Non-standard logical geometries break under QEMU.
A virtual disk which contains an operating system which depends on logical geometries (consistent values being reported from BIOS INT13 AH=08) will most likely break under QEMU/SeaBIOS if it has non-standard logical geometries - for example 56 SPT (sectors per track). No matter what QEMU will guess - SeaBIOS, for large enough disks - will use LBA translation, which will report 63 SPT instead.
In addition we can not enforce SeaBIOS to rely on phyiscal geometries at all. A virtio-blk-pci virtual disk with 255 phyiscal heads can not report more than 16 physical heads when moved to an IDE controller, the ATA spec allows a maximum of 16 heads - this is an artifact of virtualization.
By supplying the logical geometies directly we are able to support such "exotic" disks.
We will use fw_cfg to do just that.
Sam Eiderman (8): block: Refactor macros - fix tabbing block: Support providing LCHS from user bootdevice: Add interface to gather LCHS scsi: Propagate unrealize() callback to scsi-hd bootdevice: Gather LCHS from all relevant devices bootdevice: Refactor get_boot_devices_list bootdevice: FW_CFG interface for LCHS values hd-geo-test: Add tests for lchs override
bootdevice.c | 158 ++++++++++--- hw/block/virtio-blk.c | 6 + hw/ide/qdev.c | 7 +- hw/nvram/fw_cfg.c | 14 +- hw/scsi/scsi-bus.c | 15 ++ hw/scsi/scsi-disk.c | 14 ++ include/hw/block/block.h | 22 +- include/hw/scsi/scsi.h | 1 + include/sysemu/sysemu.h | 4 + tests/Makefile.include | 2 +- tests/hd-geo-test.c | 565 +++++++++++++++++++++++++++++++++++++++++++++++ 11 files changed, 767 insertions(+), 41 deletions(-)
Fixing tabbing in block related macros.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- hw/ide/qdev.c | 2 +- include/hw/block/block.h | 16 ++++++++-------- 2 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/hw/ide/qdev.c b/hw/ide/qdev.c index 360cd20bd8..9cae3205df 100644 --- a/hw/ide/qdev.c +++ b/hw/ide/qdev.c @@ -285,7 +285,7 @@ static void ide_drive_realize(IDEDevice *dev, Error **errp) DEFINE_BLOCK_PROPERTIES(IDEDrive, dev.conf), \ DEFINE_BLOCK_ERROR_PROPERTIES(IDEDrive, dev.conf), \ DEFINE_PROP_STRING("ver", IDEDrive, dev.version), \ - DEFINE_PROP_UINT64("wwn", IDEDrive, dev.wwn, 0), \ + DEFINE_PROP_UINT64("wwn", IDEDrive, dev.wwn, 0), \ DEFINE_PROP_STRING("serial", IDEDrive, dev.serial),\ DEFINE_PROP_STRING("model", IDEDrive, dev.model)
diff --git a/include/hw/block/block.h b/include/hw/block/block.h index 607539057a..fd55a30bca 100644 --- a/include/hw/block/block.h +++ b/include/hw/block/block.h @@ -50,21 +50,21 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf) _conf.logical_block_size), \ DEFINE_PROP_BLOCKSIZE("physical_block_size", _state, \ _conf.physical_block_size), \ - DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0), \ + DEFINE_PROP_UINT16("min_io_size", _state, _conf.min_io_size, 0), \ DEFINE_PROP_UINT32("opt_io_size", _state, _conf.opt_io_size, 0), \ - DEFINE_PROP_UINT32("discard_granularity", _state, \ - _conf.discard_granularity, -1), \ - DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, \ - ON_OFF_AUTO_AUTO), \ + DEFINE_PROP_UINT32("discard_granularity", _state, \ + _conf.discard_granularity, -1), \ + DEFINE_PROP_ON_OFF_AUTO("write-cache", _state, _conf.wce, \ + ON_OFF_AUTO_AUTO), \ DEFINE_PROP_BOOL("share-rw", _state, _conf.share_rw, false)
#define DEFINE_BLOCK_PROPERTIES(_state, _conf) \ DEFINE_PROP_DRIVE("drive", _state, _conf.blk), \ DEFINE_BLOCK_PROPERTIES_BASE(_state, _conf)
-#define DEFINE_BLOCK_CHS_PROPERTIES(_state, _conf) \ - DEFINE_PROP_UINT32("cyls", _state, _conf.cyls, 0), \ - DEFINE_PROP_UINT32("heads", _state, _conf.heads, 0), \ +#define DEFINE_BLOCK_CHS_PROPERTIES(_state, _conf) \ + DEFINE_PROP_UINT32("cyls", _state, _conf.cyls, 0), \ + DEFINE_PROP_UINT32("heads", _state, _conf.heads, 0), \ DEFINE_PROP_UINT32("secs", _state, _conf.secs, 0)
#define DEFINE_BLOCK_ERROR_PROPERTIES(_state, _conf) \
Add logical geometry variables to BlockConf.
A user can now supply "lcyls", "lheads" & "lsecs" for any HD device that supports CHS ("cyls", "heads", "secs").
