init(s);

hw/arm/pxa2xx.c

@@ -742,7 +742,7 @@ static void pxa2xx_ssp_save(QEMUFile *f, void *opaque)
 static int pxa2xx_ssp_load(QEMUFile *f, void *opaque, int version_id)
 {
     PXA2xxSSPState *s = (PXA2xxSSPState *) opaque;
-    int i;
+    int i, v;
 
     s->enable = qemu_get_be32(f);
 
@@ -756,7 +756,11 @@ static int pxa2xx_ssp_load(QEMUFile *f, void *opaque, int version_id)
     qemu_get_8s(f, &s->ssrsa);
     qemu_get_8s(f, &s->ssacd);
 
-    s->rx_level = qemu_get_byte(f);
+    v = qemu_get_byte(f);
+    if (v < 0 || v > ARRAY_SIZE(s->rx_fifo)) {
+        return -EINVAL;
+    }
+    s->rx_level = v;
     s->rx_start = 0;
     for (i = 0; i < s->rx_level; i ++)
         s->rx_fifo[i] = qemu_get_byte(f);
@@ -2053,7 +2057,7 @@ PXA2xxState *pxa270_init(MemoryRegion *address_space,
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    s->reset = qemu_allocate_irqs(pxa2xx_reset, s, 1)[0];
+    s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0);
 
     /* SDRAM & Internal Memory Storage */
     memory_region_init_ram(&s->sdram, NULL, "pxa270.sdram", sdram_size);
@@ -2184,7 +2188,7 @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size)
         fprintf(stderr, "Unable to find CPU definition\n");
         exit(1);
     }
-    s->reset = qemu_allocate_irqs(pxa2xx_reset, s, 1)[0];
+    s->reset = qemu_allocate_irq(pxa2xx_reset, s, 0);
 
     /* SDRAM & Internal Memory Storage */
     memory_region_init_ram(&s->sdram, NULL, "pxa255.sdram", sdram_size);

hw/arm/spitz.c

@@ -743,7 +743,7 @@ static void spitz_i2c_setup(PXA2xxState *cpu)
 
     spitz_wm8750_addr(wm, 0, 0);
     qdev_connect_gpio_out(cpu->gpio, SPITZ_GPIO_WM,
-                    qemu_allocate_irqs(spitz_wm8750_addr, wm, 1)[0]);
+                          qemu_allocate_irq(spitz_wm8750_addr, wm, 0));
     /* .. and to the sound interface.  */
     cpu->i2s->opaque = wm;
     cpu->i2s->codec_out = wm8750_dac_dat;
@@ -849,7 +849,7 @@ static void spitz_gpio_setup(PXA2xxState *cpu, int slots)
      * wouldn't guarantee that a guest ever exits the loop.
      */
     spitz_hsync = 0;
-    lcd_hsync = qemu_allocate_irqs(spitz_lcd_hsync_handler, cpu, 1)[0];
+    lcd_hsync = qemu_allocate_irq(spitz_lcd_hsync_handler, cpu, 0);
     pxa2xx_gpio_read_notifier(cpu->gpio, lcd_hsync);
     pxa2xx_lcd_vsync_notifier(cpu->lcd, lcd_hsync);
 

hw/arm/z2.c

@@ -359,7 +359,7 @@ static void z2_init(QEMUMachineInitArgs *args)
     wm8750_data_req_set(wm, mpu->i2s->data_req, mpu->i2s);
 
     qdev_connect_gpio_out(mpu->gpio, Z2_GPIO_LCD_CS,
-        qemu_allocate_irqs(z2_lcd_cs, z2_lcd, 1)[0]);
+                          qemu_allocate_irq(z2_lcd_cs, z2_lcd, 0));
 
     z2_binfo.kernel_filename = kernel_filename;
     z2_binfo.kernel_cmdline = kernel_cmdline;

hw/audio/adlib.c

@@ -347,8 +347,8 @@ static void adlib_realizefn (DeviceState *dev, Error **errp)
     s->samples = AUD_get_buffer_size_out (s->voice) >> SHIFT;
     s->mixbuf = g_malloc0 (s->samples << SHIFT);
 
-    adlib_portio_list[1].offset = s->port;
+    adlib_portio_list[0].offset = s->port;
-    adlib_portio_list[2].offset = s->port + 8;
+    adlib_portio_list[1].offset = s->port + 8;
     portio_list_init (port_list, OBJECT(s), adlib_portio_list, s, "adlib");
     portio_list_add (port_list, isa_address_space_io(&s->parent_obj), 0);
 }

hw/audio/intel-hda.c

@@ -444,6 +444,7 @@ static bool intel_hda_xfer(HDACodecDevice *dev, uint32_t stnr, bool output,
         }
     }
     if (d->dp_lbase & 0x01) {
+        s = st - d->st;
         addr = intel_hda_addr(d->dp_lbase & ~0x01, d->dp_ubase);
         stl_le_pci_dma(&d->pci, addr + 8*s, st->lpib);
     }

hw/block/virtio-blk.c

@@ -728,20 +728,18 @@ static int virtio_blk_device_init(VirtIODevice *vdev)
     return 0;
 }
 
-static int virtio_blk_device_exit(DeviceState *dev)
+static void virtio_blk_device_exit(VirtIODevice *vdev)
 {
-    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VirtIOBlock *s = VIRTIO_BLK(vdev);
-    VirtIOBlock *s = VIRTIO_BLK(dev);
 #ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
     remove_migration_state_change_notifier(&s->migration_state_notifier);
     virtio_blk_data_plane_destroy(s->dataplane);
     s->dataplane = NULL;
 #endif
     qemu_del_vm_change_state_handler(s->change);
-    unregister_savevm(dev, "virtio-blk", s);
+    unregister_savevm(DEVICE(vdev), "virtio-blk", s);
     blockdev_mark_auto_del(s->bs);
     virtio_cleanup(vdev);
-    return 0;
 }
 
 static Property virtio_blk_properties[] = {
@@ -753,10 +751,10 @@ static void virtio_blk_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_blk_device_exit;
     dc->props = virtio_blk_properties;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     vdc->init = virtio_blk_device_init;
+    vdc->exit = virtio_blk_device_exit;
     vdc->get_config = virtio_blk_update_config;
     vdc->set_config = virtio_blk_set_config;
     vdc->get_features = virtio_blk_get_features;

hw/char/virtio-serial-bus.c

@@ -670,6 +670,7 @@ static int virtio_serial_load(QEMUFile *f, void *opaque, int version_id)
     uint32_t max_nr_ports, nr_active_ports, ports_map;
     unsigned int i;
     int ret;
+    uint32_t tmp;
 
     if (version_id > 3) {
         return -EINVAL;
@@ -685,17 +686,12 @@ static int virtio_serial_load(QEMUFile *f, void *opaque, int version_id)
         return 0;
     }
 
-    /* The config space */
+    /* Unused */
-    qemu_get_be16s(f, &s->config.cols);
+    qemu_get_be16s(f, (uint16_t *) &tmp);
-    qemu_get_be16s(f, &s->config.rows);
+    qemu_get_be16s(f, (uint16_t *) &tmp);
-
+    qemu_get_be32s(f, &tmp);
-    qemu_get_be32s(f, &max_nr_ports);
-    tswap32s(&max_nr_ports);
-    if (max_nr_ports > tswap32(s->config.max_nr_ports)) {
-        /* Source could have had more ports than us. Fail migration. */
-        return -EINVAL;
-    }
 
+    max_nr_ports = tswap32(s->config.max_nr_ports);
     for (i = 0; i < (max_nr_ports + 31) / 32; i++) {
         qemu_get_be32s(f, &ports_map);
 
@@ -987,12 +983,11 @@ static const TypeInfo virtio_serial_port_type_info = {
     .class_init = virtio_serial_port_class_init,
 };
 
-static int virtio_serial_device_exit(DeviceState *dev)
+static void virtio_serial_device_exit(VirtIODevice *vdev)
 {
-    VirtIOSerial *vser = VIRTIO_SERIAL(dev);
+    VirtIOSerial *vser = VIRTIO_SERIAL(vdev);
-    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
 
-    unregister_savevm(dev, "virtio-console", vser);
+    unregister_savevm(DEVICE(vdev), "virtio-console", vser);
 
     g_free(vser->ivqs);
     g_free(vser->ovqs);
@@ -1004,7 +999,6 @@ static int virtio_serial_device_exit(DeviceState *dev)
         g_free(vser->post_load);
     }
     virtio_cleanup(vdev);
-    return 0;
 }
 
 static Property virtio_serial_properties[] = {
@@ -1016,10 +1010,10 @@ static void virtio_serial_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_serial_device_exit;
     dc->props = virtio_serial_properties;
     set_bit(DEVICE_CATEGORY_INPUT, dc->categories);
     vdc->init = virtio_serial_device_init;
+    vdc->exit = virtio_serial_device_exit;
     vdc->get_features = get_features;
     vdc->get_config = get_config;
     vdc->set_config = set_config;

hw/core/irq.c

@@ -102,7 +102,7 @@ qemu_irq qemu_irq_invert(qemu_irq irq)
 {
     /* The default state for IRQs is low, so raise the output now.  */
     qemu_irq_raise(irq);
-    return qemu_allocate_irqs(qemu_notirq, irq, 1)[0];
+    return qemu_allocate_irq(qemu_notirq, irq, 0);
 }
 
 static void qemu_splitirq(void *opaque, int line, int level)
@@ -117,7 +117,7 @@ qemu_irq qemu_irq_split(qemu_irq irq1, qemu_irq irq2)
     qemu_irq *s = g_malloc0(2 * sizeof(qemu_irq));
     s[0] = irq1;
     s[1] = irq2;
-    return qemu_allocate_irqs(qemu_splitirq, s, 1)[0];
+    return qemu_allocate_irq(qemu_splitirq, s, 0);
 }
 
 static void proxy_irq_handler(void *opaque, int n, int level)

hw/display/ssd0323.c

@@ -312,18 +312,42 @@ static int ssd0323_load(QEMUFile *f, void *opaque, int version_id)
         return -EINVAL;
 
     s->cmd_len = qemu_get_be32(f);
+    if (s->cmd_len < 0 || s->cmd_len > ARRAY_SIZE(s->cmd_data)) {
+        return -EINVAL;
+    }
     s->cmd = qemu_get_be32(f);
     for (i = 0; i < 8; i++)
         s->cmd_data[i] = qemu_get_be32(f);
     s->row = qemu_get_be32(f);
+    if (s->row < 0 || s->row >= 80) {
+        return -EINVAL;
+    }
     s->row_start = qemu_get_be32(f);
+    if (s->row_start < 0 || s->row_start >= 80) {
+        return -EINVAL;
+    }
     s->row_end = qemu_get_be32(f);
+    if (s->row_end < 0 || s->row_end >= 80) {
+        return -EINVAL;
+    }
     s->col = qemu_get_be32(f);
+    if (s->col < 0 || s->col >= 64) {
+        return -EINVAL;
+    }
     s->col_start = qemu_get_be32(f);
+    if (s->col_start < 0 || s->col_start >= 64) {
+        return -EINVAL;
+    }
     s->col_end = qemu_get_be32(f);
+    if (s->col_end < 0 || s->col_end >= 64) {
+        return -EINVAL;
+    }
     s->redraw = qemu_get_be32(f);
     s->remap = qemu_get_be32(f);
     s->mode = qemu_get_be32(f);
+    if (s->mode != SSD0323_CMD && s->mode != SSD0323_DATA) {
+        return -EINVAL;
+    }
     qemu_get_buffer(f, s->framebuffer, sizeof(s->framebuffer));
 
     ss->cs = qemu_get_be32(f);

hw/dma/omap_dma.c

@@ -1660,7 +1660,7 @@ struct soc_dma_s *omap_dma_init(hwaddr base, qemu_irq *irqs,
     }
 
     omap_dma_setcaps(s);
-    omap_clk_adduser(s->clk, qemu_allocate_irqs(omap_dma_clk_update, s, 1)[0]);
+    omap_clk_adduser(s->clk, qemu_allocate_irq(omap_dma_clk_update, s, 0));
     omap_dma_reset(s->dma);
     omap_dma_clk_update(s, 0, 1);
 
@@ -2082,7 +2082,7 @@ struct soc_dma_s *omap_dma4_init(hwaddr base, qemu_irq *irqs,
     s->intr_update = omap_dma_interrupts_4_update;
 
     omap_dma_setcaps(s);
-    omap_clk_adduser(s->clk, qemu_allocate_irqs(omap_dma_clk_update, s, 1)[0]);
+    omap_clk_adduser(s->clk, qemu_allocate_irq(omap_dma_clk_update, s, 0));
     omap_dma_reset(s->dma);
     omap_dma_clk_update(s, 0, !!s->dma->freq);
 

hw/gpio/zaurus.c

@@ -203,6 +203,15 @@ static bool is_version_0 (void *opaque, int version_id)
     return version_id == 0;
 }
 
+static bool vmstate_scoop_validate(void *opaque, int version_id)
+{
+    ScoopInfo *s = opaque;
+
+    return !(s->prev_level & 0xffff0000) &&
+        !(s->gpio_level & 0xffff0000) &&
+        !(s->gpio_dir & 0xffff0000);
+}
+
 static const VMStateDescription vmstate_scoop_regs = {
     .name = "scoop",
     .version_id = 1,
@@ -215,6 +224,7 @@ static const VMStateDescription vmstate_scoop_regs = {
         VMSTATE_UINT32(gpio_level, ScoopInfo),
         VMSTATE_UINT32(gpio_dir, ScoopInfo),
         VMSTATE_UINT32(prev_level, ScoopInfo),
+        VMSTATE_VALIDATE("irq levels are 16 bit", vmstate_scoop_validate),
         VMSTATE_UINT16(mcr, ScoopInfo),
         VMSTATE_UINT16(cdr, ScoopInfo),
         VMSTATE_UINT16(ccr, ScoopInfo),

hw/i386/acpi-build.c

@@ -1075,15 +1075,16 @@ void acpi_build(PcGuestInfo *guest_info, AcpiBuildTables *tables)
     /* ACPI tables pointed to by RSDT */
     acpi_add_table(table_offsets, tables->table_data);
     build_fadt(tables->table_data, tables->linker, &pm, facs, dsdt);
-    acpi_add_table(table_offsets, tables->table_data);
 
+    acpi_add_table(table_offsets, tables->table_data);
     build_ssdt(tables->table_data, tables->linker, &cpu, &pm, &misc, &pci,
                guest_info);
-    acpi_add_table(table_offsets, tables->table_data);
 
-    build_madt(tables->table_data, tables->linker, &cpu, guest_info);
     acpi_add_table(table_offsets, tables->table_data);
+    build_madt(tables->table_data, tables->linker, &cpu, guest_info);
+
     if (misc.has_hpet) {
+        acpi_add_table(table_offsets, tables->table_data);
         build_hpet(tables->table_data, tables->linker);
     }
     if (guest_info->numa_nodes) {

hw/i386/bios-linker-loader.c

@@ -18,11 +18,10 @@
  * with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#include "qemu-common.h"
 #include "bios-linker-loader.h"
 #include "hw/nvram/fw_cfg.h"
 
