diff options
55 files changed, 1931 insertions, 437 deletions
@@ -1274,6 +1274,33 @@ out: g_free(tmp_filename); } +static QDict *parse_json_filename(const char *filename, Error **errp) +{ + QObject *options_obj; + QDict *options; + int ret; + + ret = strstart(filename, "json:", &filename); + assert(ret); + + options_obj = qobject_from_json(filename); + if (!options_obj) { + error_setg(errp, "Could not parse the JSON options"); + return NULL; + } + + if (qobject_type(options_obj) != QTYPE_QDICT) { + qobject_decref(options_obj); + error_setg(errp, "Invalid JSON object given"); + return NULL; + } + + options = qobject_to_qdict(options_obj); + qdict_flatten(options); + + return options; +} + /* * Opens a disk image (raw, qcow2, vmdk, ...) * @@ -1337,6 +1364,20 @@ int bdrv_open(BlockDriverState **pbs, const char *filename, options = qdict_new(); } + if (filename && g_str_has_prefix(filename, "json:")) { + QDict *json_options = parse_json_filename(filename, &local_err); + if (local_err) { + ret = -EINVAL; + goto fail; + } + + /* Options given in the filename have lower priority than options + * specified directly */ + qdict_join(options, json_options, false); + QDECREF(json_options); + filename = NULL; + } + bs->options = options; options = qdict_clone_shallow(options); @@ -3248,6 +3289,15 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs, ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req); + if (!ret && bs->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF && + !(flags & BDRV_REQ_ZERO_WRITE) && drv->bdrv_co_write_zeroes && + qemu_iovec_is_zero(qiov)) { + flags |= BDRV_REQ_ZERO_WRITE; + if (bs->detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP) { + flags |= BDRV_REQ_MAY_UNMAP; + } + } + if (ret < 0) { /* Do nothing, write notifier decided to fail this request */ } else if (flags & BDRV_REQ_ZERO_WRITE) { @@ -3864,7 +3914,7 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, if (!bs->drv->bdrv_co_get_block_status) { *pnum = nb_sectors; - ret = BDRV_BLOCK_DATA; + ret = BDRV_BLOCK_DATA | BDRV_BLOCK_ALLOCATED; if (bs->drv->protocol_name) { ret |= BDRV_BLOCK_OFFSET_VALID | (sector_num * BDRV_SECTOR_SIZE); } @@ -3883,6 +3933,10 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs, *pnum, pnum); } + if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) { + ret |= BDRV_BLOCK_ALLOCATED; + } + if (!(ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO)) { if (bdrv_unallocated_blocks_are_zero(bs)) { ret |= BDRV_BLOCK_ZERO; @@ -3959,9 +4013,7 @@ int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num, if (ret < 0) { return ret; } - return - (ret & BDRV_BLOCK_DATA) || - ((ret & BDRV_BLOCK_ZERO) && !bdrv_has_zero_init(bs)); + return (ret & BDRV_BLOCK_ALLOCATED); } /* diff --git a/block/curl.c b/block/curl.c index d2f1084b91..f491b0ba4c 100644 --- a/block/curl.c +++ b/block/curl.c @@ -23,6 +23,7 @@ */ #include "qemu-common.h" #include "block/block_int.h" +#include "qapi/qmp/qbool.h" #include <curl/curl.h> // #define DEBUG @@ -37,6 +38,21 @@ #if LIBCURL_VERSION_NUM >= 0x071000 /* The multi interface timer callback was introduced in 7.16.0 */ #define NEED_CURL_TIMER_CALLBACK +#define HAVE_SOCKET_ACTION +#endif + +#ifndef HAVE_SOCKET_ACTION +/* If curl_multi_socket_action isn't available, define it statically here in + * terms of curl_multi_socket. Note that ev_bitmask will be ignored, which is + * less efficient but still safe. */ +static CURLMcode __curl_multi_socket_action(CURLM *multi_handle, + curl_socket_t sockfd, + int ev_bitmask, + int *running_handles) +{ + return curl_multi_socket(multi_handle, sockfd, running_handles); +} +#define curl_multi_socket_action __curl_multi_socket_action #endif #define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \ @@ -46,12 +62,16 @@ #define CURL_NUM_STATES 8 #define CURL_NUM_ACB 8 #define SECTOR_SIZE 512 -#define READ_AHEAD_SIZE (256 * 1024) +#define READ_AHEAD_DEFAULT (256 * 1024) #define FIND_RET_NONE 0 #define FIND_RET_OK 1 #define FIND_RET_WAIT 2 +#define CURL_BLOCK_OPT_URL "url" +#define CURL_BLOCK_OPT_READAHEAD "readahead" +#define CURL_BLOCK_OPT_SSLVERIFY "sslverify" + struct BDRVCURLState; typedef struct CURLAIOCB { @@ -88,6 +108,7 @@ typedef struct BDRVCURLState { CURLState states[CURL_NUM_STATES]; char *url; size_t readahead_size; + bool sslverify; bool accept_range; } BDRVCURLState; @@ -354,6 +375,8 @@ static CURLState *curl_init_state(BDRVCURLState *s) return NULL; } curl_easy_setopt(state->curl, CURLOPT_URL, s->url); + curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER, + (long) s->sslverify); curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5); curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb); @@ -396,43 +419,7 @@ static void curl_clean_state(CURLState *s) static void curl_parse_filename(const char *filename, QDict *options, Error **errp) { - - #define RA_OPTSTR ":readahead=" - char *file; - char *ra; - const char *ra_val; - int parse_state = 0; - - file = g_strdup(filename); - - /* Parse a trailing ":readahead=#:" param, if present. */ - ra = file + strlen(file) - 1; - while (ra >= file) { - if (parse_state == 0) { - if (*ra == ':') { - parse_state++; - } else { - break; - } - } else if (parse_state == 1) { - if (*ra > '9' || *ra < '0') { - char *opt_start = ra - strlen(RA_OPTSTR) + 1; - if (opt_start > file && - strncmp(opt_start, RA_OPTSTR, strlen(RA_OPTSTR)) == 0) { - ra_val = ra + 1; - ra -= strlen(RA_OPTSTR) - 1; - *ra = '\0'; - qdict_put(options, "readahead", qstring_from_str(ra_val)); - } - break; - } - } - ra--; - } - - qdict_put(options, "url", qstring_from_str(file)); - - g_free(file); + qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename)); } static QemuOptsList runtime_opts = { @@ -440,15 +427,20 @@ static QemuOptsList runtime_opts = { .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head), .desc = { { - .name = "url", + .name = CURL_BLOCK_OPT_URL, .type = QEMU_OPT_STRING, .help = "URL to open", }, { - .name = "readahead", + .name = CURL_BLOCK_OPT_READAHEAD, .type = QEMU_OPT_SIZE, .help = "Readahead size", }, + { + .name = CURL_BLOCK_OPT_SSLVERIFY, + .type = QEMU_OPT_BOOL, + .help = "Verify SSL certificate" + }, { /* end of list */ } }, }; @@ -477,14 +469,17 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, goto out_noclean; } - s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE); + s->readahead_size = qemu_opt_get_size(opts, CURL_BLOCK_OPT_READAHEAD, + READ_AHEAD_DEFAULT); if ((s->readahead_size & 0x1ff) != 0) { error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512", s->readahead_size); goto out_noclean; } - file = qemu_opt_get(opts, "url"); + s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true); + + file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL); if (file == NULL) { error_setg(errp, "curl block driver requires an 'url' option"); goto out_noclean; diff --git a/block/iscsi.c b/block/iscsi.c index d649424e5c..3892cc551e 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -381,6 +381,7 @@ retry: } +#if defined(LIBISCSI_FEATURE_IOVECTOR) static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun, int64_t sector_num, int nb_sectors) { @@ -393,9 +394,6 @@ static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun, sector_num / iscsilun->cluster_sectors) == size); } - -#if defined(LIBISCSI_FEATURE_IOVECTOR) - static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum) diff --git a/block/qapi.c b/block/qapi.c index af114452e0..75f44f1537 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -50,6 +50,7 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs) } info->backing_file_depth = bdrv_get_backing_file_depth(bs); + info->detect_zeroes = bs->detect_zeroes; if (bs->io_limits_enabled) { ThrottleConfig cfg; diff --git a/block/qcow.c b/block/qcow.c index 937dd6dd1c..7fd57d744a 100644 --- a/block/qcow.c +++ b/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)); @@ -127,11 +129,25 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } - if (header.size <= 1 || header.cluster_bits < 9) { - error_setg(errp, "invalid value in qcow header"); + 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) { error_setg(errp, "invalid encryption method in qcow header"); ret = -EINVAL; @@ -151,7 +167,19 @@ 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)); @@ -175,7 +203,9 @@ 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); diff --git a/block/vhdx.c b/block/vhdx.c index 509baaf484..353c74d35f 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -473,7 +473,14 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s, } else if (h2_seq > h1_seq) { s->curr_header = 1; } else { - goto fail; + /* The Microsoft Disk2VHD tool will create 2 identical + * headers, with identical sequence numbers. If the headers are + * identical, don't consider the file corrupt */ + if (!memcmp(header1, header2, sizeof(VHDXHeader))) { + s->curr_header = 0; + } else { + goto fail; + } } } diff --git a/blockdev.c b/blockdev.c index 7810e9fb68..1cbcc1c785 100644 --- a/blockdev.c +++ b/blockdev.c @@ -288,6 +288,25 @@ static int parse_block_error_action(const char *buf, bool is_read, Error **errp) } } +static inline int parse_enum_option(const char *lookup[], const char *buf, + int max, int def, Error **errp) +{ + int i; + + if (!buf) { + return def; + } + + for (i = 0; i < max; i++) { + if (!strcmp(buf, lookup[i])) { + return i; + } + } + + error_setg(errp, "invalid parameter value: %s", buf); + return def; +} + static bool check_throttle_config(ThrottleConfig *cfg, Error **errp) { if (throttle_conflicting(cfg)) { @@ -324,6 +343,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts, QemuOpts *opts; const char *id; bool has_driver_specific_opts; + BlockdevDetectZeroesOptions detect_zeroes; BlockDriver *drv = NULL; /* Check common options by copying from bs_opts to opts, all other options @@ -452,6 +472,24 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts, } } + detect_zeroes = + parse_enum_option(BlockdevDetectZeroesOptions_lookup, + qemu_opt_get(opts, "detect-zeroes"), + BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX, + BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF, + &error); + if (error) { + error_propagate(errp, error); + goto early_err; + } + + if (detect_zeroes == BLOCKDEV_DETECT_ZEROES_OPTIONS_UNMAP && + !(bdrv_flags & BDRV_O_UNMAP)) { + error_setg(errp, "setting detect-zeroes to unmap is not allowed " + "without setting discard operation to unmap"); + goto early_err; + } + /* init */ dinfo = g_malloc0(sizeof(*dinfo)); dinfo->id = g_strdup(qemu_opts_id(opts)); @@ -462,6 +500,7 @@ static DriveInfo *blockdev_init(const char *file, QDict *bs_opts, } dinfo->bdrv->open_flags = snapshot ? BDRV_O_SNAPSHOT : 0; dinfo->bdrv->read_only = ro; + dinfo->bdrv->detect_zeroes = detect_zeroes; dinfo->refcount = 1; if (serial != NULL) { dinfo->serial = g_strdup(serial); @@ -2455,6 +2494,10 @@ QemuOptsList qemu_common_drive_opts = { .name = "copy-on-read", .type = QEMU_OPT_BOOL, .help = "copy read data from backing file into image file", + },{ + .name = "detect-zeroes", + .type = QEMU_OPT_STRING, + .help = "try to optimize zero writes (off, on, unmap)", }, { /* end of list */ } }, diff --git a/default-configs/s390x-softmmu.mak b/default-configs/s390x-softmmu.mak index d843dc0d57..126d88dc15 100644 --- a/default-configs/s390x-softmmu.mak +++ b/default-configs/s390x-softmmu.mak @@ -1,3 +1,4 @@ CONFIG_VIRTIO=y CONFIG_SCLPCONSOLE=y -CONFIG_S390_FLIC=$(CONFIG_KVM) +CONFIG_S390_FLIC=y +CONFIG_S390_FLIC_KVM=$(CONFIG_KVM) @@ -341,6 +341,11 @@ void hmp_info_block(Monitor *mon, const QDict *qdict) info->value->inserted->backing_file_depth); } + if (info->value->inserted->detect_zeroes != BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF) { + monitor_printf(mon, " Detect zeroes: %s\n", + BlockdevDetectZeroesOptions_lookup[info->value->inserted->detect_zeroes]); + } + if (info->value->inserted->bps || info->value->inserted->bps_rd || info->value->inserted->bps_wr diff --git a/hw/audio/intel-hda.c b/hw/audio/intel-hda.c index d41f82cec4..3cfb66c5d8 100644 --- a/hw/audio/intel-hda.c +++ b/hw/audio/intel-hda.c @@ -245,7 +245,7 @@ static void intel_hda_update_int_sts(IntelHDAState *d) /* update global status */ if (sts & d->int_ctl) { - sts |= (1 << 31); + sts |= (1U << 31); } d->int_sts = sts; @@ -257,7 +257,7 @@ static void intel_hda_update_irq(IntelHDAState *d) int level; intel_hda_update_int_sts(d); - if (d->int_sts & (1 << 31) && d->int_ctl & (1 << 31)) { + if (d->int_sts & (1U << 31) && d->int_ctl & (1U << 31)) { level = 1; } else { level = 0; @@ -574,7 +574,7 @@ static void intel_hda_set_st_ctl(IntelHDAState *d, const IntelHDAReg *reg, uint3 if (st->ctl & 0x01) { /* reset */ dprint(d, 1, "st #%d: reset\n", reg->stream); - st->ctl = 0; + st->ctl = SD_STS_FIFO_READY << 24; } if ((st->ctl & 0x02) != (old & 0x02)) { uint32_t stnr = (st->ctl >> 20) & 0x0f; @@ -829,6 +829,7 @@ static const struct IntelHDAReg regtab[] = { .wclear = 0x1c000000, \ .offset = offsetof(IntelHDAState, st[_i].ctl), \ .whandler = intel_hda_set_st_ctl, \ + .reset = SD_STS_FIFO_READY << 24 \ }, \ [ ST_REG(_i, ICH6_REG_SD_LPIB) ] = { \ .stream = _i, \ diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs index c8a2318d56..843864a3ef 100644 --- a/hw/intc/Makefile.objs +++ b/hw/intc/Makefile.objs @@ -26,3 +26,4 @@ obj-$(CONFIG_XICS) += xics.o obj-$(CONFIG_XICS_KVM) += xics_kvm.o obj-$(CONFIG_ALLWINNER_A10_PIC) += allwinner-a10-pic.o obj-$(CONFIG_S390_FLIC) += s390_flic.o +obj-$(CONFIG_S390_FLIC_KVM) += s390_flic_kvm.o diff --git a/hw/intc/s390_flic.c b/hw/intc/s390_flic.c index b2ef3e3f8e..03c5e89f4e 100644 --- a/hw/intc/s390_flic.c +++ b/hw/intc/s390_flic.c @@ -1,322 +1,103 @@ /* - * QEMU S390x KVM floating interrupt controller (flic) + * QEMU S390x floating interrupt controller (flic) * * Copyright 2014 IBM Corp. * Author(s): Jens Freimann <jfrei@linux.vnet.ibm.com> + * Cornelia Huck <cornelia.huck@de.ibm.com> * * This work is licensed under the terms of the GNU GPL, version 2 or (at * your option) any later version. See the COPYING file in the top-level * directory. */ -#include <sys/ioctl.h> #include "qemu/error-report.h" #include "hw/sysbus.h" -#include "sysemu/kvm.h" #include "migration/qemu-file.h" #include "hw/s390x/s390_flic.h" #include "trace.h" -#define FLIC_SAVE_INITIAL_SIZE getpagesize() -#define FLIC_FAILED (-1UL) -#define FLIC_SAVEVM_VERSION 1 - -void s390_flic_init(void) -{ - DeviceState *dev; - int r; - - if (kvm_enabled()) { - dev = qdev_create(NULL, "s390-flic"); - object_property_add_child(qdev_get_machine(), "s390-flic", - OBJECT(dev), NULL); - r = qdev_init(dev); - if (r) { - error_report("flic: couldn't create qdev"); - } - } -} - -/** - * flic_get_all_irqs - store all pending irqs in buffer - * @buf: pointer to buffer which is passed to kernel - * @len: length of buffer - * @flic: pointer to flic device state - * - * Returns: -ENOMEM if buffer is too small, - * -EINVAL if attr.group is invalid, - * -EFAULT if copying to userspace failed, - * on success return number of stored interrupts - */ -static int flic_get_all_irqs(KVMS390FLICState *flic, - void *buf, int len) +S390FLICState *s390_get_flic(void) { - struct kvm_device_attr attr = { - .group = KVM_DEV_FLIC_GET_ALL_IRQS, - .addr = (uint64_t) buf, - .attr = len, - }; - int rc; - - rc = ioctl(flic->fd, KVM_GET_DEVICE_ATTR, &attr); - - return rc == -1 ? -errno : rc; -} + S390FLICState *fs; -static void flic_enable_pfault(KVMS390FLICState *flic) -{ - struct kvm_device_attr attr = { - .group = KVM_DEV_FLIC_APF_ENABLE, - }; - int rc; - - rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); - - if (rc) { - fprintf(stderr, "flic: couldn't enable pfault\n"); + fs = S390_FLIC_COMMON(object_resolve_path(TYPE_KVM_S390_FLIC, NULL)); + if (!fs) { + fs = S390_FLIC_COMMON(object_resolve_path(TYPE_QEMU_S390_FLIC, NULL)); } + return fs; } -static void flic_disable_wait_pfault(KVMS390FLICState *flic) -{ - struct kvm_device_attr attr = { - .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, - }; - int rc; - - rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); - - if (rc) { - fprintf(stderr, "flic: couldn't disable pfault\n"); - } -} - -/** flic_enqueue_irqs - returns 0 on success - * @buf: pointer to buffer which is passed to kernel - * @len: length of buffer - * @flic: pointer to flic device state - * - * Returns: -EINVAL if attr.group is unknown - */ -static int flic_enqueue_irqs(void *buf, uint64_t len, - KVMS390FLICState *flic) -{ - int rc; - struct kvm_device_attr attr = { - .group = KVM_DEV_FLIC_ENQUEUE, - .addr = (uint64_t) buf, - .attr = len, - }; - - rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); - - return rc ? -errno : 0; -} - -/** - * __get_all_irqs - store all pending irqs in buffer - * @flic: pointer to flic device state - * @buf: pointer to pointer to a buffer - * @len: length of buffer - * - * Returns: return value of flic_get_all_irqs - * Note: Retry and increase buffer size until flic_get_all_irqs - * either returns a value >= 0 or a negative error code. - * -ENOMEM is an exception, which means the buffer is too small - * and we should try again. Other negative error codes can be - * -EFAULT and -EINVAL which we ignore at this point - */ -static int __get_all_irqs(KVMS390FLICState *flic, - void **buf, int len) +void s390_flic_init(void) { + DeviceState *dev; int r; - do { - /* returns -ENOMEM if buffer is too small and number - * of queued interrupts on success */ - r = flic_get_all_irqs(flic, *buf, len); - if (r >= 0) { - break; - } - len *= 2; - *buf = g_try_realloc(*buf, len); - if (!buf) { - return -ENOMEM; - } - } while (r == -ENOMEM && len <= KVM_S390_FLIC_MAX_BUFFER); - - return r; -} - -/** - * kvm_flic_save - Save pending floating interrupts - * @f: QEMUFile containing migration state - * @opaque: pointer to flic device state - * - * Note: Pass buf and len to kernel. Start with one page and - * increase until buffer is sufficient or maxium size is - * reached - */ -static void kvm_flic_save(QEMUFile *f, void *opaque) -{ - KVMS390FLICState *flic = opaque; - int len = FLIC_SAVE_INITIAL_SIZE; - void *buf; - int count; - - flic_disable_wait_pfault((struct KVMS390FLICState *) opaque); - - buf = g_try_malloc0(len); - if (!buf) { - /* Storing FLIC_FAILED into the count field here will cause the - * target system to fail when attempting to load irqs from the - * migration state */ - error_report("flic: couldn't allocate memory"); - qemu_put_be64(f, FLIC_FAILED); - return; + dev = s390_flic_kvm_create(); + if (!dev) { + dev = qdev_create(NULL, TYPE_QEMU_S390_FLIC); + object_property_add_child(qdev_get_machine(), TYPE_QEMU_S390_FLIC, + OBJECT(dev), NULL); } - - count = __get_all_irqs(flic, &buf, len); - if (count < 0) { - error_report("flic: couldn't retrieve irqs from kernel, rc %d", - count); - /* Storing FLIC_FAILED into the count field here will cause the - * target system to fail when attempting to load irqs from the - * migration state */ - qemu_put_be64(f, FLIC_FAILED); - } else { - qemu_put_be64(f, count); - qemu_put_buffer(f, (uint8_t *) buf, - count * sizeof(struct kvm_s390_irq)); + r = qdev_init(dev); + if (r) { + error_report("flic: couldn't create qdev"); } - g_free(buf); } -/** - * kvm_flic_load - Load pending floating interrupts - * @f: QEMUFile containing migration state - * @opaque: pointer to flic device state - * @version_id: version id for migration - * - * Returns: value of flic_enqueue_irqs, -EINVAL on error - * Note: Do nothing when no interrupts where stored - * in QEMUFile - */ -static int kvm_flic_load(QEMUFile *f, void *opaque, int version_id) +static int qemu_s390_register_io_adapter(S390FLICState *fs, uint32_t id, + uint8_t isc, bool swap, + bool is_maskable) { - uint64_t len = 0; - uint64_t count = 0; - void *buf = NULL; - int r = 0; - - if (version_id != FLIC_SAVEVM_VERSION) { - r = -EINVAL; - goto out; - } - - flic_enable_pfault((struct KVMS390FLICState *) opaque); - - count = qemu_get_be64(f); - len = count * sizeof(struct kvm_s390_irq); - if (count == FLIC_FAILED) { - r = -EINVAL; - goto out; - } - if (count == 0) { - r = 0; - goto out; - } - buf = g_try_malloc0(len); - if (!buf) { - r = -ENOMEM; - goto out; - } - - if (qemu_get_buffer(f, (uint8_t *) buf, len) != len) { - r = -EINVAL; - goto out_free; - } - r = flic_enqueue_irqs(buf, len, (struct KVMS390FLICState *) opaque); - -out_free: - g_free(buf); -out: - return r; + /* nothing to do */ + return 0; } -static void kvm_s390_flic_realize(DeviceState *dev, Error **errp) +static int qemu_s390_io_adapter_map(S390FLICState *fs, uint32_t id, + uint64_t map_addr, bool do_map) { - KVMS390FLICState *flic_state = KVM_S390_FLIC(dev); - struct kvm_create_device cd = {0}; - int ret; - - flic_state->fd = -1; - if (!kvm_check_extension(kvm_state, KVM_CAP_DEVICE_CTRL)) { - trace_flic_no_device_api(errno); - return; - } - - cd.type = KVM_DEV_TYPE_FLIC; - ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd); - if (ret < 0) { - trace_flic_create_device(errno); - return; - } - flic_state->fd = cd.fd; - - /* Register savevm handler for floating interrupts */ - register_savevm(NULL, "s390-flic", 0, 1, kvm_flic_save, - kvm_flic_load, (void *) flic_state); + /* nothing to do */ + return 0; } -static void kvm_s390_flic_unrealize(DeviceState *dev, Error **errp) +static int qemu_s390_add_adapter_routes(S390FLICState *fs, + AdapterRoutes *routes) { - KVMS390FLICState *flic_state = KVM_S390_FLIC(dev); - - unregister_savevm(DEVICE(flic_state), "s390-flic", flic_state); + return -ENOSYS; } -static void kvm_s390_flic_reset(DeviceState *dev) +static void qemu_s390_release_adapter_routes(S390FLICState *fs, + AdapterRoutes *routes) { - KVMS390FLICState *flic = KVM_S390_FLIC(dev); - struct kvm_device_attr attr = { - .group = KVM_DEV_FLIC_CLEAR_IRQS, - }; - int rc = 0; - - if (flic->fd == -1) { - return; - } - - flic_disable_wait_pfault(flic); - - rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); - if (rc) { - trace_flic_reset_failed(errno); - } - - flic_enable_pfault(flic); } -static void kvm_s390_flic_class_init(ObjectClass *oc, void *data) +static void qemu_s390_flic_class_init(ObjectClass *oc, void *data) { - DeviceClass *dc = DEVICE_CLASS(oc); + S390FLICStateClass *fsc = S390_FLIC_COMMON_CLASS(oc); - dc->realize = kvm_s390_flic_realize; - dc->unrealize = kvm_s390_flic_unrealize; - dc->reset = kvm_s390_flic_reset; + fsc->register_io_adapter = qemu_s390_register_io_adapter; + fsc->io_adapter_map = qemu_s390_io_adapter_map; + fsc->add_adapter_routes = qemu_s390_add_adapter_routes; + fsc->release_adapter_routes = qemu_s390_release_adapter_routes; } -static const TypeInfo kvm_s390_flic_info = { - .name = TYPE_KVM_S390_FLIC, +static const TypeInfo qemu_s390_flic_info = { + .name = TYPE_QEMU_S390_FLIC, + .parent = TYPE_S390_FLIC_COMMON, + .instance_size = sizeof(QEMUS390FLICState), + .class_init = qemu_s390_flic_class_init, +}; + +static const TypeInfo s390_flic_common_info = { + .name = TYPE_S390_FLIC_COMMON, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(KVMS390FLICState), - .class_init = kvm_s390_flic_class_init, + .instance_size = sizeof(S390FLICState), + .class_size = sizeof(S390FLICStateClass), }; -static void kvm_s390_flic_register_types(void) +static void qemu_s390_flic_register_types(void) { - type_register_static(&kvm_s390_flic_info); + type_register_static(&s390_flic_common_info); + type_register_static(&qemu_s390_flic_info); } -type_init(kvm_s390_flic_register_types) +type_init(qemu_s390_flic_register_types) diff --git a/hw/intc/s390_flic_kvm.c b/hw/intc/s390_flic_kvm.c new file mode 100644 index 0000000000..46c9e612d1 --- /dev/null +++ b/hw/intc/s390_flic_kvm.c @@ -0,0 +1,420 @@ +/* + * QEMU S390x KVM floating interrupt controller (flic) + * + * Copyright 2014 IBM Corp. + * Author(s): Jens Freimann <jfrei@linux.vnet.ibm.com> + * Cornelia Huck <cornelia.huck@de.