These devices include: * ide-hd * scsi-hd * virtio-blk-pci
In future commits we will use the provided LCHS and pass it to the BIOS through fw_cfg to be supplied using INT13 routines.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- include/hw/block/block.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/include/hw/block/block.h b/include/hw/block/block.h index fd55a30bca..d7246f3862 100644 --- a/include/hw/block/block.h +++ b/include/hw/block/block.h @@ -26,6 +26,7 @@ typedef struct BlockConf { uint32_t discard_granularity; /* geometry, not all devices use this */ uint32_t cyls, heads, secs; + uint32_t lcyls, lheads, lsecs; OnOffAuto wce; bool share_rw; BlockdevOnError rerror; @@ -65,7 +66,10 @@ static inline unsigned int get_physical_block_exp(BlockConf *conf) #define DEFINE_BLOCK_CHS_PROPERTIES(_state, _conf) \ DEFINE_PROP_UINT32("cyls", _state, _conf.cyls, 0), \ DEFINE_PROP_UINT32("heads", _state, _conf.heads, 0), \ - DEFINE_PROP_UINT32("secs", _state, _conf.secs, 0) + DEFINE_PROP_UINT32("secs", _state, _conf.secs, 0), \ + DEFINE_PROP_UINT32("lcyls", _state, _conf.lcyls, 0), \ + DEFINE_PROP_UINT32("lheads", _state, _conf.lheads, 0), \ + DEFINE_PROP_UINT32("lsecs", _state, _conf.lsecs, 0)
#define DEFINE_BLOCK_ERROR_PROPERTIES(_state, _conf) \ DEFINE_PROP_BLOCKDEV_ON_ERROR("rerror", _state, _conf.rerror, \
Add an interface to provide direct logical CHS values for boot devices. We will use this interface in the next commits.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- bootdevice.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++ include/sysemu/sysemu.h | 3 +++ 2 files changed, 58 insertions(+)
diff --git a/bootdevice.c b/bootdevice.c index 1d225202f9..bc5e1c2de4 100644 --- a/bootdevice.c +++ b/bootdevice.c @@ -343,3 +343,58 @@ void device_add_bootindex_property(Object *obj, int32_t *bootindex, /* initialize devices' bootindex property to -1 */ object_property_set_int(obj, -1, name, NULL); } + +typedef struct FWLCHSEntry FWLCHSEntry; + +struct FWLCHSEntry { + QTAILQ_ENTRY(FWLCHSEntry) link; + DeviceState *dev; + char *suffix; + uint32_t lcyls; + uint32_t lheads; + uint32_t lsecs; +}; + +static QTAILQ_HEAD(, FWLCHSEntry) fw_lchs = + QTAILQ_HEAD_INITIALIZER(fw_lchs); + +void add_boot_device_lchs(DeviceState *dev, const char *suffix, + uint32_t lcyls, uint32_t lheads, uint32_t lsecs) +{ + FWLCHSEntry *node; + + if (!lcyls && !lheads && !lsecs) { + return; + } + + assert(dev != NULL || suffix != NULL); + + node = g_malloc0(sizeof(FWLCHSEntry)); + node->suffix = g_strdup(suffix); + node->dev = dev; + node->lcyls = lcyls; + node->lheads = lheads; + node->lsecs = lsecs; + + QTAILQ_INSERT_TAIL(&fw_lchs, node, link); +} + +void del_boot_device_lchs(DeviceState *dev, const char *suffix) +{ + FWLCHSEntry *i; + + if (dev == NULL) { + return; + } + + QTAILQ_FOREACH(i, &fw_lchs, link) { + if ((!suffix || !g_strcmp0(i->suffix, suffix)) && + i->dev == dev) { + QTAILQ_REMOVE(&fw_lchs, i, link); + g_free(i->suffix); + g_free(i); + + break; + } + } +} diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 61579ae71e..173dfbb539 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -171,6 +171,9 @@ void device_add_bootindex_property(Object *obj, int32_t *bootindex, DeviceState *dev, Error **errp); void restore_boot_order(void *opaque); void validate_bootdevices(const char *devices, Error **errp); +void add_boot_device_lchs(DeviceState *dev, const char *suffix, + uint32_t lcyls, uint32_t lheads, uint32_t lsecs); +void del_boot_device_lchs(DeviceState *dev, const char *suffix);
/* handler to set the boot_device order for a specific type of MachineClass */ typedef void QEMUBootSetHandler(void *opaque, const char *boot_order,
We will need to add LCHS removal logic to scsi-hd's unrealize() in the next commit.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- hw/scsi/scsi-bus.c | 15 +++++++++++++++ include/hw/scsi/scsi.h | 1 + 2 files changed, 16 insertions(+)
diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c index c480553083..f6fe497a1a 100644 --- a/hw/scsi/scsi-bus.c +++ b/hw/scsi/scsi-bus.c @@ -55,6 +55,14 @@ static void scsi_device_realize(SCSIDevice *s, Error **errp) } }
+static void scsi_device_unrealize(SCSIDevice *s, Error **errp) +{ + SCSIDeviceClass *sc = SCSI_DEVICE_GET_CLASS(s); + if (sc->unrealize) { + sc->unrealize(s, errp); + } +} + int scsi_bus_parse_cdb(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf, void *hba_private) { @@ -213,11 +221,18 @@ static void scsi_qdev_realize(DeviceState *qdev, Error **errp) static void scsi_qdev_unrealize(DeviceState *qdev, Error **errp) { SCSIDevice *dev = SCSI_DEVICE(qdev); + Error *local_err = NULL;
if (dev->vmsentry) { qemu_del_vm_change_state_handler(dev->vmsentry); }
+ scsi_device_unrealize(dev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + scsi_device_purge_requests(dev, SENSE_CODE(NO_SENSE)); blockdev_mark_auto_del(dev->conf.blk); } diff --git a/include/hw/scsi/scsi.h b/include/hw/scsi/scsi.h index 426566a5c6..8cf71f910d 100644 --- a/include/hw/scsi/scsi.h +++ b/include/hw/scsi/scsi.h @@ -59,6 +59,7 @@ struct SCSIRequest { typedef struct SCSIDeviceClass { DeviceClass parent_class; void (*realize)(SCSIDevice *dev, Error **errp); + void (*unrealize)(SCSIDevice *dev, Error **errp); int (*parse_cdb)(SCSIDevice *dev, SCSICommand *cmd, uint8_t *buf, void *hba_private); SCSIRequest *(*alloc_req)(SCSIDevice *s, uint32_t tag, uint32_t lun,
Relevant devices are: * ide-hd (and ide-cd, ide-drive) * scsi-hd (and scsi-cd, scsi-disk, scsi-block) * virtio-blk-pci
We do not call del_boot_device_lchs() for ide-* since we don't need to - IDE block devices do not support unplugging.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- hw/block/virtio-blk.c | 6 ++++++ hw/ide/qdev.c | 5 +++++ hw/scsi/scsi-disk.c | 14 ++++++++++++++ 3 files changed, 25 insertions(+)
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index 06e57a4d39..787bbd768a 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -1182,6 +1182,11 @@ static void virtio_blk_device_realize(DeviceState *dev, Error **errp) blk_set_guest_block_size(s->blk, s->conf.conf.logical_block_size);
