diff options
387 files changed, 9625 insertions, 6201 deletions
diff --git a/.gitlab-ci.d/container-cross.yml b/.gitlab-ci.d/container-cross.yml index e0d75d5824..2848166ba3 100644 --- a/.gitlab-ci.d/container-cross.yml +++ b/.gitlab-ci.d/container-cross.yml @@ -95,6 +95,7 @@ riscv64-debian-cross-container: allow_failure: true variables: NAME: debian-riscv64-cross + QEMU_JOB_OPTIONAL: 1 # we can however build TCG tests using a non-sid base riscv64-debian-test-cross-container: diff --git a/.mailmap b/.mailmap index d214959288..94f19a0ac9 100644 --- a/.mailmap +++ b/.mailmap @@ -81,6 +81,9 @@ Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org> Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com> +Luc Michel <luc@lmichel.fr> <luc.michel@git.antfield.fr> +Luc Michel <luc@lmichel.fr> <luc.michel@greensocs.com> +Luc Michel <luc@lmichel.fr> <lmichel@kalray.eu> Radoslaw Biernacki <rad@semihalf.com> <radoslaw.biernacki@linaro.org> Paul Brook <paul@nowt.org> <paul@codesourcery.com> Paul Burton <paulburton@kernel.org> <paul.burton@mips.com> diff --git a/MAINTAINERS b/MAINTAINERS index 68d086a0f3..e1a96c1a6c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -248,7 +248,6 @@ F: disas/hppa.c LoongArch TCG CPUs M: Song Gao <gaosong@loongson.cn> -M: Xiaojuan Yang <yangxiaojuan@loongson.cn> S: Maintained F: target/loongarch/ F: tests/tcg/loongarch64/ @@ -296,6 +295,7 @@ S: Odd Fixes F: docs/system/openrisc/cpu-features.rst F: target/openrisc/ F: hw/openrisc/ +F: include/hw/openrisc/ F: tests/tcg/openrisc/ PowerPC TCG CPUs @@ -886,7 +886,7 @@ S: Odd Fixes F: hw/arm/raspi.c F: hw/arm/raspi_platform.h F: hw/*/bcm283* -F: include/hw/arm/raspi* +F: include/hw/arm/rasp* F: include/hw/*/bcm283* F: docs/system/arm/raspi.rst @@ -1180,10 +1180,12 @@ R: Helge Deller <deller@gmx.de> S: Odd Fixes F: configs/devices/hppa-softmmu/default.mak F: hw/hppa/ +F: hw/input/lasips2.c F: hw/net/*i82596* F: hw/misc/lasi.c F: hw/pci-host/astro.c F: hw/pci-host/dino.c +F: include/hw/input/lasips2.h F: include/hw/misc/lasi.h F: include/hw/net/lasi_82596.h F: include/hw/pci-host/astro.h @@ -1194,7 +1196,6 @@ F: roms/seabios-hppa/ LoongArch Machines ------------------ Virt -M: Xiaojuan Yang <yangxiaojuan@loongson.cn> M: Song Gao <gaosong@loongson.cn> S: Maintained F: docs/system/loongarch/virt.rst @@ -1327,10 +1328,7 @@ M: Philippe Mathieu-Daudé <philmd@linaro.org> R: Jiaxun Yang <jiaxun.yang@flygoat.com> S: Odd Fixes F: hw/mips/fuloong2e.c -F: hw/isa/vt82c686.c F: hw/pci-host/bonito.c -F: hw/usb/vt82c686-uhci-pci.c -F: include/hw/isa/vt82c686.h F: include/hw/pci-host/bonito.h F: tests/avocado/machine_mips_fuloong2e.py @@ -1342,6 +1340,7 @@ F: hw/intc/loongson_liointc.c F: hw/mips/loongson3_bootp.c F: hw/mips/loongson3_bootp.h F: hw/mips/loongson3_virt.c +F: include/hw/intc/loongson_liointc.h F: tests/avocado/machine_mips_loongson3v.py Boston @@ -2486,6 +2485,15 @@ S: Maintained F: hw/isa/piix4.c F: include/hw/southbridge/piix.h +VIA South Bridges (VT82C686B, VT8231) +M: BALATON Zoltan <balaton@eik.bme.hu> +M: Philippe Mathieu-Daudé <philmd@linaro.org> +R: Jiaxun Yang <jiaxun.yang@flygoat.com> +S: Maintained +F: hw/isa/vt82c686.c +F: hw/usb/vt82c686-uhci-pci.c +F: include/hw/isa/vt82c686.h + Firmware configuration (fw_cfg) M: Philippe Mathieu-Daudé <philmd@linaro.org> R: Gerd Hoffmann <kraxel@redhat.com> @@ -2894,6 +2902,7 @@ F: hw/mem/pc-dimm.c F: include/hw/mem/memory-device.h F: include/hw/mem/nvdimm.h F: include/hw/mem/pc-dimm.h +F: stubs/memory_device.c F: docs/nvdimm.txt SPICE @@ -3146,6 +3155,7 @@ M: Laurent Vivier <lvivier@redhat.com> R: Paolo Bonzini <pbonzini@redhat.com> S: Maintained F: system/qtest.c +F: include/sysemu/qtest.h F: accel/qtest/ F: tests/qtest/ F: docs/devel/qgraph.rst @@ -3867,7 +3877,7 @@ F: docs/block-replication.txt PVRDMA M: Yuval Shaia <yuval.shaia.ml@gmail.com> M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> -S: Maintained +S: Odd Fixes F: hw/rdma/* F: hw/rdma/vmw/* F: docs/pvrdma.txt diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 72e1d1141c..3f7eafe08c 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -174,13 +174,31 @@ void kvm_resample_fd_notify(int gsi) } } -int kvm_get_max_memslots(void) +unsigned int kvm_get_max_memslots(void) { KVMState *s = KVM_STATE(current_accel()); return s->nr_slots; } +unsigned int kvm_get_free_memslots(void) +{ + unsigned int used_slots = 0; + KVMState *s = kvm_state; + int i; + + kvm_slots_lock(); + for (i = 0; i < s->nr_as; i++) { + if (!s->as[i].ml) { + continue; + } + used_slots = MAX(used_slots, s->as[i].ml->nr_used_slots); + } + kvm_slots_unlock(); + + return s->nr_slots - used_slots; +} + /* Called with KVMMemoryListener.slots_lock held */ static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml) { @@ -196,19 +214,6 @@ static KVMSlot *kvm_get_free_slot(KVMMemoryListener *kml) return NULL; } -bool kvm_has_free_slot(MachineState *ms) -{ - KVMState *s = KVM_STATE(ms->accelerator); - bool result; - KVMMemoryListener *kml = &s->memory_listener; - - kvm_slots_lock(); - result = !!kvm_get_free_slot(kml); - kvm_slots_unlock(); - - return result; -} - /* Called with KVMMemoryListener.slots_lock held */ static KVMSlot *kvm_alloc_slot(KVMMemoryListener *kml) { @@ -1387,6 +1392,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, } start_addr += slot_size; size -= slot_size; + kml->nr_used_slots--; } while (size); return; } @@ -1412,6 +1418,7 @@ static void kvm_set_phys_mem(KVMMemoryListener *kml, ram_start_offset += slot_size; ram += slot_size; size -= slot_size; + kml->nr_used_slots++; } while (size); } diff --git a/accel/stubs/kvm-stub.c b/accel/stubs/kvm-stub.c index 235dc661bc..51f522e52e 100644 --- a/accel/stubs/kvm-stub.c +++ b/accel/stubs/kvm-stub.c @@ -109,9 +109,14 @@ int kvm_irqchip_remove_irqfd_notifier_gsi(KVMState *s, EventNotifier *n, return -ENOSYS; } -bool kvm_has_free_slot(MachineState *ms) +unsigned int kvm_get_max_memslots(void) { - return false; + return 0; +} + +unsigned int kvm_get_free_memslots(void) +{ + return 0; } void kvm_init_cpu_signals(CPUState *cpu) diff --git a/block.c b/block.c index af04c8ac6f..f9cf05ddcf 100644 --- a/block.c +++ b/block.c @@ -279,8 +279,9 @@ bool bdrv_is_read_only(BlockDriverState *bs) return !