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#include <sys/ioctl.h> +#include "qemu/error-report.h" +#include "hw/sysbus.h" +#include "sysemu/kvm.h" +#include "migration/qemu-file.h" +#include "hw/s390x/s390_flic.h" +#include "hw/s390x/adapter.h" +#include "trace.h" + +#define FLIC_SAVE_INITIAL_SIZE getpagesize() +#define FLIC_FAILED (-1UL) +#define FLIC_SAVEVM_VERSION 1 + +typedef struct KVMS390FLICState { + S390FLICState parent_obj; + + uint32_t fd; +} KVMS390FLICState; + +DeviceState *s390_flic_kvm_create(void) +{ + DeviceState *dev = NULL; + + if (kvm_enabled()) { + dev = qdev_create(NULL, TYPE_KVM_S390_FLIC); + object_property_add_child(qdev_get_machine(), TYPE_KVM_S390_FLIC, + OBJECT(dev), NULL); + } + return dev; +} + +/** + * flic_get_all_irqs - store all pending irqs in buffer + * @buf: pointer to buffer which is passed to kernel + * @len: length of buffer + * @flic: pointer to flic device state + * + * Returns: -ENOMEM if buffer is too small, + * -EINVAL if attr.group is invalid, + * -EFAULT if copying to userspace failed, + * on success return number of stored interrupts + */ +static int flic_get_all_irqs(KVMS390FLICState *flic, + void *buf, int len) +{ + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_GET_ALL_IRQS, + .addr = (uint64_t) buf, + .attr = len, + }; + int rc; + + rc = ioctl(flic->fd, KVM_GET_DEVICE_ATTR, &attr); + + return rc == -1 ? -errno : rc; +} + +static void flic_enable_pfault(KVMS390FLICState *flic) +{ + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_APF_ENABLE, + }; + int rc; + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + if (rc) { + fprintf(stderr, "flic: couldn't enable pfault\n"); + } +} + +static void flic_disable_wait_pfault(KVMS390FLICState *flic) +{ + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_APF_DISABLE_WAIT, + }; + int rc; + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + if (rc) { + fprintf(stderr, "flic: couldn't disable pfault\n"); + } +} + +/** flic_enqueue_irqs - returns 0 on success + * @buf: pointer to buffer which is passed to kernel + * @len: length of buffer + * @flic: pointer to flic device state + * + * Returns: -EINVAL if attr.group is unknown + */ +static int flic_enqueue_irqs(void *buf, uint64_t len, + KVMS390FLICState *flic) +{ + int rc; + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_ENQUEUE, + .addr = (uint64_t) buf, + .attr = len, + }; + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + return rc ? -errno : 0; +} + +/** + * __get_all_irqs - store all pending irqs in buffer + * @flic: pointer to flic device state + * @buf: pointer to pointer to a buffer + * @len: length of buffer + * + * Returns: return value of flic_get_all_irqs + * Note: Retry and increase buffer size until flic_get_all_irqs + * either returns a value >= 0 or a negative error code. + * -ENOMEM is an exception, which means the buffer is too small + * and we should try again. Other negative error codes can be + * -EFAULT and -EINVAL which we ignore at this point + */ +static int __get_all_irqs(KVMS390FLICState *flic, + void **buf, int len) +{ + int r; + + do { + /* returns -ENOMEM if buffer is too small and number + * of queued interrupts on success */ + r = flic_get_all_irqs(flic, *buf, len); + if (r >= 0) { + break; + } + len *= 2; + *buf = g_try_realloc(*buf, len); + if (!buf) { + return -ENOMEM; + } + } while (r == -ENOMEM && len <= KVM_S390_FLIC_MAX_BUFFER); + + return r; +} + +static int kvm_s390_register_io_adapter(S390FLICState *fs, uint32_t id, + uint8_t isc, bool swap, + bool is_maskable) +{ + struct kvm_s390_io_adapter adapter = { + .id = id, + .isc = isc, + .maskable = is_maskable, + .swap = swap, + }; + KVMS390FLICState *flic = KVM_S390_FLIC(fs); + int r, ret; + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_ADAPTER_REGISTER, + .addr = (uint64_t)&adapter, + }; + + if (!kvm_check_extension(kvm_state, KVM_CAP_IRQ_ROUTING)) { + return -ENOSYS; + } + + r = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + + ret = r ? -errno : 0; + return ret; +} + +static int kvm_s390_io_adapter_map(S390FLICState *fs, uint32_t id, + uint64_t map_addr, bool do_map) +{ + struct kvm_s390_io_adapter_req req = { + .id = id, + .type = do_map ? KVM_S390_IO_ADAPTER_MAP : KVM_S390_IO_ADAPTER_UNMAP, + .addr = map_addr, + }; + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_ADAPTER_MODIFY, + .addr = (uint64_t)&req, + }; + KVMS390FLICState *flic = KVM_S390_FLIC(fs); + int r; + + if (!kvm_check_extension(kvm_state, KVM_CAP_IRQ_ROUTING)) { + return -ENOSYS; + } + + r = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + return r ? -errno : 0; +} + +static int kvm_s390_add_adapter_routes(S390FLICState *fs, + AdapterRoutes *routes) +{ + int ret, i; + uint64_t ind_offset = routes->adapter.ind_offset; + + for (i = 0; i < routes->num_routes; i++) { + ret = kvm_irqchip_add_adapter_route(kvm_state, &routes->adapter); + if (ret < 0) { + goto out_undo; + } + routes->gsi[i] = ret; + routes->adapter.ind_offset++; + } + /* Restore passed-in structure to original state. */ + routes->adapter.ind_offset = ind_offset; + return 0; +out_undo: + while (--i >= 0) { + kvm_irqchip_release_virq(kvm_state, routes->gsi[i]); + routes->gsi[i] = -1; + } + routes->adapter.ind_offset = ind_offset; + return ret; +} + +static void kvm_s390_release_adapter_routes(S390FLICState *fs, + AdapterRoutes *routes) +{ + int i; + + for (i = 0; i < routes->num_routes; i++) { + if (routes->gsi[i] >= 0) { + kvm_irqchip_release_virq(kvm_state, routes->gsi[i]); + routes->gsi[i] = -1; + } + } +} + +/** + * kvm_flic_save - Save pending floating interrupts + * @f: QEMUFile containing migration state + * @opaque: pointer to flic device state + * + * Note: Pass buf and len to kernel. Start with one page and + * increase until buffer is sufficient or maxium size is + * reached + */ +static void kvm_flic_save(QEMUFile *f, void *opaque) +{ + KVMS390FLICState *flic = opaque; + int len = FLIC_SAVE_INITIAL_SIZE; + void *buf; + int count; + + flic_disable_wait_pfault((struct KVMS390FLICState *) opaque); + + buf = g_try_malloc0(len); + if (!buf) { + /* Storing FLIC_FAILED into the count field here will cause the + * target system to fail when attempting to load irqs from the + * migration state */ + error_report("flic: couldn't allocate memory"); + qemu_put_be64(f, FLIC_FAILED); + return; + } + + count = __get_all_irqs(flic, &buf, len); + if (count < 0) { + error_report("flic: couldn't retrieve irqs from kernel, rc %d", + count); + /* Storing FLIC_FAILED into the count field here will cause the + * target system to fail when attempting to load irqs from the + * migration state */ + qemu_put_be64(f, FLIC_FAILED); + } else { + qemu_put_be64(f, count); + qemu_put_buffer(f, (uint8_t *) buf, + count * sizeof(struct kvm_s390_irq)); + } + g_free(buf); +} + +/** + * kvm_flic_load - Load pending floating interrupts + * @f: QEMUFile containing migration state + * @opaque: pointer to flic device state + * @version_id: version id for migration + * + * Returns: value of flic_enqueue_irqs, -EINVAL on error + * Note: Do nothing when no interrupts where stored + * in QEMUFile + */ +static int kvm_flic_load(QEMUFile *f, void *opaque, int version_id) +{ + uint64_t len = 0; + uint64_t count = 0; + void *buf = NULL; + int r = 0; + + if (version_id != FLIC_SAVEVM_VERSION) { + r = -EINVAL; + goto out; + } + + flic_enable_pfault((struct KVMS390FLICState *) opaque); + + count = qemu_get_be64(f); + len = count * sizeof(struct kvm_s390_irq); + if (count == FLIC_FAILED) { + r = -EINVAL; + goto out; + } + if (count == 0) { + r = 0; + goto out; + } + buf = g_try_malloc0(len); + if (!buf) { + r = -ENOMEM; + goto out; + } + + if (qemu_get_buffer(f, (uint8_t *) buf, len) != len) { + r = -EINVAL; + goto out_free; + } + r = flic_enqueue_irqs(buf, len, (struct KVMS390FLICState *) opaque); + +out_free: + g_free(buf); +out: + return r; +} + +static void kvm_s390_flic_realize(DeviceState *dev, Error **errp) +{ + KVMS390FLICState *flic_state = KVM_S390_FLIC(dev); + struct kvm_create_device cd = {0}; + int ret; + + flic_state->fd = -1; + if (!kvm_check_extension(kvm_state, KVM_CAP_DEVICE_CTRL)) { + trace_flic_no_device_api(errno); + return; + } + + cd.type = KVM_DEV_TYPE_FLIC; + ret = kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd); + if (ret < 0) { + trace_flic_create_device(errno); + return; + } + flic_state->fd = cd.fd; + + /* Register savevm handler for floating interrupts */ + register_savevm(NULL, "s390-flic", 0, 1, kvm_flic_save, + kvm_flic_load, (void *) flic_state); +} + +static void kvm_s390_flic_unrealize(DeviceState *dev, Error **errp) +{ + KVMS390FLICState *flic_state = KVM_S390_FLIC(dev); + + unregister_savevm(DEVICE(flic_state), "s390-flic", flic_state); +} + +static void kvm_s390_flic_reset(DeviceState *dev) +{ + KVMS390FLICState *flic = KVM_S390_FLIC(dev); + struct kvm_device_attr attr = { + .group = KVM_DEV_FLIC_CLEAR_IRQS, + }; + int rc = 0; + + if (flic->fd == -1) { + return; + } + + flic_disable_wait_pfault(flic); + + rc = ioctl(flic->fd, KVM_SET_DEVICE_ATTR, &attr); + if (rc) { + trace_flic_reset_failed(errno); + } + + flic_enable_pfault(flic); +} + +static void kvm_s390_flic_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + S390FLICStateClass *fsc = S390_FLIC_COMMON_CLASS(oc); + + dc->realize = kvm_s390_flic_realize; + dc->unrealize = kvm_s390_flic_unrealize; + dc->reset = kvm_s390_flic_reset; + fsc->register_io_adapter = kvm_s390_register_io_adapter; + fsc->io_adapter_map = kvm_s390_io_adapter_map; + fsc->add_adapter_routes = kvm_s390_add_adapter_routes; + fsc->release_adapter_routes = kvm_s390_release_adapter_routes; +} + +static const TypeInfo kvm_s390_flic_info = { + .name = TYPE_KVM_S390_FLIC, + .parent = TYPE_S390_FLIC_COMMON, + .instance_size = sizeof(KVMS390FLICState), + .class_init = kvm_s390_flic_class_init, +}; + +static void kvm_s390_flic_register_types(void) +{ + type_register_static(&kvm_s390_flic_info); +} + +type_init(kvm_s390_flic_register_types) diff --git a/hw/s390x/css.c b/hw/s390x/css.c index 122cc7e66f..2678e4432c 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -16,6 +16,7 @@ #include "ioinst.h" #include "css.h" #include "trace.h" +#include "hw/s390x/s390_flic.h" typedef struct CrwContainer { CRW crw; @@ -39,6 +40,13 @@ typedef struct CssImage { ChpInfo chpids[MAX_CHPID + 1]; } CssImage; +typedef struct IoAdapter { + uint32_t id; + uint8_t type; + uint8_t isc; + QTAILQ_ENTRY(IoAdapter) sibling; +} IoAdapter; + typedef struct ChannelSubSys { QTAILQ_HEAD(, CrwContainer) pending_crws; bool do_crw_mchk; @@ -49,6 +57,7 @@ typedef struct ChannelSubSys { uint64_t chnmon_area; CssImage *css[MAX_CSSID + 1]; uint8_t default_cssid; + QTAILQ_HEAD(, IoAdapter) io_adapters; } ChannelSubSys; static ChannelSubSys *channel_subsys; @@ -69,6 +78,46 @@ int css_create_css_image(uint8_t cssid, bool default_image) return 0; } +int css_register_io_adapter(uint8_t type, uint8_t isc, bool swap, + bool maskable, uint32_t *id) +{ + IoAdapter *adapter; + bool found = false; + int ret; + S390FLICState *fs = s390_get_flic(); + S390FLICStateClass *fsc = S390_FLIC_COMMON_GET_CLASS(fs); + + *id = 0; + QTAILQ_FOREACH(adapter, &channel_subsys->io_adapters, sibling) { + if ((adapter->type == type) && (adapter->isc == isc)) { + *id = adapter->id; + found = true; + ret = 0; + break; + } + if (adapter->id >= *id) { + *id = adapter->id + 1; + } + } + if (found) { + goto out; + } + adapter = g_new0(IoAdapter, 1); + ret = fsc->register_io_adapter(fs, *id, isc, swap, maskable); + if (ret == 0) { + adapter->id = *id; + adapter->isc = isc; + adapter->type = type; + QTAILQ_INSERT_TAIL(&channel_subsys->io_adapters, adapter, sibling); + } else { + g_free(adapter); + fprintf(stderr, "Unexpected error %d when registering adapter %d\n", + ret, *id); + } +out: + return ret; +} + uint16_t css_build_subchannel_id(SubchDev *sch) { if (channel_subsys->max_cssid > 0) { @@ -1235,6 +1284,7 @@ static void css_init(void) channel_subsys->do_crw_mchk = true; channel_subsys->crws_lost = false; channel_subsys->chnmon_active = false; + QTAILQ_INIT(&channel_subsys->io_adapters); } machine_init(css_init); diff --git a/hw/s390x/css.h b/hw/s390x/css.h index 220169e7c3..6586106fa7 100644 --- a/hw/s390x/css.h +++ b/hw/s390x/css.h @@ -98,4 +98,8 @@ void css_generate_sch_crws(uint8_t cssid, uint8_t ssid, uint16_t schid, int hotplugged, int add); void css_generate_chp_crws(uint8_t cssid, uint8_t chpid); void css_adapter_interrupt(uint8_t isc); + +#define CSS_IO_ADAPTER_VIRTIO 1 +int css_register_io_adapter(uint8_t type, uint8_t isc, bool swap, + bool maskable, uint32_t *id); #endif diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index 1cb4e2c2f8..c4f21d3816 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -21,12 +21,77 @@ #include "hw/sysbus.h" #include "qemu/bitops.h" #include "hw/virtio/virtio-bus.h" +#include "hw/s390x/adapter.h" +#include "hw/s390x/s390_flic.h" #include "ioinst.h" #include "css.h" #include "virtio-ccw.h" #include "trace.h" +static QTAILQ_HEAD(, IndAddr) indicator_addresses = + QTAILQ_HEAD_INITIALIZER(indicator_addresses); + +static IndAddr *get_indicator(hwaddr ind_addr, int len) +{ + IndAddr *indicator; + + QTAILQ_FOREACH(indicator, &indicator_addresses, sibling) { + if (indicator->addr == ind_addr) { + indicator->refcnt++; + return indicator; + } + } + indicator = g_new0(IndAddr, 1); + indicator->addr = ind_addr; + indicator->len = len; + indicator->refcnt = 1; + QTAILQ_INSERT_TAIL(&indicator_addresses, indicator, sibling); + return indicator; +} + +static int s390_io_adapter_map(AdapterInfo *adapter, uint64_t map_addr, + bool do_map) +{ + S390FLICState *fs = s390_get_flic(); + S390FLICStateClass *fsc = S390_FLIC_COMMON_GET_CLASS(fs); + + return fsc->io_adapter_map(fs, adapter->adapter_id, map_addr, do_map); +} + +static void release_indicator(AdapterInfo *adapter, IndAddr *indicator) +{ + assert(indicator->refcnt > 0); + indicator->refcnt--; + if (indicator->refcnt > 0) { + return; + } + QTAILQ_REMOVE(&indicator_addresses, indicator, sibling); + if (indicator->map) { + s390_io_adapter_map(adapter, indicator->map, false); + } + g_free(indicator); +} + +static