-#include <string.h>
-#include <assert.h>
 #include "qemu/bswap.h"
 
 #define BIOS_LINKER_LOADER_FILESZ FW_CFG_MAX_FILE_PATH

hw/i386/kvm/pci-assign.c

@@ -1257,6 +1257,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
     if (pos != 0 && kvm_device_msix_supported(kvm_state)) {
         int bar_nr;
         uint32_t msix_table_entry;
+        uint16_t msix_max;
 
         if (!check_irqchip_in_kernel()) {
             return -ENOTSUP;
@@ -1268,9 +1269,10 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
         }
         pci_dev->msix_cap = pos;
 
-        pci_set_word(pci_dev->config + pos + PCI_MSIX_FLAGS,
+        msix_max = (pci_get_word(pci_dev->config + pos + PCI_MSIX_FLAGS) &
-                     pci_get_word(pci_dev->config + pos + PCI_MSIX_FLAGS) &
+                    PCI_MSIX_FLAGS_QSIZE) + 1;
-                     PCI_MSIX_FLAGS_QSIZE);
+        msix_max = MIN(msix_max, KVM_MAX_MSIX_PER_DEV);
+        pci_set_word(pci_dev->config + pos + PCI_MSIX_FLAGS, msix_max - 1);
 
         /* Only enable and function mask bits are writable */
         pci_set_word(pci_dev->wmask + pos + PCI_MSIX_FLAGS,
@@ -1280,9 +1282,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
         bar_nr = msix_table_entry & PCI_MSIX_FLAGS_BIRMASK;
         msix_table_entry &= ~PCI_MSIX_FLAGS_BIRMASK;
         dev->msix_table_addr = pci_region[bar_nr].base_addr + msix_table_entry;
-        dev->msix_max = pci_get_word(pci_dev->config + pos + PCI_MSIX_FLAGS);
+        dev->msix_max = msix_max;
-        dev->msix_max &= PCI_MSIX_FLAGS_QSIZE;
-        dev->msix_max += 1;
     }
 
     /* Minimal PM support, nothing writable, device appears to NAK changes */

hw/i386/pc.c

@@ -1093,21 +1093,13 @@ PcGuestInfo *pc_guest_info_init(ram_addr_t below_4g_mem_size,
     return guest_info;
 }
 
-void pc_init_pci64_hole(PcPciInfo *pci_info, uint64_t pci_hole64_start,
+/* setup pci memory address space mapping into system address space */
-                        uint64_t pci_hole64_size)
+void pc_pci_as_mapping_init(Object *owner, MemoryRegion *system_memory,
+                            MemoryRegion *pci_address_space)
 {
-    if ((sizeof(hwaddr) == 4) || (!pci_hole64_size)) {
+    /* Set to lower priority than RAM */
-        return;
+    memory_region_add_subregion_overlap(system_memory, 0x0,
-    }
+                                        pci_address_space, -1);
-    /*
-     * BIOS does not set MTRR entries for the 64 bit window, so no need to
-     * align address to power of two.  Align address at 1G, this makes sure
-     * it can be exactly covered with a PAT entry even when using huge
-     * pages.
-     */
-    pci_info->w64.begin = ROUND_UP(pci_hole64_start, 0x1ULL << 30);
-    pci_info->w64.end = pci_info->w64.begin + pci_hole64_size;
-    assert(pci_info->w64.begin <= pci_info->w64.end);
 }
 
 void pc_acpi_init(const char *default_dsdt)

hw/i386/pc_piix.c

@@ -150,7 +150,6 @@ static void pc_init1(QEMUMachineInitArgs *args,
         pci_bus = i440fx_init(&i440fx_state, &piix3_devfn, &isa_bus, gsi,
                               system_memory, system_io, args->ram_size,
                               below_4g_mem_size,
-                              0x100000000ULL - below_4g_mem_size,
                               above_4g_mem_size,
                               pci_memory, ram_memory);
     } else {

hw/ide/ahci.c

@@ -1290,7 +1290,7 @@ const VMStateDescription vmstate_ahci = {
         VMSTATE_UINT32(control_regs.impl, AHCIState),
         VMSTATE_UINT32(control_regs.version, AHCIState),
         VMSTATE_UINT32(idp_index, AHCIState),
-        VMSTATE_INT32(ports, AHCIState),
+        VMSTATE_INT32_EQUAL(ports, AHCIState),
         VMSTATE_END_OF_LIST()
     },
 };

hw/ide/core.c

@@ -1601,7 +1601,7 @@ static bool cmd_smart(IDEState *s, uint8_t cmd)
         case 2: /* extended self test */
             s->smart_selftest_count++;
             if (s->smart_selftest_count > 21) {
-                s->smart_selftest_count = 0;
+                s->smart_selftest_count = 1;
             }
             n = 2 + (s->smart_selftest_count - 1) * 24;
             s->smart_selftest_data[n] = s->sector;

hw/ide/microdrive.c

@@ -594,7 +594,7 @@ static void microdrive_realize(DeviceState *dev, Error **errp)
 {
     MicroDriveState *md = MICRODRIVE(dev);
 
-    ide_init2(&md->bus, qemu_allocate_irqs(md_set_irq, md, 1)[0]);
+    ide_init2(&md->bus, qemu_allocate_irq(md_set_irq, md, 0));
 }
 
 static void microdrive_init(Object *obj)

hw/input/tsc210x.c

@@ -1070,9 +1070,21 @@ static int tsc210x_load(QEMUFile *f, void *opaque, int version_id)
     s->enabled = qemu_get_byte(f);
     s->host_mode = qemu_get_byte(f);
     s->function = qemu_get_byte(f);
+    if (s->function < 0 || s->function >= ARRAY_SIZE(mode_regs)) {
+        return -EINVAL;
+    }
     s->nextfunction = qemu_get_byte(f);
+    if (s->nextfunction < 0 || s->nextfunction >= ARRAY_SIZE(mode_regs)) {
+        return -EINVAL;
+    }
     s->precision = qemu_get_byte(f);
+    if (s->precision < 0 || s->precision >= ARRAY_SIZE(resolution)) {
+        return -EINVAL;
+    }
     s->nextprecision = qemu_get_byte(f);
+    if (s->nextprecision < 0 || s->nextprecision >= ARRAY_SIZE(resolution)) {
+        return -EINVAL;
+    }
     s->filter = qemu_get_byte(f);
     s->pin_func = qemu_get_byte(f);
     s->ref = qemu_get_byte(f);

hw/intc/exynos4210_combiner.c

@@ -418,7 +418,7 @@ static int exynos4210_combiner_init(SysBusDevice *sbd)
     qdev_init_gpio_in(dev, exynos4210_combiner_handler, IIC_NIRQ);
 
     /* Connect SysBusDev irqs to device specific irqs */
-    for (i = 0; i < IIC_NIRQ; i++) {
+    for (i = 0; i < IIC_NGRP; i++) {
         sysbus_init_irq(sbd, &s->output_irq[i]);
     }
 

hw/intc/gic_internal.h

@@ -41,7 +41,7 @@
 #define GIC_SET_MODEL(irq) s->irq_state[irq].model = true
 #define GIC_CLEAR_MODEL(irq) s->irq_state[irq].model = false
 #define GIC_TEST_MODEL(irq) s->irq_state[irq].model
-#define GIC_SET_LEVEL(irq, cm) s->irq_state[irq].level = (cm)
+#define GIC_SET_LEVEL(irq, cm) s->irq_state[irq].level |= (cm)
 #define GIC_CLEAR_LEVEL(irq, cm) s->irq_state[irq].level &= ~(cm)
 #define GIC_TEST_LEVEL(irq, cm) ((s->irq_state[irq].level & (cm)) != 0)
 #define GIC_SET_TRIGGER(irq) s->irq_state[irq].trigger = true

hw/intc/openpic.c

@@ -41,6 +41,7 @@
 #include "hw/sysbus.h"
 #include "hw/pci/msi.h"
 #include "qemu/bitops.h"
+#include "qapi/qmp/qerror.h"
 
 //#define DEBUG_OPENPIC
 
@@ -1416,7 +1417,7 @@ static void openpic_load_IRQ_queue(QEMUFile* f, IRQQueue *q)
 static int openpic_load(QEMUFile* f, void *opaque, int version_id)
 {
     OpenPICState *opp = (OpenPICState *)opaque;
-    unsigned int i;
+    unsigned int i, nb_cpus;
 
     if (version_id != 1) {
         return -EINVAL;
@@ -1428,7 +1429,11 @@ static int openpic_load(QEMUFile* f, void *opaque, int version_id)
     qemu_get_be32s(f, &opp->spve);
     qemu_get_be32s(f, &opp->tfrr);
 
-    qemu_get_be32s(f, &opp->nb_cpus);
+    qemu_get_be32s(f, &nb_cpus);
+    if (opp->nb_cpus != nb_cpus) {
+        return -EINVAL;
+    }
+    assert(nb_cpus > 0 && nb_cpus <= MAX_CPU);
 
     for (i = 0; i < opp->nb_cpus; i++) {
         qemu_get_sbe32s(f, &opp->dst[i].ctpr);
@@ -1567,6 +1572,13 @@ static void openpic_realize(DeviceState *dev, Error **errp)
         {NULL}
     };
 
+    if (opp->nb_cpus > MAX_CPU) {
+        error_set(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE,
+                  TYPE_OPENPIC, "nb_cpus", (uint64_t)opp->nb_cpus,
+                  (uint64_t)0, (uint64_t)MAX_CPU);
+        return;
+    }
+
     switch (opp->model) {
     case OPENPIC_MODEL_FSL_MPIC_20:
     default:

hw/misc/arm_sysctl.c

@@ -276,7 +276,7 @@ static bool vexpress_cfgctrl_read(arm_sysctl_state *s, unsigned int dcc,
         }
         break;
     case SYS_CFG_OSC:
-        if (site == SYS_CFG_SITE_MB && device < sizeof(s->mb_clock)) {
+        if (site == SYS_CFG_SITE_MB && device < ARRAY_SIZE(s->mb_clock)) {
             /* motherboard clock */
             *val = s->mb_clock[device];
             return true;
@@ -324,7 +324,7 @@ static bool vexpress_cfgctrl_write(arm_sysctl_state *s, unsigned int dcc,
 
     switch (function) {
     case SYS_CFG_OSC:
-        if (site == SYS_CFG_SITE_MB && device < sizeof(s->mb_clock)) {
+        if (site == SYS_CFG_SITE_MB && device < ARRAY_SIZE(s->mb_clock)) {
             /* motherboard clock */
             s->mb_clock[device] = val;
             return true;

hw/misc/cbus.c

@@ -135,9 +135,9 @@ CBus *cbus_init(qemu_irq dat)
     CBusPriv *s = (CBusPriv *) g_malloc0(sizeof(*s));
 
     s->dat_out = dat;
-    s->cbus.clk = qemu_allocate_irqs(cbus_clk, s, 1)[0];
+    s->cbus.clk = qemu_allocate_irq(cbus_clk, s, 0);
-    s->cbus.dat = qemu_allocate_irqs(cbus_dat, s, 1)[0];
+    s->cbus.dat = qemu_allocate_irq(cbus_dat, s, 0);
-    s->cbus.sel = qemu_allocate_irqs(cbus_sel, s, 1)[0];
+    s->cbus.sel = qemu_allocate_irq(cbus_sel, s, 0);
 
     s->sel = 1;
     s->clk = 0;

hw/misc/vfio.c

@@ -878,8 +878,20 @@ static void vfio_disable_msi_common(VFIODevice *vdev)
 
 static void vfio_disable_msix(VFIODevice *vdev)
 {
+    int i;
+
     msix_unset_vector_notifiers(&vdev->pdev);
 
+    /*
+     * MSI-X will only release vectors if MSI-X is still enabled on the
+     * device, check through the rest and release it ourselves if necessary.
+     */
+    for (i = 0; i < vdev->nr_vectors; i++) {
+        if (vdev->msi_vectors[i].use) {
+            vfio_msix_vector_release(&vdev->pdev, i);
+        }
+    }
+
     if (vdev->nr_vectors) {
         vfio_disable_irqindex(vdev, VFIO_PCI_MSIX_IRQ_INDEX);
     }

hw/net/stellaris_enet.c

@@ -8,6 +8,7 @@
  */
 #include "hw/sysbus.h"
 #include "net/net.h"
+#include "migration/migration.h"
 #include <zlib.h>
 
 //#define DEBUG_STELLARIS_ENET 1
@@ -75,6 +76,7 @@ typedef struct {
     NICConf conf;
     qemu_irq irq;
     MemoryRegion mmio;
+    Error *migration_blocker;
 } stellaris_enet_state;
 
 static void stellaris_enet_update(stellaris_enet_state *s)
@@ -252,17 +254,19 @@ static void stellaris_enet_write(void *opaque, hwaddr offset,
                 s->tx_fifo[s->tx_fifo_len++] = value >> 24;
             }
         } else {
-            s->tx_fifo[s->tx_fifo_len++] = value;
+            if (s->tx_fifo_len + 4 <= ARRAY_SIZE(s->tx_fifo)) {
-            s->tx_fifo[s->tx_fifo_len++] = value >> 8;
+                s->tx_fifo[s->tx_fifo_len++] = value;
-            s->tx_fifo[s->tx_fifo_len++] = value >> 16;
+                s->tx_fifo[s->tx_fifo_len++] = value >> 8;
-            s->tx_fifo[s->tx_fifo_len++] = value >> 24;
+                s->tx_fifo[s->tx_fifo_len++] = value >> 16;
+                s->tx_fifo[s->tx_fifo_len++] = value >> 24;
+            }
             if (s->tx_fifo_len >= s->tx_frame_len) {
                 /* We don't implement explicit CRC, so just chop it off.  */
                 if ((s->tctl & SE_TCTL_CRC) == 0)
                     s->tx_frame_len -= 4;
                 if ((s->tctl & SE_TCTL_PADEN) && s->tx_frame_len < 60) {
                     memset(&s->tx_fifo[s->tx_frame_len], 0, 60 - s->tx_frame_len);
-                    s->tx_fifo_len = 60;
+                    s->tx_frame_len = 60;
                 }
                 qemu_send_packet(qemu_get_queue(s->nic), s->tx_fifo,
                                  s->tx_frame_len);
@@ -359,7 +363,7 @@ static int stellaris_enet_load(QEMUFile *f, void *opaque, int version_id)
     stellaris_enet_state *s = (stellaris_enet_state *)opaque;
     int i;
 
-    if (version_id != 1)
+    if (1)
         return -EINVAL;
 
     s->ris = qemu_get_be32(f);
@@ -420,6 +424,10 @@ static int stellaris_enet_init(SysBusDevice *sbd)
     stellaris_enet_reset(s);
     register_savevm(dev, "stellaris_enet", -1, 1,
                     stellaris_enet_save, stellaris_enet_load, s);
+
+    error_setg(&s->migration_blocker,
+            "stellaris_enet does not support migration");
+    migrate_add_blocker(s->migration_blocker);
     return 0;
 }
 