(bs->open_flags & BDRV_O_RDWR); } -static int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, - bool ignore_allow_rdw, Error **errp) +static int GRAPH_RDLOCK +bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, + bool ignore_allow_rdw, Error **errp) { IO_CODE(); @@ -371,8 +372,9 @@ char *bdrv_get_full_backing_filename_from_filename(const char *backed, * setting @errp. In all other cases, NULL will only be returned with * @errp set. */ -static char *bdrv_make_absolute_filename(BlockDriverState *relative_to, - const char *filename, Error **errp) +static char * GRAPH_RDLOCK +bdrv_make_absolute_filename(BlockDriverState *relative_to, + const char *filename, Error **errp) { char *dir, *full_name; @@ -1192,19 +1194,19 @@ static char *bdrv_child_get_parent_desc(BdrvChild *c) return g_strdup_printf("node '%s'", bdrv_get_node_name(parent)); } -static void bdrv_child_cb_drained_begin(BdrvChild *child) +static void GRAPH_RDLOCK bdrv_child_cb_drained_begin(BdrvChild *child) { BlockDriverState *bs = child->opaque; bdrv_do_drained_begin_quiesce(bs, NULL); } -static bool bdrv_child_cb_drained_poll(BdrvChild *child) +static bool GRAPH_RDLOCK bdrv_child_cb_drained_poll(BdrvChild *child) { BlockDriverState *bs = child->opaque; return bdrv_drain_poll(bs, NULL, false); } -static void bdrv_child_cb_drained_end(BdrvChild *child) +static void GRAPH_RDLOCK bdrv_child_cb_drained_end(BdrvChild *child) { BlockDriverState *bs = child->opaque; bdrv_drained_end(bs); @@ -1250,7 +1252,7 @@ static void bdrv_temp_snapshot_options(int *child_flags, QDict *child_options, *child_flags &= ~BDRV_O_NATIVE_AIO; } -static void bdrv_backing_attach(BdrvChild *c) +static void GRAPH_WRLOCK bdrv_backing_attach(BdrvChild *c) { BlockDriverState *parent = c->opaque; BlockDriverState *backing_hd = c->bs; @@ -1874,7 +1876,10 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, } if (file != NULL) { + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(blk_bs(file)); + bdrv_graph_rdunlock_main_loop(); + filename = blk_bs(file)->filename; } else { /* @@ -1901,7 +1906,9 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file, if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, ro)) { if (!ro && bdrv_is_whitelisted(drv, true)) { + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, NULL, NULL); + bdrv_graph_rdunlock_main_loop(); } else { ret = -ENOTSUP; } @@ -2966,6 +2973,8 @@ static void bdrv_child_free(BdrvChild *child) { assert(!child->bs); GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + assert(!child->next.le_prev); /* not in children list */ g_free(child->name); @@ -3644,7 +3653,10 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, implicit_backing = !strcmp(bs->auto_backing_file, bs->backing_file); } + bdrv_graph_rdlock_main_loop(); backing_filename = bdrv_get_full_backing_filename(bs, &local_err); + bdrv_graph_rdunlock_main_loop(); + if (local_err) { ret = -EINVAL; error_propagate(errp, local_err); @@ -3675,7 +3687,9 @@ int bdrv_open_backing_file(BlockDriverState *bs, QDict *parent_options, } if (implicit_backing) { + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(backing_hd); + bdrv_graph_rdunlock_main_loop(); pstrcpy(bs->auto_backing_file, sizeof(bs->auto_backing_file), backing_hd->filename); } @@ -4314,8 +4328,8 @@ static int bdrv_reset_options_allowed(BlockDriverState *bs, /* * Returns true if @child can be reached recursively from @bs */ -static bool bdrv_recurse_has_child(BlockDriverState *bs, - BlockDriverState *child) +static bool GRAPH_RDLOCK +bdrv_recurse_has_child(BlockDriverState *bs, BlockDriverState *child) { BdrvChild *c; @@ -4356,15 +4370,12 @@ static bool bdrv_recurse_has_child(BlockDriverState *bs, * * To be called with bs->aio_context locked. */ -static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, - BlockDriverState *bs, - QDict *options, - const BdrvChildClass *klass, - BdrvChildRole role, - bool parent_is_format, - QDict *parent_options, - int parent_flags, - bool keep_old_opts) +static BlockReopenQueue * GRAPH_RDLOCK +bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, BlockDriverState *bs, + QDict *options, const BdrvChildClass *klass, + BdrvChildRole role, bool parent_is_format, + QDict *parent_options, int parent_flags, + bool keep_old_opts) { assert(bs != NULL); @@ -4376,6 +4387,11 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue, GLOBAL_STATE_CODE(); + /* + * Strictly speaking, draining is illegal under GRAPH_RDLOCK. We know that + * we've been called with bdrv_graph_rdlock_main_loop(), though, so it's ok + * in practice. + */ bdrv_drained_begin(bs); if (bs_queue == NULL) { @@ -4517,6 +4533,7 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue, QDict *options, bool keep_old_opts) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); return bdrv_reopen_queue_child(bs_queue, bs, options, NULL, 0, false, NULL, 0, keep_old_opts); @@ -4736,9 +4753,10 @@ int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only, * Callers must make sure that their AioContext locking is still correct after * this. */ -static int bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, - bool is_backing, Transaction *tran, - Error **errp) +static int GRAPH_UNLOCKED +bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, + bool is_backing, Transaction *tran, + Error **errp) { BlockDriverState *bs = reopen_state->bs; BlockDriverState *new_child_bs; @@ -4748,6 +4766,7 @@ static int bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, QObject *value; const char *str; AioContext *ctx, *old_ctx; + bool has_child; int ret; GLOBAL_STATE_CODE(); @@ -4767,7 +4786,13 @@ static int bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, new_child_bs = bdrv_lookup_bs(NULL, str, errp); if (new_child_bs == NULL) { return -EINVAL; - } else if (bdrv_recurse_has_child(new_child_bs, bs)) { + } + + bdrv_graph_rdlock_main_loop(); + has_child = bdrv_recurse_has_child(new_child_bs, bs); + bdrv_graph_rdunlock_main_loop(); + + if (has_child) { error_setg(errp, "Making '%s' a %s child of '%s' would create a " "cycle", str, child_name, bs->node_name); return -EINVAL; @@ -4866,9 +4891,9 @@ static int bdrv_reopen_parse_file_or_backing(BDRVReopenState *reopen_state, * After calling this function, the transaction @change_child_tran may only be * completed while holding a writer lock for the graph. */ -static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, - BlockReopenQueue *queue, - Transaction *change_child_tran, Error **errp) +static int GRAPH_UNLOCKED +bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, + Transaction *change_child_tran, Error **errp) { int ret = -1; int old_flags; @@ -4930,7 +4955,10 @@ static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, * to r/w. Attempting to set to r/w may fail if either BDRV_O_ALLOW_RDWR is * not set, or if the BDS still has copy_on_read enabled */ read_only = !