int map_indicator(AdapterInfo *adapter, IndAddr *indicator) +{ + int ret; + + if (indicator->map) { + return 0; /* already mapped is not an error */ + } + indicator->map = indicator->addr; + ret = s390_io_adapter_map(adapter, indicator->map, true); + if ((ret != 0) && (ret != -ENOSYS)) { + goto out_err; + } + return 0; + +out_err: + indicator->map = 0; + return ret; +} + static void virtio_ccw_bus_new(VirtioBusState *bus, size_t bus_size, VirtioCcwDevice *dev); @@ -445,7 +510,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) ret = -EFAULT; } else { indicators = ldq_phys(&address_space_memory, ccw.cda); - dev->indicators = indicators; + dev->indicators = get_indicator(indicators, sizeof(uint64_t)); sch->curr_status.scsw.count = ccw.count - sizeof(indicators); ret = 0; } @@ -465,7 +530,7 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) ret = -EFAULT; } else { indicators = ldq_phys(&address_space_memory, ccw.cda); - dev->indicators2 = indicators; + dev->indicators2 = get_indicator(indicators, sizeof(uint64_t)); sch->curr_status.scsw.count = ccw.count - sizeof(indicators); ret = 0; } @@ -517,13 +582,20 @@ static int virtio_ccw_cb(SubchDev *sch, CCW1 ccw) ret = -EFAULT; } else { len = hw_len; - dev->summary_indicator = thinint->summary_indicator; - dev->indicators = thinint->device_indicator; + dev->summary_indicator = + get_indicator(thinint->summary_indicator, sizeof(uint8_t)); + dev->indicators = get_indicator(thinint->device_indicator, + thinint->ind_bit / 8 + 1); dev->thinint_isc = thinint->isc; - dev->ind_bit = thinint->ind_bit; + dev->routes.adapter.ind_offset = thinint->ind_bit; + dev->routes.adapter.summary_offset = 7; cpu_physical_memory_unmap(thinint, hw_len, 0, hw_len); - sch->thinint_active = ((dev->indicators != 0) && - (dev->summary_indicator != 0)); + ret = css_register_io_adapter(CSS_IO_ADAPTER_VIRTIO, + dev->thinint_isc, true, false, + &dev->routes.adapter.adapter_id); + assert(ret == 0); + sch->thinint_active = ((dev->indicators != NULL) && + (dev->summary_indicator != NULL)); sch->curr_status.scsw.count = ccw.count - len; ret = 0; } @@ -554,7 +626,7 @@ static int virtio_ccw_device_init(VirtioCcwDevice *dev, VirtIODevice *vdev) sch->driver_data = dev; dev->sch = sch; - dev->indicators = 0; + dev->indicators = NULL; /* Initialize subchannel structure. */ sch->channel_prog = 0x0; @@ -693,7 +765,10 @@ static int virtio_ccw_exit(VirtioCcwDevice *dev) css_subch_assign(sch->cssid, sch->ssid, sch->schid, sch->devno, NULL); g_free(sch); } - dev->indicators = 0; + if (dev->indicators) { + release_indicator(&dev->routes.adapter, dev->indicators); + dev->indicators = NULL; + } return 0; } @@ -950,17 +1025,19 @@ static void virtio_ccw_notify(DeviceState *d, uint16_t vector) * ind_bit indicates the start of the indicators in a big * endian notation. */ - virtio_set_ind_atomic(sch, dev->indicators + - (dev->ind_bit + vector) / 8, - 0x80 >> ((dev->ind_bit + vector) % 8)); - if (!virtio_set_ind_atomic(sch, dev->summary_indicator, + uint64_t ind_bit = dev->routes.adapter.ind_offset; + + virtio_set_ind_atomic(sch, dev->indicators->addr + + (ind_bit + vector) / 8, + 0x80 >> ((ind_bit + vector) % 8)); + if (!virtio_set_ind_atomic(sch, dev->summary_indicator->addr, 0x01)) { css_adapter_interrupt(dev->thinint_isc); } } else { - indicators = ldq_phys(&address_space_memory, dev->indicators); + indicators = ldq_phys(&address_space_memory, dev->indicators->addr); indicators |= 1ULL << vector; - stq_phys(&address_space_memory, dev->indicators, indicators); + stq_phys(&address_space_memory, dev->indicators->addr, indicators); css_conditional_io_interrupt(sch); } } else { @@ -968,9 +1045,9 @@ static void virtio_ccw_notify(DeviceState *d, uint16_t vector) return; } vector = 0; - indicators = ldq_phys(&address_space_memory, dev->indicators2); + indicators = ldq_phys(&address_space_memory, dev->indicators2->addr); indicators |= 1ULL << vector; - stq_phys(&address_space_memory, dev->indicators2, indicators); + stq_phys(&address_space_memory, dev->indicators2->addr, indicators); css_conditional_io_interrupt(sch); } } @@ -991,9 +1068,18 @@ static void virtio_ccw_reset(DeviceState *d) virtio_ccw_stop_ioeventfd(dev); virtio_reset(vdev); css_reset_sch(dev->sch); - dev->indicators = 0; - dev->indicators2 = 0; - dev->summary_indicator = 0; + if (dev->indicators) { + release_indicator(&dev->routes.adapter, dev->indicators); + dev->indicators = NULL; + } + if (dev->indicators2) { + release_indicator(&dev->routes.adapter, dev->indicators2); + dev->indicators2 = NULL; + } + if (dev->summary_indicator) { + release_indicator(&dev->routes.adapter, dev->summary_indicator); + dev->summary_indicator = NULL; + } } static void virtio_ccw_vmstate_change(DeviceState *d, bool running) @@ -1027,6 +1113,79 @@ static int virtio_ccw_set_host_notifier(DeviceState *d, int n, bool assign) return virtio_ccw_set_guest2host_notifier(dev, n, assign, false); } +static int virtio_ccw_get_mappings(VirtioCcwDevice *dev) +{ + int r; + + if (!dev->sch->thinint_active) { + return -EINVAL; + } + + r = map_indicator(&dev->routes.adapter, dev->summary_indicator); + if (r) { + return r; + } + r = map_indicator(&dev->routes.adapter, dev->indicators); + if (r) { + return r; + } + dev->routes.adapter.summary_addr = dev->summary_indicator->map; + dev->routes.adapter.ind_addr = dev->indicators->map; + + return 0; +} + +static int virtio_ccw_setup_irqroutes(VirtioCcwDevice *dev, int nvqs) +{ + int i; + VirtIODevice *vdev = virtio_bus_get_device(&dev->bus); + int ret; + S390FLICState *fs = s390_get_flic(); + S390FLICStateClass *fsc = S390_FLIC_COMMON_GET_CLASS(fs); + + ret = virtio_ccw_get_mappings(dev); + if (ret) { + return ret; + } + for (i = 0; i < nvqs; i++) { + if (!virtio_queue_get_num(vdev, i)) { + break; + } + } + dev->routes.num_routes = i; + return fsc->add_adapter_routes(fs, &dev->routes); +} + +static void virtio_ccw_release_irqroutes(VirtioCcwDevice *dev, int nvqs) +{ + S390FLICState *fs = s390_get_flic(); + S390FLICStateClass *fsc = S390_FLIC_COMMON_GET_CLASS(fs); + + fsc->release_adapter_routes(fs, &dev->routes); +} + +static int virtio_ccw_add_irqfd(VirtioCcwDevice *dev, int n) +{ + VirtIODevice *vdev = virtio_bus_get_device(&dev->bus); + VirtQueue *vq = virtio_get_queue(vdev, n); + EventNotifier *notifier = virtio_queue_get_guest_notifier(vq); + + return kvm_irqchip_add_irqfd_notifier(kvm_state, notifier, NULL, + dev->routes.gsi[n]); +} + +static void virtio_ccw_remove_irqfd(VirtioCcwDevice *dev, int n) +{ + VirtIODevice *vdev = virtio_bus_get_device(&dev->bus); + VirtQueue *vq = virtio_get_queue(vdev, n); + EventNotifier *notifier = virtio_queue_get_guest_notifier(vq); + int ret; + + ret = kvm_irqchip_remove_irqfd_notifier(kvm_state, notifier, + dev->routes.gsi[n]); + assert(ret == 0); +} + static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n, bool assign, bool with_irqfd) { @@ -1042,11 +1201,17 @@ static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n, return r; } virtio_queue_set_guest_notifier_fd_handler(vq, true, with_irqfd); - /* We do not support irqfd for classic I/O interrupts, because the - * classic interrupts are intermixed with the subchannel status, that - * is queried with test subchannel. We want to use vhost, though. - * Lets make sure to have vhost running and wire up the irq fd to - * land in qemu (and only the irq fd) in this code. + if (with_irqfd) { + r = virtio_ccw_add_irqfd(dev, n); + if (r) { + virtio_queue_set_guest_notifier_fd_handler(vq, false, + with_irqfd); + return r; + } + } + /* + * We do not support individual masking for channel devices, so we + * need to manually trigger any guest masking callbacks here. */ if (k->guest_notifier_mask) { k->guest_notifier_mask(vdev, n, false); @@ -1060,6 +1225,9 @@ static int virtio_ccw_set_guest_notifier(VirtioCcwDevice *dev, int n, if (k->guest_notifier_mask) { k->guest_notifier_mask(vdev, n, true); } + if (with_irqfd) { + virtio_ccw_remove_irqfd(dev, n); + } virtio_queue_set_guest_notifier_fd_handler(vq, false, with_irqfd); event_notifier_cleanup(notifier); } @@ -1071,24 +1239,39 @@ static int virtio_ccw_set_guest_notifiers(DeviceState *d, int nvqs, { VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d); VirtIODevice *vdev = virtio_bus_get_device(&dev->bus); + bool with_irqfd = dev->sch->thinint_active && kvm_irqfds_enabled(); int r, n; + if (with_irqfd && assigned) { + /* irq routes need to be set up before assigning irqfds */ + r = virtio_ccw_setup_irqroutes(dev, nvqs); + if (r < 0) { + goto irqroute_error; + } + } for (n = 0; n < nvqs; n++) { if (!virtio_queue_get_num(vdev, n)) { break; } - /* false -> true, as soon as irqfd works */ - r = virtio_ccw_set_guest_notifier(dev, n, assigned, false); + r = virtio_ccw_set_guest_notifier(dev, n, assigned, with_irqfd); if (r < 0) { goto assign_error; } } + if (with_irqfd && !assigned) { + /* release irq routes after irqfds have been released */ + virtio_ccw_release_irqroutes(dev, nvqs); + } return 0; assign_error: while (--n >= 0) { virtio_ccw_set_guest_notifier(dev, n, !assigned, false); } +irqroute_error: + if (with_irqfd && assigned) { + virtio_ccw_release_irqroutes(dev, nvqs); + } return r; } diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h index 4393e44814..b8b8a8abaa 100644 --- a/hw/s390x/virtio-ccw.h +++ b/hw/s390x/virtio-ccw.h @@ -22,6 +22,7 @@ #include <hw/virtio/virtio-balloon.h> #include <hw/virtio/virtio-rng.h> #include <hw/virtio/virtio-bus.h> +#include <hw/s390x/s390_flic.h> #define VIRTUAL_CSSID 0xfe @@ -75,6 +76,14 @@ typedef struct VirtIOCCWDeviceClass { #define VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT 1 #define VIRTIO_CCW_FLAG_USE_IOEVENTFD (1 << VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT) +typedef struct IndAddr { + hwaddr addr; + uint64_t map; + unsigned long refcnt; + int len; + QTAILQ_ENTRY(IndAddr) sibling; +} IndAddr; + struct VirtioCcwDevice { DeviceState parent_obj; SubchDev *sch; @@ -85,10 +94,11 @@ struct VirtioCcwDevice { bool ioeventfd_disabled; uint32_t flags; uint8_t thinint_isc; + AdapterRoutes routes; /* Guest provided values: */ - hwaddr indicators; - hwaddr indicators2; - hwaddr summary_indicator; + IndAddr *indicators; + IndAddr *indicators2; + IndAddr *summary_indicator; uint64_t ind_bit; }; diff --git a/hw/scsi/megasas.c b/hw/scsi/megasas.c index baee46f981..0e109a2844 100644 --- a/hw/scsi/megasas.c +++ b/hw/scsi/megasas.c @@ -728,8 +728,8 @@ static int megasas_ctrl_get_info(MegasasState *s, MegasasCmd *cmd) snprintf(info.package_version, 0x60, "%s-QEMU", QEMU_VERSION); memcpy(info.image_component[0].name, "APP", 3); memcpy(info.image_component[0].version, MEGASAS_VERSION "-QEMU", 9); - memcpy(info.image_component[0].build_date, __DATE__, 11); - memcpy(info.image_component[0].build_time, __TIME__, 8); + memcpy(info.image_component[0].build_date, "Apr 1 2014", 11); + memcpy(info.image_component[0].build_time, "12:34:56", 8); info.image_component_count = 1; if (pci_dev->has_rom) { uint8_t biosver[32]; diff --git a/hw/scsi/scsi-bus.c b/hw/scsi/scsi-bus.c index abe73022c0..06399fa37e 100644 --- a/hw/scsi/scsi-bus.c +++ b/hw/scsi/scsi-bus.c @@ -938,6 +938,7 @@ static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf) if (cmd->xfer == 0) { cmd->xfer = 256; } + /* fall through */ case WRITE_10: case WRITE_VERIFY_10: case WRITE_12: @@ -952,6 +953,7 @@ static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf) if (cmd->xfer == 0) { cmd->xfer = 256; } + /* fall through */ case READ_10: case RECOVER_BUFFERED_DATA: case READ_12: diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 175219376c..14261fb1a7 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -498,7 +498,7 @@ 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; @@ -507,6 +507,7 @@ 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; diff --git a/include/block/block.h b/include/block/block.h index 1b119aac24..59be83f3c2 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -120,6 +120,8 @@ typedef enum { /* BDRV_BLOCK_DATA: data is read from bs->file or another file * BDRV_BLOCK_ZERO: sectors read as zero * BDRV_BLOCK_OFFSET_VALID: sector stored in bs->file as raw data + * BDRV_BLOCK_ALLOCATED: the content of the block is determined by this + * layer (as opposed to the backing file) * BDRV_BLOCK_RAW: used internally to indicate that the request * was answered by the raw driver and that one * should look in bs->file directly. @@ -141,10 +143,11 @@ typedef enum { * f t f not allocated or unknown offset, read as zero * f f f not allocated or unknown offset, read from backing_hd */ -#define BDRV_BLOCK_DATA 1 -#define BDRV_BLOCK_ZERO 