diff options
-rw-r--r-- | audio/audio_pt_int.c | 1 | ||||
-rw-r--r-- | audio/wavcapture.c | 1 | ||||
-rw-r--r-- | coroutine-sigaltstack.c | 4 | ||||
-rw-r--r-- | hw/ide/atapi.c | 15 | ||||
-rw-r--r-- | hw/ide/core.c | 6 | ||||
-rw-r--r-- | hw/qdev-monitor.c | 5 | ||||
-rw-r--r-- | hw/qxl.c | 1 | ||||
-rw-r--r-- | hw/usb/bus.c | 7 | ||||
-rw-r--r-- | hw/usb/hcd-ehci-pci.c | 1 | ||||
-rw-r--r-- | hw/usb/hcd-ehci-sysbus.c | 1 | ||||
-rw-r--r-- | hw/usb/hcd-ohci.c | 1 | ||||
-rw-r--r-- | hw/usb/hcd-uhci.c | 1 | ||||
-rw-r--r-- | hw/usb/hcd-xhci.c | 1 | ||||
-rw-r--r-- | hw/virtio-rng.c | 12 | ||||
-rw-r--r-- | hw/virtio-serial-bus.c | 2 | ||||
-rw-r--r-- | hw/virtio.c | 15 | ||||
-rw-r--r-- | hw/virtio.h | 3 | ||||
-rw-r--r-- | include/qemu/ratelimit.h | 2 | ||||
-rw-r--r-- | pc-bios/multiboot.bin | bin | 1024 -> 1024 bytes | |||
-rw-r--r-- | pc-bios/optionrom/multiboot.S | 7 | ||||
-rw-r--r-- | qapi/qapi-dealloc-visitor.c | 2 | ||||
-rw-r--r-- | qemu-doc.texi | 167 | ||||
-rw-r--r-- | qemu-img.texi | 84 | ||||
-rw-r--r-- | qemu-options.hx | 40 | ||||
-rw-r--r-- | qemu-seccomp.c | 156 | ||||
-rw-r--r-- | qemu-tech.texi | 10 |
26 files changed, 414 insertions, 131 deletions
diff --git a/audio/audio_pt_int.c b/audio/audio_pt_int.c index e3ccb11944..9a9c306a9c 100644 --- a/audio/audio_pt_int.c +++ b/audio/audio_pt_int.c @@ -1,4 +1,3 @@ -/* public domain */ #include "qemu-common.h" #include "audio.h" diff --git a/audio/wavcapture.c b/audio/wavcapture.c index f73691cc9b..4f785f5f49 100644 --- a/audio/wavcapture.c +++ b/audio/wavcapture.c @@ -1,4 +1,3 @@ -/* public domain */ #include "hw/hw.h" #include "monitor.h" #include "audio.h" diff --git a/coroutine-sigaltstack.c b/coroutine-sigaltstack.c index 861e87805a..39dbaa5da1 100644 --- a/coroutine-sigaltstack.c +++ b/coroutine-sigaltstack.c @@ -171,8 +171,8 @@ static Coroutine *coroutine_new(void) CoroutineThreadState *coTS; struct sigaction sa; struct sigaction osa; - struct sigaltstack ss; - struct sigaltstack oss; + stack_t ss; + stack_t oss; sigset_t sigs; sigset_t osigs; jmp_buf old_env; diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c index 685cbaa889..861fd2bec3 100644 --- a/hw/ide/atapi.c +++ b/hw/ide/atapi.c @@ -1124,12 +1124,17 @@ void ide_atapi_cmd(IDEState *s) * GET_EVENT_STATUS_NOTIFICATION to detect such tray open/close * states rely on this behavior. */ - if (!s->tray_open && bdrv_is_inserted(s->bs) && s->cdrom_changed) { - ide_atapi_cmd_error(s, NOT_READY, ASC_MEDIUM_NOT_PRESENT); + if (!(atapi_cmd_table[s->io_buffer[0]].flags & ALLOW_UA) && + !s->tray_open && bdrv_is_inserted(s->bs) && s->cdrom_changed) { + + if (s->cdrom_changed == 1) { + ide_atapi_cmd_error(s, NOT_READY, ASC_MEDIUM_NOT_PRESENT); + s->cdrom_changed = 2; + } else { + ide_atapi_cmd_error(s, UNIT_ATTENTION, ASC_MEDIUM_MAY_HAVE_CHANGED); + s->cdrom_changed = 0; + } - s->cdrom_changed = 0; - s->sense_key = UNIT_ATTENTION; - s->asc = ASC_MEDIUM_MAY_HAVE_CHANGED; return; } diff --git a/hw/ide/core.c b/hw/ide/core.c index 8da894f240..c4f93d0e47 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -2160,12 +2160,6 @@ static int ide_drive_post_load(void *opaque, int version_id) { IDEState *s = opaque; - if (version_id < 3) { - if (s->sense_key == UNIT_ATTENTION && - s->asc == ASC_MEDIUM_MAY_HAVE_CHANGED) { - s->cdrom_changed = 1; - } - } if (s->identify_set) { bdrv_set_enable_write_cache(s->bs, !!(s->identify_data[85] & (1 << 5))); } diff --git a/hw/qdev-monitor.c b/hw/qdev-monitor.c index 479eecda31..a1b4d6ae5f 100644 --- a/hw/qdev-monitor.c +++ b/hw/qdev-monitor.c @@ -289,8 +289,7 @@ static BusState *qbus_find_recursive(BusState *bus, const char *name, if (name && (strcmp(bus->name, name) != 0)) { match = 0; } - if (bus_typename && - (strcmp(object_get_typename(OBJECT(bus)), bus_typename) != 0)) { + if (bus_typename && !object_dynamic_cast(OBJECT(bus), bus_typename)) { match = 0; } if (match) { @@ -435,7 +434,7 @@ DeviceState *qdev_device_add(QemuOpts *opts) if (!bus) { return NULL; } - if (strcmp(object_get_typename(OBJECT(bus)), k->bus_type) != 0) { + if (!object_dynamic_cast(OBJECT(bus), k->bus_type)) { qerror_report(QERR_BAD_BUS_FOR_DEVICE, driver, object_get_typename(OBJECT(bus))); return