@@ -427,6 +435,9 @@ static void stellaris_enet_unrealize(DeviceState *dev, Error **errp)
 {
     stellaris_enet_state *s = STELLARIS_ENET(dev);
 
+    migrate_del_blocker(s->migration_blocker);
+    error_free(s->migration_blocker);
+
     unregister_savevm(DEVICE(s), "stellaris_enet", s);
 
     memory_region_destroy(&s->mmio);

hw/net/virtio-net.c

@@ -515,6 +515,12 @@ static void virtio_net_set_features(VirtIODevice *vdev, uint32_t features)
         }
         vhost_net_ack_features(tap_get_vhost_net(nc->peer), features);
     }
+
+    if ((1 << VIRTIO_NET_F_CTRL_VLAN) & features) {
+        memset(n->vlans, 0, MAX_VLAN >> 3);
+    } else {
+        memset(n->vlans, 0xff, MAX_VLAN >> 3);
+    }
 }
 
 static int virtio_net_handle_rx_mode(VirtIONet *n, uint8_t cmd,
@@ -837,6 +843,14 @@ static int virtio_net_has_buffers(VirtIONetQueue *q, int bufsize)
     return 1;
 }
 
+static void virtio_net_hdr_swap(struct virtio_net_hdr *hdr)
+{
+    tswap16s(&hdr->hdr_len);
+    tswap16s(&hdr->gso_size);
+    tswap16s(&hdr->csum_start);
+    tswap16s(&hdr->csum_offset);
+}
+
 /* dhclient uses AF_PACKET but doesn't pass auxdata to the kernel so
  * it never finds out that the packets don't have valid checksums.  This
  * causes dhclient to get upset.  Fedora's carried a patch for ages to
@@ -872,6 +886,7 @@ static void receive_header(VirtIONet *n, const struct iovec *iov, int iov_cnt,
         void *wbuf = (void *)buf;
         work_around_broken_dhclient(wbuf, wbuf + n->host_hdr_len,
                                     size - n->host_hdr_len);
+        virtio_net_hdr_swap(wbuf);
         iov_from_buf(iov, iov_cnt, 0, buf, sizeof(struct virtio_net_hdr));
     } else {
         struct virtio_net_hdr hdr = {
@@ -1080,6 +1095,14 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
             exit(1);
         }
 
+        if (n->has_vnet_hdr) {
+            if (out_sg[0].iov_len < n->guest_hdr_len) {
+                error_report("virtio-net header incorrect");
+                exit(1);
+            }
+            virtio_net_hdr_swap((void *) out_sg[0].iov_base);
+        }
+
         /*
          * If host wants to see the guest header as is, we can
          * pass it on unchanged. Otherwise, copy just the parts
@@ -1336,10 +1359,17 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
         if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) {
             qemu_get_buffer(f, n->mac_table.macs,
                             n->mac_table.in_use * ETH_ALEN);
-        } else if (n->mac_table.in_use) {
+        } else {
-            uint8_t *buf = g_malloc0(n->mac_table.in_use);
+            int64_t i;
-            qemu_get_buffer(f, buf, n->mac_table.in_use * ETH_ALEN);
+
-            g_free(buf);
+            /* Overflow detected - can happen if source has a larger MAC table.
+             * We simply set overflow flag so there's no need to maintain the
+             * table of addresses, discard them all.
+             * Note: 64 bit math to avoid integer overflow.
+             */
+            for (i = 0; i < (int64_t)n->mac_table.in_use * ETH_ALEN; ++i) {
+                qemu_get_byte(f);
+            }
             n->mac_table.multi_overflow = n->mac_table.uni_overflow = 1;
             n->mac_table.in_use = 0;
         }
@@ -1381,6 +1411,11 @@ static int virtio_net_load(QEMUFile *f, void *opaque, int version_id)
         }
 
         n->curr_queues = qemu_get_be16(f);
+        if (n->curr_queues > n->max_queues) {
+            error_report("virtio-net: curr_queues %x > max_queues %x",
+                         n->curr_queues, n->max_queues);
+            return -1;
+        }
         for (i = 1; i < n->curr_queues; i++) {
             n->vqs[i].tx_waiting = qemu_get_be32(f);
         }
@@ -1570,16 +1605,15 @@ static int virtio_net_device_init(VirtIODevice *vdev)
     return 0;
 }
 
-static int virtio_net_device_exit(DeviceState *qdev)
+static void virtio_net_device_exit(VirtIODevice *vdev)
 {
-    VirtIONet *n = VIRTIO_NET(qdev);
+    VirtIONet *n = VIRTIO_NET(vdev);
-    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
     int i;
 
     /* This will stop vhost backend if appropriate. */
     virtio_net_set_status(vdev, 0);
 
-    unregister_savevm(qdev, "virtio-net", n);
+    unregister_savevm(DEVICE(vdev), "virtio-net", n);
 
     if (n->netclient_name) {
         g_free(n->netclient_name);
@@ -1610,8 +1644,6 @@ static int virtio_net_device_exit(DeviceState *qdev)
     g_free(n->vqs);
     qemu_del_nic(n->nic);
     virtio_cleanup(vdev);
-
-    return 0;
 }
 
 static void virtio_net_instance_init(Object *obj)
@@ -1638,10 +1670,10 @@ static void virtio_net_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_net_device_exit;
     dc->props = virtio_net_properties;
     set_bit(DEVICE_CATEGORY_NETWORK, dc->categories);
     vdc->init = virtio_net_device_init;
+    vdc->exit = virtio_net_device_exit;
     vdc->get_config = virtio_net_get_config;
     vdc->set_config = virtio_net_set_config;
     vdc->get_features = virtio_net_get_features;

hw/net/vmxnet3.c

@@ -52,6 +52,9 @@
 #define VMXNET3_DEVICE_VERSION    0x1
 #define VMXNET3_DEVICE_REVISION   0x1
 
+/* Number of interrupt vectors for non-MSIx modes */
+#define VMXNET3_MAX_NMSIX_INTRS   (1)
+
 /* Macros for rings descriptors access */
 #define VMXNET3_READ_TX_QUEUE_DESCR8(dpa, field) \
     (vmw_shmem_ld8(dpa + offsetof(struct Vmxnet3_TxQueueDesc, field)))
@@ -1305,6 +1308,51 @@ static bool vmxnet3_verify_intx(VMXNET3State *s, int intx)
            (pci_get_byte(s->parent_obj.config + PCI_INTERRUPT_PIN) - 1));
 }
 
+static void vmxnet3_validate_interrupt_idx(bool is_msix, int idx)
+{
+    int max_ints = is_msix ? VMXNET3_MAX_INTRS : VMXNET3_MAX_NMSIX_INTRS;
+    if (idx >= max_ints) {
+        hw_error("Bad interrupt index: %d\n", idx);
+    }
+}
+
+static void vmxnet3_validate_interrupts(VMXNET3State *s)
+{
+    int i;
+
+    VMW_CFPRN("Verifying event interrupt index (%d)", s->event_int_idx);
+    vmxnet3_validate_interrupt_idx(s->msix_used, s->event_int_idx);
+
+    for (i = 0; i < s->txq_num; i++) {
+        int idx = s->txq_descr[i].intr_idx;
+        VMW_CFPRN("Verifying TX queue %d interrupt index (%d)", i, idx);
+        vmxnet3_validate_interrupt_idx(s->msix_used, idx);
+    }
+
+    for (i = 0; i < s->rxq_num; i++) {
+        int idx = s->rxq_descr[i].intr_idx;
+        VMW_CFPRN("Verifying RX queue %d interrupt index (%d)", i, idx);
+        vmxnet3_validate_interrupt_idx(s->msix_used, idx);
+    }
+}
+
+static void vmxnet3_validate_queues(VMXNET3State *s)
+{
+    /*
+    * txq_num and rxq_num are total number of queues
+    * configured by guest. These numbers must not
+    * exceed corresponding maximal values.
+    */
+
+    if (s->txq_num > VMXNET3_DEVICE_MAX_TX_QUEUES) {
+        hw_error("Bad TX queues number: %d\n", s->txq_num);
+    }
+
+    if (s->rxq_num > VMXNET3_DEVICE_MAX_RX_QUEUES) {
+        hw_error("Bad RX queues number: %d\n", s->rxq_num);
+    }
+}
+
 static void vmxnet3_activate_device(VMXNET3State *s)
 {
     int i;
@@ -1351,7 +1399,7 @@ static void vmxnet3_activate_device(VMXNET3State *s)
         VMXNET3_READ_DRV_SHARED8(s->drv_shmem, devRead.misc.numRxQueues);
 
     VMW_CFPRN("Number of TX/RX queues %u/%u", s->txq_num, s->rxq_num);
-    assert(s->txq_num <= VMXNET3_DEVICE_MAX_TX_QUEUES);
+    vmxnet3_validate_queues(s);
 
     qdescr_table_pa =
         VMXNET3_READ_DRV_SHARED64(s->drv_shmem, devRead.misc.queueDescPA);
@@ -1447,6 +1495,8 @@ static void vmxnet3_activate_device(VMXNET3State *s)
                sizeof(s->rxq_descr[i].rxq_stats));
     }
 
+    vmxnet3_validate_interrupts(s);
+
     /* Make sure everything is in place before device activation */
     smp_wmb();
 
@@ -2007,7 +2057,6 @@ vmxnet3_cleanup_msix(VMXNET3State *s)
     }
 }
 
-#define VMXNET3_MSI_NUM_VECTORS   (1)
 #define VMXNET3_MSI_OFFSET        (0x50)
 #define VMXNET3_USE_64BIT         (true)
 #define VMXNET3_PER_VECTOR_MASK   (false)
@@ -2018,7 +2067,7 @@ vmxnet3_init_msi(VMXNET3State *s)
     PCIDevice *d = PCI_DEVICE(s);
     int res;
 
-    res = msi_init(d, VMXNET3_MSI_OFFSET, VMXNET3_MSI_NUM_VECTORS,
+    res = msi_init(d, VMXNET3_MSI_OFFSET, VMXNET3_MAX_NMSIX_INTRS,
                    VMXNET3_USE_64BIT, VMXNET3_PER_VECTOR_MASK);
     if (0 > res) {
         VMW_WRPRN("Failed to initialize MSI, error %d", res);
@@ -2344,6 +2393,9 @@ static int vmxnet3_post_load(void *opaque, int version_id)
         }
     }
 
+    vmxnet3_validate_queues(s);
+    vmxnet3_validate_interrupts(s);
+
     return 0;
 }
 

hw/pci-host/piix.c

@@ -103,8 +103,6 @@ struct PCII440FXState {
     MemoryRegion *system_memory;
     MemoryRegion *pci_address_space;
     MemoryRegion *ram_memory;
-    MemoryRegion pci_hole;
-    MemoryRegion pci_hole_64bit;
     PAMMemoryRegion pam_regions[13];
     MemoryRegion smram_region;
     uint8_t smm_enabled;
@@ -313,8 +311,7 @@ PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
                     MemoryRegion *address_space_mem,
                     MemoryRegion *address_space_io,
                     ram_addr_t ram_size,
-                    hwaddr pci_hole_start,
+                    ram_addr_t below_4g_mem_size,
-                    hwaddr pci_hole_size,
                     ram_addr_t above_4g_mem_size,
                     MemoryRegion *pci_address_space,
                     MemoryRegion *ram_memory)
@@ -327,7 +324,6 @@ PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
     PCII440FXState *f;
     unsigned i;
     I440FXState *i440fx;
-    uint64_t pci_hole64_size;
 
     dev = qdev_create(NULL, TYPE_I440FX_PCI_HOST_BRIDGE);
     s = PCI_HOST_BRIDGE(dev);
@@ -345,33 +341,12 @@ PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
     f->ram_memory = ram_memory;
 
     i440fx = I440FX_PCI_HOST_BRIDGE(dev);
-    /* Set PCI window size the way seabios has always done it. */
+    i440fx->pci_info.w32.begin = below_4g_mem_size;
-    /* Power of 2 so bios can cover it with a single MTRR */
-    if (ram_size <= 0x80000000) {
-        i440fx->pci_info.w32.begin = 0x80000000;
-    } else if (ram_size <= 0xc0000000) {
-        i440fx->pci_info.w32.begin = 0xc0000000;
-    } else {
-        i440fx->pci_info.w32.begin = 0xe0000000;
-    }
 
-    memory_region_init_alias(&f->pci_hole, OBJECT(d), "pci-hole", f->pci_address_space,
+    /* setup pci memory mapping */
-                             pci_hole_start, pci_hole_size);
+    pc_pci_as_mapping_init(OBJECT(f), f->system_memory,
-    memory_region_add_subregion(f->system_memory, pci_hole_start, &f->pci_hole);
+                           f->pci_address_space);
 
-    pci_hole64_size = pci_host_get_hole64_size(i440fx->pci_hole64_size);
-
-    pc_init_pci64_hole(&i440fx->pci_info, 0x100000000ULL + above_4g_mem_size,
-                       pci_hole64_size);
-    memory_region_init_alias(&f->pci_hole_64bit, OBJECT(d), "pci-hole64",
-                             f->pci_address_space,
-                             i440fx->pci_info.w64.begin,
-                             pci_hole64_size);
-    if (pci_hole64_size) {
-        memory_region_add_subregion(f->system_memory,
-                                    i440fx->pci_info.w64.begin,
-                                    &f->pci_hole_64bit);
-    }
     memory_region_init_alias(&f->smram_region, OBJECT(d), "smram-region",
                              f->pci_address_space, 0xa0000, 0x20000);
     memory_region_add_subregion_overlap(f->system_memory, 0xa0000,

hw/pci-host/q35.c

@@ -356,28 +356,11 @@ static int mch_init(PCIDevice *d)
 {
     int i;
     MCHPCIState *mch = MCH_PCI_DEVICE(d);
-    uint64_t pci_hole64_size;
 
-    /* setup pci memory regions */
+    /* setup pci memory mapping */
-    memory_region_init_alias(&mch->pci_hole, OBJECT(mch), "pci-hole",
+    pc_pci_as_mapping_init(OBJECT(mch), mch->system_memory,
-                             mch->pci_address_space,
+                           mch->pci_address_space);
-                             mch->below_4g_mem_size,
-                             0x100000000ULL - mch->below_4g_mem_size);
-    memory_region_add_subregion(mch->system_memory, mch->below_4g_mem_size,
-                                &mch->pci_hole);
 