blk_iostatus_enable(s->blk); + + add_boot_device_lchs(dev, "/disk@0,0", + (&conf->conf)->lcyls, + (&conf->conf)->lheads, + (&conf->conf)->lsecs); }
static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp) @@ -1189,6 +1194,7 @@ static void virtio_blk_device_unrealize(DeviceState *dev, Error **errp) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOBlock *s = VIRTIO_BLK(dev);
+ del_boot_device_lchs(dev, "/disk@0,0"); virtio_blk_data_plane_destroy(s->dataplane); s->dataplane = NULL; qemu_del_vm_change_state_handler(s->change); diff --git a/hw/ide/qdev.c b/hw/ide/qdev.c index 9cae3205df..07f429d5e3 100644 --- a/hw/ide/qdev.c +++ b/hw/ide/qdev.c @@ -215,6 +215,11 @@ static void ide_dev_initfn(IDEDevice *dev, IDEDriveKind kind, Error **errp)
add_boot_device_path(dev->conf.bootindex, &dev->qdev, dev->unit ? "/disk@1" : "/disk@0"); + + add_boot_device_lchs(&dev->qdev, dev->unit ? "/disk@1" : "/disk@0", + (&dev->conf)->lcyls, + (&dev->conf)->lheads, + (&dev->conf)->lsecs); }
static void ide_dev_get_bootindex(Object *obj, Visitor *v, const char *name, diff --git a/hw/scsi/scsi-disk.c b/hw/scsi/scsi-disk.c index 7b89ac798b..3451aefdea 100644 --- a/hw/scsi/scsi-disk.c +++ b/hw/scsi/scsi-disk.c @@ -2390,6 +2390,16 @@ static void scsi_realize(SCSIDevice *dev, Error **errp) blk_set_guest_block_size(s->qdev.conf.blk, s->qdev.blocksize);
blk_iostatus_enable(s->qdev.conf.blk); + + add_boot_device_lchs(&dev->qdev, NULL, + (&dev->conf)->lcyls, + (&dev->conf)->lheads, + (&dev->conf)->lsecs); +} + +static void scsi_unrealize(SCSIDevice *dev, Error **errp) +{ + del_boot_device_lchs(&dev->qdev, NULL); }
static void scsi_hd_realize(SCSIDevice *dev, Error **errp) @@ -2988,6 +2998,7 @@ static void scsi_hd_class_initfn(ObjectClass *klass, void *data) SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_hd_realize; + sc->unrealize = scsi_unrealize; sc->alloc_req = scsi_new_request; sc->unit_attention_reported = scsi_disk_unit_attention_reported; dc->desc = "virtual SCSI disk"; @@ -3019,6 +3030,7 @@ static void scsi_cd_class_initfn(ObjectClass *klass, void *data) SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_cd_realize; + sc->unrealize = scsi_unrealize; sc->alloc_req = scsi_new_request; sc->unit_attention_reported = scsi_disk_unit_attention_reported; dc->desc = "virtual SCSI CD-ROM"; @@ -3054,6 +3066,7 @@ static void scsi_block_class_initfn(ObjectClass *klass, void *data) SCSIDiskClass *sdc = SCSI_DISK_BASE_CLASS(klass);
sc->realize = scsi_block_realize; + sc->unrealize = scsi_unrealize; sc->alloc_req = scsi_block_new_request; sc->parse_cdb = scsi_block_parse_cdb; sdc->dma_readv = scsi_block_dma_readv; @@ -3095,6 +3108,7 @@ static void scsi_disk_class_initfn(ObjectClass *klass, void *data) SCSIDeviceClass *sc = SCSI_DEVICE_CLASS(klass);
sc->realize = scsi_disk_realize; + sc->unrealize = scsi_unrealize; sc->alloc_req = scsi_new_request; sc->unit_attention_reported = scsi_disk_unit_attention_reported; dc->fw_name = "disk";
Move device name construction to a separate function.
We will reuse this function in the following commit to pass logical CHS parameters through fw_cfg much like we currently pass bootindex.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- bootdevice.c | 61 +++++++++++++++++++++++++++++++++--------------------------- 1 file changed, 34 insertions(+), 27 deletions(-)
diff --git a/bootdevice.c b/bootdevice.c index bc5e1c2de4..2b12fb85a4 100644 --- a/bootdevice.c +++ b/bootdevice.c @@ -202,6 +202,39 @@ DeviceState *get_boot_device(uint32_t position) return res; }
+static char *get_boot_device_path(DeviceState *dev, bool ignore_suffixes, + char *suffix) +{ + char *devpath = NULL, *s = NULL, *d, *bootpath; + + if (dev) { + devpath = qdev_get_fw_dev_path(dev); + assert(devpath); + } + + if (!ignore_suffixes) { + if (dev) { + d = qdev_get_own_fw_dev_path_from_handler(dev->parent_bus, dev); + if (d) { + assert(!suffix); + s = d; + } else { + s = g_strdup(suffix); + } + } else { + s = g_strdup(suffix); + } + } + + bootpath = g_strdup_printf("%s%s", + devpath ? devpath : "", + s ? s : ""); + g_free(devpath); + g_free(s); + + return bootpath; +} + /* * This function returns null terminated string that consist of new line * separated device paths. @@ -218,36 +251,10 @@ char *get_boot_devices_list(size_t *size) bool ignore_suffixes = mc->ignore_boot_device_suffixes;
QTAILQ_FOREACH(i, &fw_boot_order, link) { - char *devpath = NULL, *suffix = NULL; char *bootpath; - char *d; size_t len;
- if (i->dev) { - devpath = qdev_get_fw_dev_path(i->dev); - assert(devpath); - } - - if (!ignore_suffixes) { - if (i->dev) { - d = qdev_get_own_fw_dev_path_from_handler(i->dev->parent_bus, - i->dev); - if (d) { - assert(!i->suffix); - suffix = d; - } else { - suffix = g_strdup(i->suffix); - } - } else { - suffix = g_strdup(i->suffix); - } - } - - bootpath = g_strdup_printf("%s%s", - devpath ? devpath : "", - suffix ? suffix : ""); - g_free(devpath); - g_free(suffix); + bootpath = get_boot_device_path(i->dev, ignore_suffixes, i->suffix);
if (total) { list[total-1] = '\n';
Using fw_cfg, supply logical CHS values directly from QEMU to the BIOS.
Non-standard logical geometries break under QEMU.
A virtual disk which contains an operating system which depends on logical geometries (consistent values being reported from BIOS INT13 AH=08) will most likely break under QEMU/SeaBIOS if it has non-standard logical geometries - for example 56 SPT (sectors per track). No matter what QEMU will report - SeaBIOS, for large enough disks - will use LBA translation, which will report 63 SPT instead.
In addition we cannot force SeaBIOS to rely on physical geometries at all. A virtio-blk-pci virtual disk with 255 phyiscal heads cannot report more than 16 physical heads when moved to an IDE controller, since the ATA spec allows a maximum of 16 heads - this is an artifact of virtualization.
By supplying the logical geometries directly we are able to support such "exotic" disks.
We serialize this information in a similar way to the "bootorder" interface. The fw_cfg entry is "bootdevices" and it serializes a struct. At the moment the struct holds the values of logical CHS values but it can be expanded easily due to the extendable ABI implemented.