NULL; @@ -2146,6 +2146,7 @@ static int qxl_post_load(void *opaque, int version) switch (newmode) { case QXL_MODE_UNDEFINED: + qxl_create_memslots(d); break; case QXL_MODE_VGA: qxl_create_memslots(d); diff --git a/hw/usb/bus.c b/hw/usb/bus.c index 99aac7a2c0..55d0edd5c3 100644 --- a/hw/usb/bus.c +++ b/hw/usb/bus.c @@ -590,6 +590,13 @@ USBDevice *usbdevice_create(const char *cmdline) return NULL; } + if (!bus) { + error_report("Error: no usb bus to attach usbdevice %s, " + "please try -machine usb=on and check that " + "the machine model supports USB", driver); + return NULL; + } + if (!f->usbdevice_init) { if (*params) { error_report("usbdevice %s accepts no params", driver); diff --git a/hw/usb/hcd-ehci-pci.c b/hw/usb/hcd-ehci-pci.c index 5887eab197..41dbb539f2 100644 --- a/hw/usb/hcd-ehci-pci.c +++ b/hw/usb/hcd-ehci-pci.c @@ -123,6 +123,7 @@ static void ehci_class_init(ObjectClass *klass, void *data) k->revision = i->revision; k->class_id = PCI_CLASS_SERIAL_USB; k->config_write = usb_ehci_pci_write_config; + k->no_hotplug = 1; dc->vmsd = &vmstate_ehci_pci; dc->props = ehci_pci_properties; } diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c index 1584079796..803df92f31 100644 --- a/hw/usb/hcd-ehci-sysbus.c +++ b/hw/usb/hcd-ehci-sysbus.c @@ -45,6 +45,7 @@ static int usb_ehci_sysbus_initfn(SysBusDevice *dev) s->capsbase = 0x100; s->opregbase = 0x140; + s->dma = &dma_context_memory; usb_ehci_initfn(s, DEVICE(dev)); sysbus_init_irq(dev, &s->irq); diff --git a/hw/usb/hcd-ohci.c b/hw/usb/hcd-ohci.c index 64de906e41..e16a2ecab4 100644 --- a/hw/usb/hcd-ohci.c +++ b/hw/usb/hcd-ohci.c @@ -1882,6 +1882,7 @@ static void ohci_pci_class_init(ObjectClass *klass, void *data) k->vendor_id = PCI_VENDOR_ID_APPLE; k->device_id = PCI_DEVICE_ID_APPLE_IPID_USB; k->class_id = PCI_CLASS_SERIAL_USB; + k->no_hotplug = 1; dc->desc = "Apple USB Controller"; dc->props = ohci_pci_properties; } diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c index 8e478030ad..d053791de0 100644 --- a/hw/usb/hcd-uhci.c +++ b/hw/usb/hcd-uhci.c @@ -1327,6 +1327,7 @@ static void uhci_class_init(ObjectClass *klass, void *data) k->device_id = info->device_id; k->revision = info->revision; k->class_id = PCI_CLASS_SERIAL_USB; + k->no_hotplug = 1; dc->vmsd = &vmstate_uhci; dc->props = uhci_properties; u->info = *info; diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c index 8ef4b0730e..efb509e423 100644 --- a/hw/usb/hcd-xhci.c +++ b/hw/usb/hcd-xhci.c @@ -3167,6 +3167,7 @@ static void xhci_class_init(ObjectClass *klass, void *data) k->class_id = PCI_CLASS_SERIAL_USB; k->revision = 0x03; k->is_express = 1; + k->no_hotplug = 1; } static TypeInfo xhci_info = { diff --git a/hw/virtio-rng.c b/hw/virtio-rng.c index df329f25e1..a73ef8e334 100644 --- a/hw/virtio-rng.c +++ b/hw/virtio-rng.c @@ -43,11 +43,11 @@ static bool is_guest_ready(VirtIORNG *vrng) return false; } -static size_t get_request_size(VirtQueue *vq) +static size_t get_request_size(VirtQueue *vq, unsigned quota) { unsigned int in, out; - virtqueue_get_avail_bytes(vq, &in, &out); + virtqueue_get_avail_bytes(vq, &in, &out, quota, 0); return in; } @@ -84,12 +84,18 @@ static void chr_read(void *opaque, const void *buf, size_t size) static void virtio_rng_process(VirtIORNG *vrng) { size_t size; + unsigned quota; if (!is_guest_ready(vrng)) { return; } - size = get_request_size(vrng->vq); + if (vrng->quota_remaining < 0) { + quota = 0; + } else { + quota = MIN((uint64_t)vrng->quota_remaining, (uint64_t)UINT32_MAX); + } + size = get_request_size(vrng->vq, quota); size = MIN(vrng->quota_remaining, size); if (size) { rng_backend_request_entropy(vrng->rng, size, chr_read, vrng); diff --git a/hw/virtio-serial-bus.c b/hw/virtio-serial-bus.c index efa8a81db6..155da58dcd 100644 --- a/hw/virtio-serial-bus.c +++ b/hw/virtio-serial-bus.c @@ -306,7 +306,7 @@ size_t virtio_serial_guest_ready(VirtIOSerialPort *port) if (use_multiport(port->vser) && !port->guest_connected) { return 0; } - virtqueue_get_avail_bytes(vq, &bytes, NULL); + virtqueue_get_avail_bytes(vq, &bytes, NULL, 4096, 0); return bytes; } diff --git a/hw/virtio.c b/hw/virtio.c index ec8b7d8463..f40a8c5571 100644 --- a/hw/virtio.c +++ b/hw/virtio.c @@ -336,7 +336,8 @@ static unsigned virtqueue_next_desc(hwaddr desc_pa, } void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, - unsigned int *out_bytes) + unsigned int *out_bytes, + unsigned max_in_bytes, unsigned max_out_bytes) { unsigned int idx; unsigned int total_bufs, in_total, out_total; @@ -385,6 +386,9 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, } else { out_total += vring_desc_len(desc_pa, i); } + if (in_total >= max_in_bytes && out_total >= max_out_bytes) { + goto done; + } } while ((i = virtqueue_next_desc(desc_pa, i, max)) != max); if (!indirect) @@ -392,6 +396,7 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, else total_bufs++; } +done: if (in_bytes) { *in_bytes = in_total; } @@ -405,12 +410,8 @@ int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes, { unsigned int in_total, out_total; - virtqueue_get_avail_bytes(vq, &in_total, &out_total); - if ((in_bytes && in_bytes < in_total) - || (out_bytes && out_bytes < out_total)) { - return 1; - } - return 0; + virtqueue_get_avail_bytes(vq, &in_total, &out_total, in_bytes, out_bytes); + return in_bytes <= in_total && out_bytes <= out_total; } void virtqueue_map_sg(struct iovec *sg, hwaddr *addr, diff --git a/hw/virtio.h b/hw/virtio.h index df8d0f7b69..7c17f7ba0b 100644 --- a/hw/virtio.h +++ b/hw/virtio.h @@ -150,7 +150,8 @@ int virtqueue_pop(VirtQueue *vq, VirtQueueElement *elem); int virtqueue_avail_bytes(VirtQueue *vq, unsigned int in_bytes, unsigned int out_bytes); void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, - unsigned int *out_bytes); + unsigned int *out_bytes, + unsigned max_in_bytes, unsigned max_out_bytes); void virtio_notify(VirtIODevice *vdev, VirtQueue *vq); diff --git a/include/qemu/ratelimit.h b/include/qemu/ratelimit.h index c6ac281141..d1610f135b 100644 --- a/include/qemu/ratelimit.h +++ b/include/qemu/ratelimit.h @@ -42,7 +42,7 @@ static inline void ratelimit_set_speed(RateLimit *limit, uint64_t speed, uint64_t slice_ns) { limit->slice_ns = slice_ns; - limit->slice_quota = ((double)speed * 1000000000ULL) / slice_ns; + limit->slice_quota = ((double)speed * slice_ns)/1000000000ULL; } #endif diff --git a/pc-bios/multiboot.bin b/pc-bios/multiboot.bin Binary files differindex f74a6e142f..7b3c1745a4 100644 --- a/pc-bios/multiboot.bin +++ b/pc-bios/multiboot.bin diff --git a/pc-bios/optionrom/multiboot.S b/pc-bios/optionrom/multiboot.S index f08222a3c6..003bcfb49f 100644 --- a/pc-bios/optionrom/multiboot.S +++ b/pc-bios/optionrom/multiboot.S @@ -75,6 +75,13 @@ run_multiboot: shr $4, %eax mov %ax, %fs + /* Account for the EBDA in the multiboot structure's e801 + * map. + */ + int $0x12 + cwtl + movl %eax, %fs:4 + /* ES = mmap_addr */ mov %fs:48, %eax shr $4, %eax diff --git a/qapi/qapi-dealloc-visitor.c b/qapi/qapi-dealloc-visitor.c index a07b171b86..75214e7daa 100644 --- a/qapi/qapi-dealloc-visitor.c +++ b/qapi/qapi-dealloc-visitor.c @@ -132,7 +132,7 @@ static void qapi_dealloc_type_number(Visitor *v, double *obj, const char *name, { } -static void qapi_dealloc_type_size(Visitor *v, size_t *obj, const char *name, +static void qapi_dealloc_type_size(Visitor *v, uint64_t *obj, const char *name, Error **errp) { } diff --git a/qemu-doc.texi b/qemu-doc.texi index 6ff309ddf4..6d7f50d832 100644 --- a/qemu-doc.texi +++ b/qemu-doc.texi @@ -416,6 +416,7 @@ snapshots. * vm_snapshots:: VM snapshots * qemu_img_invocation:: qemu-img Invocation * qemu_nbd_invocation:: qemu-nbd Invocation +* disk_images_formats:: Disk image file formats * host_drives:: Using host drives * disk_images_fat_images:: Virtual FAT disk images * disk_images_nbd:: NBD access @@ -507,6 +508,172 @@ state is not saved or restored properly (in particular USB). @include qemu-nbd.texi +@node disk_images_formats +@subsection Disk image file formats + +QEMU supports many image file formats that can be used with VMs as well as with +any of the tools (like @code{qemu-img}). This includes the preferred formats +raw and qcow2 as well as formats that are supported for compatibility with +older QEMU versions or other hypervisors. + +Depending on the image format, different options can be passed to +@code{qemu-img create} and @code{qemu-img