diff options
| -rw-r--r-- | audio/audio.c | 2 | ||||
| -rw-r--r-- | audio/wavaudio.c | 46 | ||||
| -rw-r--r-- | audio/wavcapture.c | 79 | ||||
| -rw-r--r-- | block/nbd.c | 4 | ||||
| -rw-r--r-- | block/raw-posix.c | 9 | ||||
| -rw-r--r-- | block/rbd.c | 83 | ||||
| -rw-r--r-- | block/vmdk.c | 14 | ||||
| -rwxr-xr-x | configure | 1 | ||||
| -rw-r--r-- | cpus.c | 25 | ||||
| -rw-r--r-- | cpus.h | 1 | ||||
| -rw-r--r-- | dma-helpers.c | 58 | ||||
| -rw-r--r-- | dma.h | 10 | ||||
| -rw-r--r-- | gdbstub.c | 34 | ||||
| -rw-r--r-- | hw/ac97.c | 1 | ||||
| -rw-r--r-- | hw/e1000.c | 3 | ||||
| -rw-r--r-- | hw/es1370.c | 1 | ||||
| -rw-r--r-- | hw/etraxfs_dma.c | 2 | ||||
| -rw-r--r-- | hw/ide/ahci.c | 10 | ||||
| -rw-r--r-- | hw/ide/core.c | 6 | ||||
| -rw-r--r-- | hw/ide/internal.h | 3 | ||||
| -rw-r--r-- | hw/ide/macio.c | 2 | ||||
| -rw-r--r-- | hw/ide/pci.c | 2 | ||||
| -rw-r--r-- | hw/kvmclock.c | 5 | ||||
| -rw-r--r-- | hw/lsi53c895a.c | 3 | ||||
| -rw-r--r-- | hw/ne2000.c | 3 | ||||
| -rw-r--r-- | hw/pci.c | 76 | ||||
| -rw-r--r-- | hw/pci.h | 4 | ||||
| -rw-r--r-- | hw/pci_bridge.c | 85 | ||||
| -rw-r--r-- | hw/pci_internals.h | 19 | ||||
| -rw-r--r-- | hw/pcnet-pci.c | 2 | ||||
| -rw-r--r-- | hw/qxl.c | 5 | ||||
| -rw-r--r-- | hw/rtl8139.c | 2 | ||||
| -rw-r--r-- | hw/scsi-bus.c | 22 | ||||
| -rw-r--r-- | hw/scsi-disk.c | 88 | ||||
| -rw-r--r-- | hw/scsi-generic.c | 6 | ||||
| -rw-r--r-- | hw/usb-ehci.c | 2 | ||||
| -rw-r--r-- | hw/usb-ohci.c | 3 | ||||
| -rw-r--r-- | hw/usb-uhci.c | 2 | ||||
| -rw-r--r-- | hw/virtio-blk.c | 5 | ||||
| -rw-r--r-- | hw/virtio.c | 4 | ||||
| -rw-r--r-- | hw/watchdog.c | 2 | ||||
| -rw-r--r-- | kvm-all.c | 2 | ||||
| -rw-r--r-- | linux-aio.c | 11 | ||||
| -rw-r--r-- | migration.c | 14 | ||||
| -rw-r--r-- | monitor.c | 22 | ||||
| -rw-r--r-- | nbd.c | 42 | ||||
| -rw-r--r-- | nbd.h | 20 | ||||
| -rw-r--r-- | posix-aio-compat.c | 38 | ||||
| -rw-r--r-- | qemu-nbd.c | 13 | ||||
| -rw-r--r-- | qemu-timer.c | 9 | ||||
| -rw-r--r-- | qerror.c | 4 | ||||
| -rw-r--r-- | qerror.h | 3 | ||||
| -rw-r--r-- | qmp-commands.hx | 19 | ||||
| -rw-r--r-- | savevm.c | 8 | ||||
| -rw-r--r-- | slirp/tcp_input.c | 1 | ||||
| -rw-r--r-- | sysemu.h | 42 | ||||
| -rw-r--r-- | target-i386/kvm.c | 4 | ||||
| -rw-r--r-- | ui/sdl.c | 6 | ||||
| -rw-r--r-- | ui/spice-display.c | 3 | ||||
| -rw-r--r-- | ui/spice-display.h | 4 | ||||
| -rw-r--r-- | vl.c | 156 | ||||
| -rw-r--r-- | xen-all.c | 12 |
62 files changed, 750 insertions, 417 deletions
diff --git a/audio/audio.c b/audio/audio.c index 5649075b01..50d0d7183f 100644 --- a/audio/audio.c +++ b/audio/audio.c @@ -1743,7 +1743,7 @@ static int audio_driver_init (AudioState *s, struct audio_driver *drv) } static void audio_vm_change_state_handler (void *opaque, int running, - int reason) + RunState state) { AudioState *s = opaque; HWVoiceOut *hwo = NULL; diff --git a/audio/wavaudio.c b/audio/wavaudio.c index aed18176ee..a449b5127e 100644 --- a/audio/wavaudio.c +++ b/audio/wavaudio.c @@ -30,7 +30,7 @@ typedef struct WAVVoiceOut { HWVoiceOut hw; - QEMUFile *f; + FILE *f; int64_t old_ticks; void *pcm_buf; int total_samples; @@ -76,7 +76,10 @@ static int wav_run_out (HWVoiceOut *hw, int live) dst = advance (wav->pcm_buf, rpos << hw->info.shift); hw->clip (dst, src, convert_samples); - qemu_put_buffer (wav->f, dst, convert_samples << hw->info.shift); + if (fwrite (dst, convert_samples << hw->info.shift, 1, wav->f) != 1) { + dolog ("wav_run_out: fwrite of %d bytes failed\nReaons: %s\n", + convert_samples << hw->info.shift, strerror (errno)); + } rpos = (rpos + convert_samples) % hw->samples; samples -= convert_samples; @@ -152,7 +155,7 @@ static int wav_init_out (HWVoiceOut *hw, struct audsettings *as) le_store (hdr + 28, hw->info.freq << (bits16 + stereo), 4); le_store (hdr + 32, 1 << (bits16 + stereo), 2); - wav->f = qemu_fopen (conf.wav_path, "wb"); + wav->f = fopen (conf.wav_path, "wb"); if (!wav->f) { dolog ("Failed to open wave file `%s'\nReason: %s\n", conf.wav_path, strerror (errno)); @@ -161,7 +164,11 @@ static int wav_init_out (HWVoiceOut *hw, struct audsettings *as) return -1; } - qemu_put_buffer (wav->f, hdr, sizeof (hdr)); + if (fwrite (hdr, sizeof (hdr), 1, wav->f) != 1) { + dolog ("wav_init_out: failed to write header\nReason: %s\n", + strerror(errno)); + return -1; + } return 0; } @@ -180,13 +187,32 @@ static void wav_fini_out (HWVoiceOut *hw) le_store (rlen, rifflen, 4); le_store (dlen, datalen, 4); - qemu_fseek (wav->f, 4, SEEK_SET); - qemu_put_buffer (wav->f, rlen, 4); - - qemu_fseek (wav->f, 32, SEEK_CUR); - qemu_put_buffer (wav->f, dlen, 4); + if (fseek (wav->f, 4, SEEK_SET)) { + dolog ("wav_fini_out: fseek to rlen failed\nReason: %s\n", + strerror(errno)); + goto doclose; + } + if (fwrite (rlen, 4, 1, wav->f) != 1) { + dolog ("wav_fini_out: failed to write rlen\nReason: %s\n", + strerror (errno)); + goto doclose; + } + if (fseek (wav->f, 32, SEEK_CUR)) { + dolog ("wav_fini_out: fseek to dlen failed\nReason: %s\n", + strerror (errno)); + goto doclose; + } + if (fwrite (dlen, 4, 1, wav->f) != 1) { + dolog ("wav_fini_out: failed to write dlen\nReaons: %s\n", + strerror (errno)); + goto doclose; + } - qemu_fclose (wav->f); + doclose: + if (fclose (wav->f)) { + dolog ("wav_fini_out: fclose %p failed\nReason: %s\n", + wav->f, strerror (errno)); + } wav->f = NULL; g_free (wav->pcm_buf); diff --git a/audio/wavcapture.c b/audio/wavcapture.c index c64f0ef075..4f785f5f49 100644 --- a/audio/wavcapture.c +++ b/audio/wavcapture.c @@ -3,7 +3,7 @@ #include "audio.h" typedef struct { - QEMUFile *f; + FILE *f; int bytes; char *path; int freq; @@ -35,17 +35,37 @@ static void wav_destroy (void *opaque) uint8_t dlen[4]; uint32_t datalen = wav->bytes; uint32_t rifflen = datalen + 36; + Monitor *mon = cur_mon; if (wav->f) { le_store (rlen, rifflen, 4); le_store (dlen, datalen, 4); - qemu_fseek (wav->f, 4, SEEK_SET); - qemu_put_buffer (wav->f, rlen, 4); - - qemu_fseek (wav->f, 32, SEEK_CUR); - qemu_put_buffer (wav->f, dlen, 4); - qemu_fclose (wav->f); + if (fseek (wav->f, 4, SEEK_SET)) { + monitor_printf (mon, "wav_destroy: rlen fseek failed\nReason: %s\n", + strerror (errno)); + goto doclose; + } + if (fwrite (rlen, 4, 1, wav->f) != 1) { + monitor_printf (mon, "wav_destroy: rlen fwrite failed\nReason %s\n", + strerror (errno)); + goto doclose; + } + if (fseek (wav->f, 32, SEEK_CUR)) { + monitor_printf (mon, "wav_destroy: dlen fseek failed\nReason %s\n", + strerror (errno)); + goto doclose; + } + if (fwrite (dlen, 1, 4, wav->f) != 4) { + monitor_printf (mon, "wav_destroy: dlen fwrite failed\nReason %s\n", + strerror (errno)); + goto doclose; + } + doclose: + if (fclose (wav->f)) { + fprintf (stderr, "wav_destroy: fclose failed: %s", + strerror (errno)); + } } g_free (wav->path); @@ -55,7 +75,10 @@ static void wav_capture (void *opaque, void *buf, int size) { WAVState *wav = opaque; - qemu_put_buffer (wav->f, buf, size); + if (fwrite (buf, size, 1, wav->f) != 1) { + monitor_printf (cur_mon, "wav_capture: fwrite error\nReason: %s", + strerror (errno)); + } wav->bytes += size; } @@ -71,9 +94,9 @@ static void wav_capture_info (void *opaque) WAVState *wav = opaque; char *path = wav->path; - monitor_printf(cur_mon, "Capturing audio(%d,%d,%d) to %s: %d bytes\n", - wav->freq, wav->bits, wav->nchannels, - path ? path : "<not available>", wav->bytes); + monitor_printf (cur_mon, "Capturing audio(%d,%d,%d) to %s: %d bytes\n", + wav->freq, wav->bits, wav->nchannels, + path ? path : "<not available>", wav->bytes); } static struct capture_ops wav_capture_ops = { @@ -98,13 +121,13 @@ int wav_start_capture (CaptureState *s, const char *path, int freq, CaptureVoiceOut *cap; if (bits != 8 && bits != 16) { - monitor_printf(mon, "incorrect bit count %d, must be 8 or 16\n", bits); + monitor_printf (mon, "incorrect bit count %d, must be 8 or 16\n", bits); return -1; } if (nchannels != 1 && nchannels != 2) { - monitor_printf(mon, "incorrect channel count %d, must be 1 or 2\n", - nchannels); + monitor_printf (mon, "incorrect channel count %d, must be 1 or 2\n", + nchannels); return -1; } @@ -130,10 +153,10 @@ int wav_start_capture (CaptureState *s, const char *path, int freq, le_store (hdr + 28, freq << shift, 4); le_store (hdr + 32, 1 << shift, 2); - wav->f = qemu_fopen (path, "wb"); + wav->f = fopen (path, "wb"); if (!wav->f) { - monitor_printf(mon, "Failed to open wave file `%s'\nReason: %s\n", - path, strerror (errno)); + monitor_printf (mon, "Failed to open wave file `%s'\nReason: %s\n", + path, strerror (errno)); g_free (wav); return -1; } @@ -143,19 +166,29 @@ int wav_start_capture (CaptureState *s, const char *path, int freq, wav->nchannels = nchannels; wav->freq = freq; - qemu_put_buffer (wav->f, hdr, sizeof (hdr)); + if (fwrite (hdr, sizeof (hdr), 1, wav->f) != 1) { + monitor_printf (mon, "Failed to write header\nReason: %s\n", + strerror (errno)); + goto error_free; + } cap = AUD_add_capture (&as, &ops, wav); if (!cap) { - monitor_printf(mon, "Failed to add audio capture\n"); - g_free (wav->path); - qemu_fclose (wav->f); - g_free (wav); - return -1; + monitor_printf (mon, "Failed to add audio capture\n"); + goto error_free; } wav->cap = cap; s->opaque = wav; s->ops = wav_capture_ops; return 0; + +error_free: + g_free (wav->path); + if (fclose (wav->f)) { + monitor_printf (mon, "Failed to close wave file\nReason: %s\n", + strerror (errno)); + } + g_free (wav); + return -1; } diff --git a/block/nbd.c b/block/nbd.c index 70edd81bd6..76f04d863c 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -48,6 +48,7 @@ typedef struct BDRVNBDState { int sock; + uint32_t nbdflags; off_t size; size_t blocksize; char *export_name; /* An NBD server may export several devices */ @@ -111,7 +112,6 @@ static int nbd_establish_connection(BlockDriverState *bs) int ret; off_t size; size_t blocksize; - uint32_t nbdflags; if (s->host_spec[0] == '/') { sock = unix_socket_outgoing(s->host_spec); @@ -126,7 +126,7 @@ static int nbd_establish_connection(BlockDriverState *bs) } /* NBD handshake */ - ret = nbd_receive_negotiate(sock, s->export_name, &nbdflags, &size, + ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size, &blocksize); if (ret == -1) { logout("Failed to negotiate with the NBD server\n"); diff --git a/block/raw-posix.c b/block/raw-posix.c index a624f56f86..305998ddb3 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -839,7 +839,14 @@ static int raw_create(const char *filename, QEMUOptionParameter *options) static int raw_flush(BlockDriverState *bs) { BDRVRawState *s = bs->opaque; - return qemu_fdatasync(s->fd); + int ret; + + ret = qemu_fdatasync(s->fd); + if (ret < 0) { + return -errno; + } + + return 0; } #ifdef CONFIG_XFS diff --git a/block/rbd.c