2 -#define BDRV_BLOCK_OFFSET_VALID 4 -#define BDRV_BLOCK_RAW 8 +#define BDRV_BLOCK_DATA 0x01 +#define BDRV_BLOCK_ZERO 0x02 +#define BDRV_BLOCK_OFFSET_VALID 0x04 +#define BDRV_BLOCK_RAW 0x08 +#define BDRV_BLOCK_ALLOCATED 0x10 #define BDRV_BLOCK_OFFSET_MASK BDRV_SECTOR_MASK typedef enum { diff --git a/include/block/block_int.h b/include/block/block_int.h index 9ffcb698d0..b8cc926bfe 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -364,6 +364,7 @@ struct BlockDriverState { BlockJob *job; QDict *options; + BlockdevDetectZeroesOptions detect_zeroes; }; int get_tmp_filename(char *filename, int size); diff --git a/include/hw/s390x/adapter.h b/include/hw/s390x/adapter.h new file mode 100644 index 0000000000..7f1703508c --- /dev/null +++ b/include/hw/s390x/adapter.h @@ -0,0 +1,23 @@ +/* + * s390 adapter definitions + * + * Copyright 2013,2014 IBM Corp. + * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#ifndef S390X_ADAPTER_H +#define S390X_ADAPTER_H + +struct AdapterInfo { + uint64_t ind_addr; + uint64_t summary_addr; + uint64_t ind_offset; + uint32_t summary_offset; + uint32_t adapter_id; +}; + +#endif diff --git a/include/hw/s390x/s390_flic.h b/include/hw/s390x/s390_flic.h index 497b219e30..489d73b9b3 100644 --- a/include/hw/s390x/s390_flic.h +++ b/include/hw/s390x/s390_flic.h @@ -1,33 +1,76 @@ /* - * QEMU S390x KVM floating interrupt controller (flic) + * QEMU S390x floating interrupt controller (flic) * * Copyright 2014 IBM Corp. * Author(s): Jens Freimann <jfrei@linux.vnet.ibm.com> + * Cornelia Huck <cornelia.huck@de.ibm.com> * * This work is licensed under the terms of the GNU GPL, version 2 or (at * your option) any later version. See the COPYING file in the top-level * directory. */ -#ifndef __KVM_S390_FLIC_H -#define __KVM_S390_FLIC_H +#ifndef __HW_S390_FLIC_H +#define __HW_S390_FLIC_H #include "hw/sysbus.h" +#include "hw/s390x/adapter.h" +#include "hw/virtio/virtio.h" -#define TYPE_KVM_S390_FLIC "s390-flic" +typedef struct AdapterRoutes { + AdapterInfo adapter; + int num_routes; + int gsi[VIRTIO_PCI_QUEUE_MAX]; +} AdapterRoutes; + +#define TYPE_S390_FLIC_COMMON "s390-flic" +#define S390_FLIC_COMMON(obj) \ + OBJECT_CHECK(S390FLICState, (obj), TYPE_S390_FLIC_COMMON) + +typedef struct S390FLICState { + SysBusDevice parent_obj; + +} S390FLICState; + +#define S390_FLIC_COMMON_CLASS(klass) \ + OBJECT_CLASS_CHECK(S390FLICStateClass, (klass), TYPE_S390_FLIC_COMMON) +#define S390_FLIC_COMMON_GET_CLASS(obj) \ + OBJECT_GET_CLASS(S390FLICStateClass, (obj), TYPE_S390_FLIC_COMMON) + +typedef struct S390FLICStateClass { + DeviceClass parent_class; + + int (*register_io_adapter)(S390FLICState *fs, uint32_t id, uint8_t isc, + bool swap, bool maskable); + int (*io_adapter_map)(S390FLICState *fs, uint32_t id, uint64_t map_addr, + bool do_map); + int (*add_adapter_routes)(S390FLICState *fs, AdapterRoutes *routes); + void (*release_adapter_routes)(S390FLICState *fs, AdapterRoutes *routes); +} S390FLICStateClass; + +#define TYPE_KVM_S390_FLIC "s390-flic-kvm" #define KVM_S390_FLIC(obj) \ OBJECT_CHECK(KVMS390FLICState, (obj), TYPE_KVM_S390_FLIC) -typedef struct KVMS390FLICState { - SysBusDevice parent_obj; +#define TYPE_QEMU_S390_FLIC "s390-flic-qemu" +#define QEMU_S390_FLIC(obj) \ + OBJECT_CHECK(QEMUS390FLICState, (obj), TYPE_QEMU_S390_FLIC) - uint32_t fd; -} KVMS390FLICState; +typedef struct QEMUS390FLICState { + S390FLICState parent_obj; +} QEMUS390FLICState; -#ifdef CONFIG_KVM void s390_flic_init(void); + +S390FLICState *s390_get_flic(void); + +#ifdef CONFIG_KVM +DeviceState *s390_flic_kvm_create(void); #else -static inline void s390_flic_init(void) { } +static inline DeviceState *s390_flic_kvm_create(void) +{ + return NULL; +} #endif -#endif /* __KVM_S390_FLIC_H */ +#endif /* __HW_S390_FLIC_H */ diff --git a/include/qapi/qmp/qdict.h b/include/qapi/qmp/qdict.h index 1ddf97b1c3..d68f4eb4d5 100644 --- a/include/qapi/qmp/qdict.h +++ b/include/qapi/qmp/qdict.h @@ -16,6 +16,7 @@ #include "qapi/qmp/qobject.h" #include "qapi/qmp/qlist.h" #include "qemu/queue.h" +#include <stdbool.h> #include <stdint.h> #define QDICT_BUCKET_MAX 512 @@ -70,4 +71,6 @@ void qdict_flatten(QDict *qdict); void qdict_extract_subqdict(QDict *src, QDict **dst, const char *start); void qdict_array_split(QDict *src, QList **dst); +void qdict_join(QDict *dest, QDict *src, bool overwrite); + #endif /* QDICT_H */ diff --git a/include/qemu-common.h b/include/qemu-common.h index 3f3fd60f5b..66ceceb2ad 100644 --- a/include/qemu-common.h +++ b/include/qemu-common.h @@ -318,6 +318,7 @@ void qemu_iovec_concat(QEMUIOVector *dst, void qemu_iovec_concat_iov(QEMUIOVector *dst, struct iovec *src_iov, unsigned int src_cnt, size_t soffset, size_t sbytes); +bool qemu_iovec_is_zero(QEMUIOVector *qiov); void qemu_iovec_destroy(QEMUIOVector *qiov); void qemu_iovec_reset(QEMUIOVector *qiov); size_t qemu_iovec_to_buf(QEMUIOVector *qiov, size_t offset, diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index 86bab123a4..5f20b0e263 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -74,5 +74,6 @@ typedef struct SHPCDevice SHPCDevice; typedef struct FWCfgState FWCfgState; typedef struct PcGuestInfo PcGuestInfo; typedef struct Range Range; +typedef struct AdapterInfo AdapterInfo; #endif /* QEMU_TYPEDEFS_H */ diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index e7ad9d159a..e79e92c50e 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -300,7 +300,7 @@ int kvm_check_extension(KVMState *s, unsigned int extension); }; \ uint64_t args_tmp[] = { __VA_ARGS__ }; \ int i; \ - for (i = 0; i < ARRAY_SIZE(args_tmp) && \ + for (i = 0; i < (int)ARRAY_SIZE(args_tmp) && \ i < ARRAY_SIZE(cap.args); i++) { \ cap.args[i] = args_tmp[i]; \ } \ @@ -315,7 +315,7 @@ int kvm_check_extension(KVMState *s, unsigned int extension); }; \ uint64_t args_tmp[] = { __VA_ARGS__ }; \ int i; \ - for (i = 0; i < ARRAY_SIZE(args_tmp) && \ + for (i = 0; i < (int)ARRAY_SIZE(args_tmp) && \ i < ARRAY_SIZE(cap.args); i++) { \ cap.args[i] = args_tmp[i]; \ } \ @@ -363,6 +363,8 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg); int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg); void kvm_irqchip_release_virq(KVMState *s, int virq); +int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter); + int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, EventNotifier *rn, int virq); int kvm_irqchip_remove_irqfd_notifier(KVMState *s, EventNotifier *n, int virq); @@ -27,6 +27,7 @@ #include "sysemu/sysemu.h" #include "hw/hw.h" #include "hw/pci/msi.h" +#include "hw/s390x/adapter.h" #include "exec/gdbstub.h" #include "sysemu/kvm.h" #include "qemu/bswap.h" @@ -1236,6 +1237,35 @@ static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int rfd, int virq, return kvm_vm_ioctl(s, KVM_IRQFD, &irqfd); } +int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter) +{ + struct kvm_irq_routing_entry kroute; + int virq; + + if (!kvm_gsi_routing_enabled()) { + return -ENOSYS; + } + + virq = kvm_irqchip_get_virq(s); + if (virq < 0) { + return virq; + } + + kroute.gsi = virq; + kroute.type = KVM_IRQ_ROUTING_S390_ADAPTER; + kroute.flags = 0; + kroute.u.adapter.summary_addr = adapter->summary_addr; + kroute.u.adapter.ind_addr = adapter->ind_addr; + kroute.u.adapter.summary_offset = adapter->summary_offset; + kroute.u.adapter.ind_offset = adapter->ind_offset; + kroute.u.adapter.adapter_id = adapter->adapter_id; + + kvm_add_routing_entry(s, &kroute); + kvm_irqchip_commit_routes(s); + + return virq; +} + #else /* !KVM_CAP_IRQ_ROUTING */ void kvm_init_irq_routing(KVMState *s) @@ -1256,6 +1286,11 @@ int kvm_irqchip_add_msi_route(KVMState *s, MSIMessage msg) return -ENOSYS; } +int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter) +{ + return -ENOSYS; +} + static int kvm_irqchip_assign_irqfd(KVMState *s, int fd, int virq, bool assign) { abort(); @@ -1285,7 +1320,8 @@ static int kvm_irqchip_create(KVMState *s) int ret; if (!qemu_opt_get_bool(qemu_get_machine_opts(), "kernel_irqchip", true) || - !kvm_check_extension(s, KVM_CAP_IRQCHIP)) { + (!kvm_check_extension(s, KVM_CAP_IRQCHIP) && + (kvm_vm_enable_cap(s, KVM_CAP_S390_IRQCHIP, 0) < 0))) { return 0; } diff --git a/kvm-stub.c b/kvm-stub.c index 8acda86ced..ac33d8666d 100644 --- a/kvm-stub.c +++ b/kvm-stub.c @@ -136,6 +136,11 @@ int kvm_irqchip_update_msi_route(KVMState *s, int virq, MSIMessage msg) return -ENOSYS; } +int kvm_irqchip_add_adapter_route(KVMState *s, AdapterInfo *adapter) +{ + return -ENOSYS; +} + int kvm_irqchip_add_irqfd_notifier(KVMState *s, EventNotifier *n, EventNotifier *rn, int virq) { diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h index c003c6a73b..98bedf3c18 100644 --- a/linux-headers/asm-s390/kvm.h +++ b/linux-headers/asm-s390/kvm.h @@ -15,6 +15,7 @@ #include <linux/types.h> #define __KVM_S390 +#define __KVM_HAVE_GUEST_DEBUG /* Device control API: s390-specific devices */ #define KVM_DEV_FLIC_GET_ALL_IRQS 1 @@ -54,6 +55,13 @@ struct kvm_s390_io_adapter_req { __u64 addr; }; +/* kvm attr_group on vm fd */ +#define KVM_S390_VM_MEM_CTRL 0 + +/* kvm attributes for mem_ctrl */ +#define KVM_S390_VM_MEM_ENABLE_CMMA 0 +#define KVM_S390_VM_MEM_CLR_CMMA 1 + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { /* general purpose regs for s390 */ @@ -72,11 +80,31 @@ struct kvm_fpu { __u64 fprs[16]; }; +#define KVM_GUESTDBG_USE_HW_BP 0x00010000 + +#define KVM_HW_BP 1 +#define KVM_HW_WP_WRITE 2 +#define KVM_SINGLESTEP 4 + struct kvm_debug_exit_arch { + __u64 addr; + __u8 type; + __u8 pad[7]; /* Should be set to 0 */ +}; + +struct kvm_hw_breakpoint { + __u64 addr; + __u64 phys_addr; + __u64 len; + __u8 type; + __u8 pad[7]; /* Should be set to 0 */ }; /* for KVM_SET_GUEST_DEBUG */ struct kvm_guest_debug_arch { + __u32 nr_hw_bp; + __u32 pad; /* Should be set to 0 */ + struct kvm_hw_breakpoint *hw_bp; }; #define KVM_SYNC_PREFIX (1UL << 0) diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index b278ab3326..42ddc2cabb 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -416,6 +416,8 @@ struct kvm_s390_psw { #define KVM_S390_INT_PFAULT_INIT 0xfffe0004u #define KVM_S390_INT_PFAULT_DONE 0xfffe0005u #define KVM_S390_MCHK 0xfffe1000u +#define KVM_S390_INT_CLOCK_COMP 0xffff1004u +#define KVM_S390_INT_CPU_TIMER 0xffff1005u #define KVM_S390_INT_VIRTIO 0xffff2603u #define KVM_S390_INT_SERVICE 0xffff2401u #define KVM_S390_INT_EMERGENCY 0xffff1201u @@ -515,6 +517,7 @@ enum { kvm_ioeventfd_flag_nr_pio, kvm_ioeventfd_flag_nr_deassign, kvm_ioeventfd_flag_nr_virtio_ccw_notify, + kvm_ioeventfd_flag_nr_fast_mmio, kvm_ioeventfd_flag_nr_max, }; @@ -529,7 +532,7 @@ enum { struct kvm_ioeventfd { __u64 datamatch; __u64 addr; /* legal pio/mmio address */ - __u32 len; /* 1, 2, 4, or 8 bytes */ + __u32 len; /* 1, 2, 4, or 8 bytes; or 0 to ignore length */ __s32 fd; __u32 flags; __u8 pad[36]; @@ -743,6 +746,8 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_IOAPIC_POLARITY_IGNORED 97 #define KVM_CAP_ENABLE_CAP_VM 98 #define KVM_CAP_S390_IRQCHIP 99 +#define KVM_CAP_IOEVENTFD_NO_LENGTH 100 +#define KVM_CAP_VM_ATTRIBUTES 101 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/qapi-schema.json b/qapi-schema.json index 36cb964dfd..70ed7e3b45 100644 --- a/qapi-schema.json +++ b/qapi-schema.json @@ -942,6 +942,8 @@ # @encryption_key_missing: true if the backing device is encrypted but an # valid encryption key is missing # +# @detect_zeroes: detect and optimize zero writes (Since 2.1) +# # @bps: total throughput limit in bytes per second is specified # # @bps_rd: read throughput limit in bytes per second is specified @@ -977,6 +979,7 @@ 'data': { 'file': 'str', '*node-name': 'str', 'ro': 'bool', 'drv': 'str', '*backing_file': 'str', 'backing_file_depth': 'int', 'encrypted': 'bool', 'encryption_key_missing': 'bool', + 'detect_zeroes': 'BlockdevDetectZeroesOptions', 'bps': 'int', 'bps_rd': 'int', 'bps_wr': 'int', 'iops': 'int', 'iops_rd': 'int', 'iops_wr': 'int', 'image': 'ImageInfo', @@ -4255,6 +4258,22 @@ 'data': [ 'ignore', 'unmap' ] } ## +# @BlockdevDetectZeroesOptions +# +# Describes the operation mode for the automatic conversion of plain +# zero writes by the OS to driver specific optimized zero write commands. +# +# @off: Disabled (default) +# @on: Enabled +# @unmap: Enabled and even try to unmap blocks if possible. This requires +# also that @BlockdevDiscardOptions is set to unmap for this device. +# +# Since: 2.1 +## +{ 'enum': 'BlockdevDetectZeroesOptions', + 'data': [ 'off', 'on', 'unmap' ] } + +## # @BlockdevAioOptions # # Selects the AIO backend to handle I/O requests @@ -4306,20 +4325,22 @@ # Options that are available for all block devices, independent of the block # driver. # -# @driver: block driver name -# @id: #optional id by