-    pci_hole64_size = pci_host_get_hole64_size(mch->pci_hole64_size);
-    pc_init_pci64_hole(&mch->pci_info, 0x100000000ULL + mch->above_4g_mem_size,
-                       pci_hole64_size);
-    memory_region_init_alias(&mch->pci_hole_64bit, OBJECT(mch), "pci-hole64",
-                             mch->pci_address_space,
-                             mch->pci_info.w64.begin,
-                             pci_hole64_size);
-    if (pci_hole64_size) {
-        memory_region_add_subregion(mch->system_memory,
-                                    mch->pci_info.w64.begin,
-                                    &mch->pci_hole_64bit);
-    }
     /* smram */
     cpu_smm_register(&mch_set_smm, mch);
     memory_region_init_alias(&mch->smram_region, OBJECT(mch), "smram-region",

hw/pci/pci.c

@@ -474,7 +474,7 @@ const VMStateDescription vmstate_pci_device = {
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
     .fields      = (VMStateField []) {
-        VMSTATE_INT32_LE(version_id, PCIDevice),
+        VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice),
         VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0,
                                    vmstate_info_pci_config,
                                    PCI_CONFIG_SPACE_SIZE),
@@ -491,7 +491,7 @@ const VMStateDescription vmstate_pcie_device = {
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
     .fields      = (VMStateField []) {
-        VMSTATE_INT32_LE(version_id, PCIDevice),
+        VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice),
         VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0,
                                    vmstate_info_pci_config,
                                    PCIE_CONFIG_SPACE_SIZE),
@@ -820,6 +820,7 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
     }
 
     pci_dev->bus = bus;
+    pci_dev->devfn = devfn;
     dma_as = pci_device_iommu_address_space(pci_dev);
 
     memory_region_init_alias(&pci_dev->bus_master_enable_region,
@@ -829,7 +830,6 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
     address_space_init(&pci_dev->bus_master_as, &pci_dev->bus_master_enable_region,
                        name);
 
-    pci_dev->devfn = devfn;
     pstrcpy(pci_dev->name, sizeof(pci_dev->name), name);
     pci_dev->irq_state = 0;
     pci_config_alloc(pci_dev);

hw/pci/pcie_aer.c

@@ -795,6 +795,13 @@ static const VMStateDescription vmstate_pcie_aer_err = {
     }
 };
 
+static bool pcie_aer_state_log_num_valid(void *opaque, int version_id)
+{
+    PCIEAERLog *s = opaque;
+
+    return s->log_num <= s->log_max;
+}
+
 const VMStateDescription vmstate_pcie_aer_log = {
     .name = "PCIE_AER_ERROR_LOG",
     .version_id = 1,
@@ -802,7 +809,8 @@ const VMStateDescription vmstate_pcie_aer_log = {
     .minimum_version_id_old = 1,
     .fields     = (VMStateField[]) {
         VMSTATE_UINT16(log_num, PCIEAERLog),
-        VMSTATE_UINT16(log_max, PCIEAERLog),
+        VMSTATE_UINT16_EQUAL(log_max, PCIEAERLog),
+        VMSTATE_VALIDATE("log_num <= log_max", pcie_aer_state_log_num_valid),
         VMSTATE_STRUCT_VARRAY_POINTER_UINT16(log, PCIEAERLog, log_num,
                               vmstate_pcie_aer_err, PCIEAERErr),
         VMSTATE_END_OF_LIST()

hw/pcmcia/pxa2xx.c

@@ -195,7 +195,7 @@ static void pxa2xx_pcmcia_initfn(Object *obj)
     memory_region_add_subregion(&s->container_mem, 0x0c000000,
                                 &s->common_iomem);
 
-    s->slot.irq = qemu_allocate_irqs(pxa2xx_pcmcia_set_irq, s, 1)[0];
+    s->slot.irq = qemu_allocate_irq(pxa2xx_pcmcia_set_irq, s, 0);
 
     object_property_add_link(obj, "card", TYPE_PCMCIA_CARD,
                              (Object **)&s->card, NULL);

hw/ppc/spapr_pci.c

@@ -342,6 +342,22 @@ static void rtas_ibm_change_msi(PowerPCCPU *cpu, sPAPREnvironment *spapr,
 
     /* There is no cached config, allocate MSIs */
     if (!phb->msi_table[ndev].nvec) {
+        int max_irqs = 0;
+        if (ret_intr_type == RTAS_TYPE_MSI) {
+            max_irqs = msi_nr_vectors_allocated(pdev);
+        } else if (ret_intr_type == RTAS_TYPE_MSIX) {
+            max_irqs = pdev->msix_entries_nr;
+        }
+        if (!max_irqs) {
+            fprintf(stderr,
+                    "Requested interrupt type %d is not enabled for device#%d\n",
+                    ret_intr_type, ndev);
+            rtas_st(rets, 0, -1); /* Hardware error */
+            return;
+        }
+        if (req_num > max_irqs) {
+            req_num = max_irqs;
+        }
         irq = spapr_allocate_irq_block(req_num, false,
                                        ret_intr_type == RTAS_TYPE_MSI);
         if (irq < 0) {

hw/s390x/css.c

@@ -722,9 +722,11 @@ out:
     return ret;
 }
 
-static void copy_irb_to_guest(IRB *dest, const IRB *src)
+static void copy_irb_to_guest(IRB *dest, const IRB *src, PMCW *pmcw)
 {
     int i;
+    uint16_t stctl = src->scsw.ctrl & SCSW_CTRL_MASK_STCTL;
+    uint16_t actl = src->scsw.ctrl & SCSW_CTRL_MASK_ACTL;
 
     copy_scsw_to_guest(&dest->scsw, &src->scsw);
 
@@ -734,8 +736,22 @@ static void copy_irb_to_guest(IRB *dest, const IRB *src)
     for (i = 0; i < ARRAY_SIZE(dest->ecw); i++) {
         dest->ecw[i] = cpu_to_be32(src->ecw[i]);
     }
-    for (i = 0; i < ARRAY_SIZE(dest->emw); i++) {
+    /* extended measurements enabled? */
-        dest->emw[i] = cpu_to_be32(src->emw[i]);
+    if ((src->scsw.flags & SCSW_FLAGS_MASK_ESWF) ||
+        !(pmcw->flags & PMCW_FLAGS_MASK_TF) ||
+        !(pmcw->chars & PMCW_CHARS_MASK_XMWME)) {
+        return;
+    }
+    /* extended measurements pending? */
+    if (!(stctl & SCSW_STCTL_STATUS_PEND)) {
+        return;
+    }
+    if ((stctl & SCSW_STCTL_PRIMARY) ||
+        (stctl == SCSW_STCTL_SECONDARY) ||
+        ((stctl & SCSW_STCTL_INTERMEDIATE) && (actl & SCSW_ACTL_SUSP))) {
+        for (i = 0; i < ARRAY_SIZE(dest->emw); i++) {
+            dest->emw[i] = cpu_to_be32(src->emw[i]);
+        }
     }
 }
 
@@ -781,7 +797,7 @@ int css_do_tsch(SubchDev *sch, IRB *target_irb)
         }
     }
     /* Store the irb to the guest. */
-    copy_irb_to_guest(target_irb, &irb);
+    copy_irb_to_guest(target_irb, &irb, p);
 
     /* Clear conditions on subchannel, if applicable. */
     if (stctl & SCSW_STCTL_STATUS_PEND) {

hw/s390x/s390-virtio-hcall.c

@@ -26,11 +26,14 @@ void s390_register_virtio_hypercall(uint64_t code, s390_virtio_fn fn)
 
 int s390_virtio_hypercall(CPUS390XState *env)
 {
-    s390_virtio_fn fn = s390_diag500_table[env->regs[1]];
+    s390_virtio_fn fn;
 
-    if (!fn) {
+    if (env->regs[1] < MAX_DIAG_SUBCODES) {
-        return -EINVAL;
+        fn = s390_diag500_table[env->regs[1]];
+        if (fn) {
+            return fn(&env->regs[2]);
+        }
     }
 
-    return fn(&env->regs[2]);
+    return -EINVAL;
 }

hw/s390x/virtio-ccw.c

@@ -57,9 +57,10 @@ static const TypeInfo virtual_css_bus_info = {
 VirtIODevice *virtio_ccw_get_vdev(SubchDev *sch)
 {
     VirtIODevice *vdev = NULL;
+    VirtioCcwDevice *dev = sch->driver_data;
 
-    if (sch->driver_data) {
+    if (dev) {
-        vdev = ((VirtioCcwDevice *)sch->driver_data)->vdev;
+        vdev = virtio_bus_get_device(&dev->bus);
     }
     return vdev;
 }
@@ -67,7 +68,8 @@ VirtIODevice *virtio_ccw_get_vdev(SubchDev *sch)
 static int virtio_ccw_set_guest2host_notifier(VirtioCcwDevice *dev, int n,
                                               bool assign, bool set_handler)
 {
-    VirtQueue *vq = virtio_get_queue(dev->vdev, n);
+    VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
+    VirtQueue *vq = virtio_get_queue(vdev, n);
     EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
     int r = 0;
     SubchDev *sch = dev->sch;
@@ -97,6 +99,7 @@ static int virtio_ccw_set_guest2host_notifier(VirtioCcwDevice *dev, int n,
 
 static void virtio_ccw_start_ioeventfd(VirtioCcwDevice *dev)
 {
+    VirtIODevice *vdev;
     int n, r;
 
     if (!(dev->flags & VIRTIO_CCW_FLAG_USE_IOEVENTFD) ||
@@ -104,8 +107,9 @@ static void virtio_ccw_start_ioeventfd(VirtioCcwDevice *dev)
         dev->ioeventfd_started) {
         return;
     }
+    vdev = virtio_bus_get_device(&dev->bus);
     for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
-        if (!virtio_queue_get_num(dev->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
         r = virtio_ccw_set_guest2host_notifier(dev, n, true, true);
@@ -118,7 +122,7 @@ static void virtio_ccw_start_ioeventfd(VirtioCcwDevice *dev)
 
   assign_error:
     while (--n >= 0) {
-        if (!virtio_queue_get_num(dev->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
         r = virtio_ccw_set_guest2host_notifier(dev, n, false, false);
@@ -132,13 +136,15 @@ static void virtio_ccw_start_ioeventfd(VirtioCcwDevice *dev)
 
 static void virtio_ccw_stop_ioeventfd(VirtioCcwDevice *dev)
 {
+    VirtIODevice *vdev;
     int n, r;
 
     if (!dev->ioeventfd_started) {
         return;
     }
+    vdev = virtio_bus_get_device(&dev->bus);
     for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
-        if (!virtio_queue_get_num(dev->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
         r = virtio_ccw_set_guest2host_notifier(dev, n, false, false);
@@ -189,7 +195,7 @@ typedef struct VirtioFeatDesc {
 static int virtio_ccw_set_vqs(SubchDev *sch, uint64_t addr, uint32_t align,
                               uint16_t index, uint16_t num)
 {
-    VirtioCcwDevice *dev = sch->driver_data;
+    VirtIODevice *vdev = virtio_ccw_get_vdev(sch);
 
     if (index > VIRTIO_PCI_QUEUE_MAX) {
         return -EINVAL;
@@ -200,23 +206,23 @@ static int virtio_ccw_set_vqs(SubchDev *sch, uint64_t addr, uint32_t align,
         return -EINVAL;
     }
 
-    if (!dev) {
+    if (!vdev) {
         return -EINVAL;
     }
 
-    virtio_queue_set_addr(dev->vdev, index, addr);
+    virtio_queue_set_addr(vdev, index, addr);
     if (!addr) {
-        virtio_queue_set_vector(dev->vdev, index, 0);
+        virtio_queue_set_vector(vdev, index, 0);
     } else {
         /* Fail if we don't have a big enough queue. */
         /* TODO: Add interface to handle vring.num changing */
-        if (virtio_queue_get_num(dev->vdev, index) > num) {
+        if (virtio_queue_get_num(vdev, index) > num) {
             return -EINVAL;
         }
-        virtio_queue_set_vector(dev->vdev, index, index);
+        virtio_queue_set_vector(vdev, index, index);
     }
     /* tell notify handler in case of config change */
-    dev->vdev->config_vector = VIRTIO_PCI_QUEUE_MAX;
+    vdev->config_vector = VIRTIO_PCI_QUEUE_MAX;
     return 0;
 }
 
@@ -230,6 +236,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
     hwaddr indicators;
     VqConfigBlock vq_config;
     VirtioCcwDevice *dev = sch->driver_data;
+    VirtIODevice *vdev = virtio_ccw_get_vdev(sch);
     bool check_len;
     int len;
     hwaddr hw_len;
@@ -272,7 +279,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
         break;
     case CCW_CMD_VDEV_RESET:
         virtio_ccw_stop_ioeventfd(dev);
-        virtio_reset(dev->vdev);
+        virtio_reset(vdev);
         ret = 0;
         break;
     case CCW_CMD_READ_FEAT:
@@ -319,7 +326,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             features.features = ldl_le_phys(ccw.cda);
             if (features.index < ARRAY_SIZE(dev->host_features)) {
                 virtio_bus_set_vdev_features(&dev->bus, features.features);
-                dev->vdev->guest_features = features.features;
+                vdev->guest_features = features.features;
             } else {
                 /*
                  * If the guest supports more feature bits, assert that it
@@ -337,30 +344,30 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
         break;
     case CCW_CMD_READ_CONF:
         if (check_len) {
-            if (ccw.count > dev->vdev->config_len) {
+            if (ccw.count > vdev->config_len) {
                 ret = -EINVAL;
                 break;
             }
         }
-        len = MIN(ccw.count, dev->vdev->config_len);
+        len = MIN(ccw.count, vdev->config_len);
         if (!ccw.cda) {
             ret = -EFAULT;
         } else {
-            virtio_bus_get_vdev_config(&dev->bus, dev->vdev->config);
+            virtio_bus_get_vdev_config(&dev->bus, vdev->config);
             /* XXX config space endianness */
-            cpu_physical_memory_write(ccw.cda, dev->vdev->config, len);
+            cpu_physical_memory_write(ccw.cda, vdev->config, len);
             sch->curr_status.scsw.count = ccw.count - len;
             ret = 0;
         }
         break;
     case CCW_CMD_WRITE_CONF:
         if (check_len) {
-            if (ccw.count > dev->vdev->config_len) {
+            if (ccw.count > vdev->config_len) {
                 ret = -EINVAL;
                 break;
             }
         }
-        len = MIN(ccw.count, dev->vdev->config_len);
+        len = MIN(ccw.count, vdev->config_len);
         hw_len = len;
         if (!ccw.cda) {
             ret = -EFAULT;
@@ -371,9 +378,9 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             } else {
                 len = hw_len;
                 /* XXX config space endianness */
-                memcpy(dev->vdev->config, config, len);
+                memcpy(vdev->config, config, len);
                 cpu_physical_memory_unmap(config, hw_len, 0, hw_len);
-                virtio_bus_set_vdev_config(&dev->bus, dev->vdev->config);
+                virtio_bus_set_vdev_config(&dev->bus, vdev->config);
                 sch->curr_status.scsw.count = ccw.count - len;
                 ret = 0;
             }
@@ -397,9 +404,9 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             if (!(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
                 virtio_ccw_stop_ioeventfd(dev);
             }
-            virtio_set_status(dev->vdev, status);
+            virtio_set_status(vdev, status);
-            if (dev->vdev->status == 0) {
+            if (vdev->status == 0) {
-                virtio_reset(dev->vdev);
+                virtio_reset(vdev);
             }
             if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
                 virtio_ccw_start_ioeventfd(dev);
@@ -463,7 +470,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw)
             ret = -EFAULT;
         } else {
             vq_config.index = lduw_phys(ccw.cda);
-            vq_config.num_max = virtio_queue_get_num(dev->vdev,
+            vq_config.num_max = virtio_queue_get_num(vdev,
                                                      vq_config.index);
             stw_phys(ccw.cda + sizeof(vq_config.index), vq_config.num_max);
             sch->curr_status.scsw.count = ccw.count - sizeof(vq_config);
@@ -495,7 +502,6 @@ static int virtio_ccw_device_init(VirtioCcwDevice *dev, VirtIODevice *vdev)
     sch->driver_data = dev;
     dev->sch = sch;
 