(reopen_state->flags & BDRV_O_RDWR); + + bdrv_graph_rdlock_main_loop(); ret = bdrv_can_set_read_only(reopen_state->bs, read_only, true, &local_err); + bdrv_graph_rdunlock_main_loop(); if (local_err) { error_propagate(errp, local_err); goto error; @@ -4953,7 +4981,9 @@ static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, if (local_err != NULL) { error_propagate(errp, local_err); } else { + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(reopen_state->bs); + bdrv_graph_rdunlock_main_loop(); error_setg(errp, "failed while preparing to reopen image '%s'", reopen_state->bs->filename); } @@ -4962,9 +4992,11 @@ static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, } else { /* It is currently mandatory to have a bdrv_reopen_prepare() * handler for each supported drv. */ + bdrv_graph_rdlock_main_loop(); error_setg(errp, "Block format '%s' used by node '%s' " "does not support reopening files", drv->format_name, bdrv_get_device_or_node_name(reopen_state->bs)); + bdrv_graph_rdunlock_main_loop(); ret = -1; goto error; } @@ -5010,6 +5042,8 @@ static int bdrv_reopen_prepare(BDRVReopenState *reopen_state, if (qdict_size(reopen_state->options)) { const QDictEntry *entry = qdict_first(reopen_state->options); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + do { QObject *new = entry->value; QObject *old = qdict_get(reopen_state->bs->options, entry->key); @@ -5083,7 +5117,7 @@ error: * makes them final by swapping the staging BlockDriverState contents into * the active BlockDriverState contents. */ -static void bdrv_reopen_commit(BDRVReopenState *reopen_state) +static void GRAPH_UNLOCKED bdrv_reopen_commit(BDRVReopenState *reopen_state) { BlockDriver *drv; BlockDriverState *bs; @@ -5100,6 +5134,8 @@ static void bdrv_reopen_commit(BDRVReopenState *reopen_state) drv->bdrv_reopen_commit(reopen_state); } + GRAPH_RDLOCK_GUARD_MAINLOOP(); + /* set BDS specific flags now */ qobject_unref(bs->explicit_options); qobject_unref(bs->options); @@ -5121,9 +5157,7 @@ static void bdrv_reopen_commit(BDRVReopenState *reopen_state) qdict_del(bs->explicit_options, "backing"); qdict_del(bs->options, "backing"); - bdrv_graph_rdlock_main_loop(); bdrv_refresh_limits(bs, NULL, NULL); - bdrv_graph_rdunlock_main_loop(); bdrv_refresh_total_sectors(bs, bs->total_sectors); } @@ -5131,7 +5165,7 @@ static void bdrv_reopen_commit(BDRVReopenState *reopen_state) * Abort the reopen, and delete and free the staged changes in * reopen_state */ -static void bdrv_reopen_abort(BDRVReopenState *reopen_state) +static void GRAPH_UNLOCKED bdrv_reopen_abort(BDRVReopenState *reopen_state) { BlockDriver *drv; @@ -5918,6 +5952,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, bdrv_ref(top); bdrv_drained_begin(base); + bdrv_graph_rdlock_main_loop(); if (!top->drv || !base->drv) { goto exit; @@ -5942,11 +5977,9 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, backing_file_str = base->filename; } - bdrv_graph_rdlock_main_loop(); QLIST_FOREACH(c, &top->parents, next_parent) { updated_children = g_slist_prepend(updated_children, c); } - bdrv_graph_rdunlock_main_loop(); /* * It seems correct to pass detach_subchain=true here, but it triggers @@ -5992,6 +6025,7 @@ int bdrv_drop_intermediate(BlockDriverState *top, BlockDriverState *base, ret = 0; exit: + bdrv_graph_rdunlock_main_loop(); bdrv_drained_end(base); bdrv_unref(top); return ret; @@ -6282,6 +6316,7 @@ BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, BlockDriverState *bs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); list = NULL; QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) { @@ -6667,7 +6702,8 @@ void coroutine_fn bdrv_co_debug_event(BlockDriverState *bs, BlkdebugEvent event) bs->drv->bdrv_co_debug_event(bs, event); } -static BlockDriverState *bdrv_find_debug_node(BlockDriverState *bs) +static BlockDriverState * GRAPH_RDLOCK +bdrv_find_debug_node(BlockDriverState *bs) { GLOBAL_STATE_CODE(); while (bs && bs->drv && !bs->drv->bdrv_debug_breakpoint) { @@ -6686,6 +6722,8 @@ int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event, const char *tag) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_find_debug_node(bs); if (bs) { return bs->drv->bdrv_debug_breakpoint(bs, event, tag); @@ -6697,6 +6735,8 @@ int bdrv_debug_breakpoint(BlockDriverState *bs, const char *event, int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_find_debug_node(bs); if (bs) { return bs->drv->bdrv_debug_remove_breakpoint(bs, tag); @@ -6708,6 +6748,8 @@ int bdrv_debug_remove_breakpoint(BlockDriverState *bs, const char *tag) int bdrv_debug_resume(BlockDriverState *bs, const char *tag) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + while (bs && (!bs->drv || !bs->drv->bdrv_debug_resume)) { bs = bdrv_primary_bs(bs); } @@ -6722,6 +6764,8 @@ int bdrv_debug_resume(BlockDriverState *bs, const char *tag) bool bdrv_debug_is_suspended(BlockDriverState *bs, const char *tag) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + while (bs && bs->drv && !bs->drv->bdrv_debug_is_suspended) { bs = bdrv_primary_bs(bs); } @@ -6750,6 +6794,7 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, BlockDriverState *bs_below; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (!bs || !bs->drv || !backing_file) { return NULL; @@ -6961,6 +7006,7 @@ void bdrv_activate_all(Error **errp) BdrvNextIterator it; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); @@ -6976,7 +7022,8 @@ void bdrv_activate_all(Error **errp) } } -static bool bdrv_has_bds_parent(BlockDriverState *bs, bool only_active) +static bool GRAPH_RDLOCK +bdrv_has_bds_parent(BlockDriverState *bs, bool only_active) { BdrvChild *parent; GLOBAL_STATE_CODE(); @@ -6993,14 +7040,13 @@ static bool bdrv_has_bds_parent(BlockDriverState *bs, bool only_active) return false; } -static int bdrv_inactivate_recurse(BlockDriverState *bs) +static int GRAPH_RDLOCK bdrv_inactivate_recurse(BlockDriverState *bs) { BdrvChild *child, *parent; int ret; uint64_t cumulative_perms, cumulative_shared_perms; GLOBAL_STATE_CODE(); - GRAPH_RDLOCK_GUARD_MAINLOOP(); if (!bs->drv) { return -ENOMEDIUM; @@ -7066,6 +7112,7 @@ int bdrv_inactivate_all(void) GSList *aio_ctxs = NULL, *ctx; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { AioContext *aio_context = bdrv_get_aio_context(bs); @@ -7205,6 +7252,7 @@ bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp) { BdrvOpBlocker *blocker; GLOBAL_STATE_CODE(); + assert((int) op >= 0 && op < BLOCK_OP_TYPE_MAX); if (!QLIST_EMPTY(&bs->op_blockers[op])) { blocker = QLIST_FIRST(&bs->op_blockers[op]); diff --git a/block/backup.c b/block/backup.c index db3791f4d1..9a3c4bdc82 100644 --- a/block/backup.c +++ b/block/backup.c @@ -374,6 +374,7 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs, assert(bs); assert(target); GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); /* QMP interface protects us from these cases */ assert(sync_mode != MIRROR_SYNC_MODE_INCREMENTAL); diff --git a/block/block-backend.c b/block/block-backend.c index efe2e7cbf8..39aac1bbce 100644 --- a/block/block-backend.c +++ b/block/block-backend.c @@ -780,11 +780,12 @@ BlockDriverState *blk_bs(BlockBackend *blk) return blk->root ? blk->root->bs : NULL; } -static BlockBackend *bdrv_first_blk(BlockDriverState *bs) +static BlockBackend * GRAPH_RDLOCK bdrv_first_blk(BlockDriverState *bs) { BdrvChild *child; GLOBAL_STATE_CODE(); + assert_bdrv_graph_readable(); QLIST_FOREACH(child, &bs->parents, next_parent) { if (child->klass == &child_root) { @@ -812,6 +813,8 @@ bool bdrv_is_root_node(BlockDriverState *bs) BdrvChild *c; GLOBAL_STATE_CODE(); + assert_bdrv_graph_readable(); + QLIST_FOREACH(c, &bs->parents, next_parent) { if (c->klass != &child_root) { return false; @@ -2259,6 +2262,7 @@ void blk_activate(BlockBackend *blk, Error **errp) if (qemu_in_coroutine()) { bdrv_co_activate(bs, errp); } else { + GRAPH_RDLOCK_GUARD_MAINLOOP(); bdrv_activate(bs, errp); } } @@ -2384,6 +2388,7 @@ bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp) { BlockDriverState *bs = blk_bs(blk); GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (!bs) { return false; @@ -2901,6 +2906,8 @@ const BdrvChild *blk_root(BlockBackend *blk) int blk_make_empty(BlockBackend *blk, Error **errp) { GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (!blk_is_available(blk)) { error_setg(errp, "No medium inserted"); return -ENOMEDIUM; diff --git a/block/bochs.c b/block/bochs.c index 66e7a58e5e..8c659fa9b9 100644 --- a/block/bochs.c +++ b/block/bochs.c @@ -106,7 +106,9 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags, int ret; /* No write support yet */ + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, NULL, errp); + bdrv_graph_rdunlock_main_loop(); if (ret < 0) { return ret; } diff --git a/block/cloop.c b/block/cloop.c index 835a0fe3da..773d7918be 100644 --- a/block/cloop.c +++ b/block/cloop.c @@ -67,7 +67,9 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags, uint32_t offsets_size, max_compressed_block_size = 1, i; int ret; + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, NULL, errp); + bdrv_graph_rdunlock_main_loop(); if (ret < 0) { return ret; } diff --git a/block/commit.c b/block/commit.c index aa45beb0f0..43d1de7577 100644 --- a/block/commit.c +++ b/block/commit.c @@ -434,6 +434,7 @@ int bdrv_commit(BlockDriverState *bs) Error *local_err = NULL; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (!drv) return -ENOMEDIUM; diff --git a/block/copy-before-write.c b/block/copy-before-write.c index aeaff3bb82..4ffabc5ca2 100644 --- a/block/copy-before-write.c +++ b/block/copy-before-write.c @@ -305,7 +305,7 @@ cbw_co_snapshot_block_status(BlockDriverState *bs, return -EACCES; } - ret = bdrv_block_status(child->bs, offset, cur_bytes, pnum, map, file); + ret = bdrv_co_block_status(child->bs, offset, cur_bytes, pnum, map, file); if (child == s->target) { /* * We refer to s->target only for areas that we've written to it. diff --git a/block/copy-on-read.c b/block/copy-on-read.c index b4d6b7efc3..5149fcf63a 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -146,11 +146,11 @@ cor_co_preadv_part(BlockDriverState *bs, int64_t offset, int64_t bytes, local_flags = flags; /* In case of failure, try to copy-on-read anyway */ - ret = bdrv_is_allocated(bs->file->bs, offset, bytes, &n); + ret = bdrv_co_is_allocated(bs->file->bs, offset, bytes, &n); if (ret <= 0) { - ret = bdrv_is_allocated_above(bdrv_backing_chain_next(bs->file->bs), - state->bottom_bs, true, offset, - n, &n); + ret = bdrv_co_is_allocated_above(bdrv_backing_chain_next(bs->file->bs), + state->bottom_bs, true, offset, + n, &n); if (ret > 0 || ret < 0) { local_flags |= BDRV_REQ_COPY_ON_READ; } diff --git a/block/crypto.c b/block/crypto.c index c9c9a39fa3..b3f0233d53 100644 --- a/block/crypto.c +++ b/block/crypto.c @@ -828,7 +828,7 @@ block_crypto_amend_options_generic_luks(BlockDriverState *bs, errp); } -static int +static int GRAPH_RDLOCK block_crypto_amend_options_luks(BlockDriverState *bs, QemuOpts *opts, BlockDriverAmendStatusCB *status_cb, @@ -841,8 +841,6 @@ block_crypto_amend_options_luks(BlockDriverState *bs, QCryptoBlockAmendOptions *amend_options = NULL; int ret = -EINVAL; - assume_graph_lock(); /* FIXME */ - assert(crypto); assert(crypto->block); diff --git a/block/curl.c b/block/curl.c index 0fc42d03d7..419f7c89ef 100644 --- a/block/curl.c +++ b/block/curl.c @@ -696,8 +696,10 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags, const char *protocol_delimiter; int ret; + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, "curl driver does not support writes", errp); + bdrv_graph_rdunlock_main_loop(); if (ret < 0) { return ret; } diff --git a/block/dmg.c b/block/dmg.c index 06a0244a9c..38ee72bbe5 100644 --- a/block/dmg.c +++ b/block/dmg.c @@ -452,7 +452,9 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags, int64_t offset; int ret; + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, NULL, errp); + bdrv_graph_rdunlock_main_loop(); if (ret < 0) { return ret; } diff --git a/block/export/export.c