(In the future, we can pass the bootindex through "bootdevices" instead "bootorder" - unifying all bootdevice information in one fw_cfg value)
The PV interface through fw_cfg could have also been implemented using device specific keys, e.g.: "/etc/bootdevice/%s/logical_geometry" where %s is the device name QEMU produces - but this implementation would require much more code refactoring, both in QEMU and SeaBIOS, so the current implementation was chosen.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- bootdevice.c | 42 ++++++++++++++++++++++++++++++++++++++++++ hw/nvram/fw_cfg.c | 14 +++++++++++--- include/sysemu/sysemu.h | 1 + 3 files changed, 54 insertions(+), 3 deletions(-)
diff --git a/bootdevice.c b/bootdevice.c index 2b12fb85a4..84c2a83f25 100644 --- a/bootdevice.c +++ b/bootdevice.c @@ -405,3 +405,45 @@ void del_boot_device_lchs(DeviceState *dev, const char *suffix) } } } + +typedef struct QEMU_PACKED BootDeviceEntrySerialized { + /* Do not change field order - add new fields below */ + uint32_t lcyls; + uint32_t lheads; + uint32_t lsecs; +} BootDeviceEntrySerialized; + +/* Serialized as: struct size (4) + (device name\0 + device struct) x devices */ +char *get_boot_devices_info(size_t *size) +{ + FWLCHSEntry *i; + BootDeviceEntrySerialized s; + size_t total = 0; + char *list = NULL; + + list = g_malloc0(sizeof(uint32_t)); + *((uint32_t *)list) = (uint32_t)sizeof(s); + total = sizeof(uint32_t); + + QTAILQ_FOREACH(i, &fw_lchs, link) { + char *bootpath; + size_t len; + + bootpath = get_boot_device_path(i->dev, false, i->suffix); + s.lcyls = i->lcyls; + s.lheads = i->lheads; + s.lsecs = i->lsecs; + + len = strlen(bootpath) + 1; + list = g_realloc(list, total + len + sizeof(s)); + memcpy(&list[total], bootpath, len); + memcpy(&list[total + len], &s, sizeof(s)); + total += len + sizeof(s); + + g_free(bootpath); + } + + *size = total; + + return list; +} diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index 9f7b7789bc..008b21542f 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -916,13 +916,21 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
static void fw_cfg_machine_reset(void *opaque) { + MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); + FWCfgState *s = opaque; void *ptr; size_t len; - FWCfgState *s = opaque; - char *bootindex = get_boot_devices_list(&len); + char *buf;
- ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)bootindex, len); + buf = get_boot_devices_list(&len); + ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)buf, len); g_free(ptr); + + if (!mc->legacy_fw_cfg_order) { + buf = get_boot_devices_info(&len); + ptr = fw_cfg_modify_file(s, "bootdevices", (uint8_t *)buf, len); + g_free(ptr); + } }
static void fw_cfg_machine_ready(struct Notifier *n, void *data) diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 173dfbb539..f0552006f4 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -174,6 +174,7 @@ void validate_bootdevices(const char *devices, Error **errp); void add_boot_device_lchs(DeviceState *dev, const char *suffix, uint32_t lcyls, uint32_t lheads, uint32_t lsecs); void del_boot_device_lchs(DeviceState *dev, const char *suffix); +char *get_boot_devices_info(size_t *size);
/* handler to set the boot_device order for a specific type of MachineClass */ typedef void QEMUBootSetHandler(void *opaque, const char *boot_order,
On 06/12/19 11:42, Sam Eiderman wrote:
Using fw_cfg, supply logical CHS values directly from QEMU to the BIOS.
Non-standard logical geometries break under QEMU.
A virtual disk which contains an operating system which depends on logical geometries (consistent values being reported from BIOS INT13 AH=08) will most likely break under QEMU/SeaBIOS if it has non-standard logical geometries - for example 56 SPT (sectors per track). No matter what QEMU will report - SeaBIOS, for large enough disks - will use LBA translation, which will report 63 SPT instead.
In addition we cannot force SeaBIOS to rely on physical geometries at all. A virtio-blk-pci virtual disk with 255 phyiscal heads cannot report more than 16 physical heads when moved to an IDE controller, since the ATA spec allows a maximum of 16 heads - this is an artifact of virtualization.
By supplying the logical geometries directly we are able to support such "exotic" disks.
We serialize this information in a similar way to the "bootorder" interface. The fw_cfg entry is "bootdevices" and it serializes a struct. At the moment the struct holds the values of logical CHS values but it can be expanded easily due to the extendable ABI implemented.
(In the future, we can pass the bootindex through "bootdevices" instead "bootorder" - unifying all bootdevice information in one fw_cfg value)
I would disagree with that. UEFI guest firmware doesn't seem to have any use for this new type of information ("logical CHS values"), so the current interface (the "bootorder" fw_cfg file) should continue to work. The ArmVirtQemu and OVMF platform firmwares (built from the edk2 project, and bundled with QEMU 4.1+) implement some serious parsing and processing for "bootorder".
Independently, another comment:
The PV interface through fw_cfg could have also been implemented using device specific keys, e.g.: "/etc/bootdevice/%s/logical_geometry" where %s is the device name QEMU produces - but this implementation would require much more code refactoring, both in QEMU and SeaBIOS, so the current implementation was chosen.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com
bootdevice.c | 42 ++++++++++++++++++++++++++++++++++++++++++ hw/nvram/fw_cfg.c | 14 +++++++++++--- include/sysemu/sysemu.h | 1 + 3 files changed, 54 insertions(+), 3 deletions(-)
diff --git a/bootdevice.c b/bootdevice.c index 2b12fb85a4..84c2a83f25 100644 --- a/bootdevice.c +++ b/bootdevice.c @@ -405,3 +405,45 @@ void del_boot_device_lchs(DeviceState *dev, const char *suffix) } } }
+typedef struct QEMU_PACKED BootDeviceEntrySerialized {
- /* Do not change field order - add new fields below */
- uint32_t lcyls;
- uint32_t lheads;
- uint32_t lsecs;
+} BootDeviceEntrySerialized;
+/* Serialized as: struct size (4) + (device name\0 + device struct) x devices */ +char *get_boot_devices_info(size_t *size) +{
- FWLCHSEntry *i;
- BootDeviceEntrySerialized s;
- size_t total = 0;
- char *list = NULL;
- list = g_malloc0(sizeof(uint32_t));
- *((uint32_t *)list) = (uint32_t)sizeof(s);
- total = sizeof(uint32_t);
- QTAILQ_FOREACH(i, &fw_lchs, link) {
char *bootpath;size_t len;bootpath = get_boot_device_path(i->dev, false, i->suffix);s.lcyls = i->lcyls;s.lheads = i->lheads;s.lsecs = i->lsecs;
You should document the endianness of the fields in BootDeviceEntrySerialized, and then call byte order conversion functions here accordingly (most probably cpu_to_le32()).
As written, this code would break if you ran qemu-system-x86_64 / qemu-system-i386 (with TCG acceleration) on a big endian host.