-    dev->vdev = vdev;
     dev->indicators = 0;
 
     /* Initialize subchannel structure. */
@@ -608,7 +614,7 @@ static int virtio_ccw_device_init(VirtioCcwDevice *dev, VirtIODevice *vdev)
     memset(&sch->id, 0, sizeof(SenseId));
     sch->id.reserved = 0xff;
     sch->id.cu_type = VIRTIO_CCW_CU_TYPE;
-    sch->id.cu_model = dev->vdev->device_id;
+    sch->id.cu_model = vdev->device_id;
 
     /* Only the first 32 feature bits are used. */
     dev->host_features[0] = virtio_bus_get_vdev_features(&dev->bus,
@@ -631,7 +637,6 @@ static int virtio_ccw_exit(VirtioCcwDevice *dev)
 {
     SubchDev *sch = dev->sch;
 
-    virtio_ccw_stop_ioeventfd(dev);
     if (sch) {
         css_subch_assign(sch->cssid, sch->ssid, sch->schid, sch->devno, NULL);
         g_free(sch);
@@ -892,9 +897,10 @@ static unsigned virtio_ccw_get_features(DeviceState *d)
 static void virtio_ccw_reset(DeviceState *d)
 {
     VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
 
     virtio_ccw_stop_ioeventfd(dev);
-    virtio_reset(dev->vdev);
+    virtio_reset(vdev);
     css_reset_sch(dev->sch);
     dev->indicators = 0;
     dev->indicators2 = 0;
@@ -934,9 +940,10 @@ static int virtio_ccw_set_host_notifier(DeviceState *d, int n, bool assign)
 static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n,
                                          bool assign, bool with_irqfd)
 {
-    VirtQueue *vq = virtio_get_queue(dev->vdev, n);
+    VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
+    VirtQueue *vq = virtio_get_queue(vdev, n);
     EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
-    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(dev->vdev);
+    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
 
     if (assign) {
         int r = event_notifier_init(notifier, 0);
@@ -952,16 +959,16 @@ static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n,
          * land in qemu (and only the irq fd) in this code.
          */
         if (k->guest_notifier_mask) {
-            k->guest_notifier_mask(dev->vdev, n, false);
+            k->guest_notifier_mask(vdev, n, false);
         }
         /* get lost events and re-inject */
         if (k->guest_notifier_pending &&
-            k->guest_notifier_pending(dev->vdev, n)) {
+            k->guest_notifier_pending(vdev, n)) {
             event_notifier_set(notifier);
         }
     } else {
         if (k->guest_notifier_mask) {
-            k->guest_notifier_mask(dev->vdev, n, true);
+            k->guest_notifier_mask(vdev, n, true);
         }
         virtio_queue_set_guest_notifier_fd_handler(vq, false, with_irqfd);
         event_notifier_cleanup(notifier);
@@ -973,7 +980,7 @@ static int virtio_ccw_set_guest_notifiers(DeviceState *d, int nvqs,
                                           bool assigned)
 {
     VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
-    VirtIODevice *vdev = dev->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
     int r, n;
 
     for (n = 0; n < nvqs; n++) {
@@ -1228,6 +1235,8 @@ static int virtio_ccw_busdev_unplug(DeviceState *dev)
     VirtioCcwDevice *_dev = (VirtioCcwDevice *)dev;
     SubchDev *sch = _dev->sch;
 
+    virtio_ccw_stop_ioeventfd(_dev);
+
     /*
      * We should arrive here only for device_del, since we don't support
      * direct hot(un)plug of channels, but only through virtio.

hw/s390x/virtio-ccw.h

@@ -77,7 +77,6 @@ typedef struct VirtIOCCWDeviceClass {
 struct VirtioCcwDevice {
     DeviceState parent_obj;
     SubchDev *sch;
-    VirtIODevice *vdev;
     char *bus_id;
     uint32_t host_features[VIRTIO_CCW_FEATURE_SIZE];
     VirtioBusState bus;

hw/scsi/megasas.c

@@ -1101,6 +1101,21 @@ static int megasas_dcmd_ld_get_list(MegasasState *s, MegasasCmd *cmd)
     return MFI_STAT_OK;
 }
 
+static int megasas_dcmd_ld_list_query(MegasasState *s, MegasasCmd *cmd)
+{
+    uint16_t flags;
+
+    /* mbox0 contains flags */
+    flags = le16_to_cpu(cmd->frame->dcmd.mbox[0]);
+    trace_megasas_dcmd_ld_list_query(cmd->index, flags);
+    if (flags == MR_LD_QUERY_TYPE_ALL ||
+        flags == MR_LD_QUERY_TYPE_EXPOSED_TO_HOST) {
+        return megasas_dcmd_ld_get_list(s, cmd);
+    }
+
+    return MFI_STAT_OK;
+}
+
 static int megasas_ld_get_info_submit(SCSIDevice *sdev, int lun,
                                       MegasasCmd *cmd)
 {
@@ -1404,6 +1419,8 @@ static const struct dcmd_cmd_tbl_t {
       megasas_dcmd_dummy },
     { MFI_DCMD_LD_GET_LIST, "LD_GET_LIST",
       megasas_dcmd_ld_get_list},
+    { MFI_DCMD_LD_LIST_QUERY, "LD_LIST_QUERY",
+      megasas_dcmd_ld_list_query },
     { MFI_DCMD_LD_GET_INFO, "LD_GET_INFO",
       megasas_dcmd_ld_get_info },
     { MFI_DCMD_LD_GET_PROP, "LD_GET_PROP",

hw/scsi/mfi.h

@@ -164,6 +164,7 @@ typedef enum {
     MFI_DCMD_PD_BLINK =                 0x02070100,
     MFI_DCMD_PD_UNBLINK =               0x02070200,
     MFI_DCMD_LD_GET_LIST =              0x03010000,
+    MFI_DCMD_LD_LIST_QUERY =            0x03010100,
     MFI_DCMD_LD_GET_INFO =              0x03020000,
     MFI_DCMD_LD_GET_PROP =              0x03030000,
     MFI_DCMD_LD_SET_PROP =              0x03040000,
@@ -411,6 +412,14 @@ typedef enum {
     MR_PD_QUERY_TYPE_EXPOSED_TO_HOST =  5, /*query for system drives */
 } mfi_pd_query_type;
 
+typedef enum {
+    MR_LD_QUERY_TYPE_ALL =              0,
+    MR_LD_QUERY_TYPE_EXPOSED_TO_HOST =  1,
+    MR_LD_QUERY_TYPE_USED_TGT_IDS =     2,
+    MR_LD_QUERY_TYPE_CLUSTER_ACCESS =   3,
+    MR_LD_QUERY_TYPE_CLUSTER_LOCALE =   4,
+} mfi_ld_query_type;
+
 /*
  * Other propertities and definitions
  */

hw/scsi/scsi-bus.c

@@ -469,6 +469,8 @@ static int32_t scsi_target_send_command(SCSIRequest *req, uint8_t *buf)
             r->req.dev->sense_is_ua = false;
         }
         break;
+    case TEST_UNIT_READY:
+        break;
     default:
         scsi_req_build_sense(req, SENSE_CODE(LUN_NOT_SUPPORTED));
         scsi_req_complete(req, CHECK_CONDITION);
@@ -886,7 +888,6 @@ static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
     case RELEASE:
     case ERASE:
     case ALLOW_MEDIUM_REMOVAL:
-    case VERIFY_10:
     case SEEK_10:
     case SYNCHRONIZE_CACHE:
     case SYNCHRONIZE_CACHE_16:
@@ -903,6 +904,16 @@ static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf)
     case ALLOW_OVERWRITE:
         cmd->xfer = 0;
         break;
+    case VERIFY_10:
+    case VERIFY_12:
+    case VERIFY_16:
+        if ((buf[1] & 2) == 0) {
+            cmd->xfer = 0;
+        } else if ((buf[1] & 4) != 0) {
+            cmd->xfer = 1;
+        }
+        cmd->xfer *= dev->blocksize;
+        break;
     case MODE_SENSE:
         break;
     case WRITE_SAME_10:
@@ -1100,6 +1111,9 @@ static void scsi_cmd_xfer_mode(SCSICommand *cmd)
     case WRITE_VERIFY_12:
     case WRITE_16:
     case WRITE_VERIFY_16:
+    case VERIFY_10:
+    case VERIFY_12:
+    case VERIFY_16:
     case COPY:
     case COPY_VERIFY:
     case COMPARE:

hw/scsi/scsi-disk.c

@@ -1597,6 +1597,14 @@ static void scsi_disk_emulate_write_data(SCSIRequest *req)
         scsi_disk_emulate_unmap(r, r->iov.iov_base);
         break;
 
+    case VERIFY_10:
+    case VERIFY_12:
+    case VERIFY_16:
+        if (r->req.status == -1) {
+            scsi_check_condition(r, SENSE_CODE(INVALID_FIELD));
+        }
+        break;
+
     default:
         abort();
     }
@@ -1837,6 +1845,14 @@ static int32_t scsi_disk_emulate_command(SCSIRequest *req, uint8_t *buf)
     case UNMAP:
         DPRINTF("Unmap (len %lu)\n", (long)r->req.cmd.xfer);
         break;
+    case VERIFY_10:
+    case VERIFY_12:
+    case VERIFY_16:
+        DPRINTF("Verify (bytchk %lu)\n", (r->req.buf[1] >> 1) & 3);
+        if (req->cmd.buf[1] & 6) {
+            goto illegal_request;
+        }
+        break;
     case WRITE_SAME_10:
     case WRITE_SAME_16:
         nb_sectors = scsi_data_cdb_length(r->req.cmd.buf);
@@ -1936,10 +1952,6 @@ static int32_t scsi_disk_dma_command(SCSIRequest *req, uint8_t *buf)
             scsi_check_condition(r, SENSE_CODE(WRITE_PROTECTED));
             return 0;
         }
-        /* fallthrough */
-    case VERIFY_10:
-    case VERIFY_12:
-    case VERIFY_16:
         DPRINTF("Write %s(sector %" PRId64 ", count %u)\n",
                 (command & 0xe) == 0xe ? "And Verify " : "",
                 r->req.cmd.lba, len);
@@ -2169,6 +2181,7 @@ static const SCSIReqOps scsi_disk_emulate_reqops = {
     .send_command = scsi_disk_emulate_command,
     .read_data    = scsi_disk_emulate_read_data,
     .write_data   = scsi_disk_emulate_write_data,
+    .cancel_io    = scsi_cancel_io,
     .get_buf      = scsi_get_buf,
 };
 
@@ -2207,14 +2220,14 @@ static const SCSIReqOps *const scsi_disk_reqops_dispatch[256] = {
     [UNMAP]                           = &scsi_disk_emulate_reqops,
     [WRITE_SAME_10]                   = &scsi_disk_emulate_reqops,
     [WRITE_SAME_16]                   = &scsi_disk_emulate_reqops,
+    [VERIFY_10]                       = &scsi_disk_emulate_reqops,
+    [VERIFY_12]                       = &scsi_disk_emulate_reqops,
+    [VERIFY_16]                       = &scsi_disk_emulate_reqops,
 
     [READ_6]                          = &scsi_disk_dma_reqops,
     [READ_10]                         = &scsi_disk_dma_reqops,
     [READ_12]                         = &scsi_disk_dma_reqops,
     [READ_16]                         = &scsi_disk_dma_reqops,
-    [VERIFY_10]                       = &scsi_disk_dma_reqops,
-    [VERIFY_12]                       = &scsi_disk_dma_reqops,
-    [VERIFY_16]                       = &scsi_disk_dma_reqops,
     [WRITE_6]                         = &scsi_disk_dma_reqops,
     [WRITE_10]                        = &scsi_disk_dma_reqops,
     [WRITE_12]                        = &scsi_disk_dma_reqops,
@@ -2359,7 +2372,7 @@ static SCSIRequest *scsi_block_new_request(SCSIDevice *d, uint32_t tag,
 	 * ones (such as WRITE SAME or EXTENDED COPY, etc.).  So, without
 	 * O_DIRECT everything must go through SG_IO.
          */
-        if (bdrv_get_flags(s->qdev.conf.bs) & BDRV_O_NOCACHE) {
+        if (!(bdrv_get_flags(s->qdev.conf.bs) & BDRV_O_NOCACHE)) {
             break;
         }
 

hw/scsi/scsi-generic.c

@@ -37,8 +37,6 @@ do { fprintf(stderr, "scsi-generic: " fmt , ## __VA_ARGS__); } while (0)
 #include <scsi/sg.h>
 #include "block/scsi.h"
 
-#define SCSI_SENSE_BUF_SIZE 96
-
 #define SG_ERR_DRIVER_TIMEOUT  0x06
 #define SG_ERR_DRIVER_SENSE    0x08
 

hw/scsi/spapr_vscsi.c

@@ -60,7 +60,6 @@
 #define VSCSI_MAX_SECTORS       4096
 #define VSCSI_REQ_LIMIT         24
 
-#define SCSI_SENSE_BUF_SIZE     96
 #define SRP_RSP_SENSE_DATA_LEN  18
 
 typedef union vscsi_crq {

hw/scsi/vhost-scsi.c

@@ -240,11 +240,10 @@ static int vhost_scsi_init(VirtIODevice *vdev)
     return 0;
 }
 