b/block/export/export.c index 10316b43c5..a8f274e526 100644 --- a/block/export/export.c +++ b/block/export/export.c @@ -83,6 +83,8 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) uint64_t perm; int ret; + GLOBAL_STATE_CODE(); + if (!id_wellformed(export->id)) { error_setg(errp, "Invalid block export id"); return NULL; @@ -145,7 +147,9 @@ BlockExport *blk_exp_add(BlockExportOptions *export, Error **errp) * access since the export could be available before migration handover. * ctx was acquired in the caller. */ + bdrv_graph_rdlock_main_loop(); bdrv_activate(bs, NULL); + bdrv_graph_rdunlock_main_loop(); perm = BLK_PERM_CONSISTENT_READ; if (export->writable) { diff --git a/block/gluster.c b/block/gluster.c index ad5fadbe79..cc74af06dc 100644 --- a/block/gluster.c +++ b/block/gluster.c @@ -863,11 +863,13 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options, if (ret == -EACCES || ret == -EROFS) { /* Try to degrade to read-only, but if it doesn't work, still use the * normal error message. */ + bdrv_graph_rdlock_main_loop(); if (bdrv_apply_auto_read_only(bs, NULL, NULL) == 0) { open_flags = (open_flags & ~O_RDWR) | O_RDONLY; s->fd = glfs_open(s->glfs, gconf->path, open_flags); ret = s->fd ? 0 : -errno; } + bdrv_graph_rdunlock_main_loop(); } s->supports_seek_data = qemu_gluster_test_seek(s->fd); diff --git a/block/graph-lock.c b/block/graph-lock.c index 58a799065f..e5525ee2db 100644 --- a/block/graph-lock.c +++ b/block/graph-lock.c @@ -106,12 +106,13 @@ static uint32_t reader_count(void) return rd; } -void bdrv_graph_wrlock(BlockDriverState *bs) +void no_coroutine_fn bdrv_graph_wrlock(BlockDriverState *bs) { AioContext *ctx = NULL; GLOBAL_STATE_CODE(); assert(!qatomic_read(&has_writer)); + assert(!qemu_in_coroutine()); /* * Release only non-mainloop AioContext. The mainloop often relies on the diff --git a/block/io.c b/block/io.c index e7f9448d5a..527a1de04e 100644 --- a/block/io.c +++ b/block/io.c @@ -42,13 +42,18 @@ /* Maximum bounce buffer for copy-on-read and write zeroes, in bytes */ #define MAX_BOUNCE_BUFFER (32768 << BDRV_SECTOR_BITS) -static void bdrv_parent_cb_resize(BlockDriverState *bs); +static void coroutine_fn GRAPH_RDLOCK +bdrv_parent_cb_resize(BlockDriverState *bs); + static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes, BdrvRequestFlags flags); -static void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) +static void GRAPH_RDLOCK +bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c, *next; + IO_OR_GS_CODE(); + assert_bdrv_graph_readable(); QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { if (c == ignore) { @@ -70,9 +75,12 @@ void bdrv_parent_drained_end_single(BdrvChild *c) } } -static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) +static void GRAPH_RDLOCK +bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) { BdrvChild *c; + IO_OR_GS_CODE(); + assert_bdrv_graph_readable(); QLIST_FOREACH(c, &bs->parents, next_parent) { if (c == ignore) { @@ -84,17 +92,22 @@ static void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore) bool bdrv_parent_drained_poll_single(BdrvChild *c) { + IO_OR_GS_CODE(); + if (c->klass->drained_poll) { return c->klass->drained_poll(c); } return false; } -static bool bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore, - bool ignore_bds_parents) +static bool GRAPH_RDLOCK +bdrv_parent_drained_poll(BlockDriverState *bs, BdrvChild *ignore, + bool ignore_bds_parents) { BdrvChild *c, *next; bool busy = false; + IO_OR_GS_CODE(); + assert_bdrv_graph_readable(); QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) { if (c == ignore || (ignore_bds_parents && c->klass->parent_is_bds)) { @@ -114,6 +127,7 @@ void bdrv_parent_drained_begin_single(BdrvChild *c) c->quiesced_parent = true; if (c->klass->drained_begin) { + /* called with rdlock taken, but it doesn't really need it. */ c->klass->drained_begin(c); } } @@ -263,6 +277,9 @@ bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, static bool bdrv_drain_poll_top_level(BlockDriverState *bs, BdrvChild *ignore_parent) { + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + return bdrv_drain_poll(bs, ignore_parent, false); } @@ -362,6 +379,7 @@ static void bdrv_do_drained_begin(BlockDriverState *bs, BdrvChild *parent, /* Stop things in parent-to-child order */ if (qatomic_fetch_inc(&bs->quiesce_counter) == 0) { + GRAPH_RDLOCK_GUARD_MAINLOOP(); bdrv_parent_drained_begin(bs, parent); if (bs->drv && bs->drv->bdrv_drain_begin) { bs->drv->bdrv_drain_begin(bs); @@ -408,12 +426,16 @@ static void bdrv_do_drained_end(BlockDriverState *bs, BdrvChild *parent) bdrv_co_yield_to_drain(bs, false, parent, false); return; } + + /* At this point, we should be always running in the main loop. */ + GLOBAL_STATE_CODE(); assert(bs->quiesce_counter > 0); GLOBAL_STATE_CODE(); /* Re-enable things in child-to-parent order */ old_quiesce_counter = qatomic_fetch_dec(&bs->quiesce_counter); if (old_quiesce_counter == 1) { + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bs->drv && bs->drv->bdrv_drain_end) { bs->drv->bdrv_drain_end(bs); } @@ -437,6 +459,8 @@ void bdrv_drain(BlockDriverState *bs) static void bdrv_drain_assert_idle(BlockDriverState *bs) { BdrvChild *child, *next; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); assert(qatomic_read(&bs->in_flight) == 0); QLIST_FOREACH_SAFE(child, &bs->children, next, next) { @@ -450,7 +474,9 @@ static bool bdrv_drain_all_poll(void) { BlockDriverState *bs = NULL; bool result = false; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); /* bdrv_drain_poll() can't make changes to the graph and we are holding the * main AioContext lock, so iterating bdrv_next_all_states() is safe. */ @@ -1223,8 +1249,8 @@ bdrv_co_do_copy_on_readv(BdrvChild *child, int64_t offset, int64_t bytes, ret = 1; /* "already allocated", so nothing will be copied */ pnum = MIN(align_bytes, max_transfer); } else { - ret = bdrv_is_allocated(bs, align_offset, - MIN(align_bytes, max_transfer), &pnum); + ret = bdrv_co_is_allocated(bs, align_offset, + MIN(align_bytes, max_transfer), &pnum); if (ret < 0) { /* * Safe to treat errors in querying allocation as if @@ -1371,7 +1397,7 @@ bdrv_aligned_preadv(BdrvChild *child, BdrvTrackedRequest *req, /* The flag BDRV_REQ_COPY_ON_READ has reached its addressee */ flags &= ~BDRV_REQ_COPY_ON_READ; - ret = bdrv_is_allocated(bs, offset, bytes, &pnum); + ret = bdrv_co_is_allocated(bs, offset, bytes, &pnum); if (ret < 0) { goto out; } @@ -2003,7 +2029,7 @@ bdrv_co_write_req_prepare(BdrvChild *child, int64_t offset, int64_t bytes, } } -static inline void coroutine_fn +static inline void coroutine_fn GRAPH_RDLOCK bdrv_co_write_req_finish(BdrvChild *child, int64_t offset, int64_t bytes, BdrvTrackedRequest *req, int ret) { @@ -2330,6 +2356,7 @@ int bdrv_flush_all(void) int result = 0; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); /* * bdrv queue is managed by record/replay, @@ -2383,9 +2410,9 @@ int bdrv_flush_all(void) * set to the host mapping and BDS corresponding to the guest offset. */ static int coroutine_fn GRAPH_RDLOCK -bdrv_co_block_status(BlockDriverState *bs, bool want_zero, - int64_t offset, int64_t bytes, - int64_t *pnum, int64_t *map, BlockDriverState **file) +bdrv_co_do_block_status(BlockDriverState *bs, bool want_zero, + int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, BlockDriverState **file) { int64_t total_size; int64_t n; /* bytes */ @@ -2544,8 +2571,8 @@ bdrv_co_block_status(BlockDriverState *bs, bool want_zero, if (ret & BDRV_BLOCK_RAW) { assert(ret & BDRV_BLOCK_OFFSET_VALID && local_file); - ret = bdrv_co_block_status(local_file, want_zero, local_map, - *pnum, pnum, &local_map, &local_file); + ret = bdrv_co_do_block_status(local_file, want_zero, local_map, + *pnum, pnum, &local_map, &local_file); goto out; } @@ -2572,8 +2599,8 @@ bdrv_co_block_status(BlockDriverState *bs, bool want_zero, int64_t file_pnum; int ret2; - ret2 = bdrv_co_block_status(local_file, want_zero, local_map, - *pnum, &file_pnum, NULL, NULL); + ret2 = bdrv_co_do_block_status(local_file, want_zero, local_map, + *pnum, &file_pnum, NULL, NULL); if (ret2 >= 0) { /* Ignore errors. This is just providing extra information, it * is useful but not necessary. @@ -2640,7 +2667,8 @@ bdrv_co_common_block_status_above(BlockDriverState *bs, return 0; } - ret = bdrv_co_block_status(bs, want_zero, offset, bytes, pnum, map, file); + ret = bdrv_co_do_block_status(bs, want_zero, offset, bytes, pnum, + map, file); ++*depth; if (ret < 0 || *pnum == 0 || ret & BDRV_BLOCK_ALLOCATED || bs == base) { return ret; @@ -2656,8 +2684,8 @@ bdrv_co_common_block_status_above(BlockDriverState *bs, for (p = bdrv_filter_or_cow_bs(bs); include_base || p != base; p = bdrv_filter_or_cow_bs(p)) { - ret = bdrv_co_block_status(p, want_zero, offset, bytes, pnum, map, - file); + ret = bdrv_co_do_block_status(p, want_zero, offset, bytes, pnum, + map, file); ++*depth; if (ret < 0) { return ret; @@ -2723,21 +2751,13 @@ int coroutine_fn bdrv_co_block_status_above(BlockDriverState *bs, bytes, pnum, map, file, NULL); } -int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, - int64_t offset, int64_t bytes, int64_t *pnum, - int64_t *map, BlockDriverState **file) -{ - IO_CODE(); - return bdrv_common_block_status_above(bs, base, false, true, offset, bytes, - pnum, map, file, NULL); -} - -int bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, - int64_t *pnum, int64_t *map, BlockDriverState **file) +int coroutine_fn bdrv_co_block_status(BlockDriverState *bs, int64_t offset, + int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file) { IO_CODE(); - return bdrv_block_status_above(bs, bdrv_filter_or_cow_bs(bs), - offset, bytes, pnum, map, file); + return bdrv_co_block_status_above(bs, bdrv_filter_or_cow_bs(bs), + offset, bytes, pnum, map, file); } /* @@ -2784,45 +2804,6 @@ int coroutine_fn bdrv_co_is_allocated(BlockDriverState *bs, int64_t offset, return !!(ret & BDRV_BLOCK_ALLOCATED); } -int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, - int64_t *pnum) -{ - int ret; - int64_t dummy; - IO_CODE(); - - ret = bdrv_common_block_status_above(bs, bs, true, false, offset, - bytes, pnum ? pnum : &dummy, NULL, - NULL, NULL); - if (ret < 0) { - return ret; - } - return !!(ret & BDRV_BLOCK_ALLOCATED); -} - -/* See bdrv_is_allocated_above for documentation */ -int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top, - BlockDriverState *base, - bool include_base, int64_t offset, - int64_t bytes, int64_t *pnum) -{ - int depth; - int ret; - IO_CODE(); - - ret = bdrv_co_common_block_status_above(top, base, include_base, false, - offset, bytes, pnum, NULL, NULL, - &depth); - if (ret < 0) { - return ret; - } - - if (ret & BDRV_BLOCK_ALLOCATED) { - return depth; - } - return 0; -} - /* * Given an image chain: ... -> [BASE] -> [INTER1] -> [INTER2] -> [TOP] * @@ -2840,18 +2821,18 @@ int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *top, * words, the result is not necessarily the maximum possible range); * but 'pnum' will only be 0 when end of file is reached. */ -int bdrv_is_allocated_above(BlockDriverState *top, - BlockDriverState *base, - bool include_base, int64_t offset, - int64_t bytes, int64_t *pnum) +int coroutine_fn bdrv_co_is_allocated_above(BlockDriverState *bs, + BlockDriverState *base, + bool include_base, int64_t offset, + int64_t bytes, int64_t *pnum) { int depth; int ret; IO_CODE(); - ret = bdrv_common_block_status_above(top, base, include_base, false, - offset, bytes, pnum, NULL, NULL, - &depth); + ret = bdrv_co_common_block_status_above(bs, base, include_base, false, + offset, bytes, pnum, NULL, NULL, + &depth); if (ret < 0) { return ret; } @@ -3551,9 +3532,13 @@ int coroutine_fn bdrv_co_copy_range(BdrvChild *src, int64_t src_offset, bytes, read_flags, write_flags); } -static void bdrv_parent_cb_resize(BlockDriverState *bs) +static void coroutine_fn GRAPH_RDLOCK +bdrv_parent_cb_resize(BlockDriverState *bs) { BdrvChild *c; + + assert_bdrv_graph_readable(); + QLIST_FOREACH(c, &bs->parents, next_parent) { if (c->klass->resize) { c->klass->resize(c); diff --git a/block/iscsi.c b/block/iscsi.c index 5640c8b565..2ff14b7472 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -1925,7 +1925,9 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags, /* Check the write protect flag of the LUN if we want to write */ if (iscsilun->type == TYPE_DISK && (flags & BDRV_O_RDWR) && iscsilun->write_protected) { + bdrv_graph_rdlock_main_loop(); ret = bdrv_apply_auto_read_only(bs, "LUN is write protected", errp); + bdrv_graph_rdunlock_main_loop(); if (ret < 0) { goto out; } diff --git a/block/mirror.c b/block/mirror.c index 3cc0757a03..dcd88de2e3 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -559,9 +559,9 @@ static void coroutine_fn mirror_iteration(MirrorBlockJob *s) assert(!