Thanks Laszlo
len = strlen(bootpath) + 1;list = g_realloc(list, total + len + sizeof(s));memcpy(&list[total], bootpath, len);memcpy(&list[total + len], &s, sizeof(s));total += len + sizeof(s);g_free(bootpath);- }
- *size = total;
- return list;
+} diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index 9f7b7789bc..008b21542f 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -916,13 +916,21 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
static void fw_cfg_machine_reset(void *opaque) {
- MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
- FWCfgState *s = opaque; void *ptr; size_t len;
- FWCfgState *s = opaque;
- char *bootindex = get_boot_devices_list(&len);
- char *buf;
- ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)bootindex, len);
- buf = get_boot_devices_list(&len);
- ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)buf, len); g_free(ptr);
- if (!mc->legacy_fw_cfg_order) {
buf = get_boot_devices_info(&len);ptr = fw_cfg_modify_file(s, "bootdevices", (uint8_t *)buf, len);g_free(ptr);- }
}
static void fw_cfg_machine_ready(struct Notifier *n, void *data) diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 173dfbb539..f0552006f4 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -174,6 +174,7 @@ void validate_bootdevices(const char *devices, Error **errp); void add_boot_device_lchs(DeviceState *dev, const char *suffix, uint32_t lcyls, uint32_t lheads, uint32_t lsecs); void del_boot_device_lchs(DeviceState *dev, const char *suffix); +char *get_boot_devices_info(size_t *size);
/* handler to set the boot_device order for a specific type of MachineClass */ typedef void QEMUBootSetHandler(void *opaque, const char *boot_order,
On 12 Jun 2019, at 15:27, Laszlo Ersek lersek@redhat.com wrote:
On 06/12/19 11:42, Sam Eiderman wrote:
Using fw_cfg, supply logical CHS values directly from QEMU to the BIOS.
Non-standard logical geometries break under QEMU.
A virtual disk which contains an operating system which depends on logical geometries (consistent values being reported from BIOS INT13 AH=08) will most likely break under QEMU/SeaBIOS if it has non-standard logical geometries - for example 56 SPT (sectors per track). No matter what QEMU will report - SeaBIOS, for large enough disks - will use LBA translation, which will report 63 SPT instead.
In addition we cannot force SeaBIOS to rely on physical geometries at all. A virtio-blk-pci virtual disk with 255 phyiscal heads cannot report more than 16 physical heads when moved to an IDE controller, since the ATA spec allows a maximum of 16 heads - this is an artifact of virtualization.
By supplying the logical geometries directly we are able to support such "exotic" disks.
We serialize this information in a similar way to the "bootorder" interface. The fw_cfg entry is "bootdevices" and it serializes a struct. At the moment the struct holds the values of logical CHS values but it can be expanded easily due to the extendable ABI implemented.
(In the future, we can pass the bootindex through "bootdevices" instead "bootorder" - unifying all bootdevice information in one fw_cfg value)
I would disagree with that. UEFI guest firmware doesn't seem to have any use for this new type of information ("logical CHS values"), so the current interface (the "bootorder" fw_cfg file) should continue to work. The ArmVirtQemu and OVMF platform firmwares (built from the edk2 project, and bundled with QEMU 4.1+) implement some serious parsing and processing for "bootorder”.
I agree, I didn’t mean to say that “bootdevices" will replace “bootorder”, they will have to reside side by side. I just meant to emphasis that bootorder is not extendible - adding more disk specific fields other than bootorder (that for some platforms will be unused) is not possible. “bootdevices” will work for LCHS, if another entry has to be passed - it can be added to “bootdevice”. Migrating “bootorder” into a different fw_cfg value is a tedious, probably not worth it, effort.
Independently, another comment:
The PV interface through fw_cfg could have also been implemented using device specific keys, e.g.: "/etc/bootdevice/%s/logical_geometry" where %s is the device name QEMU produces - but this implementation would require much more code refactoring, both in QEMU and SeaBIOS, so the current implementation was chosen.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com
bootdevice.c | 42 ++++++++++++++++++++++++++++++++++++++++++ hw/nvram/fw_cfg.c | 14 +++++++++++--- include/sysemu/sysemu.h | 1 + 3 files changed, 54 insertions(+), 3 deletions(-)
diff --git a/bootdevice.c b/bootdevice.c index 2b12fb85a4..84c2a83f25 100644 --- a/bootdevice.c +++ b/bootdevice.c @@ -405,3 +405,45 @@ void del_boot_device_lchs(DeviceState *dev, const char *suffix) } } }
+typedef struct QEMU_PACKED BootDeviceEntrySerialized {
- /* Do not change field order - add new fields below */
- uint32_t lcyls;
- uint32_t lheads;
- uint32_t lsecs;
+} BootDeviceEntrySerialized;
+/* Serialized as: struct size (4) + (device name\0 + device struct) x devices */ +char *get_boot_devices_info(size_t *size) +{
- FWLCHSEntry *i;
- BootDeviceEntrySerialized s;
- size_t total = 0;
- char *list = NULL;
- list = g_malloc0(sizeof(uint32_t));
- *((uint32_t *)list) = (uint32_t)sizeof(s);
- total = sizeof(uint32_t);
- QTAILQ_FOREACH(i, &fw_lchs, link) {
char *bootpath;size_t len;bootpath = get_boot_device_path(i->dev, false, i->suffix);s.lcyls = i->lcyls;s.lheads = i->lheads;s.lsecs = i->lsecs;You should document the endianness of the fields in BootDeviceEntrySerialized, and then call byte order conversion functions here accordingly (most probably cpu_to_le32()).
As written, this code would break if you ran qemu-system-x86_64 / qemu-system-i386 (with TCG acceleration) on a big endian host.
Nice catch, thanks!
Thanks Laszlo
len = strlen(bootpath) + 1;list = g_realloc(list, total + len + sizeof(s));memcpy(&list[total], bootpath, len);memcpy(&list[total + len], &s, sizeof(s));total += len + sizeof(s);g_free(bootpath);- }
- *size = total;
- return list;
+} diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index 9f7b7789bc..008b21542f 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -916,13 +916,21 @@ void *fw_cfg_modify_file(FWCfgState *s, const char *filename,
static void fw_cfg_machine_reset(void *opaque) {
- MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
- FWCfgState *s = opaque; void *ptr; size_t len;
- FWCfgState *s = opaque;
- char *bootindex = get_boot_devices_list(&len);
- char *buf;
- ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)bootindex, len);
- buf = get_boot_devices_list(&len);
- ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)buf, len); g_free(ptr);
- if (!mc->legacy_fw_cfg_order) {
buf = get_boot_devices_info(&len);ptr = fw_cfg_modify_file(s, "bootdevices", (uint8_t *)buf, len);g_free(ptr);- }
}
static void fw_cfg_machine_ready(struct Notifier *n, void *data) diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 173dfbb539..f0552006f4 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -174,6 +174,7 @@ void validate_bootdevices(const char *devices, Error **errp); void add_boot_device_lchs(DeviceState *dev, const char *suffix, uint32_t lcyls, uint32_t lheads, uint32_t lsecs); void del_boot_device_lchs(DeviceState *dev, const char *suffix); +char *get_boot_devices_info(size_t *size);
/* handler to set the boot_device order for a specific type of MachineClass */ typedef void QEMUBootSetHandler(void *opaque, const char *boot_order,
Add QTest tests to check the logical geometry override option.
The tests in hd-geo-test are out of date - they only test IDE and do not test interesting MBRs.
I added a few helper functions which will make adding more tests easier.
QTest's fw_cfg helper functions support only legacy fw_cfg, so I had to read the new fw_cfg layout on my own.
Creating qcow2 disks with specific size and MBR layout is currently unused - we only use a default empty MBR.