b/block/rbd.c index 1b78d51398..3068c829fe 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -13,35 +13,33 @@ #include "qemu-common.h" #include "qemu-error.h" - #include "block_int.h" #include <rbd/librbd.h> - - /* * When specifying the image filename use: * * rbd:poolname/devicename[@snapshotname][:option1=value1[:option2=value2...]] * - * poolname must be the name of an existing rados pool + * poolname must be the name of an existing rados pool. * - * devicename is the basename for all objects used to - * emulate the raw device. + * devicename is the name of the rbd image. * - * Each option given is used to configure rados, and may be - * any Ceph option, or "conf". The "conf" option specifies - * a Ceph configuration file to read. + * Each option given is used to configure rados, and may be any valid + * Ceph option, "id", or "conf". * - * Metadata information (image size, ...) is stored in an - * object with the name "devicename.rbd". + * The "id" option indicates what user we should authenticate as to + * the Ceph cluster. If it is excluded we will use the Ceph default + * (normally 'admin'). * - * The raw device is split into 4MB sized objects by default. - * The sequencenumber is encoded in a 12 byte long hex-string, - * and is attached to the devicename, separated by a dot. - * e.g. "devicename.1234567890ab" + * The "conf" option specifies a Ceph configuration file to read. If + * it is not specified, we will read from the default Ceph locations + * (e.g., /etc/ceph/ceph.conf). To avoid reading _any_ configuration + * file, specify conf=/dev/null. * + * Configuration values containing :, @, or = can be escaped with a + * leading "\". */ #define OBJ_MAX_SIZE (1UL << OBJ_DEFAULT_OBJ_ORDER) @@ -104,8 +102,15 @@ static int qemu_rbd_next_tok(char *dst, int dst_len, *p = NULL; if (delim != '\0') { - end = strchr(src, delim); - if (end) { + for (end = src; *end; ++end) { + if (*end == delim) { + break; + } + if (*end == '\\' && end[1] != '\0') { + end++; + } + } + if (*end == delim) { *p = end + 1; *end = '\0'; } @@ -124,6 +129,19 @@ static int qemu_rbd_next_tok(char *dst, int dst_len, return 0; } +static void qemu_rbd_unescape(char *src) +{ + char *p; + + for (p = src; *src; ++src, ++p) { + if (*src == '\\' && src[1] != '\0') { + src++; + } + *p = *src; + } + *p = '\0'; +} + static int qemu_rbd_parsename(const char *filename, char *pool, int pool_len, char *snap, int snap_len, @@ -148,6 +166,7 @@ static int qemu_rbd_parsename(const char *filename, ret = -EINVAL; goto done; } + qemu_rbd_unescape(pool); if (strchr(p, '@')) { ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p); @@ -155,9 +174,11 @@ static int qemu_rbd_parsename(const char *filename, goto done; } ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p); + qemu_rbd_unescape(snap); } else { ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p); } + qemu_rbd_unescape(name); if (ret < 0 || !p) { goto done; } @@ -213,6 +234,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf) if (ret < 0) { break; } + qemu_rbd_unescape(name); if (!p) { error_report("conf option %s has no value", name); @@ -225,6 +247,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf) if (ret < 0) { break; } + qemu_rbd_unescape(value); if (strcmp(name, "conf") == 0) { ret = rados_conf_read_file(cluster, value); @@ -298,11 +321,8 @@ static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options) } if (strstr(conf, "conf=") == NULL) { - if (rados_conf_read_file(cluster, NULL) < 0) { - error_report("error reading config file"); - rados_shutdown(cluster); - return -EIO; - } + /* try default location, but ignore failure */ + rados_conf_read_file(cluster, NULL); } if (conf[0] != '\0' && @@ -441,11 +461,8 @@ static int qemu_rbd_open(BlockDriverState *bs, const char *filename, int flags) } if (strstr(conf, "conf=") == NULL) { - r = rados_conf_read_file(s->cluster, NULL); - if (r < 0) { - error_report("error reading config file"); - goto failed_shutdown; - } + /* try default location, but ignore failure */ + rados_conf_read_file(s->cluster, NULL); } if (conf[0] != '\0') { @@ -688,6 +705,17 @@ static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs, return rbd_aio_rw_vector(bs, sector_num, qiov, nb_sectors, cb, opaque, 1); } +static int qemu_rbd_flush(BlockDriverState *bs) +{ +#if LIBRBD_VERSION_CODE >= LIBRBD_VERSION(0, 1, 1) + /* rbd_flush added in 0.1.1 */ + BDRVRBDState *s = bs->opaque; + return rbd_flush(s->image); +#else + return 0; +#endif +} + static int qemu_rbd_getinfo(BlockDriverState *bs, BlockDriverInfo *bdi) { BDRVRBDState *s = bs->opaque; @@ -823,6 +851,7 @@ static BlockDriver bdrv_rbd = { .bdrv_file_open = qemu_rbd_open, .bdrv_close = qemu_rbd_close, .bdrv_create = qemu_rbd_create, + .bdrv_flush = qemu_rbd_flush, .bdrv_get_info = qemu_rbd_getinfo, .create_options = qemu_rbd_create_options, .bdrv_getlength = qemu_rbd_getlength, diff --git a/block/vmdk.c b/block/vmdk.c index 6c8edfc190..5d16ec49bc 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -179,11 +179,16 @@ static void vmdk_free_extents(BlockDriverState *bs) { int i; BDRVVmdkState *s = bs->opaque; + VmdkExtent *e; for (i = 0; i < s->num_extents; i++) { - g_free(s->extents[i].l1_table); - g_free(s->extents[i].l2_cache); - g_free(s->extents[i].l1_backup_table); + e = &s->extents[i]; + g_free(e->l1_table); + g_free(e->l2_cache); + g_free(e->l1_backup_table); + if (e->file != bs->file) { + bdrv_delete(e->file); + } } g_free(s->extents); } @@ -619,12 +624,13 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, s->desc_offset = 0; ret = vmdk_parse_extents(buf, bs, bs->file->filename); if (ret) { + vmdk_free_extents(bs); return ret; } /* try to open parent images, if exist */ if (vmdk_parent_open(bs)) { - g_free(s->extents); + vmdk_free_extents(bs); return -EINVAL; } s->parent_cid = vmdk_read_cid(bs, 1); @@ -855,6 +855,7 @@ if [ "$softmmu" = "yes" ] ; then default_target_list="\ i386-softmmu \ x86_64-softmmu \ +alpha-softmmu \ arm-softmmu \ cris-softmmu \ lm32-softmmu \ @@ -115,16 +115,16 @@ void cpu_synchronize_all_post_init(void) int cpu_is_stopped(CPUState *env) { - return !vm_running || env->stopped; + return !runstate_is_running() || env->stopped; } -static void do_vm_stop(int reason) +static void do_vm_stop(RunState state) { - if (vm_running) { + if (runstate_is_running()) { cpu_disable_ticks(); - vm_running = 0; pause_all_vcpus(); - vm_state_notify(0, reason); + runstate_set(state); + vm_state_notify(0, state); qemu_aio_flush(); bdrv_flush_all(); monitor_protocol_event(QEVENT_STOP, NULL); @@ -136,7 +136,7 @@ static int cpu_can_run(CPUState *env) if (env->stop) { return 0; } - if (env->stopped || !vm_running) { + if (env->stopped || !runstate_is_running()) { return 0; } return 1; @@ -147,7 +147,7 @@ static bool cpu_thread_is_idle(CPUState *env) if (env->stop || env->queued_work_first) { return false; } - if (env->stopped || !vm_running) { + if (env->stopped || !runstate_is_running()) { return true; } if (!env->halted || qemu_cpu_has_work(env) || @@ -380,11 +380,6 @@ static int qemu_signal_init(void) int sigfd; sigset_t set; - /* SIGUSR2 used by posix-aio-compat.c */ - sigemptyset(&set); - sigaddset(&set, SIGUSR2); - pthread_sigmask(SIG_UNBLOCK, &set, NULL); - /* * SIG_IPI must be blocked in the main thread and must not be caught * by sigwait() in the signal thread. Otherwise, the cpu thread will @@ -878,10 +873,10 @@ void cpu_stop_current(void) } } -void vm_stop(int reason) +void vm_stop(RunState state) { if (!qemu_thread_is_self(&io_thread)) { - qemu_system_vmstop_request(reason); + qemu_system_vmstop_request(state); /* * FIXME: should not return to device code in case * vm_stop() has been requested. @@ -889,7 +884,7 @@ void vm_stop(int reason) cpu_stop_current(); return; } - do_vm_stop(reason); + do_vm_stop(state); } static int tcg_cpu_exec(CPUState *env) @@ -15,7 +15,6 @@ void cpu_synchronize_all_post_init(void); /* vl.c */ extern int smp_cores; extern int smp_threads; -void vm_state_notify(int running, int reason); bool cpu_exec_all(void); void set_numa_modes(void); void set_cpu_log(const char *optarg); diff --git a/dma-helpers.c b/dma-helpers.c index 4610ea0420..86d2d0a997 100644 --- a/dma-helpers.c +++ b/dma-helpers.c @@ -42,7 +42,8 @@ typedef struct { BlockDriverAIOCB *acb; QEMUSGList *sg; uint64_t sector_num; - int is_write; + bool to_dev; + bool in_cancel; int sg_cur_index; target_phys_addr_t sg_cur_byte; QEMUIOVector iov; @@ -58,7 +59,7 @@ static void reschedule_dma(void *opaque) qemu_bh_delete(dbs->bh); dbs->bh = NULL; - dma_bdrv_cb(opaque, 0); + dma_bdrv_cb(dbs, 0); } static void continue_after_map_failure(void *opaque) @@ -75,9 +76,29 @@ static void dma_bdrv_unmap(DMAAIOCB *dbs) for (i = 0; i < dbs->iov.niov; ++i) { cpu_physical_memory_unmap(dbs->iov.iov[i].iov_base, - dbs->iov.iov[i].iov_len, !dbs->is_write, + dbs->iov.iov[i].iov_len, !dbs->to_dev, dbs->iov.iov[i].iov_len); } + qemu_iovec_reset(&dbs->iov); +} + +static void dma_complete(DMAAIOCB *dbs, int ret) +{ + dma_bdrv_unmap(dbs); + if (dbs->common.cb) { + dbs->common.cb(dbs->common.opaque, ret); + } + qemu_iovec_destroy(&dbs->iov); + if (dbs->bh) { + qemu_bh_delete(dbs->bh); + dbs->bh = NULL; + } + if (!dbs->in_cancel) { + /* Requests may complete while dma_aio_cancel is in progress. In + * this case, the AIOCB should not be released because it is still + * referenced by dma_aio_cancel. */ + qemu_aio_release(dbs); + } } static void dma_bdrv_cb(void *opaque, int ret) @@ -89,19 +110,16 @@ static void dma_bdrv_cb(void *opaque, int ret) dbs->acb = NULL; dbs->sector_num += dbs->iov.size / 512; dma_bdrv_unmap(dbs); - qemu_iovec_reset(&dbs->iov); if (dbs->sg_cur_index == dbs->sg->nsg || ret < 0) { - dbs->common.cb(dbs->common.opaque, ret); - qemu_iovec_destroy(&dbs->iov); - qemu_aio_release(dbs); + dma_complete(dbs, ret); return; } while (dbs->sg_cur_index < dbs->sg->nsg) { cur_addr = dbs->sg->sg[dbs->sg_cur_index].base + dbs->sg_cur_byte; cur_len = dbs->sg->sg[dbs->sg_cur_index].len - dbs->sg_cur_byte; - mem = cpu_physical_memory_map(cur_addr, &cur_len, !dbs->is_write); + mem = cpu_physical_memory_map(cur_addr, &cur_len, !dbs->to_dev); if (!mem) break; qemu_iovec_add(&dbs->iov, mem, cur_len); @@ -120,9 +138,7 @@ static void dma_bdrv_cb(void *opaque, int ret) dbs->acb = dbs->io_func(dbs->bs, dbs->sector_num, &dbs->iov, dbs->iov.size / 512, dma_bdrv_cb, dbs); if (!dbs->acb) { - dma_bdrv_unmap(dbs); - qemu_iovec_destroy(&dbs->iov); - return; + dma_complete(dbs, -EIO); } } @@ -131,8 +147,14 @@ static void dma_aio_cancel(BlockDriverAIOCB *acb) DMAAIOCB *dbs = container_of(acb, DMAAIOCB, common); if (dbs->acb) { - bdrv_aio_cancel(dbs->acb); + BlockDriverAIOCB *acb = dbs->acb; + dbs->acb = NULL; + dbs->in_cancel = true; + bdrv_aio_cancel(acb); + dbs->in_cancel = false; } + dbs->common.cb = NULL; + dma_complete(dbs, 0); } static AIOPool dma_aio_pool = { @@ -143,7 +165,7 @@ static AIOPool dma_aio_pool = { BlockDriverAIOCB *dma_bdrv_io( BlockDriverState *bs, QEMUSGList *sg, uint64_t sector_num, DMAIOFunc *io_func, BlockDriverCompletionFunc *cb, - void *opaque, int is_write) + void *opaque, bool to_dev) { DMAAIOCB *dbs = qemu_aio_get(&dma_aio_pool, bs, cb, opaque); @@ -153,15 +175,11 @@ BlockDriverAIOCB *dma_bdrv_io( dbs->sector_num = sector_num; dbs->sg_cur_index = 0; dbs->sg_cur_byte = 0; - dbs->is_write = is_write; + dbs->to_dev = to_dev; dbs->io_func = io_func; dbs->bh = NULL; qemu_iovec_init(&dbs->iov, sg->nsg); dma_bdrv_cb(dbs, 0); - if (!dbs->acb) { - qemu_aio_release(dbs); - return NULL; - } return &dbs->common; } @@ -170,12 +188,12 @@ BlockDriverAIOCB *dma_bdrv_read(BlockDriverState *bs, QEMUSGList *sg, uint64_t sector, void (*cb)(void *opaque, int ret), void *opaque) { - return dma_bdrv_io(bs, sg, sector, bdrv_aio_readv, cb, opaque, 0); + return dma_bdrv_io(bs, sg, sector, bdrv_aio_readv, cb, opaque, false); } BlockDriverAIOCB *dma_bdrv_write(BlockDriverState *bs, QEMUSGList *sg, uint64_t sector, void (*cb)(void *opaque, int ret), void *opaque) { - return dma_bdrv_io(bs, sg, sector, bdrv_aio_writev, cb, opaque, 1); + return dma_bdrv_io(bs, sg, sector, bdrv_aio_writev, cb, opaque, true); } @@ -15,10 +15,13 @@ #include "hw/hw.h" #include "block.h" -typedef struct { +typedef struct ScatterGatherEntry ScatterGatherEntry; + +#if defined(TARGET_PHYS_ADDR_BITS) +struct ScatterGatherEntry { target_phys_addr_t base; target_phys_addr_t len; -} ScatterGatherEntry; +}; struct QEMUSGList { ScatterGatherEntry *sg; @@ -31,6 +34,7 @@ void qemu_sglist_init(QEMUSGList *qsg, int alloc_hint); void qemu_sglist_add(QEMUSGList *qsg, target_phys_addr_t base, target_phys_addr_t len); void qemu_sglist_destroy(QEMUSGList *qsg); +#endif typedef BlockDriverAIOCB *DMAIOFunc(BlockDriverState *bs, int64_t sector_num, QEMUIOVector *iov, int nb_sectors, @@ -39,7 +43,7 @@ typedef BlockDriverAIOCB *DMAIOFunc(BlockDriverState *bs, int64_t sector_num, BlockDriverAIOCB *dma_bdrv_io(BlockDriverState *bs, QEMUSGList *sg, uint64_t sector_num, DMAIOFunc *io_func, BlockDriverCompletionFunc *cb, - void *opaque, int is_write); + void *opaque, bool to_dev); BlockDriverAIOCB *dma_bdrv_read(BlockDriverState *bs, QEMUSGList *sg, uint64_t sector, BlockDriverCompletionFunc *cb, void *opaque); @@ -2373,7 +2373,7 @@ void gdb_set_stop_cpu(CPUState *env) } #ifndef CONFIG_USER_ONLY -static void gdb_vm_state_change(void *opaque, int running, int reason) +static void gdb_vm_state_change(void *opaque, int running, RunState state) { GDBState *s = gdbserver_state; CPUState *env = s->c_cpu; @@ -2384,8 +2384,8 @@ static void gdb_vm_state_change(void *opaque, int running, int reason) if (running || s->state == RS_INACTIVE || s->state == RS_SYSCALL) { return; } - switch (reason) { - case VMSTOP_DEBUG: + switch (state) { + case RSTATE_DEBUG: if (env->watchpoint_hit) { switch (env->watchpoint_hit->flags & BP_MEM_ACCESS) { case BP_MEM_READ: @@ -2408,25 +2408,25 @@ static void gdb_vm_state_change(void *opaque, int running, int reason) tb_flush(env); ret = GDB_SIGNAL_TRAP; break; - case VMSTOP_USER: + case RSTATE_PAUSED: ret = GDB_SIGNAL_INT; break; - case VMSTOP_SHUTDOWN: + case RSTATE_SHUTDOWN: ret = GDB_SIGNAL_QUIT; break; - case VMSTOP_DISKFULL: + case RSTATE_IO_ERROR: ret = GDB_SIGNAL_IO; break; - case VMSTOP_WATCHDOG: + case RSTATE_WATCHDOG: ret = GDB_SIGNAL_ALRM; break; - case VMSTOP_PANIC: + case RSTATE_PANICKED: ret = GDB_SIGNAL_ABRT; break; - case VMSTOP_SAVEVM: - case VMSTOP_LOADVM: + case RSTATE_SAVEVM: + case RSTATE_RESTORE: return; - case VMSTOP_MIGRATE: + case RSTATE_PRE_MIGRATE: ret = GDB_SIGNAL_XCPU; break; default: @@ -2463,7 +2463,7 @@ void gdb_do_syscall(gdb_syscall_complete_cb cb, const char *fmt, ...) gdb_current_syscall_cb = cb; s->state = RS_SYSCALL; #ifndef CONFIG_USER_ONLY - vm_stop(VMSTOP_DEBUG); + vm_stop(RSTATE_DEBUG); #endif s->state = RS_IDLE; va_start(va, fmt); @@ -2534,10 +2534,10 @@ static void gdb_read_byte(GDBState *s, int ch) if (ch != '$') return; } - if (vm_running) { + if (runstate_is_running()) { /* when the CPU is running, we cannot do anything except stop it when receiving a char */ - vm_stop(VMSTOP_USER); + vm_stop(RSTATE_PAUSED); } else #endif { @@ -2799,7 +2799,7 @@ static void gdb_chr_event(void *opaque, int event) { switch (event) { case CHR_EVENT_OPENED: - vm_stop(VMSTOP_USER); + vm_stop(RSTATE_PAUSED); gdb_has_xml = 0; break; default: @@ -2839,8 +2839,8 @@ static int gdb_monitor_write(CharDriverState *chr, const uint8_t *buf, int len) #ifndef _WIN32 static void gdb_sigterm_handler(int signal) { - if (vm_running) { - vm_stop(VMSTOP_USER); + if (runstate_is_running()) { + vm_stop(RSTATE_PAUSED); } } #endif @@ -1311,7 +1311,6 @@ static int ac97_initfn (PCIDevice *dev) c[PCI_SUBSYSTEM_ID + 1] = 0x00; c[PCI_INTERRUPT_LINE] = 0x00; /* intr_ln interrupt line rw */ - /* TODO: RST# value should be 0. */ c[PCI_INTERRUPT_PIN] = 0x01; /* intr_pn interrupt pin ro */ memory_region_init_io (&s->io_nam, &ac97_io_nam_ops, s, "ac97-nam", 1024); diff --git a/hw/e1000.c b/hw/e1000.c index a6d12c55fb..6a3a941488 100644 --- a/hw/e1000.c +++ b/hw/e1000.c @@ -1156,8 +1156,7 @@ static int pci_e1000_init(PCIDevice *pci_dev) /* TODO: RST# value should be 0, PCI spec 6.2.4 */ pci_conf[PCI_CACHE_LINE_SIZE] = 0x10; - /* TODO: RST# value should be 0 if programmable, PCI spec 6.2.4 */ - pci_conf[PCI_INTERRUPT_PIN] = 1; // interrupt pin 0 + pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */ e1000_mmio_setup(d); diff --git a/hw/es1370.c b/hw/es1370.c index a9387d15cc..2daadde0e6 100644 --- a/hw/es1370.c +++ b/hw/es1370.c @@ -1003,7 +1003,6 @@ static int es1370_initfn (PCIDevice *dev) c[0xdc] = 0x00; #endif - /* TODO: RST# value should be 0. */ c[PCI_INTERRUPT_PIN] = 1; c[PCI_MIN_GNT] = 0x0c; c[PCI_MAX_LAT] = 0x80; diff --git a/hw/etraxfs_dma.c b/hw/etraxfs_dma.c index e8ad9e6a0b..d3082acc8f 100644 --- a/hw/etraxfs_dma.c +++ b/hw/etraxfs_dma.c @@ -732,7 +732,7 @@ static void DMA_run(void *opaque) struct fs_dma_ctrl *etraxfs_dmac = opaque; int p = 1; - if (vm_running) + if (runstate_is_running()) p = etraxfs_dmac_run(etraxfs_dmac); if (p) diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c index a8659cf8b9..226230ca2b 100644 --- a/hw/ide/ahci.c +++ b/hw/ide/ahci.c @@ -499,10 +499,7 @@ static void ahci_reset_port(AHCIState *s, int port) ide_bus_reset(&d->port); ide_state->ncq_queues = AHCI_MAX_CMDS; - pr->irq_stat = 0; - pr->irq_mask = 0; pr->scr_stat = 0; - pr->scr_ctl = 0; pr->scr_err = 0; pr->scr_act = 0; d->busy_slot = -1; @@ -1103,7 +1100,7 @@ static void ahci_irq_set(void *opaque, int n, int level) { } -static void ahci_dma_restart_cb(void *opaque, int running, int reason) +static void ahci_dma_restart_cb(void *opaque, int running, RunState state) { } @@ -1159,12 +1156,17 @@ void ahci_uninit(AHCIState *s) void ahci_reset(void *opaque) { struct AHCIPCIState *d = opaque; + AHCIPortRegs *pr; int i; d->ahci.control_regs.irqstatus = 0; d->ahci.control_regs.ghc = 0; for (i = 0; i < d->ahci.ports; i++) { + pr = &d->ahci.dev[i].port_regs; + pr->irq_stat = 0; + pr->irq_mask = 0; + pr->scr_ctl = 0; ahci_reset_port(&d->ahci, i); } } diff --git a/hw/ide/core.c b/hw/ide/core.c index 9297b9e657..4e76fc78d3 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -527,7 +527,7 @@ static int ide_handle_rw_error(IDEState *s, int error, int op) s->bus->dma->ops->set_unit(s->bus->dma, s->unit); s->bus->error_status = op; bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read); - vm_stop(VMSTOP_DISKFULL); + vm_stop(RSTATE_IO_ERROR); } else { if (op & BM_STATUS_DMA_RETRY) { dma_buf_commit(s, 0); @@ -603,7 +603,7 @@ handle_rw_error: break; case IDE_DMA_TRIM: s->bus->dma->aiocb = dma_bdrv_io(s->bs, &s->sg, sector_num, - ide_issue_trim, ide_dma_cb, s, 1); + ide_issue_trim, ide_dma_cb, s, true); break; } @@ -1910,7 +1910,7 @@ static int ide_nop_int(IDEDMA *dma, int x) return 0; } -static void ide_nop_restart(void *opaque, int x, int y) +static void ide_nop_restart(void *opaque, int x, RunState y) { } diff --git a/hw/ide/internal.h b/hw/ide/internal.h index 233915ce0d..9046e96013 100644 --- a/hw/ide/internal.h +++ b/hw/ide/internal.h @@ -9,6 +9,7 @@ #include <hw/ide.h> #include "iorange.h" #include "dma.h" +#include "sysemu.h" /* debug IDE devices */ //#define DEBUG_IDE @@ -387,7 +388,7 @@ typedef void EndTransferFunc(IDEState *); typedef void DMAStartFunc(IDEDMA *, IDEState *, BlockDriverCompletionFunc *); typedef int DMAFunc(IDEDMA *); typedef int DMAIntFunc(IDEDMA *, int); -typedef void DMARestartFunc(void *, int, int); +typedef void DMARestartFunc(void *, int, RunState); struct unreported_events { bool eject_request; diff --git a/hw/ide/macio.c b/hw/ide/macio.c index c1844cb738..37b8239b4d 100644 --- a/hw/ide/macio.c +++ b/hw/ide/macio.c @@ -156,7 +156,7 @@ static void pmac_ide_transfer_cb(void *opaque, int ret) break; case IDE_DMA_TRIM: m->aiocb = dma_bdrv_io(s->bs, &s->sg, sector_num, - ide_issue_trim, pmac_ide_transfer_cb, s, 1); + ide_issue_trim, pmac_ide_transfer_cb, s, true); break; } diff --git a/hw/ide/pci.c b/hw/ide/pci.c index 9fded02954..f133c422b6 100644 --- a/hw/ide/pci.c +++ b/hw/ide/pci.c @@ -222,7 +222,7 @@ static void bmdma_restart_bh(void *opaque) } } -static void bmdma_restart_cb(void *opaque, int running, int reason) +static void bmdma_restart_cb(void *opaque, int running, RunState state) { IDEDMA *dma = opaque; BMDMAState *bm = DO_UPCAST(BMDMAState, dma, dma); diff --git a/hw/kvmclock.c b/hw/kvmclock.c index b73aec409c..5388bc489d 100644 --- a/hw/kvmclock.c +++ b/hw/kvmclock.c @@ -46,7 +46,7 @@ static void kvmclock_pre_save(void *opaque) * it on next vmsave (which would return a different value). Will be reset * when the VM is continued. */ - s->clock_valid = !vm_running; + s->clock_valid = !runstate_is_running(); } static int kvmclock_post_load(void *opaque, int version_id) @@ -59,7 +59,8 @@ static int kvmclock_post_load(void *opaque, int version_id) return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data); } -static void kvmclock_vm_state_change(void *opaque, int running, int reason) +static void kvmclock_vm_state_change(void *opaque, int running, + RunState state) { KVMClockState *s = opaque; diff --git a/hw/lsi53c895a.c b/hw/lsi53c895a.c index dbb3bdf2ce..75a03a74b9 100644 --- a/hw/lsi53c895a.c +++ b/hw/lsi53c895a.c @@ -2106,8 +2106,7 @@ static int lsi_scsi_init(PCIDevice *dev) /* PCI latency timer = 255 */ pci_conf[PCI_LATENCY_TIMER] = 0xff; - /* TODO: RST# value should be 0 */ - /* Interrupt pin 1 */ + /* Interrupt pin A */ pci_conf[PCI_INTERRUPT_PIN] = 0x01; memory_region_init_io(&s->mmio_io, &lsi_mmio_ops, s, "lsi-mmio", 0x400); diff --git a/hw/ne2000.c b/hw/ne2000.c index a035a85244..62e082f8a9 100644 --- a/hw/ne2000.c +++ b/hw/ne2000.c @@ -749,8 +749,7 @@ static int pci_ne2000_init(PCIDevice *pci_dev) uint8_t *pci_conf; pci_conf = d->dev.config; - /* TODO: RST# value should be 0. PCI spec 6.2.4 */ - pci_conf[PCI_INTERRUPT_PIN] = 1; // interrupt pin 0 + pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */ s = &d->ne2000; ne2000_setup_io(s, 0x100); @@ -878,7 +878,6 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, r = &pci_dev->io_regions[region_num]; r->addr = PCI_BAR_UNMAPPED; r->size = size; - r->filtered_size = size; r->type = type; r->memory = NULL; @@ -909,41 +908,6 @@ pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num) return pci_dev->io_regions[region_num].addr; } -static void pci_bridge_filter(PCIDevice *d, pcibus_t *addr, pcibus_t *size, - uint8_t type) -{ - pcibus_t base = *addr; - pcibus_t limit = *addr + *size - 1; - PCIDevice *br; - - for (br = d->bus->parent_dev; br; br = br->bus->parent_dev) { - uint16_t cmd = pci_get_word(d->config + PCI_COMMAND); - - if (type & PCI_BASE_ADDRESS_SPACE_IO) { - if (!