convert} using the @code{-o} option. +This section describes each format and the options that are supported for it. + +@table @option +@item raw + +Raw disk image format. This format has the advantage of +being simple and easily exportable to all other emulators. If your +file system supports @emph{holes} (for example in ext2 or ext3 on +Linux or NTFS on Windows), then only the written sectors will reserve +space. Use @code{qemu-img info} to know the real size used by the +image or @code{ls -ls} on Unix/Linux. + +@item qcow2 +QEMU image format, the most versatile format. Use it to have smaller +images (useful if your filesystem does not supports holes, for example +on Windows), optional AES encryption, zlib based compression and +support of multiple VM snapshots. + +Supported options: +@table @code +@item compat +Determines the qcow2 version to use. @code{compat=0.10} uses the traditional +image format that can be read by any QEMU since 0.10 (this is the default). +@code{compat=1.1} enables image format extensions that only QEMU 1.1 and +newer understand. Amongst others, this includes zero clusters, which allow +efficient copy-on-read for sparse images. + +@item backing_file +File name of a base image (see @option{create} subcommand) +@item backing_fmt +Image format of the base image +@item encryption +If this option is set to @code{on}, the image is encrypted. + +Encryption uses the AES format which is very secure (128 bit keys). Use +a long password (16 characters) to get maximum protection. + +@item cluster_size +Changes the qcow2 cluster size (must be between 512 and 2M). Smaller cluster +sizes can improve the image file size whereas larger cluster sizes generally +provide better performance. + +@item preallocation +Preallocation mode (allowed values: off, metadata). An image with preallocated +metadata is initially larger but can improve performance when the image needs +to grow. + +@item lazy_refcounts +If this option is set to @code{on}, reference count updates are postponed with +the goal of avoiding metadata I/O and improving performance. This is +particularly interesting with @option{cache=writethrough} which doesn't batch +metadata updates. The tradeoff is that after a host crash, the reference count +tables must be rebuilt, i.e. on the next open an (automatic) @code{qemu-img +check -r all} is required, which may take some time. + +This option can only be enabled if @code{compat=1.1} is specified. + +@end table + +@item qed +Old QEMU image format with support for backing files and compact image files +(when your filesystem or transport medium does not support holes). + +When converting QED images to qcow2, you might want to consider using the +@code{lazy_refcounts=on} option to get a more QED-like behaviour. + +Supported options: +@table @code +@item backing_file +File name of a base image (see @option{create} subcommand). +@item backing_fmt +Image file format of backing file (optional). Useful if the format cannot be +autodetected because it has no header, like some vhd/vpc files. +@item cluster_size +Changes the cluster size (must be power-of-2 between 4K and 64K). Smaller +cluster sizes can improve the image file size whereas larger cluster sizes +generally provide better performance. +@item table_size +Changes the number of clusters per L1/L2 table (must be power-of-2 between 1 +and 16). There is normally no need to change this value but this option can be +used for performance benchmarking. +@end table + +@item qcow +Old QEMU image format with support for backing files, compact image files, +encryption and compression. + +Supported options: +@table @code +@item backing_file +File name of a base image (see @option{create} subcommand) +@item encryption +If this option is set to @code{on}, the image is encrypted. +@end table + +@item cow +User Mode Linux Copy On Write image format. It is supported only for +compatibility with previous versions. +Supported options: +@table @code +@item backing_file +File name of a base image (see @option{create} subcommand) +@end table + +@item vdi +VirtualBox 1.1 compatible image format. +Supported options: +@table @code +@item static +If this option is set to @code{on}, the image is created with metadata +preallocation. +@end table + +@item vmdk +VMware 3 and 4 compatible image format. + +Supported options: +@table @code +@item backing_file +File name of a base image (see @option{create} subcommand). +@item compat6 +Create a VMDK version 6 image (instead of version 4) +@item subformat +Specifies which VMDK subformat to use. Valid options are +@code{monolithicSparse} (default), +@code{monolithicFlat}, +@code{twoGbMaxExtentSparse}, +@code{twoGbMaxExtentFlat} and +@code{streamOptimized}. +@end table + +@item vpc +VirtualPC compatible image format (VHD). +Supported options: +@table @code +@item subformat +Specifies which VHD subformat to use. Valid options are +@code{dynamic} (default) and @code{fixed}. +@end table +@end table + +@subsubsection Read-only formats +More disk image file formats are supported in a read-only mode. +@table @option +@item bochs +Bochs images of @code{growing} type. +@item cloop +Linux Compressed Loop image, useful only to reuse directly compressed +CD-ROM images present for example in the Knoppix CD-ROMs. +@item dmg +Apple disk image. +@item parallels +Parallels disk image format. +@end table + + @node host_drives @subsection Using host drives diff --git a/qemu-img.texi b/qemu-img.texi index 60b83fc11a..00fca8da86 100644 --- a/qemu-img.texi +++ b/qemu-img.texi @@ -226,7 +226,10 @@ After using this command to grow a disk image, you must use file system and partitioning tools inside the VM to actually begin using the new space on the device. @end table +@c man end +@ignore +@c man begin NOTES Supported image file formats: @table @option @@ -247,6 +250,13 @@ support of multiple VM snapshots. Supported options: @table @code +@item compat +Determines the qcow2 version to use. @code{compat=0.10} uses the traditional +image format that can be read by any QEMU since 0.10 (this is the default). +@code{compat=1.1} enables image format extensions that only QEMU 1.1 and +newer understand. Amongst others, this includes zero clusters, which allow +efficient copy-on-read for sparse images. + @item backing_file File name of a base image (see @option{create} subcommand) @item backing_fmt @@ -267,73 +277,33 @@ Preallocation mode (allowed values: off, metadata). An image with preallocated metadata is initially larger but can improve performance when the image needs to grow. -@end table +@item lazy_refcounts +If this option is set to @code{on}, reference count updates are postponed with +the goal of avoiding metadata I/O and improving performance. This is +particularly interesting with @option{cache=writethrough} which doesn't batch +metadata updates. The tradeoff is that after a host crash, the reference count +tables must be rebuilt, i.e. on the next open an (automatic) @code{qemu-img +check -r all} is required, which may take some time. -@item qed -Image format with support for backing files and compact image files (when your -filesystem or transport medium does not support holes). Good performance due -to less metadata than the more featureful qcow2 format, especially with -cache=writethrough or cache=directsync. Consider using qcow2 which will soon -have a similar optimization and is most actively developed. +This option can only be enabled if @code{compat=1.1} is specified. -Supported options: -@table @code -@item backing_file -File name of a base image (see @option{create} subcommand). -@item backing_fmt -Image file format of backing file (optional). Useful if the format cannot be -autodetected because it has no header, like some vhd/vpc files. -@item cluster_size -Changes the cluster size (must be power-of-2 between 4K and 64K). Smaller -cluster sizes can improve the image file size whereas larger cluster sizes -generally provide better performance. -@item table_size -Changes the number of clusters per L1/L2 table (must be power-of-2 between 1 -and 16). There is normally no need to change this value but this option can be -used for performance benchmarking. @end table -@item qcow -Old QEMU image format. Left for compatibility. +@item Other +QEMU also supports various other image file formats for compatibility with +older QEMU versions or other