(offset % s->granularity)); WITH_GRAPH_RDLOCK_GUARD() { - ret = bdrv_block_status_above(source, NULL, offset, - nb_chunks * s->granularity, - &io_bytes, NULL, NULL); + ret = bdrv_co_block_status_above(source, NULL, offset, + nb_chunks * s->granularity, + &io_bytes, NULL, NULL); } if (ret < 0) { io_bytes = MIN(nb_chunks * s->granularity, max_io_bytes); @@ -879,8 +879,8 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) } WITH_GRAPH_RDLOCK_GUARD() { - ret = bdrv_is_allocated_above(bs, s->base_overlay, true, offset, - bytes, &count); + ret = bdrv_co_is_allocated_above(bs, s->base_overlay, true, offset, + bytes, &count); } if (ret < 0) { return ret; diff --git a/block/monitor/block-hmp-cmds.c b/block/monitor/block-hmp-cmds.c index ca2599de44..7645c7e5fb 100644 --- a/block/monitor/block-hmp-cmds.c +++ b/block/monitor/block-hmp-cmds.c @@ -144,6 +144,9 @@ void hmp_drive_del(Monitor *mon, const QDict *qdict) AioContext *aio_context; Error *local_err = NULL; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_find_node(id); if (bs) { qmp_blockdev_del(id, &local_err); @@ -896,6 +899,8 @@ void hmp_info_snapshots(Monitor *mon, const QDict *qdict) SnapshotEntry *snapshot_entry; Error *err = NULL; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_all_find_vmstate_bs(NULL, false, NULL, &err); if (!bs) { error_report_err(err); diff --git a/block/nbd.c b/block/nbd.c index 52ebc8b2f5..b9d4f935e0 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -275,7 +275,8 @@ static bool nbd_client_will_reconnect(BDRVNBDState *s) * Return failure if the server's advertised options are incompatible with the * client's needs. */ -static int nbd_handle_updated_info(BlockDriverState *bs, Error **errp) +static int coroutine_fn GRAPH_RDLOCK +nbd_handle_updated_info(BlockDriverState *bs, Error **errp) { BDRVNBDState *s = (BDRVNBDState *)bs->opaque; int ret; diff --git a/block/nfs.c b/block/nfs.c index c24df49747..f737e19cd3 100644 --- a/block/nfs.c +++ b/block/nfs.c @@ -843,7 +843,7 @@ static void nfs_refresh_filename(BlockDriverState *bs) } } -static char *nfs_dirname(BlockDriverState *bs, Error **errp) +static char * GRAPH_RDLOCK nfs_dirname(BlockDriverState *bs, Error **errp) { NFSClient *client = bs->opaque; diff --git a/block/parallels.c b/block/parallels.c index d026ce9e2f..6b46623241 100644 --- a/block/parallels.c +++ b/block/parallels.c @@ -1363,9 +1363,12 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags, bitmap_new(DIV_ROUND_UP(s->header_size, s->bat_dirty_block)); /* Disable migration until bdrv_activate method is added */ + bdrv_graph_rdlock_main_loop(); error_setg(&s->migration_blocker, "The Parallels format used by node '%s' " "does not support live migration", bdrv_get_device_or_node_name(bs)); + bdrv_graph_rdunlock_main_loop(); + ret = migrate_add_blocker(s->migration_blocker, errp); if (ret < 0) { error_setg(errp, "Migration blocker error"); diff --git a/block/qapi-sysemu.c b/block/qapi-sysemu.c index ef07151892..3f614cbc04 100644 --- a/block/qapi-sysemu.c +++ b/block/qapi-sysemu.c @@ -169,14 +169,16 @@ void qmp_blockdev_close_tray(const char *device, } } -static void blockdev_remove_medium(const char *device, const char *id, - Error **errp) +static void GRAPH_UNLOCKED +blockdev_remove_medium(const char *device, const char *id, Error **errp) { BlockBackend *blk; BlockDriverState *bs; AioContext *aio_context; bool has_attached_device; + GLOBAL_STATE_CODE(); + blk = qmp_get_blk(device, id, errp); if (!blk) { return; @@ -205,9 +207,12 @@ static void blockdev_remove_medium(const char *device, const char *id, aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); + bdrv_graph_rdlock_main_loop(); if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_EJECT, errp)) { + bdrv_graph_rdunlock_main_loop(); goto out; } + bdrv_graph_rdunlock_main_loop(); blk_remove_bs(blk); @@ -279,6 +284,8 @@ static void blockdev_insert_medium(const char *device, const char *id, BlockBackend *blk; BlockDriverState *bs; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + blk = qmp_get_blk(device, id, errp); if (!blk) { return; diff --git a/block/qapi.c b/block/qapi.c index 1cbb0935ff..82a30b38fe 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -225,9 +225,8 @@ int bdrv_query_snapshot_info_list(BlockDriverState *bs, * Helper function for other query info functions. Store information about @bs * in @info, setting @errp on error. */ -static void bdrv_do_query_node_info(BlockDriverState *bs, - BlockNodeInfo *info, - Error **errp) +static void GRAPH_RDLOCK +bdrv_do_query_node_info(BlockDriverState *bs, BlockNodeInfo *info, Error **errp) { int64_t size; const char *backing_filename; @@ -423,8 +422,8 @@ fail: } /* @p_info will be set only on success. */ -static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info, - Error **errp) +static void GRAPH_RDLOCK +bdrv_query_info(BlockBackend *blk, BlockInfo **p_info, Error **errp) { BlockInfo *info = g_malloc0(sizeof(*info)); BlockDriverState *bs = blk_bs(blk); @@ -672,6 +671,8 @@ BlockInfoList *qmp_query_block(Error **errp) BlockBackend *blk; Error *local_err = NULL; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + for (blk = blk_all_next(NULL); blk; blk = blk_all_next(blk)) { BlockInfoList *info; diff --git a/block/qcow.c b/block/qcow.c index d56d24ab6d..38a16253b8 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -301,9 +301,12 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags, } /* Disable migration when qcow images are used */ + bdrv_graph_rdlock_main_loop(); error_setg(&s->migration_blocker, "The qcow format used by node '%s' " "does not support live migration", bdrv_get_device_or_node_name(bs)); + bdrv_graph_rdunlock_main_loop(); + ret = migrate_add_blocker(s->migration_blocker, errp); if (ret < 0) { error_free(s->migration_blocker); diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index ffd5cd3b23..3058309c47 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -156,10 +156,9 @@ static int64_t get_bitmap_bytes_needed(int64_t len, uint32_t granularity) return