(cmd & PCI_COMMAND_IO)) { - goto no_map; - } - } else { - if (!(cmd & PCI_COMMAND_MEMORY)) { - goto no_map; - } - } - - base = MAX(base, pci_bridge_get_base(br, type)); - limit = MIN(limit, pci_bridge_get_limit(br, type)); - } - - if (base > limit) { - goto no_map; - } - *addr = base; - *size = limit - base + 1; - return; -no_map: - *addr = PCI_BAR_UNMAPPED; - *size = 0; -} - static pcibus_t pci_bar_address(PCIDevice *d, int reg, uint8_t type, pcibus_t size) { @@ -1013,7 +977,7 @@ static void pci_update_mappings(PCIDevice *d) { PCIIORegion *r; int i; - pcibus_t new_addr, filtered_size; + pcibus_t new_addr; for(i = 0; i < PCI_NUM_REGIONS; i++) { r = &d->io_regions[i]; @@ -1024,14 +988,8 @@ static void pci_update_mappings(PCIDevice *d) new_addr = pci_bar_address(d, i, r->type, r->size); - /* bridge filtering */ - filtered_size = r->size; - if (new_addr != PCI_BAR_UNMAPPED) { - pci_bridge_filter(d, &new_addr, &filtered_size, r->type); - } - /* This bar isn't changed */ - if (new_addr == r->addr && filtered_size == r->filtered_size) + if (new_addr == r->addr) continue; /* now do the real mapping */ @@ -1039,15 +997,7 @@ static void pci_update_mappings(PCIDevice *d) memory_region_del_subregion(r->address_space, r->memory); } r->addr = new_addr; - r->filtered_size = filtered_size; if (r->addr != PCI_BAR_UNMAPPED) { - /* - * TODO: currently almost all the map funcions assumes - * filtered_size == size and addr & ~(size - 1) == addr. - * However with bridge filtering, they aren't always true. - * Teach them such cases, such that filtered_size < size and - * addr & (size - 1) != 0. - */ if (r->type & PCI_BASE_ADDRESS_SPACE_IO) { memory_region_add_subregion_overlap(r->address_space, r->addr, @@ -1564,22 +1514,6 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, const char *default_model, return res; } -static void pci_bridge_update_mappings_fn(PCIBus *b, PCIDevice *d) -{ - pci_update_mappings(d); -} - -void pci_bridge_update_mappings(PCIBus *b) -{ - PCIBus *child; - - pci_for_each_device_under_bus(b, pci_bridge_update_mappings_fn); - - QLIST_FOREACH(child, &b->child, sibling) { - pci_bridge_update_mappings(child); - } -} - /* Whether a given bus number is in range of the secondary * bus of the given bridge device. */ static bool pci_secondary_bus_in_range(PCIDevice *dev, int bus_num) @@ -2016,12 +1950,6 @@ void pci_del_capability(PCIDevice *pdev, uint8_t cap_id, uint8_t size) pdev->config[PCI_STATUS] &= ~PCI_STATUS_CAP_LIST; } -/* Reserve space for capability at a known offset (to call after load). */ -void pci_reserve_capability(PCIDevice *pdev, uint8_t offset, uint8_t size) -{ - memset(pdev->used + offset, 0xff, size); -} - uint8_t pci_find_capability(PCIDevice *pdev, uint8_t cap_id) { return pci_find_capability_list(pdev, cap_id, NULL); @@ -90,7 +90,6 @@ typedef struct PCIIORegion { pcibus_t addr; /* current PCI mapping address. -1 means not mapped */ #define PCI_BAR_UNMAPPED (~(pcibus_t)0) pcibus_t size; - pcibus_t filtered_size; uint8_t type; MemoryRegion *memory; MemoryRegion *address_space; @@ -209,8 +208,6 @@ int pci_add_capability(PCIDevice *pdev, uint8_t cap_id, void pci_del_capability(PCIDevice *pci_dev, uint8_t cap_id, uint8_t cap_size); -void pci_reserve_capability(PCIDevice *pci_dev, uint8_t offset, uint8_t size); - uint8_t pci_find_capability(PCIDevice *pci_dev, uint8_t cap_id); @@ -275,7 +272,6 @@ int pci_read_devaddr(Monitor *mon, const char *addr, int *domp, int *busp, void do_pci_info_print(Monitor *mon, const QObject *data); void do_pci_info(Monitor *mon, QObject **ret_data); -void pci_bridge_update_mappings(PCIBus *b); void pci_device_deassert_intx(PCIDevice *dev); diff --git a/hw/pci_bridge.c b/hw/pci_bridge.c index 464d89708f..b6287cdc6d 100644 --- a/hw/pci_bridge.c +++ b/hw/pci_bridge.c @@ -135,6 +135,76 @@ pcibus_t pci_bridge_get_limit(const PCIDevice *bridge, uint8_t type) return limit; } +static void pci_bridge_init_alias(PCIBridge *bridge, MemoryRegion *alias, + uint8_t type, const char *name, + MemoryRegion *space, + MemoryRegion *parent_space, + bool enabled) +{ + pcibus_t base = pci_bridge_get_base(&bridge->dev, type); + pcibus_t limit = pci_bridge_get_limit(&bridge->dev, type); + /* TODO: this doesn't handle base = 0 limit = 2^64 - 1 correctly. + * Apparently no way to do this with existing memory APIs. */ + pcibus_t size = enabled && limit >= base ? limit + 1 - base : 0; + + memory_region_init_alias(alias, name, space, base, size); + memory_region_add_subregion_overlap(parent_space, base, alias, 1); +} + +static void pci_bridge_cleanup_alias(MemoryRegion *alias, + MemoryRegion *parent_space) +{ + memory_region_del_subregion(parent_space, alias); + memory_region_destroy(alias); +} + +static void pci_bridge_region_init(PCIBridge *br) +{ + PCIBus *parent = br->dev.bus; + uint16_t cmd = pci_get_word(br->dev.config + PCI_COMMAND); + + pci_bridge_init_alias(br, &br->alias_pref_mem, + PCI_BASE_ADDRESS_MEM_PREFETCH, + "pci_bridge_pref_mem", + &br->address_space_mem, + parent->address_space_mem, + cmd & PCI_COMMAND_MEMORY); + pci_bridge_init_alias(br, &br->alias_mem, + PCI_BASE_ADDRESS_SPACE_MEMORY, + "pci_bridge_mem", + &br->address_space_mem, + parent->address_space_mem, + cmd & PCI_COMMAND_MEMORY); + pci_bridge_init_alias(br, &br->alias_io, + PCI_BASE_ADDRESS_SPACE_IO, + "pci_bridge_io", + &br->address_space_io, + parent->address_space_io, + cmd & PCI_COMMAND_IO); + /* TODO: optinal VGA and VGA palette snooping support. */ +} + +static void pci_bridge_region_cleanup(PCIBridge *br) +{ + PCIBus *parent = br->dev.bus; + pci_bridge_cleanup_alias(&br->alias_io, + parent->address_space_io); + pci_bridge_cleanup_alias(&br->alias_mem, + parent->address_space_mem); + pci_bridge_cleanup_alias(&br->alias_pref_mem, + parent->address_space_mem); +} + +static void pci_bridge_update_mappings(PCIBridge *br) +{ + /* Make updates atomic to: handle the case of one VCPU updating the bridge + * while another accesses an unaffected region. */ + memory_region_transaction_begin(); + pci_bridge_region_cleanup(br); + pci_bridge_region_init(br); + memory_region_transaction_commit(); +} + /* default write_config function for PCI-to-PCI bridge */ void pci_bridge_write_config(PCIDevice *d, uint32_t address, uint32_t val, int len) @@ -145,13 +215,15 @@ void pci_bridge_write_config(PCIDevice *d, pci_default_write_config(d, address, val, len); - if (/* io base/limit */ + if (ranges_overlap(address, len, PCI_COMMAND, 2) || + + /* io base/limit */ ranges_overlap(address, len, PCI_IO_BASE, 2) || /* memory base/limit, prefetchable base/limit and io base/limit upper 16 */ ranges_overlap(address, len, PCI_MEMORY_BASE, 20)) { - pci_bridge_update_mappings(&s->sec_bus); + pci_bridge_update_mappings(s); } newctl = pci_get_word(d->config + PCI_BRIDGE_CONTROL); @@ -246,7 +318,11 @@ int pci_bridge_initfn(PCIDevice *dev) br->bus_name); sec_bus->parent_dev = dev; sec_bus->map_irq = br->map_irq; - + sec_bus->address_space_mem = &br->address_space_mem; + memory_region_init(&br->address_space_mem, "pci_pridge_pci", INT64_MAX); + sec_bus->address_space_io = &br->address_space_io; + memory_region_init(&br->address_space_io, "pci_bridge_io", 65536); + pci_bridge_region_init(br); QLIST_INIT(&sec_bus->child); QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling); return 0; @@ -258,6 +334,9 @@ int pci_bridge_exitfn(PCIDevice *pci_dev) PCIBridge *s = DO_UPCAST(PCIBridge, dev, pci_dev); assert(QLIST_EMPTY(&s->sec_bus.child)); QLIST_REMOVE(&s->sec_bus, sibling); + pci_bridge_region_cleanup(s); + memory_region_destroy(&s->address_space_mem); + memory_region_destroy(&s->address_space_io); /* qbus_free() is called automatically by qdev_free() */ return 0; } diff --git a/hw/pci_internals.h b/hw/pci_internals.h index c7fd23dc54..96690b72d3 100644 --- a/hw/pci_internals.h +++ b/hw/pci_internals.h @@ -24,7 +24,6 @@ struct PCIBus { void *irq_opaque; PCIDevice *devices[PCI_SLOT_MAX * PCI_FUNC_MAX]; PCIDevice *parent_dev; - target_phys_addr_t mem_base; MemoryRegion *address_space_mem; MemoryRegion *address_space_io; @@ -42,6 +41,24 @@ struct PCIBridge { /* private member */ PCIBus sec_bus; + /* + * Memory regions for the bridge's address spaces. These regions are not + * directly added to system_memory/system_io or its descendants. + * Bridge's secondary bus points to these, so that devices + * under the bridge see these regions as its address spaces. + * The regions are as large as the entire address space - + * they don't take into account any windows. + */ + MemoryRegion address_space_mem; + MemoryRegion address_space_io; + /* + * Aliases for each of the address space windows that the bridge + * can forward. Mapped into the bridge's parent's address space, + * as subregions. + */ + MemoryRegion alias_pref_mem; + MemoryRegion alias_mem; + MemoryRegion alias_io; pci_map_irq_fn map_irq; const char *bus_name; }; diff --git a/hw/pcnet-pci.c b/hw/pcnet-pci.c index 51e132050f..fb2a00caad 100644 --- a/hw/pcnet-pci.c +++ b/hw/pcnet-pci.c @@ -285,7 +285,7 @@ static int pci_pcnet_init(PCIDevice *pci_dev) pci_set_word(pci_conf + PCI_SUBSYSTEM_VENDOR_ID, 0x0); pci_set_word(pci_conf + PCI_SUBSYSTEM_ID, 0x0); - pci_conf[PCI_INTERRUPT_PIN] = 1; // interrupt pin 0 + pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */ pci_conf[PCI_MIN_GNT] = 0x06; pci_conf[PCI_MAX_LAT] = 0xff; @@ -1453,10 +1453,11 @@ static void qxl_hw_text_update(void *opaque, console_ch_t *chardata) } } -static void qxl_vm_change_state_handler(void *opaque, int running, int reason) +static void qxl_vm_change_state_handler(void *opaque, int running, + RunState state) { PCIQXLDevice *qxl = opaque; - qemu_spice_vm_change_state_handler(&qxl->ssd, running, reason); + qemu_spice_vm_change_state_handler(&qxl->ssd, running, state); if (running) { /* diff --git a/hw/rtl8139.c b/hw/rtl8139.c index c5de5b48ba..37539508c5 100644 --- a/hw/rtl8139.c +++ b/hw/rtl8139.c @@ -3464,7 +3464,7 @@ static int pci_rtl8139_init(PCIDevice *dev) uint8_t *pci_conf; pci_conf = s->dev.config; - pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin 0 */ + pci_conf[PCI_INTERRUPT_PIN] = 1; /* interrupt pin A */ /* TODO: start of capability list, but no capability * list bit in status register, and offset 0xdc seems unused. */ pci_conf[PCI_CAPABILITY_LIST] = 0xdc; diff --git a/hw/scsi-bus.c b/hw/scsi-bus.c index 02482947ca..aca65a16df 100644 --- a/hw/scsi-bus.c +++ b/hw/scsi-bus.c @@ -542,15 +542,15 @@ static int scsi_req_length(SCSICommand *cmd, SCSIDevice *dev, uint8_t *buf) break; case 1: case 2: - cmd->xfer = buf[8] | (buf[7] << 8); + cmd->xfer = lduw_be_p(&buf[7]); cmd->len = 10; break; case 4: - cmd->xfer = buf[13] | (buf[12] << 8) | (buf[11] << 16) | (buf[10] << 24); + cmd->xfer = ldl_be_p(&buf[10]); cmd->len = 16; break; case 5: - cmd->xfer = buf[9] | (buf[8] << 8) | (buf[7] << 16) | (buf[6] << 24); + cmd->xfer = ldl_be_p(&buf[6]); cmd->len = 12; break; default: @@ -710,23 +710,15 @@ static uint64_t scsi_cmd_lba(SCSICommand *cmd) switch (buf[0] >> 5) { case 0: - lba = (uint64_t) buf[3] | ((uint64_t) buf[2] << 8) | - (((uint64_t) buf[1] & 0x1f) << 16); + lba = ldl_be_p(&buf[0]) & 0x1fffff; break; case 1: case 2: - lba = (uint64_t) buf[5] | ((uint64_t) buf[4] << 8) | - ((uint64_t) buf[3] << 16) | ((uint64_t) buf[2] << 24); + case 5: + lba = ldl_be_p(&buf[2]); break; case 4: - lba = (uint64_t) buf[9] | ((uint64_t) buf[8] << 8) | - ((uint64_t) buf[7] << 16) | ((uint64_t) buf[6] << 24) | - ((uint64_t) buf[5] << 32) | ((uint64_t) buf[4] << 40) | - ((uint64_t) buf[3] << 48) | ((uint64_t) buf[2] << 56); - break; - case 5: - lba = (uint64_t) buf[5] | ((uint64_t) buf[4] << 8) | - ((uint64_t) buf[3] << 16) | ((uint64_t) buf[2] << 24); + lba = ldq_be_p(&buf[2]); break; default: lba = -1; diff --git a/hw/scsi-disk.c b/hw/scsi-disk.c index 4a60820b18..e843f712c2 100644 --- a/hw/scsi-disk.c +++ b/hw/scsi-disk.c @@ -55,6 +55,7 @@ typedef struct SCSIDiskReq { /* Both sector and sector_count are in terms of qemu 512 byte blocks. */ uint64_t sector; uint32_t sector_count; + uint32_t buflen; struct iovec iov; QEMUIOVector qiov; uint32_t status; @@ -78,13 +79,15 @@ struct SCSIDiskState }; static int scsi_handle_rw_error(SCSIDiskReq *r, int error, int type); -static int scsi_disk_emulate_command(SCSIDiskReq *r, uint8_t *outbuf); +static int scsi_disk_emulate_command(SCSIDiskReq *r); static void scsi_free_request(SCSIRequest *req) { SCSIDiskReq *r = DO_UPCAST(SCSIDiskReq, req, req); - qemu_vfree(r->iov.iov_base); + if (r->iov.iov_base) { + qemu_vfree(r->iov.iov_base); + } } /* Helper function for command completion with sense. */ @@ -108,6 +111,19 @@ static void scsi_cancel_io(SCSIRequest *req) r->req.aiocb = NULL; } +static uint32_t scsi_init_iovec(SCSIDiskReq *r) +{ + SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); + + if (!r->iov.iov_base) { + r->buflen = SCSI_DMA_BUF_SIZE; + r->iov.iov_base = qemu_blockalign(s->bs, r->buflen); + } + r->iov.iov_len = MIN(r->sector_count * 512, r->buflen); + qemu_iovec_init_external(&r->qiov, &r->iov, 1); + return r->qiov.size / 512; +} + static void scsi_read_complete(void * opaque, int ret) { SCSIDiskReq *r = (SCSIDiskReq *)opaque; @@ -125,12 +141,12 @@ static void scsi_read_complete(void * opaque, int ret) } } - DPRINTF("Data ready tag=0x%x len=%zd\n", r->req.tag, r->iov.iov_len); + DPRINTF("Data ready tag=0x%x len=%zd\n", r->req.tag, r->qiov.size); - n = r->iov.iov_len / 512; + n = r->qiov.size / 512; r->sector += n; r->sector_count -= n; - scsi_req_data(&r->req, r->iov.iov_len); + scsi_req_data(&r->req, r->qiov.size); } static void scsi_flush_complete(void * opaque, int ret) @@ -181,16 +197,10 @@ static void scsi_read_data(SCSIRequest *req) return; } - n = r->sector_count; - if (n > SCSI_DMA_BUF_SIZE / 512) - n = SCSI_DMA_BUF_SIZE / 512; - if (s->tray_open) { scsi_read_complete(r, -ENOMEDIUM); } - r->iov.iov_len = n * 512; - qemu_iovec_init_external(&r->qiov, &r->iov, 1); - + n = scsi_init_iovec(r); bdrv_acct_start(s->bs, &r->acct, n * BDRV_SECTOR_SIZE, BDRV_ACCT_READ); r->req.aiocb = bdrv_aio_readv(s->bs, r->sector, &r->qiov, n, scsi_read_complete, r); @@ -217,7 +227,7 @@ static int scsi_handle_rw_error(SCSIDiskReq *r, int error, int type) r->status |= SCSI_REQ_STATUS_RETRY | type; bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read); - vm_stop(VMSTOP_DISKFULL); + vm_stop(RSTATE_IO_ERROR); } else { switch (error) { case ENOMEM: @@ -239,7 +249,6 @@ static void scsi_write_complete(void * opaque, int ret) { SCSIDiskReq *r = (SCSIDiskReq *)opaque; SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, r->req.dev); - uint32_t len; uint32_t n; if (r->req.aiocb != NULL) { @@ -253,19 +262,15 @@ static void scsi_write_complete(void * opaque, int ret) } } - n = r->iov.iov_len / 512; + n = r->qiov.size / 512; r->sector += n; r->sector_count -= n; if (r->sector_count == 0) { scsi_req_complete(&r->req, GOOD); } else { - len = r->sector_count * 512; - if (len > SCSI_DMA_BUF_SIZE) { - len = SCSI_DMA_BUF_SIZE; - } - r->iov.iov_len = len; - DPRINTF("Write complete tag=0x%x more=%d\n", r->req.tag, len); - scsi_req_data(&r->req, len); + scsi_init_iovec(r); + DPRINTF("Write complete tag=0x%x more=%d\n", r->req.tag, r->qiov.size); + scsi_req_data(&r->req, r->qiov.size); } } @@ -284,21 +289,19 @@ static void scsi_write_data(SCSIRequest *req) return; } - n = r->iov.iov_len / 512; + n = r->qiov.size / 512; if (n) { if (s->tray_open) { scsi_write_complete(r, -ENOMEDIUM); } - qemu_iovec_init_external(&r->qiov, &r->iov, 1); - bdrv_acct_start(s->bs, &r->acct, n * BDRV_SECTOR_SIZE, BDRV_ACCT_WRITE); r->req.aiocb = bdrv_aio_writev(s->bs, r->sector, &r->qiov, n, - scsi_write_complete, r); + scsi_write_complete, r); if (r->req.aiocb == NULL) { scsi_write_complete(r, -ENOMEM); } } else { - /* Invoke completion routine to fetch data from host. */ + /* Called for the first time. Ask the driver to send us more data. */ scsi_write_complete(r, 0); } } @@ -329,7 +332,7 @@ static void scsi_dma_restart_bh(void *opaque) scsi_write_data(&r->req); break; case SCSI_REQ_STATUS_RETRY_FLUSH: - ret = scsi_disk_emulate_command(r, r->iov.iov_base); + ret = scsi_disk_emulate_command(r); if (ret == 0) { scsi_req_complete(&r->req, GOOD); } @@ -338,7 +341,7 @@ static void scsi_dma_restart_bh(void *opaque) } } -static void scsi_dma_restart_cb(void *opaque, int running, int reason) +static void scsi_dma_restart_cb(void *opaque, int running, RunState state) { SCSIDiskState *s = opaque; @@ -844,13 +847,31 @@ static int scsi_disk_emulate_start_stop(SCSIDiskReq *r) return 0; } -static int scsi_disk_emulate_command(SCSIDiskReq *r, uint8_t *outbuf) +static int scsi_disk_emulate_command(SCSIDiskReq *r) { SCSIRequest *req = &r->req; SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev); uint64_t nb_sectors; + uint8_t *outbuf; int buflen = 0; + if (!r->iov.iov_base) { + /* + * FIXME: we shouldn't return anything bigger than 4k, but the code + * requires the buffer to be as big as req->cmd.xfer in several + * places. So, do not allow CDBs with a very large ALLOCATION + * LENGTH. The real fix would be to modify scsi_read_data and + * dma_buf_read, so that they return data beyond the buflen + * as all zeros. + */ + if (req->cmd.xfer > 65536) { + goto illegal_request; + } + r->buflen = MAX(4096, req->cmd.xfer); + r->iov.iov_base = qemu_blockalign(s->bs, r->buflen); + } + + outbuf = r->iov.iov_base; switch (req->cmd.buf[0]) { case TEST_UNIT_READY: if (s->tray_open || !bdrv_is_inserted(s->bs)) @@ -1001,11 +1022,9 @@ static int32_t scsi_send_command(SCSIRequest *req, uint8_t *buf) SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, req->dev); int32_t len; uint8_t command; - uint8_t *outbuf; int rc; command = buf[0]; - outbuf = (uint8_t *)r->iov.iov_base; DPRINTF("Command: lun=%d tag=0x%x data=0x%02x", req->lun, req->tag, buf[0]); #ifdef DEBUG_SCSI @@ -1034,7 +1053,7 @@ static int32_t scsi_send_command(SCSIRequest *req, uint8_t *buf) case GET_CONFIGURATION: case SERVICE_ACTION_IN_16: case VERIFY_10: - rc = scsi_disk_emulate_command(r, outbuf); + rc = scsi_disk_emulate_command(r); if (rc < 0) { return 0; } @@ -1285,11 +1304,8 @@ static SCSIRequest *scsi_new_request(SCSIDevice *d, uint32_t tag, { SCSIDiskState *s = DO_UPCAST(SCSIDiskState, qdev, d); SCSIRequest *req; - SCSIDiskReq *r; req = scsi_req_alloc(&scsi_disk_reqops, &s->qdev, tag, lun, hba_private); - r = DO_UPCAST(SCSIDiskReq, req, req); - r->iov.iov_base = qemu_blockalign(s->bs, SCSI_DMA_BUF_SIZE); return req; } diff --git a/hw/scsi-generic.c b/hw/scsi-generic.c index 5ce01afdce..8f6b70df2b 100644 --- a/hw/scsi-generic.c +++ b/hw/scsi-generic.c @@ -244,12 +244,6 @@ static uint8_t *scsi_get_buf(SCSIRequest *req) static void scsi_req_fixup(SCSIRequest *req) { switch(req->cmd.buf[0]) { - case WRITE_10: - req->cmd.buf[1] &= ~0x08; /* disable FUA */ - break; - case READ_10: - req->cmd.buf[1] &= ~0x08; /* disable FUA */ - break; case REWIND: case START_STOP: if (req->dev->type == TYPE_TAPE) { diff --git a/hw/usb-ehci.c b/hw/usb-ehci.c index e9e0789795..27376a2351 100644 --- a/hw/usb-ehci.c +++ b/hw/usb-ehci.c @@ -2291,7 +2291,7 @@ static int usb_ehci_initfn(PCIDevice *dev) pci_set_byte(&pci_conf[PCI_CAPABILITY_LIST], 0x00); //pci_set_byte(&pci_conf[PCI_CAPABILITY_LIST], 0x50); - pci_set_byte(&pci_conf[PCI_INTERRUPT_PIN], 4); // interrupt pin 3 + pci_set_byte(&pci_conf[PCI_INTERRUPT_PIN], 4); /* interrupt pin D */ pci_set_byte(&pci_conf[PCI_MIN_GNT], 0); pci_set_byte(&pci_conf[PCI_MAX_LAT], 0); diff --git a/hw/usb-ohci.c b/hw/usb-ohci.c index 503ca2d31f..c3be65a2e9 100644 --- a/hw/usb-ohci.c +++ b/hw/usb-ohci.c @@ -1780,8 +1780,7 @@ static int usb_ohci_initfn_pci(struct PCIDevice *dev) OHCIPCIState *ohci = DO_UPCAST(OHCIPCIState, pci_dev, dev); ohci->pci_dev.config[PCI_CLASS_PROG] = 0x10; /* OHCI */ - /* TODO: RST# value should be 0. */ - ohci->pci_dev.config[PCI_INTERRUPT_PIN] = 0x01; /* interrupt pin 1 */ + ohci->pci_dev.config[PCI_INTERRUPT_PIN] = 0x01; /* interrupt pin A */ if (usb_ohci_init(&ohci->state, &dev->qdev, ohci->num_ports, 0, ohci->masterbus, ohci->firstport) != 0) { diff --git a/hw/usb-uhci.c b/hw/usb-uhci.c index 