-static int vhost_scsi_exit(DeviceState *qdev)
+static void vhost_scsi_exit(VirtIODevice *vdev)
 {
-    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
+    VHostSCSI *s = VHOST_SCSI(vdev);
-    VHostSCSI *s = VHOST_SCSI(qdev);
+    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev);
-    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(qdev);
 
     migrate_del_blocker(s->migration_blocker);
     error_free(s->migration_blocker);
@@ -253,7 +252,7 @@ static int vhost_scsi_exit(DeviceState *qdev)
     vhost_scsi_set_status(vdev, 0);
 
     g_free(s->dev.vqs);
-    return virtio_scsi_common_exit(vs);
+    virtio_scsi_common_exit(vs);
 }
 
 static Property vhost_scsi_properties[] = {
@@ -265,10 +264,10 @@ static void vhost_scsi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = vhost_scsi_exit;
     dc->props = vhost_scsi_properties;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     vdc->init = vhost_scsi_init;
+    vdc->exit = vhost_scsi_exit;
     vdc->get_features = vhost_scsi_get_features;
     vdc->set_config = vhost_scsi_set_config;
     vdc->set_status = vhost_scsi_set_status;

hw/scsi/virtio-scsi.c

@@ -147,6 +147,15 @@ static void *virtio_scsi_load_request(QEMUFile *f, SCSIRequest *sreq)
     qemu_get_be32s(f, &n);
     assert(n < vs->conf.num_queues);
     qemu_get_buffer(f, (unsigned char *)&req->elem, sizeof(req->elem));
+    /* TODO: add a way for SCSIBusInfo's load_request to fail,
+     * and fail migration instead of asserting here.
+     * When we do, we might be able to re-enable NDEBUG below.
+     */
+#ifdef NDEBUG
+#error building with NDEBUG is not supported
+#endif
+    assert(req->elem.in_num <= ARRAY_SIZE(req->elem.in_sg));
+    assert(req->elem.out_num <= ARRAY_SIZE(req->elem.out_sg));
     virtio_scsi_parse_req(s, vs->cmd_vqs[n], req);
 
     scsi_req_ref(sreq);
@@ -306,6 +315,10 @@ static void virtio_scsi_command_complete(SCSIRequest *r, uint32_t status,
     VirtIOSCSIReq *req = r->hba_private;
     uint32_t sense_len;
 
+    if (r->io_canceled) {
+        return;
+    }
+
     req->resp.cmd->response = VIRTIO_SCSI_S_OK;
     req->resp.cmd->status = status;
     if (req->resp.cmd->status == GOOD) {
@@ -483,7 +496,7 @@ static void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
                                    uint32_t event, uint32_t reason)
 {
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
-    VirtIOSCSIReq *req = virtio_scsi_pop_req(s, vs->event_vq);
+    VirtIOSCSIReq *req;
     VirtIOSCSIEvent *evt;
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
     int in_size;
@@ -492,6 +505,7 @@ static void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
         return;
     }
 
+    req = virtio_scsi_pop_req(s, vs->event_vq);
     if (!req) {
         s->events_dropped = true;
         return;
@@ -516,7 +530,7 @@ static void virtio_scsi_push_event(VirtIOSCSI *s, SCSIDevice *dev,
     evt->event = event;
     evt->reason = reason;
     if (!dev) {
-        assert(event == VIRTIO_SCSI_T_NO_EVENT);
+        assert(event == VIRTIO_SCSI_T_EVENTS_MISSED);
     } else {
         evt->lun[0] = 1;
         evt->lun[1] = dev->id;
@@ -644,22 +658,21 @@ static int virtio_scsi_device_init(VirtIODevice *vdev)
     return 0;
 }
 
-int virtio_scsi_common_exit(VirtIOSCSICommon *vs)
+void virtio_scsi_common_exit(VirtIOSCSICommon *vs)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(vs);
 
     g_free(vs->cmd_vqs);
     virtio_cleanup(vdev);
-    return 0;
 }
 
-static int virtio_scsi_device_exit(DeviceState *qdev)
+static void virtio_scsi_device_exit(VirtIODevice *vdev)
 {
-    VirtIOSCSI *s = VIRTIO_SCSI(qdev);
+    VirtIOSCSI *s = VIRTIO_SCSI(vdev);
-    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(qdev);
+    VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(vdev);
 
-    unregister_savevm(qdev, "virtio-scsi", s);
+    unregister_savevm(DEVICE(vdev), "virtio-scsi", s);
-    return virtio_scsi_common_exit(vs);
+    virtio_scsi_common_exit(vs);
 }
 
 static Property virtio_scsi_properties[] = {
@@ -680,10 +693,10 @@ static void virtio_scsi_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_scsi_device_exit;
     dc->props = virtio_scsi_properties;
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     vdc->init = virtio_scsi_device_init;
+    vdc->exit = virtio_scsi_device_exit;
     vdc->set_config = virtio_scsi_set_config;
     vdc->get_features = virtio_scsi_get_features;
     vdc->reset = virtio_scsi_reset;

hw/sd/omap_mmc.c

@@ -625,7 +625,7 @@ struct omap_mmc_s *omap2_mmc_init(struct omap_target_agent_s *ta,
         exit(1);
     }
 
-    s->cdet = qemu_allocate_irqs(omap_mmc_cover_cb, s, 1)[0];
+    s->cdet = qemu_allocate_irq(omap_mmc_cover_cb, s, 0);
     sd_set_cb(s->card, NULL, s->cdet);
 
     return s;

hw/sd/sdhci.c

@@ -1169,8 +1169,8 @@ static void sdhci_initfn(Object *obj)
     if (s->card == NULL) {
         exit(1);
     }
-    s->eject_cb = qemu_allocate_irqs(sdhci_insert_eject_cb, s, 1)[0];
+    s->eject_cb = qemu_allocate_irq(sdhci_insert_eject_cb, s, 0);
-    s->ro_cb = qemu_allocate_irqs(sdhci_card_readonly_cb, s, 1)[0];
+    s->ro_cb = qemu_allocate_irq(sdhci_card_readonly_cb, s, 0);
     sd_set_cb(s->card, s->ro_cb, s->eject_cb);
 
     s->insert_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, sdhci_raise_insertion_irq, s);
@@ -1185,8 +1185,8 @@ static void sdhci_uninitfn(Object *obj)
     timer_free(s->insert_timer);
     timer_del(s->transfer_timer);
     timer_free(s->transfer_timer);
-    qemu_free_irqs(&s->eject_cb);
+    qemu_free_irq(s->eject_cb);
-    qemu_free_irqs(&s->ro_cb);
+    qemu_free_irq(s->ro_cb);
 
     if (s->fifo_buffer) {
         g_free(s->fifo_buffer);

hw/sd/ssi-sd.c

@@ -230,8 +230,17 @@ static int ssi_sd_load(QEMUFile *f, void *opaque, int version_id)
     for (i = 0; i < 5; i++)
         s->response[i] = qemu_get_be32(f);
     s->arglen = qemu_get_be32(f);
+    if (s->mode == SSI_SD_CMDARG &&
+        (s->arglen < 0 || s->arglen >= ARRAY_SIZE(s->cmdarg))) {
+        return -EINVAL;
+    }
     s->response_pos = qemu_get_be32(f);
     s->stopping = qemu_get_be32(f);
+    if (s->mode == SSI_SD_RESPONSE &&
+        (s->response_pos < 0 || s->response_pos >= ARRAY_SIZE(s->response) ||
+        (!s->stopping && s->arglen > ARRAY_SIZE(s->response)))) {
+        return -EINVAL;
+    }
 
     ss->cs = qemu_get_be32(f);
 

hw/sh4/sh7750.c

@@ -838,6 +838,5 @@ SH7750State *sh7750_init(SuperHCPU *cpu, MemoryRegion *sysmem)
 qemu_irq sh7750_irl(SH7750State *s)
 {
     sh_intc_toggle_source(sh_intc_source(&s->intc, IRL), 1, 0); /* enable */
-    return qemu_allocate_irqs(sh_intc_set_irl, sh_intc_source(&s->intc, IRL),
+    return qemu_allocate_irq(sh_intc_set_irl, sh_intc_source(&s->intc, IRL), 0);
-                               1)[0];
 }

hw/ssi/pl022.c

@@ -240,11 +240,25 @@ static const MemoryRegionOps pl022_ops = {
     .endianness = DEVICE_NATIVE_ENDIAN,
 };
 
+static int pl022_post_load(void *opaque, int version_id)
+{
+    PL022State *s = opaque;
+
+    if (s->tx_fifo_head < 0 ||
+        s->tx_fifo_head >= ARRAY_SIZE(s->tx_fifo) ||
+        s->rx_fifo_head < 0 ||
+        s->rx_fifo_head >= ARRAY_SIZE(s->rx_fifo)) {
+        return -1;
+    }
+    return 0;
+}
+
 static const VMStateDescription vmstate_pl022 = {
     .name = "pl022_ssp",
     .version_id = 1,
     .minimum_version_id = 1,
     .minimum_version_id_old = 1,
+    .post_load = pl022_post_load,
     .fields      = (VMStateField[]) {
         VMSTATE_UINT32(cr0, PL022State),
         VMSTATE_UINT32(cr1, PL022State),

hw/timer/arm_timer.c

@@ -320,6 +320,7 @@ static uint64_t icp_pit_read(void *opaque, hwaddr offset,
     n = offset >> 8;
     if (n > 2) {
         qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad timer %d\n", __func__, n);
+        return 0;
     }
 
     return arm_timer_read(s->timer[n], offset & 0xff);
@@ -334,6 +335,7 @@ static void icp_pit_write(void *opaque, hwaddr offset,
     n = offset >> 8;
     if (n > 2) {
         qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad timer %d\n", __func__, n);
+        return;
     }
 
     arm_timer_write(s->timer[n], offset & 0xff, value);

hw/timer/hpet.c

@@ -42,7 +42,6 @@
 
 #define HPET_MSI_SUPPORT        0
 
-#define TYPE_HPET "hpet"
 #define HPET(obj) OBJECT_CHECK(HPETState, (obj), TYPE_HPET)
 
 struct HPETState;
@@ -228,6 +227,18 @@ static int hpet_pre_load(void *opaque)
     return 0;
 }
 
+static bool hpet_validate_num_timers(void *opaque, int version_id)
+{
+    HPETState *s = opaque;
+
+    if (s->num_timers < HPET_MIN_TIMERS) {
+        return false;
+    } else if (s->num_timers > HPET_MAX_TIMERS) {
+        return false;
+    }
+    return true;
+}
+
 static int hpet_post_load(void *opaque, int version_id)
 {
     HPETState *s = opaque;
@@ -296,6 +307,7 @@ static const VMStateDescription vmstate_hpet = {
         VMSTATE_UINT64(isr, HPETState),
         VMSTATE_UINT64(hpet_counter, HPETState),
         VMSTATE_UINT8_V(num_timers, HPETState, 2),
+        VMSTATE_VALIDATE("num_timers in range", hpet_validate_num_timers),
         VMSTATE_STRUCT_VARRAY_UINT8(timer, HPETState, num_timers, 0,
                                     vmstate_hpet_timer, HPETTimer),
         VMSTATE_END_OF_LIST()
@@ -757,11 +769,6 @@ static void hpet_device_class_init(ObjectClass *klass, void *data)
     dc->props = hpet_device_properties;
 }
 
-bool hpet_find(void)
-{
-    return object_resolve_path_type("", TYPE_HPET, NULL);
-}
-
 static const TypeInfo hpet_device_info = {
     .name          = TYPE_HPET,
     .parent        = TYPE_SYS_BUS_DEVICE,

hw/timer/omap_gptimer.c

@@ -227,7 +227,7 @@ static void omap_gp_timer_clk_update(void *opaque, int line, int on)
 static void omap_gp_timer_clk_setup(struct omap_gp_timer_s *timer)
 {
     omap_clk_adduser(timer->clk,
-                    qemu_allocate_irqs(omap_gp_timer_clk_update, timer, 1)[0]);
+                     qemu_allocate_irq(omap_gp_timer_clk_update, timer, 0));
     timer->rate = omap_clk_getrate(timer->clk);
 }
 
@@ -476,7 +476,7 @@ struct omap_gp_timer_s *omap_gp_timer_init(struct omap_target_agent_s *ta,
     s->clk = fclk;
     s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, omap_gp_timer_tick, s);
     s->match = timer_new_ns(QEMU_CLOCK_VIRTUAL, omap_gp_timer_match, s);
-    s->in = qemu_allocate_irqs(omap_gp_timer_input, s, 1)[0];
+    s->in = qemu_allocate_irq(omap_gp_timer_input, s, 0);
     omap_gp_timer_reset(s);
     omap_gp_timer_clk_setup(s);
 

hw/usb/bus.c

@@ -47,7 +47,9 @@ static int usb_device_post_load(void *opaque, int version_id)
     } else {
         dev->attached = 1;
     }
-    if (dev->setup_index >= sizeof(dev->data_buf) ||
+    if (dev->setup_index < 0 ||
+        dev->setup_len < 0 ||
+        dev->setup_index >= sizeof(dev->data_buf) ||
         dev->setup_len >= sizeof(dev->data_buf)) {
         return -EINVAL;
     }

hw/usb/dev-bluetooth.c

@@ -19,6 +19,7 @@
  */
 
 #include "qemu-common.h"
+#include "qemu/error-report.h"
 #include "hw/usb.h"
 #include "hw/usb/desc.h"
 #include "sysemu/bt.h"
@@ -506,6 +507,14 @@ static int usb_bt_initfn(USBDevice *dev)
 
     usb_desc_create_serial(dev);
     usb_desc_init(dev);
+    s->dev.opaque = s;
+    if (!s->hci) {
+        s->hci = bt_new_hci(qemu_find_bt_vlan(0));
+    }
+    s->hci->opaque = s;
+    s->hci->evt_recv = usb_bt_out_hci_packet_event;
+    s->hci->acl_recv = usb_bt_out_hci_packet_acl;
+    usb_bt_handle_reset(&s->dev);
     s->intr = usb_ep_get(dev, USB_TOKEN_IN, USB_EVT_EP);
 
     return 0;
@@ -516,6 +525,7 @@ static USBDevice *usb_bt_init(USBBus *bus, const char *cmdline)
     USBDevice *dev;
     struct USBBtState *s;
     HCIInfo *hci;
+    const char *name = "usb-bt-dongle";
 
     if (*cmdline) {
         hci = hci_init(cmdline);
@@ -525,19 +535,17 @@ static USBDevice *usb_bt_init(USBBus *bus, const char *cmdline)
 
     if (!hci)
         return NULL;
-    dev = usb_create_simple(bus, "usb-bt-dongle");
+    dev = usb_create(bus, name);
     if (!dev) {
+        error_report("Failed to create USB device '%s'", name);
         return NULL;
     }
     s = DO_UPCAST(struct USBBtState, dev, dev);
-    s->dev.opaque = s;
-
     s->hci = hci;
-    s->hci->opaque = s;
+    if (qdev_init(&dev->qdev) < 0) {
-    s->hci->evt_recv = usb_bt_out_hci_packet_event;
+        error_report("Failed to initialize USB device '%s'", name);
-    s->hci->acl_recv = usb_bt_out_hci_packet_acl;
+        return NULL;
-
+    }
-    usb_bt_handle_reset(&s->dev);
 
     return dev;
 }

hw/virtio/vhost.c

@@ -309,7 +309,9 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev,
                                       uint64_t size)
 {
     int i;
-    for (i = 0; i < dev->nvqs; ++i) {
+    int r = 0;
+
+    for (i = 0; !r && i < dev->nvqs; ++i) {
         struct vhost_virtqueue *vq = dev->vqs + i;
         hwaddr l;
         void *p;
@@ -321,15 +323,15 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev,
         p = cpu_physical_memory_map(vq->ring_phys, &l, 1);
         if (!p || l != vq->ring_size) {
             fprintf(stderr, "Unable to map ring buffer for ring %d\n", i);
-            return -ENOMEM;
+            r = -ENOMEM;
         }
         if (p != vq->ring) {
             fprintf(stderr, "Ring buffer relocated for ring %d\n", i);
-            return -EBUSY;
+            r = -EBUSY;
         }
         cpu_physical_memory_unmap(p, l, 0, 0);
     }
-    return 0;
+    return r;
 }
 
 static struct vhost_memory_region *vhost_dev_find_reg(struct vhost_dev *dev,

hw/virtio/virtio-balloon.c

@@ -370,16 +370,14 @@ static int virtio_balloon_device_init(VirtIODevice *vdev)
     return 0;
 }
 