Reviewed-by: Karl Heubaum karl.heubaum@oracle.com Reviewed-by: Arbel Moshe arbel.moshe@oracle.com Signed-off-by: Sam Eiderman shmuel.eiderman@oracle.com --- tests/Makefile.include | 2 +- tests/hd-geo-test.c | 565 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 566 insertions(+), 1 deletion(-)
diff --git a/tests/Makefile.include b/tests/Makefile.include index 46a36c2c95..55ea165ed4 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -765,7 +765,7 @@ tests/ide-test$(EXESUF): tests/ide-test.o $(libqos-pc-obj-y) tests/ahci-test$(EXESUF): tests/ahci-test.o $(libqos-pc-obj-y) qemu-img$(EXESUF) tests/ipmi-kcs-test$(EXESUF): tests/ipmi-kcs-test.o tests/ipmi-bt-test$(EXESUF): tests/ipmi-bt-test.o -tests/hd-geo-test$(EXESUF): tests/hd-geo-test.o +tests/hd-geo-test$(EXESUF): tests/hd-geo-test.o $(libqos-obj-y) tests/boot-order-test$(EXESUF): tests/boot-order-test.o $(libqos-obj-y) tests/boot-serial-test$(EXESUF): tests/boot-serial-test.o $(libqos-obj-y) tests/bios-tables-test$(EXESUF): tests/bios-tables-test.o \ diff --git a/tests/hd-geo-test.c b/tests/hd-geo-test.c index 62eb624726..16e7447f75 100644 --- a/tests/hd-geo-test.c +++ b/tests/hd-geo-test.c @@ -17,7 +17,11 @@
#include "qemu/osdep.h" #include "qemu-common.h" +#include "qemu/bswap.h" +#include "qapi/qmp/qlist.h" #include "libqtest.h" +#include "libqos/fw_cfg.h" +#include "standard-headers/linux/qemu_fw_cfg.h"
#define ARGV_SIZE 256
@@ -388,6 +392,557 @@ static void test_ide_drive_cd_0(void) qtest_quit(qts); }
+typedef struct { + bool active; + uint32_t head; + uint32_t sector; + uint32_t cyl; + uint32_t end_head; + uint32_t end_sector; + uint32_t end_cyl; + uint32_t start_sect; + uint32_t nr_sects; +} MBRpartitions[4]; + +static MBRpartitions empty_mbr = { {false, 0, 0, 0, 0, 0, 0, 0, 0}, + {false, 0, 0, 0, 0, 0, 0, 0, 0}, + {false, 0, 0, 0, 0, 0, 0, 0, 0}, + {false, 0, 0, 0, 0, 0, 0, 0, 0} }; + +static char *create_qcow2_with_mbr(MBRpartitions mbr, uint64_t sectors) +{ + const char *template = "/tmp/qtest.XXXXXX"; + char *raw_path = strdup(template); + char *qcow2_path = strdup(template); + char cmd[100 + 2 * PATH_MAX]; + uint8_t buf[512]; + int i, ret, fd, offset; + uint64_t qcow2_size = sectors * 512; + uint8_t status, parttype, head, sector, cyl; + + offset = 0xbe; + + for (i = 0; i < 4; i++) { + status = mbr[i].active ? 0x80 : 0x00; + g_assert(mbr[i].head < 256); + g_assert(mbr[i].sector < 64); + g_assert(mbr[i].cyl < 1024); + head = mbr[i].head; + sector = mbr[i].sector + ((mbr[i].cyl & 0x300) >> 2); + cyl = mbr[i].cyl & 0xff; + + buf[offset + 0x0] = status; + buf[offset + 0x1] = head; + buf[offset + 0x2] = sector; + buf[offset + 0x3] = cyl; + + parttype = 0; + g_assert(mbr[i].end_head < 256); + g_assert(mbr[i].end_sector < 64); + g_assert(mbr[i].end_cyl < 1024); + head = mbr[i].end_head; + sector = mbr[i].end_sector + ((mbr[i].end_cyl & 0x300) >> 2); + cyl = mbr[i].end_cyl & 0xff; + + buf[offset + 0x4] = parttype; + buf[offset + 0x5] = head; + buf[offset + 0x6] = sector; + buf[offset + 0x7] = cyl; + + (*(uint32_t *)&buf[offset + 0x8]) = cpu_to_le32(mbr[i].start_sect); + (*(uint32_t *)&buf[offset + 0xc]) = cpu_to_le32(mbr[i].nr_sects); + + offset += 0x10; + } + + fd = mkstemp(raw_path); + g_assert(fd); + close(fd); + + fd = open(raw_path, O_WRONLY); + g_assert(fd >= 0); + ret = write(fd, buf, sizeof(buf)); + g_assert(ret == sizeof(buf)); + close(fd); + + fd = mkstemp(qcow2_path); + g_assert(fd); + close(fd); + + ret = snprintf(cmd, sizeof(cmd), + "$QTEST_QEMU_IMG convert -f raw -O qcow2 %s %s > /dev/null", + raw_path, qcow2_path); + g_assert((0 < ret) && (ret <= sizeof(cmd))); + ret = system(cmd); + g_assert(ret == 0); + + ret = snprintf(cmd, sizeof(cmd), + "$QTEST_QEMU_IMG resize %s %" PRIu64 " > /dev/null", + qcow2_path, qcow2_size); + g_assert((0 < ret) && (ret <= sizeof(cmd))); + ret = system(cmd); + g_assert(ret == 0); + + unlink(raw_path); + free(raw_path); + + return qcow2_path; +} + +struct QemuCfgFile { + uint32_t size; /* file size */ + uint16_t select; /* write this to 0x510 to read it */ + uint16_t reserved; + char name[56]; +}; + +static uint16_t find_fw_cfg_file(QFWCFG *fw_cfg, + const char *filename) +{ + struct QemuCfgFile qfile; + uint32_t count, e; + uint16_t select; + + count = qfw_cfg_get_u32(fw_cfg, FW_CFG_FILE_DIR); + count = be32_to_cpu(count); + for (select = 0, e = 0; e < count; e++) { + qfw_cfg_read_data(fw_cfg, &qfile, sizeof(qfile)); + if (!strcmp(filename, qfile.name)) { + select = be16_to_cpu(qfile.select); + } + } + + return select; +} + +static void read_fw_cfg_file(QFWCFG *fw_cfg, + const char *filename, + void *data, + size_t len) +{ + uint16_t select = find_fw_cfg_file(fw_cfg, filename); + + g_assert(select); + + qfw_cfg_get(fw_cfg, select, data, len); +} + +#define BOOTDEVICES_MAX_SIZE 10000 + +typedef struct { + uint32_t c; + uint32_t h; + uint32_t s; +} CHS; + +typedef struct { + const char *dev_path; + CHS chs; +} CHSResult; + +static void read_bootdevices(QFWCFG *fw_cfg, CHSResult expected[]) +{ + uint32_t info_size; + char *buf = g_malloc0(BOOTDEVICES_MAX_SIZE); + void *cur; + char *name; + CHS *chs; + GList *results = NULL, *cur_result; + CHSResult *r; + int i; + bool found; + + read_fw_cfg_file(fw_cfg, "bootdevices", buf, BOOTDEVICES_MAX_SIZE); + + cur = buf; + + info_size = *((uint32_t *)cur); + + g_assert(info_size >= sizeof(*chs)); + + cur += 4; + + while (strlen(cur)) { + name = cur; + chs = cur + strlen(cur) + 1; + + r = g_malloc0(sizeof(*r)); + r->dev_path = name; + r->chs = *chs; + + results = g_list_prepend(results, r); + + cur += strlen(cur) + 1 + info_size; + } + + i = 0; + + while (expected[i].dev_path) { + found = false; + cur_result = results; + while (cur_result) { + r = cur_result->data; + if (!strcmp(r->dev_path, expected[i].dev_path) && + !memcmp(&(r->chs), &(expected[i].chs), sizeof(r->chs))) { + found = true; + break; + } + cur_result = g_list_next(cur_result); + } + g_assert(found); + g_free(cur_result->data); + results = g_list_delete_link(results, cur_result); + i++; + } + + g_assert(results == NULL); + + g_free(buf); +} + +#define MAX_DRIVES 30 + +typedef struct { + char **argv; + int argc; + char **drives; + int n_drives; + int n_scsi_disks; + int n_scsi_controllers; + int n_virtio_disks; +} TestArgs; + +static TestArgs *create_args(void) +{ + TestArgs *args = g_malloc0(sizeof(*args)); + args->argv = g_new0(char *, ARGV_SIZE); + args->argc = append_arg(args->argc, args->argv, + ARGV_SIZE, g_strdup("-nodefaults")); + args->drives = g_new0(char *, MAX_DRIVES); + return args; +} + +static void add_drive_with_mbr(TestArgs *args, + MBRpartitions mbr, uint64_t sectors) +{ + char *img_file_name; + char part[300]; + int ret; + + g_assert(args->n_drives < MAX_DRIVES); + + img_file_name = create_qcow2_with_mbr(mbr, sectors); + + args->drives[args->n_drives] = img_file_name; + ret = snprintf(part, sizeof(part), + "-drive file=%s,if=none,format=qcow2,id=disk%d", + img_file_name, args->n_drives); + g_assert((0 < ret) && (ret <= sizeof(part))); + args->argc = append_arg(args->argc, args->argv, ARGV_SIZE, g_strdup(part)); + args->n_drives++; +} + +static void add_ide_disk(TestArgs *args, + int drive_idx, int bus, int unit, int c, int h, int s) +{ + char part[300]; + int ret; + + ret = snprintf(part, sizeof(part), + "-device ide-hd,drive=disk%d,bus=ide.%d,unit=%d," + "lcyls=%d,lheads=%d,lsecs=%d", + drive_idx, bus, unit, c, h, s); + g_assert((0 < ret) && (ret <= sizeof(part))); + args->argc = append_arg(args->argc, args->argv, ARGV_SIZE, g_strdup(part)); +} + +static void add_scsi_controller(TestArgs *args, + const char *type, + const char *bus, + int addr) +{ + char part[300]; + int ret; + + ret = snprintf(part, sizeof(part), + "-device %s,id=scsi%d,bus=%s,addr=%d", + type, args->n_scsi_controllers, bus, addr); + g_assert((0 < ret) && (ret <= sizeof(part))); + args->argc = append_arg(args->argc, args->argv, ARGV_SIZE, g_strdup(part)); + args->n_scsi_controllers++; +} + +static void add_scsi_disk(TestArgs *args, + int drive_idx, int bus, + int channel, int scsi_id, int lun, + int c, int h, int s) +{ + char part[300]; + int ret; + + ret = snprintf(part, sizeof(part), + "-device scsi-hd,id=scsi-disk%d,drive=disk%d," + "bus=scsi%d.0," + "channel=%d,scsi-id=%d,lun=%d," + "lcyls=%d,lheads=%d,lsecs=%d", + args->n_scsi_disks, drive_idx, bus, channel, scsi_id, lun, + c, h, s); + g_assert((0 < ret) && (ret <= sizeof(part))); + args->argc = append_arg(args->argc, args->argv, ARGV_SIZE, g_strdup(part)); + args->n_scsi_disks++; +} + +static void add_virtio_disk(TestArgs *args, + int drive_idx, const char *bus, int addr, + int c, int h, int s) +{ + char part[300]; + int ret; + + ret = snprintf(part, sizeof(part), + "-device virtio-blk-pci,id=virtio-disk%d," + "drive=disk%d,bus=%s,addr=%d," + "lcyls=%d,lheads=%d,lsecs=%d", + args->n_virtio_disks, drive_idx, bus, addr, c, h, s); + g_assert((0 < ret) && (ret <= sizeof(part))); + args->argc = append_arg(args->argc, args->argv, ARGV_SIZE, g_strdup(part)); + args->n_virtio_disks++; +} + +static void test_override(TestArgs *args, CHSResult expected[]) +{ + char *joined_args; + QFWCFG *fw_cfg; + int i; + + joined_args = g_strjoinv(" ", args->argv); + + qtest_start(joined_args); + fw_cfg = pc_fw_cfg_init(global_qtest); + + read_bootdevices(fw_cfg, expected); + + g_free(joined_args); + qtest_end(); + + g_free(fw_cfg); + + for (i = 0; i < args->n_drives; i++) { + unlink(args->drives[i]); + free(args->drives[i]); + } + g_free(args->drives); + g_strfreev(args->argv); + g_free(args); +} + +static void test_override_ide(void) +{ + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/ide@1,1/drive@0/disk@0", 10000, 120, 30}, + {"/pci@i0cf8/ide@1,1/drive@0/disk@1", 9000, 120, 30}, + {"/pci@i0cf8/ide@1,1/drive@1/disk@0", 0, 1, 1}, + {"/pci@i0cf8/ide@1,1/drive@1/disk@1", 1, 0, 0}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_ide_disk(args, 0, 0, 0, 10000, 120, 30); + add_ide_disk(args, 1, 0, 1, 9000, 120, 30); + add_ide_disk(args, 2, 1, 0, 0, 1, 1); + add_ide_disk(args, 3, 1, 1, 1, 0, 0); + test_override(args, expected); +} + +static void test_override_scsi(void) +{ + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/scsi@3/channel@0/disk@0,0", 10000, 120, 30}, + {"/pci@i0cf8/scsi@3/channel@0/disk@1,0", 9000, 120, 30}, + {"/pci@i0cf8/scsi@3/channel@0/disk@2,0", 1, 0, 0}, + {"/pci@i0cf8/scsi@3/channel@0/disk@3,0", 0, 1, 0}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_scsi_controller(args, "lsi53c895a", "pci.0", 3); + add_scsi_disk(args, 0, 0, 0, 0, 0, 10000, 120, 30); + add_scsi_disk(args, 1, 0, 0, 1, 0, 