64f7b36c00..17992cf003 100644 --- a/hw/usb-uhci.c +++ b/hw/usb-uhci.c @@ -1131,7 +1131,7 @@ static int usb_uhci_common_initfn(PCIDevice *dev) pci_conf[PCI_CLASS_PROG] = 0x00; /* TODO: reset value should be 0. */ - pci_conf[PCI_INTERRUPT_PIN] = 4; // interrupt pin 3 + pci_conf[PCI_INTERRUPT_PIN] = 4; /* interrupt pin D */ pci_conf[USB_SBRN] = USB_RELEASE_1; // release number if (s->masterbus) { diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c index c2ee0001eb..daa8e42be7 100644 --- a/hw/virtio-blk.c +++ b/hw/virtio-blk.c @@ -77,7 +77,7 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error, req->next = s->rq; s->rq = req; bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read); - vm_stop(VMSTOP_DISKFULL); + vm_stop(RSTATE_IO_ERROR); } else { virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR); bdrv_acct_done(s->bs, &req->acct); @@ -439,7 +439,8 @@ static void virtio_blk_dma_restart_bh(void *opaque) virtio_submit_multiwrite(s->bs, &mrb); } -static void virtio_blk_dma_restart_cb(void *opaque, int running, int reason) +static void virtio_blk_dma_restart_cb(void *opaque, int running, + RunState state) { VirtIOBlock *s = opaque; diff --git a/hw/virtio.c b/hw/virtio.c index 946d911580..d9bf266492 100644 --- a/hw/virtio.c +++ b/hw/virtio.c @@ -847,7 +847,7 @@ void virtio_cleanup(VirtIODevice *vdev) g_free(vdev); } -static void virtio_vmstate_change(void *opaque, int running, int reason) +static void virtio_vmstate_change(void *opaque, int running, RunState state) { VirtIODevice *vdev = opaque; bool backend_run = running && (vdev->status & VIRTIO_CONFIG_S_DRIVER_OK); @@ -880,7 +880,7 @@ VirtIODevice *virtio_common_init(const char *name, uint16_t device_id, vdev->queue_sel = 0; vdev->config_vector = VIRTIO_NO_VECTOR; vdev->vq = g_malloc0(sizeof(VirtQueue) * VIRTIO_PCI_QUEUE_MAX); - vdev->vm_running = vm_running; + vdev->vm_running = runstate_is_running(); for(i = 0; i < VIRTIO_PCI_QUEUE_MAX; i++) { vdev->vq[i].vector = VIRTIO_NO_VECTOR; vdev->vq[i].vdev = vdev; diff --git a/hw/watchdog.c b/hw/watchdog.c index 1c900a1189..71c6c7df63 100644 --- a/hw/watchdog.c +++ b/hw/watchdog.c @@ -132,7 +132,7 @@ void watchdog_perform_action(void) case WDT_PAUSE: /* same as 'stop' command in monitor */ watchdog_mon_event("pause"); - vm_stop(VMSTOP_WATCHDOG); + vm_stop(RSTATE_WATCHDOG); break; case WDT_DEBUG: @@ -1014,7 +1014,7 @@ int kvm_cpu_exec(CPUState *env) if (ret < 0) { cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE); - vm_stop(VMSTOP_PANIC); + vm_stop(RSTATE_PANICKED); } env->exit_request = 0; diff --git a/linux-aio.c b/linux-aio.c index 5265a029b2..bffa6cd0e3 100644 --- a/linux-aio.c +++ b/linux-aio.c @@ -68,15 +68,6 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s, qemu_aio_release(laiocb); } -/* - * All requests are directly processed when they complete, so there's nothing - * left to do during qemu_aio_wait(). - */ -static int qemu_laio_process_requests(void *opaque) -{ - return 0; -} - static void qemu_laio_completion_cb(void *opaque) { struct qemu_laio_state *s = opaque; @@ -215,7 +206,7 @@ void *laio_init(void) goto out_close_efd; qemu_aio_set_fd_handler(s->efd, qemu_laio_completion_cb, NULL, - qemu_laio_flush_cb, qemu_laio_process_requests, s); + qemu_laio_flush_cb, NULL, s); return s; diff --git a/migration.c b/migration.c index f5959b4391..7dd8f4eee9 100644 --- a/migration.c +++ b/migration.c @@ -70,10 +70,11 @@ void process_incoming_migration(QEMUFile *f) qemu_announce_self(); DPRINTF("successfully loaded vm state\n"); - incoming_expected = false; - - if (autostart) + if (autostart) { vm_start(); + } else { + runstate_set(RSTATE_PRE_LAUNCH); + } } int do_migrate(Monitor *mon, const QDict *qdict, QObject **ret_data) @@ -371,10 +372,10 @@ void migrate_fd_put_ready(void *opaque) DPRINTF("iterate\n"); if (qemu_savevm_state_iterate(s->mon, s->file) == 1) { int state; - int old_vm_running = vm_running; + int old_vm_running = runstate_is_running(); DPRINTF("done iterating\n"); - vm_stop(VMSTOP_MIGRATE); + vm_stop(RSTATE_PRE_MIGRATE); if ((qemu_savevm_state_complete(s->mon, s->file)) < 0) { if (old_vm_running) { @@ -390,6 +391,9 @@ void migrate_fd_put_ready(void *opaque) } state = MIG_STATE_ERROR; } + if (state == MIG_STATE_COMPLETED) { + runstate_set(RSTATE_POST_MIGRATE); + } s->state = state; notifier_list_notify(&migration_state_notifiers, NULL); } @@ -1293,7 +1293,7 @@ static void do_singlestep(Monitor *mon, const QDict *qdict) */ static int do_stop(Monitor *mon, const QDict *qdict, QObject **ret_data) { - vm_stop(VMSTOP_USER); + vm_stop(RSTATE_PAUSED); return 0; } @@ -1311,10 +1311,15 @@ static int do_cont(Monitor *mon, const QDict *qdict, QObject **ret_data) { struct bdrv_iterate_context context = { mon, 0 }; - if (incoming_expected) { + if (runstate_check(RSTATE_IN_MIGRATE)) { qerror_report(QERR_MIGRATION_EXPECTED); return -1; + } else if (runstate_check(RSTATE_PANICKED) || + runstate_check(RSTATE_SHUTDOWN)) { + qerror_report(QERR_RESET_REQUIRED); + return -1; } + bdrv_iterate(encrypted_bdrv_it, &context); /* only resume the vm if all keys are set and valid */ if (!context.err) { @@ -2613,6 +2618,7 @@ static int do_inject_nmi(Monitor *mon, const QDict *qdict, QObject **ret_data) static void do_info_status_print(Monitor *mon, const QObject *data) { QDict *qdict; + const char *status; qdict = qobject_to_qdict(data); @@ -2626,13 +2632,17 @@ static void do_info_status_print(Monitor *mon, const QObject *data) monitor_printf(mon, "paused"); } + status = qdict_get_str(qdict, "status"); + if (strcmp(status, "paused") && strcmp(status, "running")) { + monitor_printf(mon, " (%s)", status); + } + monitor_printf(mon, "\n"); } static void do_info_status(Monitor *mon, QObject **ret_data) { - *ret_data = qobject_from_jsonf("{ 'running': %i, 'singlestep': %i }", - vm_running, singlestep); + *ret_data = qobject_from_jsonf("{ 'running': %i, 'singlestep': %i, 'status': %s }", runstate_is_running(), singlestep, runstate_as_string()); } static qemu_acl *find_acl(Monitor *mon, const char *name) @@ -2825,10 +2835,10 @@ static int do_closefd(Monitor *mon, const QDict *qdict, QObject **ret_data) static void do_loadvm(Monitor *mon, const QDict *qdict) { - int saved_vm_running = vm_running; + int saved_vm_running = runstate_is_running(); const char *name = qdict_get_str(qdict, "name"); - vm_stop(VMSTOP_LOADVM); + vm_stop(RSTATE_RESTORE); if (load_vmstate(name) == 0 && saved_vm_running) { vm_start(); @@ -30,6 +30,10 @@ #include <ctype.h> #include <inttypes.h> +#ifdef __linux__ +#include <linux/fs.h> +#endif + #include "qemu_socket.h" //#define DEBUG_NBD @@ -63,6 +67,8 @@ #define NBD_PRINT_DEBUG _IO(0xab, 6) #define NBD_SET_SIZE_BLOCKS _IO(0xab, 7) #define NBD_DISCONNECT _IO(0xab, 8) +#define NBD_SET_TIMEOUT _IO(0xab, 9) +#define NBD_SET_FLAGS _IO(0xab, 10) #define NBD_OPT_EXPORT_NAME (1 << 0) @@ -172,7 +178,7 @@ int unix_socket_outgoing(const char *path) Request (type == 2) */ -int nbd_negotiate(int csock, off_t size) +int nbd_negotiate(int csock, off_t size, uint32_t flags) { char buf[8 + 8 + 8 + 128]; @@ -180,14 +186,16 @@ int nbd_negotiate(int csock, off_t size) [ 0 .. 7] passwd ("NBDMAGIC") [ 8 .. 15] magic (0x00420281861253) [16 .. 23] size - [24 .. 151] reserved (0) + [24 .. 27] flags + [28 .. 151] reserved (0) */ TRACE("Beginning negotiation."); memcpy(buf, "NBDMAGIC", 8); cpu_to_be64w((uint64_t*)(buf + 8), 0x00420281861253LL); cpu_to_be64w((uint64_t*)(buf + 16), size); - memset(buf + 24, 0, 128); + cpu_to_be32w((uint32_t*)(buf + 24), flags | NBD_FLAG_HAS_FLAGS); + memset(buf + 28, 0, 124); if (write_sync(csock, buf, sizeof(buf)) != sizeof(buf)) { LOG("write failed"); @@ -337,8 +345,8 @@ int nbd_receive_negotiate(int csock, const char *name, uint32_t *flags, return 0; } -#ifndef _WIN32 -int nbd_init(int fd, int csock, off_t size, size_t blocksize) +#ifdef __linux__ +int nbd_init(int fd, int csock, uint32_t flags, off_t size, size_t blocksize) { TRACE("Setting block size to %lu", (unsigned long)blocksize); @@ -358,6 +366,26 @@ int nbd_init(int fd, int csock, off_t size, size_t blocksize) return -1; } + if (flags & NBD_FLAG_READ_ONLY) { + int read_only = 1; + TRACE("Setting readonly attribute"); + + if (ioctl(fd, BLKROSET, (unsigned long) &read_only) < 0) { + int serrno = errno; + LOG("Failed setting read-only attribute"); + errno = serrno; + return -1; + } + } + + if (ioctl(fd, NBD_SET_FLAGS, flags) < 0 + && errno != ENOTTY) { + int serrno = errno; + LOG("Failed setting flags"); + errno = serrno; + return -1; + } + TRACE("Clearing NBD socket"); if (ioctl(fd, NBD_CLEAR_SOCK) == -1) { @@ -548,7 +576,7 @@ static int nbd_send_reply(int csock, struct nbd_reply *reply) } int nbd_trip(BlockDriverState *bs, int csock, off_t size, uint64_t dev_offset, - off_t *offset, bool readonly, uint8_t *data, int data_size) + off_t *offset, uint32_t nbdflags, uint8_t *data, int data_size) { struct nbd_request request; struct nbd_reply reply; @@ -632,7 +660,7 @@ int nbd_trip(BlockDriverState *bs, int csock, off_t size, uint64_t dev_offset, return -1; } - if (readonly) { + if (nbdflags & NBD_FLAG_READ_ONLY) { TRACE("Server is read-only, return error"); reply.error = 1; } else { @@ -37,10 +37,22 @@ struct nbd_reply { uint64_t handle; } QEMU_PACKED; +#define NBD_FLAG_HAS_FLAGS (1 << 0) /* Flags are there */ +#define NBD_FLAG_READ_ONLY (1 << 1) /* Device is read-only */ +#define NBD_FLAG_SEND_FLUSH (1 << 2) /* Send FLUSH */ +#define NBD_FLAG_SEND_FUA (1 << 3) /* Send FUA (Force Unit Access) */ +#define NBD_FLAG_ROTATIONAL (1 << 4) /* Use elevator algorithm - rotational media */ +#define NBD_FLAG_SEND_TRIM (1 << 5) /* Send TRIM (discard) */ + +#define NBD_CMD_MASK_COMMAND 0x0000ffff +#define NBD_CMD_FLAG_FUA (1 << 16) + enum { NBD_CMD_READ = 0, NBD_CMD_WRITE = 1, - NBD_CMD_DISC = 2 + NBD_CMD_DISC = 2, + NBD_CMD_FLUSH = 3, + NBD_CMD_TRIM = 4 }; #define NBD_DEFAULT_PORT 10809 @@ -53,14 +65,14 @@ int tcp_socket_incoming_spec(const char *address_and_port); int unix_socket_outgoing(const char *path); int unix_socket_incoming(const char *path); -int nbd_negotiate(int csock, off_t size); +int nbd_negotiate(int csock, off_t size, uint32_t flags); int nbd_receive_negotiate(int csock, const char *name, uint32_t *flags, off_t *size, size_t *blocksize); -int nbd_init(int fd, int csock, off_t size, size_t blocksize); +int nbd_init(int fd, int csock, uint32_t flags, off_t size, size_t blocksize); int nbd_send_request(int csock, struct nbd_request *request); int nbd_receive_reply(int csock, struct nbd_reply *reply); int nbd_trip(BlockDriverState *bs, int csock, off_t size, uint64_t dev_offset, - off_t *offset, bool readonly, uint8_t *data, int data_size); + off_t *offset, uint32_t nbdflags, uint8_t *data, int data_size); int nbd_client(int fd); int nbd_disconnect(int fd); diff --git a/posix-aio-compat.c b/posix-aio-compat.c index 3193dbf83c..d3c1174ebf 100644 --- a/posix-aio-compat.c +++ b/posix-aio-compat.c @@ -42,7 +42,6 @@ struct qemu_paiocb { int aio_niov; size_t aio_nbytes; #define aio_ioctl_cmd aio_nbytes /* for QEMU_AIO_IOCTL */ - int ev_signo; off_t aio_offset; QTAILQ_ENTRY(qemu_paiocb) node; @@ -181,7 +180,6 @@ qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset) static ssize_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb) { - size_t offset = 0; ssize_t len; do { @@ -189,12 +187,12 @@ static ssize_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb) len = qemu_pwritev(aiocb->aio_fildes, aiocb->aio_iov, aiocb->aio_niov, - aiocb->aio_offset + offset); + aiocb->aio_offset); else len = qemu_preadv(aiocb->aio_fildes, aiocb->aio_iov, aiocb->aio_niov, - aiocb->aio_offset + offset); + aiocb->aio_offset); } while (len == -1 && errno == EINTR); if (len == -1) @@ -309,12 +307,10 @@ static ssize_t handle_aiocb_rw(struct qemu_paiocb *aiocb) return nbytes; } +static void posix_aio_notify_event(void); + static void *aio_thread(void *unused) { - pid_t pid; - - pid = getpid(); - mutex_lock(&lock); pending_threads--; mutex_unlock(&lock); @@ -381,7 +377,7 @@ static void *aio_thread(void *unused) aiocb->ret = ret; mutex_unlock(&lock); - if (kill(pid, aiocb->ev_signo)) die("kill failed"); + posix_aio_notify_event(); } cur_threads--; @@ -548,18 +544,14 @@ static int posix_aio_flush(void *opaque) static PosixAioState *posix_aio_state; -static void aio_signal_handler(int signum) +static void posix_aio_notify_event(void) { - if (posix_aio_state) { - char byte = 0; - ssize_t ret; - - ret = write(posix_aio_state->wfd, &byte, sizeof(byte)); - if (ret < 0 && errno != EAGAIN) - die("write()"); - } + char byte = 0; + ssize_t ret; - qemu_service_io(); + ret = write(posix_aio_state->wfd, &byte, sizeof(byte)); + if (ret < 0 && errno != EAGAIN) + die("write()"); } static void paio_remove(struct qemu_paiocb *acb) @@ -623,7 +615,6 @@ BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd, return NULL; acb->aio_type = type; acb->aio_fildes = fd; - acb->ev_signo = SIGUSR2; if (qiov) { acb->aio_iov = qiov->iov; @@ -651,7 +642,6 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd, return NULL; acb->aio_type = QEMU_AIO_IOCTL; acb->aio_fildes = fd; - acb->ev_signo = SIGUSR2; acb->aio_offset = 0; acb->aio_ioctl_buf = buf; acb->aio_ioctl_cmd = req; @@ -665,7 +655,6 @@ BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd, int paio_init(void) { - struct sigaction act; PosixAioState *s; int fds[2]; int ret; @@ -675,11 +664,6 @@ int paio_init(void) s = g_malloc(sizeof(PosixAioState)); - sigfillset(&act.sa_mask); - act.sa_flags = 0; /* do not restart syscalls to interrupt select() */ - act.sa_handler = aio_signal_handler; - sigaction(SIGUSR2, &act, NULL); - s->first_aio = NULL; if (qemu_pipe(fds) == -1) { fprintf(stderr, "failed to create pipe\n"); diff --git a/qemu-nbd.c b/qemu-nbd.c index 3a39145174..d8d3e15a84 100644 --- a/qemu-nbd.c +++ b/qemu-nbd.c @@ -185,7 +185,7 @@ int main(int argc, char **argv) BlockDriverState *bs; off_t dev_offset = 0; off_t offset = 0; - bool readonly = false; + uint32_t nbdflags = 0; bool disconnect = false; const char *bindto = "0.0.0.0"; int port = NBD_DEFAULT_PORT; @@ -230,7 +230,6 @@ int main(int argc, char **argv) int nb_fds = 0; int max_fd; int persistent = 0; - uint32_t nbdflags; while ((ch = getopt_long(argc, argv, sopt, lopt, &opt_ind)) != -1) { switch (ch) { @@ -263,7 +262,7 @@ int main(int argc, char **argv) } break; case 'r': - readonly = true; + nbdflags |= NBD_FLAG_READ_ONLY; flags &= ~BDRV_O_RDWR; break; case 'P': @@ -398,13 +397,13 @@ int main(int argc, char **argv) } ret = nbd_receive_negotiate(sock, NULL, &nbdflags, - &size, &blocksize); + &size, &blocksize); if (ret == -1) { ret = 1; goto out; } - ret = nbd_init(fd, sock, size, blocksize); + ret = nbd_init(fd, sock, nbdflags, size, blocksize); if (ret == -1) { ret = 1; goto out; @@ -463,7 +462,7 @@ int main(int argc, char **argv) for (i = 1; i < nb_fds && ret; i++) { if (FD_ISSET(sharing_fds[i], &fds)) { if (nbd_trip(bs, sharing_fds[i], fd_size, dev_offset, - &offset, readonly, data, NBD_BUFFER_SIZE) != 0) { + &offset, nbdflags, data, NBD_BUFFER_SIZE) != 0) { close(sharing_fds[i]); nb_fds--; sharing_fds[i] = sharing_fds[nb_fds]; @@ -479,7 +478,7 @@ int main(int argc, char **argv) (struct sockaddr *)&addr, &addr_len); if (sharing_fds[nb_fds] != -1 && - nbd_negotiate(sharing_fds[nb_fds], fd_size) != -1) { + nbd_negotiate(sharing_fds[nb_fds], fd_size, nbdflags) != -1) { if (sharing_fds[nb_fds] > max_fd) max_fd = sharing_fds[nb_fds]; nb_fds++; diff --git a/qemu-timer.c b/qemu-timer.c index 46dd483fdd..ad1fc8b871 100644 --- a/qemu-timer.c +++ b/qemu-timer.c @@ -230,7 +230,7 @@ static void icount_adjust(void) int64_t delta; static int64_t last_delta; /* If the VM is not running, then do nothing. */ - if (!vm_running) + if (!runstate_is_running()) return; cur_time = cpu_get_clock(); @@ -388,7 +388,7 @@ static void icount_warp_rt(void *opaque) return; } - if (vm_running) { + if (runstate_is_running()) { int64_t clock = qemu_get_clock_ns(rt_clock); int64_t warp_delta = clock - vm_clock_warp_start; if (use_icount == 1) { @@ -710,7 +710,7 @@ void qemu_run_all_timers(void) } /* vm time timers */ - if (vm_running) { + if (runstate_is_running()) { qemu_run_timers(vm_clock); } @@ -1116,7 +1116,8 @@ static void win32_rearm_timer(struct qemu_alarm_timer *t) #endif /* _WIN32 */ -static void alarm_timer_on_change_state_rearm(void *opaque, int running, int reason) +static void alarm_timer_on_change_state_rearm(void *opaque, int running, + RunState state) { if (running) qemu_rearm_alarm_timer((struct qemu_alarm_timer *) opaque); @@ -194,6 +194,10 @@ static const QErrorStringTable qerror_table[] = { .desc = "QMP input object member '%(member)' is unexpected", }, { + .error_fmt = QERR_RESET_REQUIRED, + .desc = "Resetting the Virtual Machine is required", + }, + { .error_fmt = QERR_SET_PASSWD_FAILED, .desc = "Could not set password", }, @@ -163,6 +163,9 @@ QError *qobject_to_qerror(const QObject *obj); #define QERR_QMP_EXTRA_MEMBER \ "{ 'class': 'QMPExtraInputObjectMember', 'data': { 'member': %s } }" +#define QERR_RESET_REQUIRED \ + "{ 'class': 'ResetRequired', 'data': {} }" + #define QERR_SET_PASSWD_FAILED \ "{ 'class': 'SetPasswdFailed', 'data': {} }" diff --git a/qmp-commands.hx b/qmp-commands.hx index d1c2c5905d..d83bce5662 100644 --- a/qmp-commands.hx +++ b/qmp-commands.hx @@ -1573,11 +1573,28 @@ Return a json-object with the following information: - "running": true if the VM is running, or false if it is paused (json-bool) - "singlestep": true if the VM is in single step mode, false otherwise (json-bool) +- "status": one of the following values (json-string) + "debug" - QEMU is running on a debugger + "inmigrate" - guest is paused waiting for an incoming migration + "internal-error" - An internal error that prevents further guest + execution has occurred + "io-error" - the last IOP has failed and the device is configured + to pause on I/O errors + "paused" - guest has been paused via the 'stop' command + "postmigrate" - guest is paused following a successful 'migrate' + "prelaunch" - QEMU was started with -S and guest has not started + "finish-migrate" - guest is paused to finish the migration process + "restore-vm" - guest is paused to restore VM state + "running" - guest is actively running + "save-vm" - guest is paused to save the VM state + "shutdown" - guest is shut down (and -no-shutdown is in use) + "watchdog" - the watchdog action is configured to pause and + has been triggered Example: -> { "execute": "query-status" } -<- { "return": { "running": true, "singlestep": false } } +<- { "return": { "running": true, "singlestep": false, "status": "running" } } EQMP @@ -1602,8 +1602,8 @@ static int qemu_savevm_state(Monitor *mon, QEMUFile *f) int saved_vm_running; int ret; - saved_vm_running = vm_running; - vm_stop(VMSTOP_SAVEVM); + saved_vm_running = runstate_is_running(); + vm_stop(RSTATE_SAVEVM); if (qemu_savevm_state_blocked(mon)) { ret = -EINVAL; @@ -1931,8 +1931,8 @@ void do_savevm(Monitor *mon, const QDict *qdict) return; } - saved_vm_running = vm_running; - vm_stop(VMSTOP_SAVEVM); + saved_vm_running = runstate_is_running(); + vm_stop(RSTATE_SAVEVM); memset(sn, 0, sizeof(*sn)); diff --git a/slirp/tcp_input.c b/slirp/tcp_input.c index 8bbd70caf1..2f1a196b39 100644 --- a/slirp/tcp_input.c +++ b/slirp/tcp_input.c @@ -610,6 +610,7 @@ findso: so->so_ti = ti; tp->t_timer[TCPT_KEEP] = TCPTV_KEEP_INIT; tp->t_state = TCPS_SYN_RECEIVED; + tcp_template(tp); } return; @@ -9,42 +9,56 @@ #include "notify.h" /* vl.c */ + +typedef enum { + RSTATE_NO_STATE, + RSTATE_DEBUG, /* qemu is running under gdb */ + RSTATE_IN_MIGRATE, /* paused waiting for an incoming migration */ + RSTATE_PANICKED, /* paused due to an internal error */ + RSTATE_IO_ERROR, /* paused due to an I/O error */ + RSTATE_PAUSED, /* paused by the user (ie. the 'stop' command) */ + RSTATE_POST_MIGRATE, /* paused following a successful migration */ + RSTATE_PRE_LAUNCH, /* qemu was started with -S and haven't started */ + RSTATE_PRE_MIGRATE, /* paused preparing to finish migrate */ + RSTATE_RESTORE, /* paused restoring the VM state */ + RSTATE_RUNNING, /* qemu is running */ + RSTATE_SAVEVM, /* paused saving VM state */ + RSTATE_SHUTDOWN, /* guest shut down and -no-shutdown is in use */ + RSTATE_WATCHDOG, /* watchdog fired and qemu is configured to pause */ + RSTATE_MAX +} RunState; + extern const char *bios_name; -extern int vm_running; extern const char *qemu_name; extern uint8_t qemu_uuid[]; int qemu_uuid_parse(const char *str, uint8_t *uuid); #define UUID_FMT "%02hhx%02hhx%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx-%02hhx%02hhx%02hhx%02hhx%02hhx%02hhx" +void runstate_init(void); +bool runstate_check(RunState state); +void runstate_set(RunState new_state); +int runstate_is_running(void); +const char *runstate_as_string(void); typedef struct vm_change_state_entry VMChangeStateEntry; -typedef void VMChangeStateHandler(void *opaque, int running, int reason); +typedef void VMChangeStateHandler(void *opaque, int running, RunState state); VMChangeStateEntry *qemu_add_vm_change_state_handler(VMChangeStateHandler *cb, void *opaque); void qemu_del_vm_change_state_handler(VMChangeStateEntry *e); - -#define VMSTOP_USER 0 -#define VMSTOP_DEBUG 1 -#define VMSTOP_SHUTDOWN 2 -#define VMSTOP_DISKFULL 3 -#define VMSTOP_WATCHDOG 4 -#define VMSTOP_PANIC 5 -#define VMSTOP_SAVEVM 6 -#define VMSTOP_LOADVM 7 -#define VMSTOP_MIGRATE 8 +void vm_state_notify(int