which the new block device can be referred to. -# This is a required option on the top level of blockdev-add, and -# currently not allowed on any other level. -# @node-name: #optional the name of a block driver state node (Since 2.0) -# @discard: #optional discard-related options (default: ignore) -# @cache: #optional cache-related options -# @aio: #optional AIO backend (default: threads) -# @rerror: #optional how to handle read errors on the device -# (default: report) -# @werror: #optional how to handle write errors on the device -# (default: enospc) -# @read-only: #optional whether the block device should be read-only -# (default: false) +# @driver: block driver name +# @id: #optional id by which the new block device can be referred to. +# This is a required option on the top level of blockdev-add, and +# currently not allowed on any other level. +# @node-name: #optional the name of a block driver state node (Since 2.0) +# @discard: #optional discard-related options (default: ignore) +# @cache: #optional cache-related options +# @aio: #optional AIO backend (default: threads) +# @rerror: #optional how to handle read errors on the device +# (default: report) +# @werror: #optional how to handle write errors on the device +# (default: enospc) +# @read-only: #optional whether the block device should be read-only +# (default: false) +# @detect-zeroes: #optional detect and optimize zero writes (Since 2.1) +# (default: off) # # Since: 1.7 ## @@ -4332,7 +4353,8 @@ '*aio': 'BlockdevAioOptions', '*rerror': 'BlockdevOnError', '*werror': 'BlockdevOnError', - '*read-only': 'bool' } } + '*read-only': 'bool', + '*detect-zeroes': 'BlockdevDetectZeroesOptions' } } ## # @BlockdevOptionsFile diff --git a/qemu-img.c b/qemu-img.c index 04ce02aeb4..1ad899e03b 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -70,11 +70,8 @@ static void add_format_to_seq(void *opaque, const char *fmt_name) { GSequence *seq = opaque; - if (!g_sequence_lookup(seq, (gpointer)fmt_name, - compare_data, NULL)) { - g_sequence_insert_sorted(seq, (gpointer)fmt_name, - compare_data, NULL); - } + g_sequence_insert_sorted(seq, (gpointer)fmt_name, + compare_data, NULL); } static void QEMU_NORETURN GCC_FMT_ATTR(1, 2) error_exit(const char *fmt, ...) diff --git a/qemu-options.hx b/qemu-options.hx index 781af14bf5..c2c0823911 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -414,6 +414,7 @@ DEF("drive", HAS_ARG, QEMU_OPTION_drive, " [,serial=s][,addr=A][,rerror=ignore|stop|report]\n" " [,werror=ignore|stop|report|enospc][,id=name][,aio=threads|native]\n" " [,readonly=on|off][,copy-on-read=on|off]\n" + " [,detect-zeroes=on|off|unmap]\n" " [[,bps=b]|[[,bps_rd=r][,bps_wr=w]]]\n" " [[,iops=i]|[[,iops_rd=r][,iops_wr=w]]]\n" " [[,bps_max=bm]|[[,bps_rd_max=rm][,bps_wr_max=wm]]]\n" @@ -475,6 +476,11 @@ Open drive @option{file} as read-only. Guest write attempts will fail. @item copy-on-read=@var{copy-on-read} @var{copy-on-read} is "on" or "off" and enables whether to copy read backing file sectors into the image file. +@item detect-zeroes=@var{detect-zeroes} +@var{detect-zeroes} is "off", "on" or "unmap" and enables the automatic +conversion of plain zero writes by the OS to driver specific optimized +zero write commands. You may even choose "unmap" if @var{discard} is set +to "unmap" to allow a zero write to be converted to an UNMAP operation. @end table By default, the @option{cache=writeback} mode is used. It will report data @@ -2191,6 +2197,74 @@ qemu-system-x86_64 --drive file=gluster://192.0.2.1/testvol/a.img @end example See also @url{http://www.gluster.org}. + +@item HTTP/HTTPS/FTP/FTPS/TFTP +QEMU supports read-only access to files accessed over http(s), ftp(s) and tftp. + +Syntax using a single filename: +@example +<protocol>://[<username>[:<password>]@@]<host>/<path> +@end example + +where: +@table @option +@item protocol +'http', 'https', 'ftp', 'ftps', or 'tftp'. + +@item username +Optional username for authentication to the remote server. + +@item password +Optional password for authentication to the remote server. + +@item host +Address of the remote server. + +@item path +Path on the remote server, including any query string. +@end table + +The following options are also supported: +@table @option +@item url +The full URL when passing options to the driver explicitly. + +@item readahead +The amount of data to read ahead with each range request to the remote server. +This value may optionally have the suffix 'T', 'G', 'M', 'K', 'k' or 'b'. If it +does not have a suffix, it will be assumed to be in bytes. The value must be a +multiple of 512 bytes. It defaults to 256k. + +@item sslverify +Whether to verify the remote server's certificate when connecting over SSL. It +can have the value 'on' or 'off'. It defaults to 'on'. +@end table + +Note that when passing options to qemu explicitly, @option{driver} is the value +of <protocol>. + +Example: boot from a remote Fedora 20 live ISO image +@example +qemu-system-x86_64 --drive media=cdrom,file=http://dl.fedoraproject.org/pub/fedora/linux/releases/20/Live/x86_64/Fedora-Live-Desktop-x86_64-20-1.iso,readonly + +qemu-system-x86_64 --drive media=cdrom,file.driver=http,file.url=http://dl.fedoraproject.org/pub/fedora/linux/releases/20/Live/x86_64/Fedora-Live-Desktop-x86_64-20-1.iso,readonly +@end example + +Example: boot from a remote Fedora 20 cloud image using a local overlay for +writes, copy-on-read, and a readahead of 64k +@example +qemu-img create -f qcow2 -o backing_file='json:@{"file.driver":"http",, "file.url":"https://dl.fedoraproject.org/pub/fedora/linux/releases/20/Images/x86_64/Fedora-x86_64-20-20131211.1-sda.qcow2",, "file.readahead":"64k"@}' /tmp/Fedora-x86_64-20-20131211.1-sda.qcow2 + +qemu-system-x86_64 -drive file=/tmp/Fedora-x86_64-20-20131211.1-sda.qcow2,copy-on-read=on +@end example + +Example: boot from an image stored on a VMware vSphere server with a self-signed +certificate using a local overlay for writes and a readahead of 64k +@example +qemu-img create -f qcow2 -o backing_file='json:@{"file.driver":"https",, "file.url":"https://user:password@@vsphere.example.com/folder/test/test-flat.vmdk?dcPath=Datacenter&dsName=datastore1",, "file.sslverify":"off",, "file.readahead":"64k"@}' /tmp/test.qcow2 + +qemu-system-x86_64 -drive file=/tmp/test.qcow2 +@end example ETEXI STEXI diff --git a/qmp-commands.hx b/qmp-commands.hx index cae890ee5d..2c53c1ba2e 100644 --- a/qmp-commands.hx +++ b/qmp-commands.hx @@ -2032,6 +2032,8 @@ Each json-object contain the following: - "iops_rd_max": read I/O operations max (json-int) - "iops_wr_max": write I/O operations max (json-int) - "iops_size": I/O size when limiting by iops (json-int) + - "detect_zeroes": detect and optimize zero writing (json-string) + - Possible values: "off", "on", "unmap" - "image": the detail of the image, it is a json-object containing the following: - "filename": image file name (json-string) @@ -2108,6 +2110,7 @@ Example: "iops_rd_max": 0, "iops_wr_max": 0, "iops_size": 0, + "detect_zeroes": "on", "image":{ "filename":"disks/test.qcow2", "format":"qcow2", diff --git a/qobject/qdict.c b/qobject/qdict.c index 42ec4c0d2c..ea239f082e 100644 --- a/qobject/qdict.c +++ b/qobject/qdict.c @@ -665,3 +665,35 @@ void qdict_array_split(QDict *src, QList **dst) qlist_append_obj(*dst, subqobj ?: QOBJECT(subqdict)); } } + +/** + * qdict_join(): Absorb the src QDict into the dest QDict, that is, move all + * elements from src to dest. + * + * If an element from src has a key already present in dest, it will not be + * moved unless overwrite is true. + * + * If overwrite is true, the conflicting values in dest will be discarded and + * replaced by the corresponding values from src. + * + * Therefore, with overwrite being true, the src QDict will always be empty when + * this function returns. If overwrite is false, the src QDict will be empty + * iff there were no conflicts. + */ +void qdict_join(QDict *dest, QDict *src, bool overwrite) +{ + const QDictEntry *entry, *next; + + entry = qdict_first(src); + while (entry) { + next = qdict_next(src, entry); + + if (overwrite || !qdict_haskey(dest, entry->key)) { + qobject_incref(entry->value); + qdict_put_obj(dest, entry->key, entry->value); + qdict_del(src, entry->key); + } + + entry = next; + } +} diff --git a/target-s390x/cpu-qom.h b/target-s390x/cpu-qom.h index ac0460eb30..f9c96d13a9 100644 --- a/target-s390x/cpu-qom.h +++ b/target-s390x/cpu-qom.h @@ -86,6 +86,7 @@ int s390_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, int s390_cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, void *opaque); hwaddr s390_cpu_get_phys_page_debug(CPUState *cpu, vaddr addr); +hwaddr s390_cpu_get_phys_addr_debug(CPUState *cpu, vaddr addr); int s390_cpu_gdb_read_register(CPUState *cpu, uint8_t *buf, int reg); int s390_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); diff --git a/target-s390x/helper.c b/target-s390x/helper.c index 7c76fc149b..3d756cae6c 100644 --- a/target-s390x/helper.c +++ b/target-s390x/helper.c @@ -489,6 +489,18 @@ hwaddr s390_cpu_get_phys_page_debug(CPUState *cs, vaddr vaddr) return raddr; } +hwaddr s390_cpu_get_phys_addr_debug(CPUState *cs, vaddr vaddr) +{ + hwaddr phys_addr; + target_ulong page; + + page = vaddr & TARGET_PAGE_MASK; + phys_addr = cpu_get_phys_page_debug(cs, page); + phys_addr += (vaddr & ~TARGET_PAGE_MASK); + + return phys_addr; +} + void load_psw(CPUS390XState *env, uint64_t mask, uint64_t addr) { if (mask & PSW_MASK_WAIT) { diff --git a/target-s390x/kvm.c b/target-s390x/kvm.c index 56179afece..7a07f9d753 100644 --- a/target-s390x/kvm.c +++ b/target-s390x/kvm.c @@ -36,6 +36,7 @@ #include "sysemu/device_tree.h" #include "qapi/qmp/qjson.h" #include "monitor/monitor.h" +#include "exec/gdbstub.h" #include "trace.h" /* #define DEBUG_KVM */ @@ -86,6 +87,14 @@ #define ICPT_CPU_STOP 0x28 #define ICPT_IO 0x40 +static CPUWatchpoint hw_watchpoint; +/* + * We don't use a list because this structure is also used to transmit the + * hardware breakpoints to the kernel. + */ +static struct kvm_hw_breakpoint *hw_breakpoints; +static int nb_hw_breakpoints; + const KVMCapabilityInfo kvm_arch_required_capabilities[] = { KVM_CAP_LAST_INFO }; @@ -320,12 +329,16 @@ static void *legacy_s390_alloc(size_t size) return mem == MAP_FAILED ? NULL : mem; } +/* DIAG 501 is used for sw breakpoints */ +static const uint8_t diag_501[] = {0x83, 0x24, 0x05, 0x01}; + int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) { - static const uint8_t diag_501[] = {0x83, 0x24, 0x05, 0x01}; - if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, 4, 0) || - cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)diag_501, 4, 1)) { + if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, + sizeof(diag_501), 0) || + cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)diag_501, + sizeof(diag_501), 1)) { return -EINVAL; } return 0; @@ -333,38 +346,140 @@ int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) { - uint8_t t[4]; - static const uint8_t diag_501[] = {0x83, 0x24, 0x05, 0x01}; + uint8_t t[sizeof(diag_501)]; - if (cpu_memory_rw_debug(cs, bp->pc, t, 4, 0)) { + if (cpu_memory_rw_debug(cs, bp->pc, t, sizeof(diag_501), 0)) { return -EINVAL; - } else if (memcmp(t, diag_501, 4)) { + } else if (memcmp(t, diag_501, sizeof(diag_501))) { return -EINVAL; - } else if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, 1, 1)) { + } else if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn, + sizeof(diag_501), 1)) { return -EINVAL; } return 0; } +static struct kvm_hw_breakpoint *find_hw_breakpoint(target_ulong addr, + int len, int type) +{ + int n; + + for (n = 0; n < nb_hw_breakpoints; n++) { + if (hw_breakpoints[n].addr == addr && hw_breakpoints[n].type == type && + (hw_breakpoints[n].len == len || len == -1)) { + return &hw_breakpoints[n]; + } + } + + return NULL; +} + +static int insert_hw_breakpoint(target_ulong addr, int len, int type) +{ + int size; + + if (find_hw_breakpoint(addr, len, type)) { + return -EEXIST; + } + + size = (nb_hw_breakpoints + 1) * sizeof(struct kvm_hw_breakpoint); + + if (!hw_breakpoints) { + nb_hw_breakpoints = 0; + hw_breakpoints = (struct kvm_hw_breakpoint *)g_try_malloc(size); + } else { + hw_breakpoints = + (struct kvm_hw_breakpoint *)g_try_realloc(hw_breakpoints, size); + } + + if (!hw_breakpoints) { + nb_hw_breakpoints = 0; + return -ENOMEM; + } + + hw_breakpoints[nb_hw_breakpoints].addr = addr; + hw_breakpoints[nb_hw_breakpoints].len = len; + hw_breakpoints[nb_hw_breakpoints].type = type; + + nb_hw_breakpoints++; + + return 0; +} + int kvm_arch_insert_hw_breakpoint(target_ulong addr, target_ulong len, int type) { - return -ENOSYS; + switch (type) { + case GDB_BREAKPOINT_HW: + type = KVM_HW_BP; + break; + case GDB_WATCHPOINT_WRITE: + if (len < 1) { + return -EINVAL; + } + type = KVM_HW_WP_WRITE; + break; + default: + return -ENOSYS; + } + return insert_hw_breakpoint(addr, len, type); } int kvm_arch_remove_hw_breakpoint(target_ulong addr, target_ulong len, int type) { - return -ENOSYS; + int size; + struct kvm_hw_breakpoint *bp = find_hw_breakpoint(addr, len, type); + + if (bp == NULL) { + return -ENOENT; + } + + nb_hw_breakpoints--; + if (nb_hw_breakpoints > 0) { + /* + * In order to trim the array, move the last element to the position to + * be removed - if necessary. + */ + if (bp != &hw_breakpoints[nb_hw_breakpoints]) { + *bp = hw_breakpoints[nb_hw_breakpoints]; + } + size = nb_hw_breakpoints * sizeof(struct kvm_hw_breakpoint); + hw_breakpoints = + (struct kvm_hw_breakpoint *)g_realloc(hw_breakpoints, size); + } else { + g_free(hw_breakpoints); + hw_breakpoints = NULL; + } + + return 0; } void kvm_arch_remove_all_hw_breakpoints(void) { + nb_hw_breakpoints = 0; + g_free(hw_breakpoints); + hw_breakpoints = NULL; } void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg) { + int i; + + if (nb_hw_breakpoints > 0) { + dbg->arch.nr_hw_bp = nb_hw_breakpoints; + dbg->arch.hw_bp = hw_breakpoints; + + for (i = 0; i < nb_hw_breakpoints; ++i) { + hw_breakpoints[i].phys_addr = s390_cpu_get_phys_addr_debug(cpu, + hw_breakpoints[i].addr); + } + dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; + } else { + dbg->arch.nr_hw_bp = 0; + dbg->arch.hw_bp = NULL; + } } void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run) @@ -579,6 +694,22 @@ static void kvm_handle_diag_308(S390CPU *cpu, struct kvm_run *run) handle_diag_308(&cpu->env, r1, r3); } +static int handle_sw_breakpoint(S390CPU *cpu, struct kvm_run *run) +{ + CPUS390XState *env = &cpu->env; + unsigned long pc; + + cpu_synchronize_state(CPU(cpu)); + + pc = env->psw.addr - 4; + if (kvm_find_sw_breakpoint(CPU(cpu), pc)) { + env->psw.addr = pc; + return EXCP_DEBUG; + } + + return -ENOENT; +} + #define DIAG_KVM_CODE_MASK 0x000000000000ffff static int handle_diag(S390CPU *cpu, struct kvm_run *run, uint32_t ipb) @@ -599,7 +730,7 @@ static int handle_diag(S390CPU *cpu, struct kvm_run *run, uint32_t ipb) r = handle_hypercall(cpu, run); break; case DIAG_KVM_BREAKPOINT: - sleep(10); + r = handle_sw_breakpoint(cpu, run); break; default: DPRINTF("KVM: unknown DIAG: 0x%x\n", func_code); @@ -701,7 +832,7 @@ out: return 0; } -static void handle_instruction(S390CPU *cpu, struct kvm_run *run) +static int handle_instruction(S390CPU *cpu, struct kvm_run *run) { unsigned int ipa0 = (run->s390_sieic.ipa & 0xff00); uint8_t ipa1 = run->s390_sieic.ipa & 0x00ff; @@ -728,8 +859,11 @@ static void handle_instruction(S390CPU *cpu, struct kvm_run *run) } if (r < 0) { + r = 0; enter_pgmcheck(cpu, 0x0001); } + + return r; } static bool is_special_wait_psw(CPUState *cs) @@ -749,7 +883,7 @@ static int handle_intercept(S390CPU *cpu) (long)cs->kvm_run->psw_addr); switch (icpt_code) { case ICPT_INSTRUCTION: - handle_instruction(cpu, run); + r = handle_instruction(cpu, run); break; case ICPT_WAITPSW: /* disabled wait, since enabled wait is handled in kernel */ @@ -830,7 +964,36 @@ static int handle_tsch(S390CPU *cpu) static int kvm_arch_handle_debug_exit(S390CPU *cpu) { - return -ENOSYS; + CPUState *cs = CPU(cpu); + struct kvm_run *run = cs->kvm_run; + + int ret = 0; + struct kvm_debug_exit_arch *arch_info = &run->debug.arch; + + switch (arch_info->type) { + case KVM_HW_WP_WRITE: + if (find_hw_breakpoint(arch_info->addr, -1, arch_info->type)) { + cs->watchpoint_hit = &hw_watchpoint; + hw_watchpoint.vaddr = arch_info->addr; + hw_watchpoint.flags = BP_MEM_WRITE; + ret = EXCP_DEBUG; + } + break; + case KVM_HW_BP: + if (find_hw_breakpoint(arch_info->addr, -1, arch_info->type)) { + ret = EXCP_DEBUG; + } + break; + case KVM_SINGLESTEP: + if (cs->singlestep_enabled) { + ret = EXCP_DEBUG; + } + break; + default: + ret = -ENOSYS; + } + + return ret; } int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) @@ -911,6 +1074,16 @@ void kvm_s390_enable_css_support(S390CPU *cpu) void kvm_arch_init_irq_routing(KVMState *s) { + /* + * Note that while irqchip capabilities generally imply that cpustates + * are handled in-kernel, it is not true for s390 (yet); therefore, we + * have to override the common code kvm_halt_in_kernel_allowed setting. + */ + if (kvm_check_extension(s, KVM_CAP_IRQ_ROUTING)) { + kvm_irqfds_allowed = true; + kvm_gsi_routing_allowed = true; + kvm_halt_in_kernel_allowed = false; + } } int kvm_s390_assign_subch_ioeventfd(EventNotifier *notifier, uint32_t sch, diff --git a/tests/check-qdict.c b/tests/check-qdict.c index 2ad0f7827e..a9296f0833 100644 --- a/tests/check-qdict.c +++ b/tests/check-qdict.c @@ -444,6 +444,92 @@ static void qdict_array_split_test(void) QDECREF(test_dict); } +static void qdict_join_test(void) +{ + QDict *dict1, *dict2; + bool overwrite = false; + int i; + + dict1 = qdict_new(); + dict2 = qdict_new(); + + + /* Test everything once without overwrite and once with */ + do + { + /* Test empty dicts */ + qdict_join(dict1, dict2, overwrite); + + g_assert(qdict_size(dict1) == 0); + g_assert(qdict_size(dict2) == 0); + + + /* First iteration: Test movement */ + /* Second iteration: Test empty source and non-empty destination */ + qdict_put(dict2, "foo", qint_from_int(42)); + + for (i = 0; i < 2; i++) { + qdict_join(dict1, dict2, overwrite); + + g_assert(qdict_size(dict1) == 1); + g_assert(qdict_size(dict2) == 0); + + g_assert(qdict_get_int(dict1, "foo") == 42); + } + + + /* Test non-empty source and destination without conflict */ + qdict_put(dict2, "bar", qint_from_int(23)); + + qdict_join(dict1, dict2, overwrite); + + g_assert(qdict_size(dict1) == 2); + g_assert(qdict_size(dict2) == 0); + + g_assert(qdict_get_int(dict1, "foo") == 42); + g_assert(qdict_get_int(dict1, "bar") == 23); + + + /* Test conflict */ + qdict_put(dict2, "foo", qint_from_int(84)); + + qdict_join(dict1, dict2, overwrite); + + g_assert(qdict_size(dict1) == 2); + g_assert(qdict_size(dict2) == !overwrite); + + g_assert(qdict_get_int(dict1, "foo") == overwrite ? 84 : 42); + g_assert(qdict_get_int(dict1, "bar") == 23); + + if (!overwrite) { + g_assert(qdict_get_int(dict2, "foo") == 84); + } + + + /* Check the references */ + g_assert(qdict_get(dict1, "foo")->refcnt == 1); + g_assert(qdict_get(dict1, "bar")->refcnt == 1); + + if (!overwrite) { + g_assert(qdict_get(dict2, "foo")->refcnt == 1); + } + + + /* Clean up */ + qdict_del(dict1, "foo"); + qdict_del(dict1, "bar"); + + if (!overwrite) { + qdict_del(dict2, "foo"); + } + } + while (overwrite ^= true); + + + QDECREF(dict1); + QDECREF(dict2); +} + /* * Errors test-cases */ @@ -584,6 +670,7 @@ int main(int argc, char **argv) g_test_add_func("/public/iterapi", qdict_iterapi_test); g_test_add_func("/public/flatten", qdict_flatten_test); g_test_add_func("/public/array_split", qdict_array_split_test); + g_test_add_func("/public/join", qdict_join_test); g_test_add_func("/errors/put_exists", qdict_put_exists_test); g_test_add_func("/errors/get_not_exists", qdict_get_not_exists_test); diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index 8cb61fd7ec..8ce2373cf5 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -35,7 +35,7 @@ class TestSingleDrive(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, mid_img) qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % mid_img, test_img) qemu_io('-c', 'write -P 0x1 0 512', backing_img) - self.vm = iotests.VM().add_drive(test_img) + self.vm = iotests.VM().add_drive("blkdebug::" + test_img) self.vm.launch() def tearDown(self): diff --git a/tests/qemu-iotests/039 b/tests/qemu-iotests/039 index b9cbe99560..27fe4bdacc 100755 --- a/tests/qemu-iotests/039 +++ b/tests/qemu-iotests/039 @@ -47,6 +47,11 @@ _supported_os Linux _default_cache_mode "writethrough" _supported_cache_modes "writethrough" +_no_dump_exec() +{ + (ulimit -c 0; exec "$@") +} + size=128M echo @@ -67,10 +72,7 @@ echo "== Creating a dirty image file ==" IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img $size -old_ulimit=$(ulimit -c) -ulimit -c 0 # do not produce a core dump on abort(3) -$QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" | _filter_qemu_io -ulimit -c "$old_ulimit" +_no_dump_exec $QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" 2>&1 | _filter_qemu_io # The dirty bit must be set ./qcow2.py "$TEST_IMG" dump-header | grep incompatible_features @@ -103,10 +105,7 @@ echo "== Opening a dirty image read/write should repair it ==" IMGOPTS="compat=1.1,lazy_refcounts=on" _make_test_img $size -old_ulimit=$(ulimit -c) -ulimit -c 0 # do not produce a core dump on abort(3) -$QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" | _filter_qemu_io -ulimit -c "$old_ulimit" +_no_dump_exec $QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" 2>&1 | _filter_qemu_io # The dirty bit must be set ./qcow2.py "$TEST_IMG" dump-header | grep incompatible_features @@ -122,10 +121,7 @@ echo "== Creating an image file with lazy_refcounts=off ==" IMGOPTS="compat=1.1,lazy_refcounts=off" _make_test_img $size -old_ulimit=$(ulimit -c) -ulimit -c 0 # do not produce a core dump on abort(3) -$QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" | _filter_qemu_io -ulimit -c "$old_ulimit" +_no_dump_exec $QEMU_IO -c "write -P 0x5a 0 512" -c "abort" "$TEST_IMG" 2>&1 | _filter_qemu_io # The dirty bit must not be set since lazy_refcounts=off ./qcow2.py "$TEST_IMG" dump-header | grep incompatible_features diff --git a/tests/qemu-iotests/039.out b/tests/qemu-iotests/039.out index fb31ae0624..67e774430f 100644 --- a/tests/qemu-iotests/039.out +++ b/tests/qemu-iotests/039.out @@ -11,6 +11,7 @@ No errors were found on the image. Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +./039: Aborted ( ulimit -c 0; exec "$@" ) incompatible_features 0x1 ERROR cluster 5 refcount=0 reference=1 ERROR OFLAG_COPIED data cluster: l2_entry=8000000000050000 refcount=0 @@ -42,6 +43,7 @@ read 512/512 bytes at offset 0 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +./039: Aborted ( ulimit -c 0; exec "$@" ) incompatible_features 0x1 Repairing cluster 5 refcount=0 reference=1 wrote 512/512 bytes at offset 0 @@ -52,6 +54,7 @@ incompatible_features 0x0 Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 wrote 512/512 bytes at offset 0 512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +./039: Aborted ( ulimit -c 0; exec "$@" ) incompatible_features 0x0 No errors were found on the image. diff --git a/tests/qemu-iotests/067.out b/tests/qemu-iotests/067.out index 8d271cc41a..7e090b95ab 100644 --- a/tests/qemu-iotests/067.out +++ b/tests/qemu-iotests/067.out @@ -6,7 +6,7 @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk -device virtio-blk-pci,drive=disk,id=virtio0 QMP_VERSION {"return": {}} -{"return": [{"io-status": "ok", "device": "disk", "locked": false, "removable": false, "inserted": {"iops_rd": 0, "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "type": "unknown"}, {"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}]} +{"return": [{"io-status": "ok", "device": "disk", "locked": false, "removable": false, "inserted": {"iops_rd": 0, "detect_zeroes": "off", "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "type": "unknown"}, {"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}]} {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "DEVICE_DELETED", "data": {"path": "/machine/peripheral/virtio0/virtio-backend"}} @@ -24,7 +24,7 @@ QMP_VERSION Testing: -drive file=TEST_DIR/t.qcow2,format=qcow2,if=none,id=disk QMP_VERSION {"return": {}} -{"return": [{"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}, {"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}]} +{"return": [{"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "detect_zeroes": "off", "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}, {"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}]} {"return": {}} {"return": {}} {"return": {}} @@ -44,7 +44,7 @@ Testing: QMP_VERSION {"return": {}} {"return": "OK\r\n"} -{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} +{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "detect_zeroes": "off", "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} {"return": {}} {"return": {}} {"return": {}} @@ -64,14 +64,14 @@ Testing: QMP_VERSION {"return": {}} {"return": {}} -{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} +{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "detect_zeroes": "off", "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} {"return": {}} {"return": {}} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "DEVICE_DELETED", "data": {"path": "/machine/peripheral/virtio0/virtio-backend"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "DEVICE_DELETED", "data": {"device": "virtio0", "path": "/machine/peripheral/virtio0"}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "RESET"} -{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"io-status": "ok", "device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} +{"return": [{"io-status": "ok", "device": "ide1-cd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "floppy0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"device": "sd0", "locked": false, "removable": true, "tray_open": false, "type": "unknown"}, {"io-status": "ok", "device": "disk", "locked": false, "removable": true, "inserted": {"iops_rd": 0, "detect_zeroes": "off", "image": {"virtual-size": 134217728, "filename": "TEST_DIR/t.qcow2", "cluster-size": 65536, "format": "qcow2", "actual-size": SIZE, "format-specific": {"type": "qcow2", "data": {"compat": "1.1", "lazy-refcounts": false}}, "dirty-flag": false}, "iops_wr": 0, "ro": false, "backing_file_depth": 0, "drv": "qcow2", "iops": 0, "bps_wr": 0, "encrypted": false, "bps": 0, "bps_rd": 0, "file": "TEST_DIR/t.qcow2", "encryption_key_missing": false}, "tray_open": false, "type": "unknown"}]} {"return": {}} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "SHUTDOWN"} {"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "DEVICE_TRAY_MOVED", "data": {"device": "ide1-cd0", "tray-open": true}} diff --git a/tests/qemu-iotests/070 b/tests/qemu-iotests/070 index ce71fa4a22..ea0dae7e9c 100755 --- a/tests/qemu-iotests/070 +++ b/tests/qemu-iotests/070 @@ -72,6 +72,13 @@ echo "=== Verify open image read-only succeeds after log replay ===" $QEMU_IO -r -c "read -pP 0xa5 0 18M" "$TEST_IMG" 2>&1 | _filter_testdir \ | _filter_qemu_io +_cleanup_test_img +_use_sample_img test-disk2vhd.vhdx.bz2 + +echo +echo "=== Verify image created by Disk2VHD can be opened ===" +$QEMU_IMG info "$TEST_IMG" 2>&1 | _filter_testdir | _filter_qemu + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/070.out b/tests/qemu-iotests/070.out index 922d62cb51..15f1fc1471 100644 --- a/tests/qemu-iotests/070.out +++ b/tests/qemu-iotests/070.out @@ -18,4 +18,11 @@ No errors were found on the image. === Verify open image read-only succeeds after log replay === read 18874368/18874368 bytes at offset 0 18 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Verify image created by Disk2VHD can be opened === +image: TEST_DIR/test-disk2vhd.vhdx +file format: vhdx +virtual size: 256M (268435456 bytes) +disk size: 260M +cluster_size: 2097152 *** done diff --git a/tests/qemu-iotests/089 b/tests/qemu-iotests/089 new file mode 100755 index 0000000000..ef476010c0 --- /dev/null +++ b/tests/qemu-iotests/089 @@ -0,0 +1,130 @@ +#!/bin/bash +# +# Test case for support of JSON filenames +# +# Copyright (C) 2014 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=mreitz@redhat.com + +seq="$(basename $0)" +echo "QA output created by $seq" + +here="$PWD" +tmp=/tmp/$$ +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt qcow2 +_supported_proto file +_supported_os Linux + +# Using an image filename containing quotation marks will render the JSON data +# below invalid. In that case, we have little choice but simply not to run this +# test. +case $TEST_IMG in + *'"'*) + _notrun "image filename may not contain quotation marks" + ;; +esac + +IMG_SIZE=64M + +# Taken from test 072 +echo +echo "=== Testing nested image formats ===" +echo + +TEST_IMG="$TEST_IMG.base" _make_test_img $IMG_SIZE + +$QEMU_IO -c 'write -P 42 0 512' -c 'write -P 23 512 512' \ + -c 'write -P 66 1024 512' "$TEST_IMG.base" | _filter_qemu_io + +$QEMU_IMG convert -f raw -O $IMGFMT "$TEST_IMG.base" "$TEST_IMG" + +$QEMU_IO -c 'read -P 42 0 512' -c 'read -P 23 512 512' \ + -c 'read -P 66 1024 512' "json:{ + \"driver\": \"$IMGFMT\", + \"file\": { + \"driver\": \"$IMGFMT\", + \"file\": { + \"filename\": \"$TEST_IMG\" + } + } +}" | _filter_qemu_io + +# This should fail (see test 072) +$QEMU_IO -c 'read -P 42 0 512' "$TEST_IMG" | _filter_qemu_io + + +# Taken from test 071 +echo +echo "=== Testing blkdebug ===" +echo + +_make_test_img $IMG_SIZE + +$QEMU_IO -c 'write -P 42 0x38000 512' "$TEST_IMG" | _filter_qemu_io + +# The "image.filename" part tests whether "a": { "b": "c" } and "a.b": "c" do +# the same (which they should). +$QEMU_IO -c 'read -P 42 0x38000 512' "json:{ + \"driver\": \"$IMGFMT\", + \"file\": { + \"driver\": \"blkdebug\", + \"inject-error\": [{ + \"event\": \"l2_load\" + }], + \"image.filename\": \"$TEST_IMG\" + } +}" | _filter_qemu_io + + +echo +echo "=== Testing qemu-img info output ===" +echo + +$QEMU_IMG info "json:{\"driver\":\"qcow2\",\"file.filename\":\"$TEST_IMG\"}" \ + | _filter_testdir | _filter_imgfmt + + +echo +echo "=== Testing option merging ===" +echo + +# Both options given directly and those given in the filename should be used +$QEMU_IO -c "open -o driver=qcow2 json:{\"file.filename\":\"$TEST_IMG\"}" \ + -c "info" 2>&1 | _filter_testdir | _filter_imgfmt + +# Options given directly should be prioritized over those given in the filename +$QEMU_IO -c "open -o driver=qcow2 json:{\"driver\":\"raw\",\"file.filename\":\"$TEST_IMG\"}" \ + -c "info" 2>&1 | _filter_testdir | _filter_imgfmt + + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/089.out b/tests/qemu-iotests/089.out new file mode 100644 index 0000000000..d6cf7835d8 --- /dev/null +++ b/tests/qemu-iotests/089.out @@ -0,0 +1,54 @@ +QA output created by 089 + +=== Testing nested image formats === + +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 +wrote 512/512 bytes at offset 0 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 512/512 bytes at offset 512 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 512/512 bytes at offset 1024 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 512/512 bytes at offset 0 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 512/512 bytes at offset 512 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read 512/512 bytes at offset 1024 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +Pattern verification failed at offset 0, 512 bytes +read 512/512 bytes at offset 0 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Testing blkdebug === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +wrote 512/512 bytes at offset 229376 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +read failed: Input/output error + +=== Testing qemu-img info output === + +image: TEST_DIR/t.IMGFMT +file format: IMGFMT +virtual size: 64M (67108864 bytes) +disk size: 324K +cluster_size: 65536 +Format specific information: + compat: 1.1 + lazy refcounts: false + +=== Testing option merging === + +format name: IMGFMT +cluster size: 64 KiB +vm state offset: 512 MiB +Format specific information: + compat: 1.1 + lazy refcounts: false +format name: IMGFMT +cluster size: 64 KiB +vm state offset: 512 MiB +Format specific information: + compat: 1.1 + lazy refcounts: false +*** done diff --git a/tests/qemu-iotests/092 b/tests/qemu-iotests/092 new file mode 100755 index 0000000000..a8c0c9ca2b --- /dev/null +++ b/tests/qemu-iotests/092 @@ -0,0 +1,98 @@ +#!/bin/bash +# +# qcow1 format input validation tests +# +# Copyright (C) 2014 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=kwolf@redhat.com + +seq=`basename $0` +echo "QA output created by $seq" + +here=`pwd` +tmp=/tmp/$$ +status=1 # failure is the default! + +_cleanup() +{ + rm -f $TEST_IMG.snap + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt qcow +_supported_proto generic +_supported_os Linux + +offset_backing_file_offset=8 +offset_backing_file_size=16 +offset_size=24 +offset_cluster_bits=32 +offset_l2_bits=33 + +echo +echo "== Invalid cluster size ==" +_make_test_img 64M +poke_file "$TEST_IMG" "$offset_cluster_bits" "\xff" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_cluster_bits" "\x1f" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_cluster_bits" "\x08" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_cluster_bits" "\x11" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir + +echo +echo "== Invalid L2 table size ==" +_make_test_img 64M +poke_file "$TEST_IMG" "$offset_l2_bits" "\xff" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_l2_bits" "\x05" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_l2_bits" "\x0e" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir + +# 1 << 0x1b = 2^31 / L2_CACHE_SIZE +poke_file "$TEST_IMG" "$offset_l2_bits" "\x1b" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir + +echo +echo "== Invalid size ==" +_make_test_img 64M +poke_file "$TEST_IMG" "$offset_size" "\xee\xee\xee\xee\xee\xee\xee\xee" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_size" "\x7f\xff\xff\xff\xff\xff\xff\xff" +{ $QEMU_IO -c "write 0 64M" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir + +echo +echo "== Invalid backing file length ==" +_make_test_img 64M +poke_file "$TEST_IMG" "$offset_backing_file_offset" "\x00\x00\x00\xff" +poke_file "$TEST_IMG" "$offset_backing_file_size" "\xff\xff\xff\xff" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir +poke_file "$TEST_IMG" "$offset_backing_file_size" "\x7f\xff\xff\xff" +{ $QEMU_IO -c "read 0 512" $TEST_IMG; } 2>&1 | _filter_qemu_io | _filter_testdir + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/092.out b/tests/qemu-iotests/092.out new file mode 100644 index 0000000000..496d8f0a63 --- /dev/null +++ b/tests/qemu-iotests/092.out @@ -0,0 +1,38 @@ +QA output created by 092 + +== Invalid cluster size == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +qemu-io: can't open device TEST_DIR/t.qcow: Cluster size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: Cluster size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: Cluster size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: Cluster size must be between 512 and 64k +no file open, try 'help open' + +== Invalid L2 table size == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +qemu-io: can't open device TEST_DIR/t.qcow: L2 table size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: L2 table size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: L2 table size must be between 512 and 64k +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: L2 table size must be between 512 and 64k +no file open, try 'help open' + +== Invalid size == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +qemu-io: can't open device TEST_DIR/t.qcow: Image too large +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: Image too large +no file open, try 'help open' + +== Invalid backing file length == +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +qemu-io: can't open device TEST_DIR/t.qcow: Backing file name too long +no file open, try 'help open' +qemu-io: can't open device TEST_DIR/t.qcow: Backing file name too long +no file open, try 'help open' +*** done diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index 776985d15e..a04df7f6dc 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -150,6 +150,7 @@ _filter_win32() _filter_qemu_io() { _filter_win32 | sed -e "s/[0-9]* ops\; [0-9/:. sec]* ([0-9/.inf]* [EPTGMKiBbytes]*\/sec and [0-9/.inf]* ops\/sec)/X ops\; XX:XX:XX.X (XXX YYY\/sec and XXX ops\/sec)/" \ + -e "s/: line [0-9][0-9]*: *[0-9][0-9]*\( Aborted\)/:\1/" \ -e "s/qemu-io> //g" } diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index cd3e4d2c27..0f074403ae 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -95,5 +95,7 @@ 086 rw auto quick 087 rw auto 088 rw auto +089 rw auto quick 090 rw auto quick 091 rw auto +092 rw auto quick diff --git a/tests/qemu-iotests/sample_images/test-disk2vhd.vhdx.bz2 b/tests/qemu-iotests/sample_images/test-disk2vhd.vhdx.bz2 Binary files differnew file mode 100644 index 0000000000..2891c9a6d6 --- /dev/null +++ b/tests/qemu-iotests/sample_images/test-disk2vhd.vhdx.bz2 diff --git a/util/iov.c b/util/iov.c index 6569b5aae1..49f88388f8 100644 --- a/util/iov.c +++ b/util/iov.c @@ -335,6 +335,27 @@ void qemu_iovec_concat(QEMUIOVector *dst, qemu_iovec_concat_iov(dst, src->iov, src->niov, soffset, sbytes); } +/* + * Check if the contents of the iovecs are all zero + */ +bool qemu_iovec_is_zero(QEMUIOVector *qiov) +{ + int i; + for (i = 0; i < qiov->niov; i++) { + size_t offs = QEMU_ALIGN_DOWN(qiov->iov[i].iov_len, 4 * sizeof(long)); + uint8_t *ptr = qiov->iov[i].iov_base; + if (offs && !buffer_is_zero(qiov->iov[i].iov_base, offs)) { + return false; + } + for (; offs < qiov->iov[i].iov_len; offs++) { + if (ptr[offs]) { + return false; + } + } + } + return true; +} + void qemu_iovec_destroy(QEMUIOVector *qiov) { assert(qiov->nalloc != -1); |