hypervisors, including VMDK, VDI, VHD (vpc), qcow1 +and QED. For a full list of supported formats see @code{qemu-img --help}. +For a more detailed description of these formats, see the QEMU Emulation User +Documentation. -Supported options: -@table @code -@item backing_file -File name of a base image (see @option{create} subcommand) -@item encryption -If this option is set to @code{on}, the image is encrypted. -@end table - -@item cow -User Mode Linux Copy On Write image format. Used to be the only growable -image format in QEMU. It is supported only for compatibility with -previous versions. It does not work on win32. -@item vdi -VirtualBox 1.1 compatible image format. -@item vmdk -VMware 3 and 4 compatible image format. - -Supported options: -@table @code -@item backing_fmt -Image format of the base image -@item compat6 -Create a VMDK version 6 image (instead of version 4) -@end table - -@item vpc -VirtualPC compatible image format (VHD). - -@item cloop -Linux Compressed Loop image, useful only to reuse directly compressed -CD-ROM images present for example in the Knoppix CD-ROMs. +The main purpose of the block drivers for these formats is image conversion. +For running VMs, it is recommended to convert the disk images to either raw or +qcow2 in order to achieve good performance. @end table @c man end -@ignore - @setfilename qemu-img @settitle QEMU disk image utility diff --git a/qemu-options.hx b/qemu-options.hx index fbcf079f47..de43b1b48b 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -206,33 +206,33 @@ Open drive @option{file} as read-only. Guest write attempts will fail. file sectors into the image file. @end table -By default, writethrough caching is used for all block device. This means that -the host page cache will be used to read and write data but write notification -will be sent to the guest only when the data has been reported as written by -the storage subsystem. - -Writeback caching will report data writes as completed as soon as the data is -present in the host page cache. This is safe as long as you trust your host. -If your host crashes or loses power, then the guest may experience data -corruption. +By default, the @option{cache=writeback} mode is used. It will report data +writes as completed as soon as the data is present in the host page cache. +This is safe as long as your guest OS makes sure to correctly flush disk caches +where needed. If your guest OS does not handle volatile disk write caches +correctly and your host crashes or loses power, then the guest may experience +data corruption. + +For such guests, you should consider using @option{cache=writethrough}. This +means that the host page cache will be used to read and write data, but write +notification will be sent to the guest only after QEMU has made sure to flush +each write to the disk. Be aware that this has a major impact on performance. The host page cache can be avoided entirely with @option{cache=none}. This will -attempt to do disk IO directly to the guests memory. QEMU may still perform -an internal copy of the data. +attempt to do disk IO directly to the guest's memory. QEMU may still perform +an internal copy of the data. Note that this is considered a writeback mode and +the guest OS must handle the disk write cache correctly in order to avoid data +corruption on host crashes. The host page cache can be avoided while only sending write notifications to -the guest when the data has been reported as written by the storage subsystem -using @option{cache=directsync}. - -Some block drivers perform badly with @option{cache=writethrough}, most notably, -qcow2. If performance is more important than correctness, -@option{cache=writeback} should be used with qcow2. +the guest when the data has been flushed to the disk using +@option{cache=directsync}. In case you don't care about data integrity over host failures, use -cache=unsafe. This option tells QEMU that it never needs to write any data -to the disk but can instead keeps things in cache. If anything goes wrong, +@option{cache=unsafe}. This option tells QEMU that it never needs to write any +data to the disk but can instead keep things in cache. If anything goes wrong, like