-static int virtio_balloon_device_exit(DeviceState *qdev)
+static void virtio_balloon_device_exit(VirtIODevice *vdev)
 {
-    VirtIOBalloon *s = VIRTIO_BALLOON(qdev);
+    VirtIOBalloon *s = VIRTIO_BALLOON(vdev);
-    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
 
     balloon_stats_destroy_timer(s);
     qemu_remove_balloon_handler(s);
-    unregister_savevm(qdev, "virtio-balloon", s);
+    unregister_savevm(DEVICE(vdev), "virtio-balloon", s);
     virtio_cleanup(vdev);
-    return 0;
 }
 
 static Property virtio_balloon_properties[] = {
@@ -390,10 +388,10 @@ static void virtio_balloon_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_balloon_device_exit;
     dc->props = virtio_balloon_properties;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     vdc->init = virtio_balloon_device_init;
+    vdc->exit = virtio_balloon_device_exit;
     vdc->get_config = virtio_balloon_get_config;
     vdc->set_config = virtio_balloon_set_config;
     vdc->get_features = virtio_balloon_get_features;

hw/virtio/virtio-bus.c

@@ -37,8 +37,8 @@ do { printf("virtio_bus: " fmt , ## __VA_ARGS__); } while (0)
 #define DPRINTF(fmt, ...) do { } while (0)
 #endif
 
-/* Plug the VirtIODevice */
+/* A VirtIODevice is being plugged */
-int virtio_bus_plug_device(VirtIODevice *vdev)
+int virtio_bus_device_plugged(VirtIODevice *vdev)
 {
     DeviceState *qdev = DEVICE(vdev);
     BusState *qbus = BUS(qdev_get_parent_bus(qdev));
@@ -46,8 +46,6 @@ int virtio_bus_plug_device(VirtIODevice *vdev)
     VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
     DPRINTF("%s: plug device.\n", qbus->name);
 
-    bus->vdev = vdev;
-
     if (klass->device_plugged != NULL) {
         klass->device_plugged(qbus->parent);
     }
@@ -58,73 +56,83 @@ int virtio_bus_plug_device(VirtIODevice *vdev)
 /* Reset the virtio_bus */
 void virtio_bus_reset(VirtioBusState *bus)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
+
     DPRINTF("%s: reset device.\n", qbus->name);
-    if (bus->vdev != NULL) {
+    if (vdev != NULL) {
-        virtio_reset(bus->vdev);
+        virtio_reset(vdev);
     }
 }
 
-/* Destroy the VirtIODevice */
+/* A VirtIODevice is being unplugged */
-void virtio_bus_destroy_device(VirtioBusState *bus)
+void virtio_bus_device_unplugged(VirtIODevice *vdev)
 {
-    BusState *qbus = BUS(bus);
+    DeviceState *qdev = DEVICE(vdev);
-    VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus);
+    BusState *qbus = BUS(qdev_get_parent_bus(qdev));
+    VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(qbus);
+
     DPRINTF("%s: remove device.\n", qbus->name);
 
-    if (bus->vdev != NULL) {
+    if (vdev != NULL) {
-        if (klass->device_unplug != NULL) {
+        if (klass->device_unplugged != NULL) {
-            klass->device_unplug(qbus->parent);
+            klass->device_unplugged(qbus->parent);
         }
-        object_unparent(OBJECT(bus->vdev));
-        bus->vdev = NULL;
     }
 }
 
 /* Get the device id of the plugged device. */
 uint16_t virtio_bus_get_vdev_id(VirtioBusState *bus)
 {
-    assert(bus->vdev != NULL);
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
-    return bus->vdev->device_id;
+    assert(vdev != NULL);
+    return vdev->device_id;
 }
 
 /* Get the config_len field of the plugged device. */
 size_t virtio_bus_get_vdev_config_len(VirtioBusState *bus)
 {
-    assert(bus->vdev != NULL);
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
-    return bus->vdev->config_len;
+    assert(vdev != NULL);
+    return vdev->config_len;
 }
 
 /* Get the features of the plugged device. */
 uint32_t virtio_bus_get_vdev_features(VirtioBusState *bus,
                                     uint32_t requested_features)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
     VirtioDeviceClass *k;
-    assert(bus->vdev != NULL);
+
-    k = VIRTIO_DEVICE_GET_CLASS(bus->vdev);
+    assert(vdev != NULL);
+    k = VIRTIO_DEVICE_GET_CLASS(vdev);
     assert(k->get_features != NULL);
-    return k->get_features(bus->vdev, requested_features);
+    return k->get_features(vdev, requested_features);
 }
 
 /* Set the features of the plugged device. */
 void virtio_bus_set_vdev_features(VirtioBusState *bus,
                                       uint32_t requested_features)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
     VirtioDeviceClass *k;
-    assert(bus->vdev != NULL);
+
-    k = VIRTIO_DEVICE_GET_CLASS(bus->vdev);
+    assert(vdev != NULL);
+    k = VIRTIO_DEVICE_GET_CLASS(vdev);
     if (k->set_features != NULL) {
-        k->set_features(bus->vdev, requested_features);
+        k->set_features(vdev, requested_features);
     }
 }
 
 /* Get bad features of the plugged device. */
 uint32_t virtio_bus_get_vdev_bad_features(VirtioBusState *bus)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
     VirtioDeviceClass *k;
-    assert(bus->vdev != NULL);
+
-    k = VIRTIO_DEVICE_GET_CLASS(bus->vdev);
+    assert(vdev != NULL);
+    k = VIRTIO_DEVICE_GET_CLASS(vdev);
     if (k->bad_features != NULL) {
-        return k->bad_features(bus->vdev);
+        return k->bad_features(vdev);
     } else {
         return 0;
     }
@@ -133,22 +141,26 @@ uint32_t virtio_bus_get_vdev_bad_features(VirtioBusState *bus)
 /* Get config of the plugged device. */
 void virtio_bus_get_vdev_config(VirtioBusState *bus, uint8_t *config)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
     VirtioDeviceClass *k;
-    assert(bus->vdev != NULL);
+
-    k = VIRTIO_DEVICE_GET_CLASS(bus->vdev);
+    assert(vdev != NULL);
+    k = VIRTIO_DEVICE_GET_CLASS(vdev);
     if (k->get_config != NULL) {
-        k->get_config(bus->vdev, config);
+        k->get_config(vdev, config);
     }
 }
 
 /* Set config of the plugged device. */
 void virtio_bus_set_vdev_config(VirtioBusState *bus, uint8_t *config)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(bus);
     VirtioDeviceClass *k;
-    assert(bus->vdev != NULL);
+
-    k = VIRTIO_DEVICE_GET_CLASS(bus->vdev);
+    assert(vdev != NULL);
+    k = VIRTIO_DEVICE_GET_CLASS(vdev);
     if (k->set_config != NULL) {
-        k->set_config(bus->vdev, config);
+        k->set_config(vdev, config);
     }
 }
 

hw/virtio/virtio-mmio.c

@@ -95,7 +95,7 @@ static void virtio_mmio_bus_new(VirtioBusState *bus, size_t bus_size,
 static uint64_t virtio_mmio_read(void *opaque, hwaddr offset, unsigned size)
 {
     VirtIOMMIOProxy *proxy = (VirtIOMMIOProxy *)opaque;
-    VirtIODevice *vdev = proxy->bus.vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
 
     DPRINTF("virtio_mmio_read offset 0x%x\n", (int)offset);
 
@@ -185,7 +185,7 @@ static void virtio_mmio_write(void *opaque, hwaddr offset, uint64_t value,
                               unsigned size)
 {
     VirtIOMMIOProxy *proxy = (VirtIOMMIOProxy *)opaque;
-    VirtIODevice *vdev = proxy->bus.vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
 
     DPRINTF("virtio_mmio_write offset 0x%x value 0x%" PRIx64 "\n",
             (int)offset, value);
@@ -298,12 +298,13 @@ static const MemoryRegionOps virtio_mem_ops = {
 static void virtio_mmio_update_irq(DeviceState *opaque, uint16_t vector)
 {
     VirtIOMMIOProxy *proxy = VIRTIO_MMIO(opaque);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     int level;
 
-    if (!proxy->bus.vdev) {
+    if (!vdev) {
         return;
     }
-    level = (proxy->bus.vdev->isr != 0);
+    level = (vdev->isr != 0);
     DPRINTF("virtio_mmio setting IRQ %d\n", level);
     qemu_set_irq(proxy->irq, level);
 }

hw/virtio/virtio-pci.c

@@ -113,31 +113,40 @@ static inline VirtIOPCIProxy *to_virtio_pci_proxy_fast(DeviceState *d)
 static void virtio_pci_notify(DeviceState *d, uint16_t vector)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy_fast(d);
+
     if (msix_enabled(&proxy->pci_dev))
         msix_notify(&proxy->pci_dev, vector);
-    else
+    else {
-        pci_set_irq(&proxy->pci_dev, proxy->vdev->isr & 1);
+        VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+        pci_set_irq(&proxy->pci_dev, vdev->isr & 1);
+    }
 }
 
 static void virtio_pci_save_config(DeviceState *d, QEMUFile *f)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     pci_device_save(&proxy->pci_dev, f);
     msix_save(&proxy->pci_dev, f);
     if (msix_present(&proxy->pci_dev))
-        qemu_put_be16(f, proxy->vdev->config_vector);
+        qemu_put_be16(f, vdev->config_vector);
 }
 
 static void virtio_pci_save_queue(DeviceState *d, int n, QEMUFile *f)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     if (msix_present(&proxy->pci_dev))
-        qemu_put_be16(f, virtio_queue_vector(proxy->vdev, n));
+        qemu_put_be16(f, virtio_queue_vector(vdev, n));
 }
 
 static int virtio_pci_load_config(DeviceState *d, QEMUFile *f)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     int ret;
     ret = pci_device_load(&proxy->pci_dev, f);
     if (ret) {
@@ -146,12 +155,12 @@ static int virtio_pci_load_config(DeviceState *d, QEMUFile *f)
     msix_unuse_all_vectors(&proxy->pci_dev);
     msix_load(&proxy->pci_dev, f);
     if (msix_present(&proxy->pci_dev)) {
-        qemu_get_be16s(f, &proxy->vdev->config_vector);
+        qemu_get_be16s(f, &vdev->config_vector);
     } else {
-        proxy->vdev->config_vector = VIRTIO_NO_VECTOR;
+        vdev->config_vector = VIRTIO_NO_VECTOR;
     }
-    if (proxy->vdev->config_vector != VIRTIO_NO_VECTOR) {
+    if (vdev->config_vector != VIRTIO_NO_VECTOR) {
-        return msix_vector_use(&proxy->pci_dev, proxy->vdev->config_vector);
+        return msix_vector_use(&proxy->pci_dev, vdev->config_vector);
     }
     return 0;
 }
@@ -159,13 +168,15 @@ static int virtio_pci_load_config(DeviceState *d, QEMUFile *f)
 static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+
     uint16_t vector;
     if (msix_present(&proxy->pci_dev)) {
         qemu_get_be16s(f, &vector);
     } else {
         vector = VIRTIO_NO_VECTOR;
     }
-    virtio_queue_set_vector(proxy->vdev, n, vector);
+    virtio_queue_set_vector(vdev, n, vector);
     if (vector != VIRTIO_NO_VECTOR) {
         return msix_vector_use(&proxy->pci_dev, vector);
     }
@@ -175,7 +186,8 @@ static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f)
 static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
                                                  int n, bool assign, bool set_handler)
 {
-    VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    VirtQueue *vq = virtio_get_queue(vdev, n);
     EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
     int r = 0;
 
@@ -200,6 +212,7 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
 
 static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     int n, r;
 
     if (!(proxy->flags & VIRTIO_PCI_FLAG_USE_IOEVENTFD) ||
@@ -209,7 +222,7 @@ static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
     }
 
     for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
-        if (!virtio_queue_get_num(proxy->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
 
@@ -223,7 +236,7 @@ static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
 
 assign_error:
     while (--n >= 0) {
-        if (!virtio_queue_get_num(proxy->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
 
@@ -236,6 +249,7 @@ assign_error:
 
 static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
 {
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     int r;
     int n;
 
@@ -244,7 +258,7 @@ static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
     }
 
     for (n = 0; n < VIRTIO_PCI_QUEUE_MAX; n++) {
-        if (!virtio_queue_get_num(proxy->vdev, n)) {
+        if (!virtio_queue_get_num(vdev, n)) {
             continue;
         }
 
@@ -257,7 +271,7 @@ static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
 static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
 {
     VirtIOPCIProxy *proxy = opaque;
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     hwaddr pa;
 
     switch (addr) {
@@ -272,7 +286,7 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
         pa = (hwaddr)val << VIRTIO_PCI_QUEUE_ADDR_SHIFT;
         if (pa == 0) {
             virtio_pci_stop_ioeventfd(proxy);
-            virtio_reset(proxy->vdev);
+            virtio_reset(vdev);
             msix_unuse_all_vectors(&proxy->pci_dev);
         }
         else
@@ -299,7 +313,7 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
         }
 
         if (vdev->status == 0) {
-            virtio_reset(proxy->vdev);
+            virtio_reset(vdev);
             msix_unuse_all_vectors(&proxy->pci_dev);
         }
 