9000, 120, 30); + add_scsi_disk(args, 2, 0, 0, 2, 0, 1, 0, 0); + add_scsi_disk(args, 3, 0, 0, 3, 0, 0, 1, 0); + test_override(args, expected); +} + +static void test_override_scsi_2_controllers(void) +{ + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/scsi@3/channel@0/disk@0,0", 10000, 120, 30}, + {"/pci@i0cf8/scsi@3/channel@0/disk@1,0", 9000, 120, 30}, + {"/pci@i0cf8/scsi@4/channel@0/disk@0,1", 1, 0, 0}, + {"/pci@i0cf8/scsi@4/channel@0/disk@1,2", 0, 1, 0}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_scsi_controller(args, "lsi53c895a", "pci.0", 3); + add_scsi_controller(args, "virtio-scsi-pci", "pci.0", 4); + add_scsi_disk(args, 0, 0, 0, 0, 0, 10000, 120, 30); + add_scsi_disk(args, 1, 0, 0, 1, 0, 9000, 120, 30); + add_scsi_disk(args, 2, 1, 0, 0, 1, 1, 0, 0); + add_scsi_disk(args, 3, 1, 0, 1, 2, 0, 1, 0); + test_override(args, expected); +} + +static void test_override_virtio_blk(void) +{ + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/scsi@3/disk@0,0", 10000, 120, 30}, + {"/pci@i0cf8/scsi@4/disk@0,0", 9000, 120, 30}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_virtio_disk(args, 0, "pci.0", 3, 10000, 120, 30); + add_virtio_disk(args, 1, "pci.0", 4, 9000, 120, 30); + test_override(args, expected); +} + +static void test_override_zero_chs(void) +{ + TestArgs *args = create_args(); + CHSResult expected[] = { + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_ide_disk(args, 0, 1, 1, 0, 0, 0); + test_override(args, expected); +} + +static void test_override_scsi_hot_unplug(void) +{ + char *joined_args; + QFWCFG *fw_cfg; + QDict *response; + int i; + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/scsi@2/channel@0/disk@0,0", 10000, 120, 30}, + {"/pci@i0cf8/scsi@2/channel@0/disk@1,0", 20, 20, 20}, + {NULL, 0, 0, 0} + }; + CHSResult expected2[] = { + {"/pci@i0cf8/scsi@2/channel@0/disk@1,0", 20, 20, 20}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_scsi_controller(args, "virtio-scsi-pci", "pci.0", 2); + add_scsi_disk(args, 0, 0, 0, 0, 0, 10000, 120, 30); + add_scsi_disk(args, 1, 0, 0, 1, 0, 20, 20, 20); + + joined_args = g_strjoinv(" ", args->argv); + + qtest_start(joined_args); + fw_cfg = pc_fw_cfg_init(global_qtest); + + read_bootdevices(fw_cfg, expected); + + /* unplug device an restart */ + response = qmp("{ 'execute': 'device_del'," + " 'arguments': {'id': 'scsi-disk0' }}"); + g_assert(response); + g_assert(!qdict_haskey(response, "error")); + qobject_unref(response); + response = qmp("{ 'execute': 'system_reset', 'arguments': { }}"); + g_assert(response); + g_assert(!qdict_haskey(response, "error")); + qobject_unref(response); + + qtest_qmp_eventwait(global_qtest, "RESET"); + + read_bootdevices(fw_cfg, expected2); + + g_free(joined_args); + qtest_end(); + + g_free(fw_cfg); + + for (i = 0; i < args->n_drives; i++) { + unlink(args->drives[i]); + free(args->drives[i]); + } + g_free(args->drives); + g_strfreev(args->argv); + g_free(args); +} + +static void test_override_virtio_hot_unplug(void) +{ + char *joined_args; + QFWCFG *fw_cfg; + QDict *response; + int i; + TestArgs *args = create_args(); + CHSResult expected[] = { + {"/pci@i0cf8/scsi@2/disk@0,0", 10000, 120, 30}, + {"/pci@i0cf8/scsi@3/disk@0,0", 20, 20, 20}, + {NULL, 0, 0, 0} + }; + CHSResult expected2[] = { + {"/pci@i0cf8/scsi@3/disk@0,0", 20, 20, 20}, + {NULL, 0, 0, 0} + }; + add_drive_with_mbr(args, empty_mbr, 1); + add_drive_with_mbr(args, empty_mbr, 1); + add_virtio_disk(args, 0, "pci.0", 2, 10000, 120, 30); + add_virtio_disk(args, 1, "pci.0", 3, 20, 20, 20); + + joined_args = g_strjoinv(" ", args->argv); + + qtest_start(joined_args); + fw_cfg = pc_fw_cfg_init(global_qtest); + + read_bootdevices(fw_cfg, expected); + + /* unplug device an restart */ + response = qmp("{ 'execute': 'device_del'," + " 'arguments': {'id': 'virtio-disk0' }}"); + g_assert(response); + g_assert(!qdict_haskey(response, "error")); + qobject_unref(response); + response = qmp("{ 'execute': 'system_reset', 'arguments': { }}"); + g_assert(response); + g_assert(!qdict_haskey(response, "error")); + qobject_unref(response); + + qtest_qmp_eventwait(global_qtest, "RESET"); + + read_bootdevices(fw_cfg, expected2); + + g_free(joined_args); + qtest_end(); + + g_free(fw_cfg); + + for (i = 0; i < args->n_drives; i++) { + unlink(args->drives[i]); + free(args->drives[i]); + } + g_free(args->drives); + g_strfreev(args->argv); + g_free(args); +} + int main(int argc, char **argv) { Backend i; @@ -413,6 +968,16 @@ int main(int argc, char **argv) qtest_add_func("hd-geo/ide/device/mbr/chs", test_ide_device_mbr_chs); qtest_add_func("hd-geo/ide/device/user/chs", test_ide_device_user_chs); qtest_add_func("hd-geo/ide/device/user/chst", test_ide_device_user_chst); + qtest_add_func("hd-geo/override/ide", test_override_ide); + qtest_add_func("hd-geo/override/scsi", test_override_scsi); + qtest_add_func("hd-geo/override/scsi_2_controllers", + test_override_scsi_2_controllers); + qtest_add_func("hd-geo/override/virtio_blk", test_override_virtio_blk); + qtest_add_func("hd-geo/override/zero_chs", test_override_zero_chs); + qtest_add_func("hd-geo/override/scsi_hot_unplug", + test_override_scsi_hot_unplug); + qtest_add_func("hd-geo/override/virtio_hot_unplug", + test_override_virtio_hot_unplug);
ret = g_test_run();
-
Laszlo Ersek -
Sam Eiderman