your host losing power, the disk storage getting disconnected accidentally, -etc. you're image will most probably be rendered unusable. When using +etc. your image will most probably be rendered unusable. When using the @option{-snapshot} option, unsafe caching is always used. Copy-on-read avoids accessing the same backing file sectors repeatedly and is diff --git a/qemu-seccomp.c b/qemu-seccomp.c index 64329a3c09..2a71d6fee9 100644 --- a/qemu-seccomp.c +++ b/qemu-seccomp.c @@ -26,8 +26,12 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = { { SCMP_SYS(timer_gettime), 254 }, { SCMP_SYS(futex), 253 }, { SCMP_SYS(select), 252 }, +#if defined(__x86_64__) { SCMP_SYS(recvfrom), 251 }, { SCMP_SYS(sendto), 250 }, +#elif defined(__i386__) + { SCMP_SYS(socketcall), 250 }, +#endif { SCMP_SYS(read), 249 }, { SCMP_SYS(brk), 248 }, { SCMP_SYS(clone), 247 }, @@ -36,15 +40,30 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = { { SCMP_SYS(execve), 245 }, { SCMP_SYS(open), 245 }, { SCMP_SYS(ioctl), 245 }, +#if defined(__x86_64__) + { SCMP_SYS(socket), 245 }, + { SCMP_SYS(setsockopt), 245 }, { SCMP_SYS(recvmsg), 245 }, { SCMP_SYS(sendmsg), 245 }, { SCMP_SYS(accept), 245 }, { SCMP_SYS(connect), 245 }, + { SCMP_SYS(socketpair), 245 }, + { SCMP_SYS(bind), 245 }, + { SCMP_SYS(listen), 245 }, + { SCMP_SYS(semget), 245 }, +#elif defined(__i386__) + { SCMP_SYS(ipc), 245 }, +#endif { SCMP_SYS(gettimeofday), 245 }, { SCMP_SYS(readlink), 245 }, { SCMP_SYS(access), 245 }, { SCMP_SYS(prctl), 245 }, { SCMP_SYS(signalfd), 245 }, + { SCMP_SYS(getrlimit), 245 }, + { SCMP_SYS(set_tid_address), 245 }, + { SCMP_SYS(statfs), 245 }, + { SCMP_SYS(unlink), 245 }, + { SCMP_SYS(wait4), 245 }, #if defined(__i386__) { SCMP_SYS(fcntl64), 245 }, { SCMP_SYS(fstat64), 245 }, @@ -56,30 +75,33 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = { { SCMP_SYS(sigreturn), 245 }, { SCMP_SYS(_newselect), 245 }, { SCMP_SYS(_llseek), 245 }, - { SCMP_SYS(mmap2), 245}, + { SCMP_SYS(mmap2), 245 }, { SCMP_SYS(sigprocmask), 245 }, -#elif defined(__x86_64__) - { SCMP_SYS(sched_getparam), 245}, - { SCMP_SYS(sched_getscheduler), 245}, - { SCMP_SYS(fstat), 245}, - { SCMP_SYS(clock_getres), 245}, - { SCMP_SYS(sched_get_priority_min), 245}, - { SCMP_SYS(sched_get_priority_max), 245}, - { SCMP_SYS(stat), 245}, - { SCMP_SYS(socket), 245}, - { SCMP_SYS(setsockopt), 245}, - { SCMP_SYS(uname), 245}, - { SCMP_SYS(semget), 245}, #endif + { SCMP_SYS(sched_getparam), 245 }, + { SCMP_SYS(sched_getscheduler), 245 }, + { SCMP_SYS(fstat), 245 }, + { SCMP_SYS(clock_getres), 245 }, + { SCMP_SYS(sched_get_priority_min), 245 }, + { SCMP_SYS(sched_get_priority_max), 245 }, + { SCMP_SYS(stat), 245 }, + { SCMP_SYS(uname), 245 }, { SCMP_SYS(eventfd2), 245 }, { SCMP_SYS(dup), 245 }, + { SCMP_SYS(dup2), 245 }, + { SCMP_SYS(dup3), 245 }, { SCMP_SYS(gettid), 245 }, + { SCMP_SYS(getgid), 245 }, + { SCMP_SYS(getegid), 245 }, + { SCMP_SYS(getuid), 245 }, + { SCMP_SYS(geteuid), 245 }, { SCMP_SYS(timer_create), 245 }, { SCMP_SYS(exit), 245 }, { SCMP_SYS(clock_gettime), 245 }, { SCMP_SYS(time), 245 }, { SCMP_SYS(restart_syscall), 245 }, { SCMP_SYS(pwrite64), 245 }, + { SCMP_SYS(nanosleep), 245 }, { SCMP_SYS(chown), 245 }, { SCMP_SYS(openat), 245 }, { SCMP_SYS(getdents), 245 }, @@ -93,8 +115,6 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = { { SCMP_SYS(lseek), 245 }, { SCMP_SYS(pselect6), 245 }, { SCMP_SYS(fork), 245 }, - { SCMP_SYS(bind), 245 }, - { SCMP_SYS(listen), 245 }, { SCMP_SYS(eventfd), 245 }, { SCMP_SYS(rt_sigprocmask), 245 }, { SCMP_SYS(write), 244 }, @@ -104,10 +124,112 @@ static const struct QemuSeccompSyscall seccomp_whitelist[] = { { SCMP_SYS(pipe2), 242 }, { SCMP_SYS(munmap), 242 }, { SCMP_SYS(mremap), 242 }, + { SCMP_SYS(fdatasync), 242 }, + { SCMP_SYS(close), 242 }, + { SCMP_SYS(rt_sigpending), 242 }, + { SCMP_SYS(rt_sigtimedwait), 242 }, + { SCMP_SYS(readv), 242 }, + { SCMP_SYS(writev), 242 }, + { SCMP_SYS(preadv), 242 }, + { SCMP_SYS(pwritev), 242 }, + { SCMP_SYS(setrlimit), 242 }, + { SCMP_SYS(ftruncate), 242 }, + { SCMP_SYS(lstat), 242 }, + { SCMP_SYS(pipe), 242 }, + { SCMP_SYS(umask), 242 }, + { SCMP_SYS(chdir), 242 }, + { SCMP_SYS(setitimer), 242 }, + { SCMP_SYS(setsid), 242 }, + { SCMP_SYS(poll), 242 }, + { SCMP_SYS(epoll_create), 242 }, + { SCMP_SYS(epoll_ctl), 242 }, + { SCMP_SYS(epoll_wait), 242 }, +#if defined(__i386__) + { SCMP_SYS(waitpid), 242 }, +#elif defined(__x86_64__) { SCMP_SYS(getsockname), 242 }, { SCMP_SYS(getpeername), 242 }, - { SCMP_SYS(fdatasync), 242 }, - { SCMP_SYS(close), 242 } + { SCMP_SYS(accept4), 242 }, + { SCMP_SYS(newfstatat), 241 }, + { SCMP_SYS(shutdown), 241 }, + { SCMP_SYS(getsockopt), 241 }, + { SCMP_SYS(semctl), 241 }, + { SCMP_SYS(semop), 241 }, + { SCMP_SYS(semtimedop), 241 }, + { SCMP_SYS(epoll_ctl_old), 241 }, + { SCMP_SYS(epoll_wait_old), 241 }, +#endif + { SCMP_SYS(epoll_pwait), 241 }, + { SCMP_SYS(epoll_create1), 241 }, + { SCMP_SYS(ppoll), 241 }, + { SCMP_SYS(creat), 241 }, + { SCMP_SYS(link), 241 }, + { SCMP_SYS(getpid), 241 }, + { SCMP_SYS(getppid), 241 }, + { SCMP_SYS(getpgrp), 241 }, + { SCMP_SYS(getpgid), 241 }, + { SCMP_SYS(getsid), 241 }, + { SCMP_SYS(getdents64), 241 }, + { SCMP_SYS(getresuid), 241 }, + { SCMP_SYS(getresgid), 241 }, + { SCMP_SYS(getgroups), 241 }, +#if defined(__i386__) + { SCMP_SYS(getresuid32), 241 }, + { SCMP_SYS(getresgid32), 241 }, + { SCMP_SYS(getgroups32), 241 }, + { SCMP_SYS(signal), 241 }, + { SCMP_SYS(sigaction), 241 }, + { SCMP_SYS(sigsuspend), 241 }, + { SCMP_SYS(sigpending), 241 }, + { SCMP_SYS(truncate64), 241 }, + { SCMP_SYS(ftruncate64), 241 }, + { SCMP_SYS(fchown32), 241 }, + { SCMP_SYS(chown32), 241 }, + { SCMP_SYS(lchown32), 241 }, + { SCMP_SYS(statfs64), 241 }, + { SCMP_SYS(fstatfs64), 241 }, + { SCMP_SYS(fstatat64), 241 }, + { SCMP_SYS(lstat64), 241 }, + { SCMP_SYS(sendfile64), 241 }, + { SCMP_SYS(ugetrlimit), 241 }, +#endif + { SCMP_SYS(alarm), 241 }, + { SCMP_SYS(rt_sigsuspend), 241 }, + { SCMP_SYS(rt_sigqueueinfo), 241 }, + { SCMP_SYS(rt_tgsigqueueinfo), 241 }, + { SCMP_SYS(sigaltstack), 241 }, + { SCMP_SYS(signalfd4), 241 }, + { SCMP_SYS(truncate), 241 }, + { SCMP_SYS(fchown), 241 }, + { SCMP_SYS(lchown), 241 }, + { SCMP_SYS(fchownat), 241 }, + { SCMP_SYS(fstatfs), 241 }, + { SCMP_SYS(sendfile), 241 }, + { SCMP_SYS(getitimer), 241 }, + { SCMP_SYS(syncfs), 241 }, + { SCMP_SYS(fsync), 241 }, + { SCMP_SYS(fchdir), 241 }, + { SCMP_SYS(flock), 241 }, + { SCMP_SYS(msync), 241 }, + { SCMP_SYS(sched_setparam), 241 }, + { SCMP_SYS(sched_setscheduler), 241 }, + { SCMP_SYS(sched_yield), 241 }, + { SCMP_SYS(sched_rr_get_interval), 241 }, + { SCMP_SYS(sched_setaffinity), 241 }, + { SCMP_SYS(sched_getaffinity), 241 }, + { SCMP_SYS(readahead), 241 }, + { SCMP_SYS(timer_getoverrun), 241 }, + { SCMP_SYS(unlinkat), 241 }, + { SCMP_SYS(readlinkat), 241 }, + { SCMP_SYS(faccessat), 241 }, + { SCMP_SYS(get_robust_list), 241 }, + { SCMP_SYS(splice), 241 }, + { SCMP_SYS(vmsplice), 241 }, + { SCMP_SYS(getcpu), 241 }, + { SCMP_SYS(sendmmsg), 241 }, + { SCMP_SYS(recvmmsg), 241 }, + { SCMP_SYS(prlimit64), 241 }, + { SCMP_SYS(waitid), 241 } }; int seccomp_start(void) diff --git a/qemu-tech.texi b/qemu-tech.texi index d73dda8e35..8aefa743a8 100644 --- a/qemu-tech.texi +++ b/qemu-tech.texi @@ -262,16 +262,16 @@ Current QEMU limitations: @item Core Xtensa ISA emulation, including most options: code density, loop, extended L32R, 16- and 32-bit multiplication, 32-bit division, -MAC16, miscellaneous operations, boolean, multiprocessor synchronization, +MAC16, miscellaneous operations, boolean, FP coprocessor, coprocessor +context, debug, multiprocessor synchronization, conditional store, exceptions, relocatable vectors, unaligned exception, interrupts (including high priority and timer), hardware alignment, region protection, region translation, MMU, windowed registers, thread pointer, processor ID. -@item Not implemented options: FP coprocessor, coprocessor context, -data/instruction cache (including cache prefetch and locking), XLMI, -processor interface, debug. Also options not covered by the core ISA -(e.g. FLIX, wide branches) are not implemented. +@item Not implemented options: data/instruction cache (including cache +prefetch and locking), XLMI, processor interface. Also options not +covered by the core ISA (e.g. FLIX, wide branches) are not implemented. @item Can run most Xtensa Linux binaries. |