@@ -335,7 +349,7 @@ static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
 
 static uint32_t virtio_ioport_read(VirtIOPCIProxy *proxy, uint32_t addr)
 {
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     uint32_t ret = 0xFFFFFFFF;
 
     switch (addr) {
@@ -381,6 +395,7 @@ static uint64_t virtio_pci_config_read(void *opaque, hwaddr addr,
                                        unsigned size)
 {
     VirtIOPCIProxy *proxy = opaque;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
     uint64_t val = 0;
     if (addr < config) {
@@ -390,16 +405,16 @@ static uint64_t virtio_pci_config_read(void *opaque, hwaddr addr,
 
     switch (size) {
     case 1:
-        val = virtio_config_readb(proxy->vdev, addr);
+        val = virtio_config_readb(vdev, addr);
         break;
     case 2:
-        val = virtio_config_readw(proxy->vdev, addr);
+        val = virtio_config_readw(vdev, addr);
         if (virtio_is_big_endian()) {
             val = bswap16(val);
         }
         break;
     case 4:
-        val = virtio_config_readl(proxy->vdev, addr);
+        val = virtio_config_readl(vdev, addr);
         if (virtio_is_big_endian()) {
             val = bswap32(val);
         }
@@ -413,6 +428,7 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr,
 {
     VirtIOPCIProxy *proxy = opaque;
     uint32_t config = VIRTIO_PCI_CONFIG(&proxy->pci_dev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     if (addr < config) {
         virtio_ioport_write(proxy, addr, val);
         return;
@@ -424,19 +440,19 @@ static void virtio_pci_config_write(void *opaque, hwaddr addr,
      */
     switch (size) {
     case 1:
-        virtio_config_writeb(proxy->vdev, addr, val);
+        virtio_config_writeb(vdev, addr, val);
         break;
     case 2:
         if (virtio_is_big_endian()) {
             val = bswap16(val);
         }
-        virtio_config_writew(proxy->vdev, addr, val);
+        virtio_config_writew(vdev, addr, val);
         break;
     case 4:
         if (virtio_is_big_endian()) {
             val = bswap32(val);
         }
-        virtio_config_writel(proxy->vdev, addr, val);
+        virtio_config_writel(vdev, addr, val);
         break;
     }
 }
@@ -455,6 +471,7 @@ static void virtio_write_config(PCIDevice *pci_dev, uint32_t address,
                                 uint32_t val, int len)
 {
     VirtIOPCIProxy *proxy = DO_UPCAST(VirtIOPCIProxy, pci_dev, pci_dev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
 
     pci_default_write_config(pci_dev, address, val, len);
 
@@ -462,8 +479,7 @@ static void virtio_write_config(PCIDevice *pci_dev, uint32_t address,
         !(pci_dev->config[PCI_COMMAND] & PCI_COMMAND_MASTER) &&
         !(proxy->flags & VIRTIO_PCI_FLAG_BUS_MASTER_BUG)) {
         virtio_pci_stop_ioeventfd(proxy);
-        virtio_set_status(proxy->vdev,
+        virtio_set_status(vdev, vdev->status & ~VIRTIO_CONFIG_S_DRIVER_OK);
-                          proxy->vdev->status & ~VIRTIO_CONFIG_S_DRIVER_OK);
     }
 }
 
@@ -506,7 +522,8 @@ static int kvm_virtio_pci_irqfd_use(VirtIOPCIProxy *proxy,
                                  unsigned int vector)
 {
     VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
-    VirtQueue *vq = virtio_get_queue(proxy->vdev, queue_no);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    VirtQueue *vq = virtio_get_queue(vdev, queue_no);
     EventNotifier *n = virtio_queue_get_guest_notifier(vq);
     int ret;
     ret = kvm_irqchip_add_irqfd_notifier(kvm_state, n, NULL, irqfd->virq);
@@ -517,7 +534,8 @@ static void kvm_virtio_pci_irqfd_release(VirtIOPCIProxy *proxy,
                                       unsigned int queue_no,
                                       unsigned int vector)
 {
-    VirtQueue *vq = virtio_get_queue(proxy->vdev, queue_no);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    VirtQueue *vq = virtio_get_queue(vdev, queue_no);
     EventNotifier *n = virtio_queue_get_guest_notifier(vq);
     VirtIOIRQFD *irqfd = &proxy->vector_irqfd[vector];
     int ret;
@@ -529,7 +547,7 @@ static void kvm_virtio_pci_irqfd_release(VirtIOPCIProxy *proxy,
 static int kvm_virtio_pci_vector_use(VirtIOPCIProxy *proxy, int nvqs)
 {
     PCIDevice *dev = &proxy->pci_dev;
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
     unsigned int vector;
     int ret, queue_no;
@@ -578,7 +596,7 @@ undo:
 static void kvm_virtio_pci_vector_release(VirtIOPCIProxy *proxy, int nvqs)
 {
     PCIDevice *dev = &proxy->pci_dev;
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     unsigned int vector;
     int queue_no;
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
@@ -606,8 +624,9 @@ static int virtio_pci_vq_vector_unmask(VirtIOPCIProxy *proxy,
                                        unsigned int vector,
                                        MSIMessage msg)
 {
-    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(proxy->vdev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    VirtQueue *vq = virtio_get_queue(proxy->vdev, queue_no);
+    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
+    VirtQueue *vq = virtio_get_queue(vdev, queue_no);
     EventNotifier *n = virtio_queue_get_guest_notifier(vq);
     VirtIOIRQFD *irqfd;
     int ret = 0;
@@ -626,10 +645,10 @@ static int virtio_pci_vq_vector_unmask(VirtIOPCIProxy *proxy,
      * Otherwise, set it up now.
      */
     if (k->guest_notifier_mask) {
-        k->guest_notifier_mask(proxy->vdev, queue_no, false);
+        k->guest_notifier_mask(vdev, queue_no, false);
         /* Test after unmasking to avoid losing events. */
         if (k->guest_notifier_pending &&
-            k->guest_notifier_pending(proxy->vdev, queue_no)) {
+            k->guest_notifier_pending(vdev, queue_no)) {
             event_notifier_set(n);
         }
     } else {
@@ -642,13 +661,14 @@ static void virtio_pci_vq_vector_mask(VirtIOPCIProxy *proxy,
                                              unsigned int queue_no,
                                              unsigned int vector)
 {
-    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(proxy->vdev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
+    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
 
     /* If guest supports masking, keep irqfd but mask it.
      * Otherwise, clean it up now.
      */ 
     if (k->guest_notifier_mask) {
-        k->guest_notifier_mask(proxy->vdev, queue_no, true);
+        k->guest_notifier_mask(vdev, queue_no, true);
     } else {
         kvm_virtio_pci_irqfd_release(proxy, queue_no, vector);
     }
@@ -658,7 +678,7 @@ static int virtio_pci_vector_unmask(PCIDevice *dev, unsigned vector,
                                     MSIMessage msg)
 {
     VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     int ret, queue_no;
 
     for (queue_no = 0; queue_no < proxy->nvqs_with_notifiers; queue_no++) {
@@ -688,7 +708,7 @@ undo:
 static void virtio_pci_vector_mask(PCIDevice *dev, unsigned vector)
 {
     VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     int queue_no;
 
     for (queue_no = 0; queue_no < proxy->nvqs_with_notifiers; queue_no++) {
@@ -707,7 +727,7 @@ static void virtio_pci_vector_poll(PCIDevice *dev,
                                    unsigned int vector_end)
 {
     VirtIOPCIProxy *proxy = container_of(dev, VirtIOPCIProxy, pci_dev);
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
     int queue_no;
     unsigned int vector;
@@ -739,8 +759,9 @@ static int virtio_pci_set_guest_notifier(DeviceState *d, int n, bool assign,
                                          bool with_irqfd)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
-    VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(proxy->vdev);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
-    VirtQueue *vq = virtio_get_queue(proxy->vdev, n);
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
+    VirtQueue *vq = virtio_get_queue(vdev, n);
     EventNotifier *notifier = virtio_queue_get_guest_notifier(vq);
 
     if (assign) {
@@ -755,7 +776,7 @@ static int virtio_pci_set_guest_notifier(DeviceState *d, int n, bool assign,
     }
 
     if (!msix_enabled(&proxy->pci_dev) && vdc->guest_notifier_mask) {
-        vdc->guest_notifier_mask(proxy->vdev, n, !assign);
+        vdc->guest_notifier_mask(vdev, n, !assign);
     }
 
     return 0;
@@ -770,7 +791,7 @@ static bool virtio_pci_query_guest_notifiers(DeviceState *d)
 static int virtio_pci_set_guest_notifiers(DeviceState *d, int nvqs, bool assign)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
-    VirtIODevice *vdev = proxy->vdev;
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
     VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(vdev);
     int r, n;
     bool with_irqfd = msix_enabled(&proxy->pci_dev) &&
@@ -864,11 +885,12 @@ static int virtio_pci_set_host_notifier(DeviceState *d, int n, bool assign)
 static void virtio_pci_vmstate_change(DeviceState *d, bool running)
 {
     VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
+    VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
 
     if (running) {
         /* Try to find out if the guest has bus master disabled, but is
            in ready state. Then we have a buggy guest OS. */
-        if ((proxy->vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
+        if ((vdev->status & VIRTIO_CONFIG_S_DRIVER_OK) &&
             !(proxy->pci_dev.config[PCI_COMMAND] & PCI_COMMAND_MASTER)) {
             proxy->flags |= VIRTIO_PCI_FLAG_BUS_MASTER_BUG;
         }
@@ -943,8 +965,6 @@ static void virtio_pci_device_plugged(DeviceState *d)
     uint8_t *config;
     uint32_t size;
 
-    proxy->vdev = bus->vdev;
-
     config = proxy->pci_dev.config;
     if (proxy->class_code) {
         pci_config_set_class(config, proxy->class_code);
@@ -982,6 +1002,15 @@ static void virtio_pci_device_plugged(DeviceState *d)
                                                       proxy->host_features);
 }
 
+static void virtio_pci_device_unplugged(DeviceState *d)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(d);
+    VirtIOPCIProxy *proxy = VIRTIO_PCI(d);
+
+    virtio_pci_stop_ioeventfd(proxy);
+    msix_uninit_exclusive_bar(pci_dev);
+}
+
 static int virtio_pci_init(PCIDevice *pci_dev)
 {
     VirtIOPCIProxy *dev = VIRTIO_PCI(pci_dev);
@@ -996,9 +1025,7 @@ static int virtio_pci_init(PCIDevice *pci_dev)
 static void virtio_pci_exit(PCIDevice *pci_dev)
 {
     VirtIOPCIProxy *proxy = VIRTIO_PCI(pci_dev);
-    virtio_pci_stop_ioeventfd(proxy);
     memory_region_destroy(&proxy->bar);
-    msix_uninit_exclusive_bar(pci_dev);
 }
 
 static void virtio_pci_reset(DeviceState *qdev)
@@ -1533,6 +1560,7 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data)
     k->set_guest_notifiers = virtio_pci_set_guest_notifiers;
     k->vmstate_change = virtio_pci_vmstate_change;
     k->device_plugged = virtio_pci_device_plugged;
+    k->device_unplugged = virtio_pci_device_unplugged;
 }
 
 static const TypeInfo virtio_pci_bus_info = {

hw/virtio/virtio-pci.h

@@ -82,7 +82,6 @@ typedef struct VirtioPCIClass {
 
 struct VirtIOPCIProxy {
     PCIDevice pci_dev;
-    VirtIODevice *vdev;
     MemoryRegion bar;
     uint32_t flags;
     uint32_t class_code;

hw/virtio/virtio-rng.c

@@ -190,16 +190,14 @@ static int virtio_rng_device_init(VirtIODevice *vdev)
     return 0;
 }
 
-static int virtio_rng_device_exit(DeviceState *qdev)
+static void virtio_rng_device_exit(VirtIODevice *vdev)
 {
-    VirtIORNG *vrng = VIRTIO_RNG(qdev);
+    VirtIORNG *vrng = VIRTIO_RNG(vdev);
-    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
 
     timer_del(vrng->rate_limit_timer);
     timer_free(vrng->rate_limit_timer);
-    unregister_savevm(qdev, "virtio-rng", vrng);
+    unregister_savevm(DEVICE(vdev), "virtio-rng", vrng);
     virtio_cleanup(vdev);
-    return 0;
 }
 
 static Property virtio_rng_properties[] = {
@@ -211,10 +209,10 @@ static void virtio_rng_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
-    dc->exit = virtio_rng_device_exit;
     dc->props = virtio_rng_properties;
     set_bit(DEVICE_CATEGORY_MISC, dc->categories);
     vdc->init = virtio_rng_device_init;
+    vdc->exit = virtio_rng_device_exit;
     vdc->get_features = get_features;
 }
 

hw/virtio/virtio.c

@@ -427,6 +427,12 @@ void virtqueue_map_sg(struct iovec *sg, hwaddr *addr,
     unsigned int i;
     hwaddr len;
 
+    if (num_sg > VIRTQUEUE_MAX_SIZE) {
+        error_report("virtio: map attempt out of bounds: %zd > %d",
+                     num_sg, VIRTQUEUE_MAX_SIZE);
+        exit(1);
+    }
+
     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);
@@ -888,7 +894,9 @@ int virtio_set_features(VirtIODevice *vdev, uint32_t val)
 
 int virtio_load(VirtIODevice *vdev, QEMUFile *f)
 {
-    int num, i, ret;
+    int i, ret;
+    int32_t config_len;
+    uint32_t num;
     uint32_t features;
     uint32_t supported_features;
     BusState *qbus = qdev_get_parent_bus(DEVICE(vdev));
@@ -903,6 +911,9 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f)
     qemu_get_8s(f, &vdev->status);
     qemu_get_8s(f, &vdev->isr);
     qemu_get_be16s(f, &vdev->queue_sel);
+    if (vdev->queue_sel >= VIRTIO_PCI_QUEUE_MAX) {
+        return -1;
+    }
     qemu_get_be32s(f, &features);
 
     if (virtio_set_features(vdev, features) < 0) {
@@ -911,11 +922,27 @@ int virtio_load(VirtIODevice *vdev, QEMUFile *f)
                      features, supported_features);
         return -1;
     }
-    vdev->config_len = qemu_get_be32(f);
+    config_len = qemu_get_be32(f);
-    qemu_get_buffer(f, vdev->config, vdev->config_len);
+
+    /*
+     * There are cases where the incoming config can be bigger or smaller
+     * than what we have; so load what we have space for, and skip
+     * any excess that's in the stream.
+     */
+    qemu_get_buffer(f, vdev->config, MIN(config_len, vdev->config_len));
+
+    while (config_len > vdev->config_len) {
+        qemu_get_byte(f);
+        config_len--;
+    }
 
     num = qemu_get_be32(f);
 
+    if (num > VIRTIO_PCI_QUEUE_MAX) {
+        error_report("Invalid number of PCI queues: 0x%x", num);
+        return -1;
+    }
+
     for (i = 0; i < num; i++) {
         vdev->vq[i].vring.num = qemu_get_be32(f);
         if (k->has_variable_vring_alignment) {
@@ -1158,14 +1185,19 @@ static int virtio_device_init(DeviceState *qdev)
     if (k->init(vdev) < 0) {
         return -1;
     }
-    virtio_bus_plug_device(vdev);
+    virtio_bus_device_plugged(vdev);
     return 0;
 }
 
 static int virtio_device_exit(DeviceState *qdev)
 {
     VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
+    VirtioDeviceClass *k = VIRTIO_DEVICE_GET_CLASS(qdev);
 
+    virtio_bus_device_unplugged(vdev);
+    if (k->exit) {
+        k->exit(vdev);
+    }
     if (vdev->bus_name) {
         g_free(vdev->bus_name);
         vdev->bus_name = NULL;