running, RunState state); #define VMRESET_SILENT false #define VMRESET_REPORT true void vm_start(void); -void vm_stop(int reason); +void vm_stop(RunState state); void qemu_system_reset_request(void); void qemu_system_shutdown_request(void); void qemu_system_powerdown_request(void); void qemu_system_debug_request(void); -void qemu_system_vmstop_request(int reason); +void qemu_system_vmstop_request(RunState reason); int qemu_shutdown_requested_get(void); int qemu_reset_requested_get(void); int qemu_shutdown_requested(void); diff --git a/target-i386/kvm.c b/target-i386/kvm.c index 22b1dd0665..b6eef047bf 100644 --- a/target-i386/kvm.c +++ b/target-i386/kvm.c @@ -334,7 +334,7 @@ static int kvm_inject_mce_oldstyle(CPUState *env) return 0; } -static void cpu_update_state(void *opaque, int running, int reason) +static void cpu_update_state(void *opaque, int running, RunState state) { CPUState *env = opaque; @@ -1130,7 +1130,7 @@ static int kvm_get_msrs(CPUState *env) if (!env->tsc_valid) { msrs[n++].index = MSR_IA32_TSC; - env->tsc_valid = !vm_running; + env->tsc_valid = !runstate_is_running(); } #ifdef TARGET_X86_64 @@ -409,7 +409,7 @@ static void sdl_update_caption(void) char icon_title[1024]; const char *status = ""; - if (!vm_running) + if (!runstate_is_running()) status = " [Stopped]"; else if (gui_grab) { if (alt_grab) @@ -853,8 +853,8 @@ static void sdl_refresh(DisplayState *ds) { SDL_Event ev1, *ev = &ev1; - if (last_vm_running != vm_running) { - last_vm_running = vm_running; + if (last_vm_running != runstate_is_running()) { + last_vm_running = runstate_is_running(); sdl_update_caption(); } diff --git a/ui/spice-display.c b/ui/spice-display.c index e38536114b..3a92a126e5 100644 --- a/ui/spice-display.c +++ b/ui/spice-display.c @@ -255,7 +255,8 @@ void qemu_spice_destroy_host_primary(SimpleSpiceDisplay *ssd) qemu_spice_destroy_primary_surface(ssd, 0, QXL_SYNC); } -void qemu_spice_vm_change_state_handler(void *opaque, int running, int reason) +void qemu_spice_vm_change_state_handler(void *opaque, int running, + RunState state) { SimpleSpiceDisplay *ssd = opaque; diff --git a/ui/spice-display.h b/ui/spice-display.h index 1388641370..5e52df99be 100644 --- a/ui/spice-display.h +++ b/ui/spice-display.h @@ -22,6 +22,7 @@ #include "qemu-thread.h" #include "console.h" #include "pflib.h" +#include "sysemu.h" #define NUM_MEMSLOTS 8 #define MEMSLOT_GENERATION_BITS 8 @@ -88,7 +89,8 @@ void qemu_spice_destroy_update(SimpleSpiceDisplay *sdpy, SimpleSpiceUpdate *upda void qemu_spice_create_host_memslot(SimpleSpiceDisplay *ssd); void qemu_spice_create_host_primary(SimpleSpiceDisplay *ssd); void qemu_spice_destroy_host_primary(SimpleSpiceDisplay *ssd); -void qemu_spice_vm_change_state_handler(void *opaque, int running, int reason); +void qemu_spice_vm_change_state_handler(void *opaque, int running, + RunState state); void qemu_spice_display_init_common(SimpleSpiceDisplay *ssd, DisplayState *ds); void qemu_spice_display_update(SimpleSpiceDisplay *ssd, @@ -185,9 +185,7 @@ int mem_prealloc = 0; /* force preallocation of physical target memory */ #endif int nb_nics; NICInfo nd_table[MAX_NICS]; -int vm_running; int autostart; -int incoming_expected; /* Started with -incoming and waiting for incoming */ static int rtc_utc = 1; static int rtc_date_offset = -1; /* -1 means no change */ QEMUClock *rtc_clock; @@ -323,6 +321,120 @@ static int default_driver_check(QemuOpts *opts, void *opaque) } /***********************************************************/ +/* QEMU state */ + +static RunState current_run_state = RSTATE_NO_STATE; + +typedef struct { + RunState from; + RunState to; +} RunStateTransition; + +static const RunStateTransition runstate_transitions_def[] = { + /* from -> to */ + { RSTATE_NO_STATE, RSTATE_RUNNING }, + { RSTATE_NO_STATE, RSTATE_IN_MIGRATE }, + { RSTATE_NO_STATE, RSTATE_PRE_LAUNCH }, + + { RSTATE_DEBUG, RSTATE_RUNNING }, + + { RSTATE_IN_MIGRATE, RSTATE_RUNNING }, + { RSTATE_IN_MIGRATE, RSTATE_PRE_LAUNCH }, + + { RSTATE_PANICKED, RSTATE_PAUSED }, + + { RSTATE_IO_ERROR, RSTATE_RUNNING }, + + { RSTATE_PAUSED, RSTATE_RUNNING }, + + { RSTATE_POST_MIGRATE, RSTATE_RUNNING }, + + { RSTATE_PRE_LAUNCH, RSTATE_RUNNING }, + { RSTATE_PRE_LAUNCH, RSTATE_POST_MIGRATE }, + + { RSTATE_PRE_MIGRATE, RSTATE_RUNNING }, + { RSTATE_PRE_MIGRATE, RSTATE_POST_MIGRATE }, + + { RSTATE_RESTORE, RSTATE_RUNNING }, + + { RSTATE_RUNNING, RSTATE_DEBUG }, + { RSTATE_RUNNING, RSTATE_PANICKED }, + { RSTATE_RUNNING, RSTATE_IO_ERROR }, + { RSTATE_RUNNING, RSTATE_PAUSED }, + { RSTATE_RUNNING, RSTATE_PRE_MIGRATE }, + { RSTATE_RUNNING, RSTATE_RESTORE }, + { RSTATE_RUNNING, RSTATE_SAVEVM }, + { RSTATE_RUNNING, RSTATE_SHUTDOWN }, + { RSTATE_RUNNING, RSTATE_WATCHDOG }, + + { RSTATE_SAVEVM, RSTATE_RUNNING }, + + { RSTATE_SHUTDOWN, RSTATE_PAUSED }, + + { RSTATE_WATCHDOG, RSTATE_RUNNING }, + + { RSTATE_MAX, RSTATE_MAX }, +}; + +static bool runstate_valid_transitions[RSTATE_MAX][RSTATE_MAX]; + +static const char *const runstate_name_tbl[RSTATE_MAX] = { + [RSTATE_DEBUG] = "debug", + [RSTATE_IN_MIGRATE] = "incoming-migration", + [RSTATE_PANICKED] = "internal-error", + [RSTATE_IO_ERROR] = "io-error", + [RSTATE_PAUSED] = "paused", + [RSTATE_POST_MIGRATE] = "post-migrate", + [RSTATE_PRE_LAUNCH] = "prelaunch", + [RSTATE_PRE_MIGRATE] = "finish-migrate", + [RSTATE_RESTORE] = "restore-vm", + [RSTATE_RUNNING] = "running", + [RSTATE_SAVEVM] = "save-vm", + [RSTATE_SHUTDOWN] = "shutdown", + [RSTATE_WATCHDOG] = "watchdog", +}; + +bool runstate_check(RunState state) +{ + return current_run_state == state; +} + +void runstate_init(void) +{ + const RunStateTransition *p; + + memset(&runstate_valid_transitions, 0, sizeof(runstate_valid_transitions)); + + for (p = &runstate_transitions_def[0]; p->from != RSTATE_MAX; p++) { + runstate_valid_transitions[p->from][p->to] = true; + } +} + +/* This function will abort() on invalid state transitions */ +void runstate_set(RunState new_state) +{ + if (new_state >= RSTATE_MAX || + !runstate_valid_transitions[current_run_state][new_state]) { + fprintf(stderr, "invalid runstate transition\n"); + abort(); + } + + current_run_state = new_state; +} + +const char *runstate_as_string(void) +{ + assert(current_run_state > RSTATE_NO_STATE && + current_run_state < RSTATE_MAX); + return runstate_name_tbl[current_run_state]; +} + +int runstate_is_running(void) +{ + return runstate_check(RSTATE_RUNNING); +} + +/***********************************************************/ /* real time host monotonic timer */ /***********************************************************/ @@ -1145,23 +1257,23 @@ void qemu_del_vm_change_state_handler(VMChangeStateEntry *e) g_free (e); } -void vm_state_notify(int running, int reason) +void vm_state_notify(int running, RunState state) { VMChangeStateEntry *e; - trace_vm_state_notify(running, reason); + trace_vm_state_notify(running, state); for (e = vm_change_state_head.lh_first; e; e = e->entries.le_next) { - e->cb(e->opaque, running, reason); + e->cb(e->opaque, running, state); } } void vm_start(void) { - if (!vm_running) { + if (!runstate_is_running()) { cpu_enable_ticks(); - vm_running = 1; - vm_state_notify(1, 0); + runstate_set(RSTATE_RUNNING); + vm_state_notify(1, RSTATE_RUNNING); resume_all_vcpus(); monitor_protocol_event(QEVENT_RESUME, NULL); } @@ -1182,7 +1294,7 @@ static int shutdown_requested, shutdown_signal = -1; static pid_t shutdown_pid; static int powerdown_requested; static int debug_requested; -static int vmstop_requested; +static RunState vmstop_requested = RSTATE_NO_STATE; int qemu_shutdown_requested_get(void) { @@ -1238,11 +1350,11 @@ static int qemu_debug_requested(void) return r; } -static int qemu_vmstop_requested(void) +static RunState qemu_vmstop_requested(void) { - int r = vmstop_requested; - vmstop_requested = 0; - return r; + RunState s = vmstop_requested; + vmstop_requested = RSTATE_NO_STATE; + return s; } void qemu_register_reset(QEMUResetHandler *func, void *opaque) @@ -1318,9 +1430,9 @@ void qemu_system_debug_request(void) qemu_notify_event(); } -void qemu_system_vmstop_request(int reason) +void qemu_system_vmstop_request(RunState state) { - vmstop_requested = reason; + vmstop_requested = state; qemu_notify_event(); } @@ -1470,13 +1582,13 @@ static void main_loop(void) #endif if (qemu_debug_requested()) { - vm_stop(VMSTOP_DEBUG); + vm_stop(RSTATE_DEBUG); } if (qemu_shutdown_requested()) { qemu_kill_report(); monitor_protocol_event(QEVENT_SHUTDOWN, NULL); if (no_shutdown) { - vm_stop(VMSTOP_SHUTDOWN); + vm_stop(RSTATE_SHUTDOWN); } else break; } @@ -1485,6 +1597,10 @@ static void main_loop(void) cpu_synchronize_all_states(); qemu_system_reset(VMRESET_REPORT); resume_all_vcpus(); + if (runstate_check(RSTATE_PANICKED) || + runstate_check(RSTATE_SHUTDOWN)) { + runstate_set(RSTATE_PAUSED); + } } if (qemu_powerdown_requested()) { monitor_protocol_event(QEVENT_POWERDOWN, NULL); @@ -2203,6 +2319,8 @@ int main(int argc, char **argv, char **envp) g_mem_set_vtable(&mem_trace); g_thread_init(NULL); + runstate_init(); + init_clocks(); qemu_cache_utils_init(envp); @@ -2953,7 +3071,6 @@ int main(int argc, char **argv, char **envp) break; case QEMU_OPTION_incoming: incoming = optarg; - incoming_expected = true; break; case QEMU_OPTION_nodefaults: default_serial = 0; @@ -3439,6 +3556,7 @@ int main(int argc, char **argv, char **envp) } if (incoming) { + runstate_set(RSTATE_IN_MIGRATE); int ret = qemu_start_incoming_migration(incoming); if (ret < 0) { fprintf(stderr, "Migration failed. Exit code %s(%d), exiting.\n", @@ -3447,6 +3565,8 @@ int main(int argc, char **argv, char **envp) } } else if (autostart) { vm_start(); + } else { + runstate_set(RSTATE_PRE_LAUNCH); } os_setup_post(); @@ -736,7 +736,7 @@ static void cpu_handle_ioreq(void *opaque) * guest resumes and does a hlt with interrupts disabled which * causes Xen to powerdown the domain. */ - if (vm_running) { + if (runstate_is_running()) { if (qemu_shutdown_requested_get()) { destroy_hvm_domain(); } @@ -846,7 +846,8 @@ static void xen_main_loop_prepare(XenIOState *state) /* Initialise Xen */ -static void xen_change_state_handler(void *opaque, int running, int reason) +static void xen_change_state_handler(void *opaque, int running, + RunState state) { if (running) { /* record state running */ @@ -854,11 +855,12 @@ static void xen_change_state_handler(void *opaque, int running, int reason) } } -static void xen_hvm_change_state_handler(void *opaque, int running, int reason) +static void xen_hvm_change_state_handler(void *opaque, int running, + RunState rstate) { - XenIOState *state = opaque; + XenIOState *xstate = opaque; if (running) { - xen_main_loop_prepare(state); + xen_main_loop_prepare(xstate); } } |