DIV_ROUND_UP(num_bits, 8); } -static int check_constraints_on_bitmap(BlockDriverState *bs, - const char *name, - uint32_t granularity, - Error **errp) +static int GRAPH_RDLOCK +check_constraints_on_bitmap(BlockDriverState *bs, const char *name, + uint32_t granularity, Error **errp) { BDRVQcow2State *s = bs->opaque; int granularity_bits = ctz32(granularity); @@ -204,8 +203,9 @@ static int check_constraints_on_bitmap(BlockDriverState *bs, return 0; } -static void clear_bitmap_table(BlockDriverState *bs, uint64_t *bitmap_table, - uint32_t bitmap_table_size) +static void GRAPH_RDLOCK +clear_bitmap_table(BlockDriverState *bs, uint64_t *bitmap_table, + uint32_t bitmap_table_size) { BDRVQcow2State *s = bs->opaque; int i; @@ -259,7 +259,8 @@ fail: return ret; } -static int free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) +static int GRAPH_RDLOCK +free_bitmap_clusters(BlockDriverState *bs, Qcow2BitmapTable *tb) { int ret; uint64_t *bitmap_table; @@ -730,8 +731,9 @@ out: * Store bitmap list to qcow2 image as a bitmap directory. * Everything is checked. */ -static int bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list, - uint64_t *offset, uint64_t *size, bool in_place) +static int GRAPH_RDLOCK +bitmap_list_store(BlockDriverState *bs, Qcow2BitmapList *bm_list, + uint64_t *offset, uint64_t *size, bool in_place) { int ret; uint8_t *dir; @@ -829,8 +831,9 @@ fail: * Bitmap List end */ -static int update_ext_header_and_dir_in_place(BlockDriverState *bs, - Qcow2BitmapList *bm_list) +static int GRAPH_RDLOCK +update_ext_header_and_dir_in_place(BlockDriverState *bs, + Qcow2BitmapList *bm_list) { BDRVQcow2State *s = bs->opaque; int ret; @@ -877,8 +880,8 @@ static int update_ext_header_and_dir_in_place(BlockDriverState *bs, */ } -static int update_ext_header_and_dir(BlockDriverState *bs, - Qcow2BitmapList *bm_list) +static int GRAPH_RDLOCK +update_ext_header_and_dir(BlockDriverState *bs, Qcow2BitmapList *bm_list) { BDRVQcow2State *s = bs->opaque; int ret; @@ -1271,9 +1274,9 @@ out: /* store_bitmap_data() * Store bitmap to image, filling bitmap table accordingly. */ -static uint64_t *store_bitmap_data(BlockDriverState *bs, - BdrvDirtyBitmap *bitmap, - uint32_t *bitmap_table_size, Error **errp) +static uint64_t * GRAPH_RDLOCK +store_bitmap_data(BlockDriverState *bs, BdrvDirtyBitmap *bitmap, + uint32_t *bitmap_table_size, Error **errp) { int ret; BDRVQcow2State *s = bs->opaque; @@ -1370,7 +1373,8 @@ fail: * Store bm->dirty_bitmap to qcow2. * Set bm->table_offset and bm->table_size accordingly. */ -static int store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp) +static int GRAPH_RDLOCK +store_bitmap(BlockDriverState *bs, Qcow2Bitmap *bm, Error **errp) { int ret; uint64_t *tb; diff --git a/block/qcow2-cache.c b/block/qcow2-cache.c index 01c67bdddc..23d9588b08 100644 --- a/block/qcow2-cache.c +++ b/block/qcow2-cache.c @@ -163,7 +163,8 @@ int qcow2_cache_destroy(Qcow2Cache *c) return 0; } -static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c) +static int GRAPH_RDLOCK +qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c) { int ret; @@ -178,7 +179,8 @@ static int qcow2_cache_flush_dependency(BlockDriverState *bs, Qcow2Cache *c) return 0; } -static int qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) +static int GRAPH_RDLOCK +qcow2_cache_entry_flush(BlockDriverState *bs, Qcow2Cache *c, int i) { BDRVQcow2State *s = bs->opaque; int ret = 0; @@ -318,8 +320,9 @@ int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c) return 0; } -static int qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, - uint64_t offset, void **table, bool read_from_disk) +static int GRAPH_RDLOCK +qcow2_cache_do_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, + void **table, bool read_from_disk) { BDRVQcow2State *s = bs->opaque; int i; diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index f4f6cd6ad0..904f00d1b3 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -207,8 +207,9 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, * the cache is used; otherwise the L2 slice is loaded from the image * file. */ -static int l2_load(BlockDriverState *bs, uint64_t offset, - uint64_t l2_offset, uint64_t **l2_slice) +static int GRAPH_RDLOCK +l2_load(BlockDriverState *bs, uint64_t offset, + uint64_t l2_offset, uint64_t **l2_slice) { BDRVQcow2State *s = bs->opaque; int start_of_slice = l2_entry_size(s) * @@ -269,7 +270,7 @@ int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index) * */ -static int l2_allocate(BlockDriverState *bs, int l1_index) +static int GRAPH_RDLOCK l2_allocate(BlockDriverState *bs, int l1_index) { BDRVQcow2State *s = bs->opaque; uint64_t old_l2_offset; @@ -751,9 +752,9 @@ fail: * * Returns 0 on success, -errno in failure case */ -static int get_cluster_table(BlockDriverState *bs, uint64_t offset, - uint64_t **new_l2_slice, - int *new_l2_index) +static int GRAPH_RDLOCK +get_cluster_table(BlockDriverState *bs, uint64_t offset, + uint64_t **new_l2_slice, int *new_l2_index) { BDRVQcow2State *s = bs->opaque; unsigned int l2_index; @@ -1155,11 +1156,10 @@ void coroutine_fn qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m) * * Returns 0 on success, -errno on failure. */ -static int coroutine_fn calculate_l2_meta(BlockDriverState *bs, - uint64_t host_cluster_offset, - uint64_t guest_offset, unsigned bytes, - uint64_t *l2_slice, QCowL2Meta **m, - bool keep_old) +static int coroutine_fn GRAPH_RDLOCK +calculate_l2_meta(BlockDriverState *bs, uint64_t host_cluster_offset, + uint64_t guest_offset, unsigned bytes, uint64_t *l2_slice, + QCowL2Meta **m, bool keep_old) { BDRVQcow2State *s = bs->opaque; int sc_index, l2_index = offset_to_l2_slice_index(s, guest_offset); @@ -1490,9 +1490,9 @@ static int coroutine_fn handle_dependencies(BlockDriverState *bs, * * -errno: in error cases */ -static int coroutine_fn handle_copied(BlockDriverState *bs, - uint64_t guest_offset, uint64_t *host_offset, uint64_t *bytes, - QCowL2Meta **m) +static int coroutine_fn GRAPH_RDLOCK +handle_copied(BlockDriverState *bs, uint64_t guest_offset, + uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; int l2_index; @@ -1600,10 +1600,9 @@ out: * function has been waiting for another request and the allocation must be * restarted, but the whole request should not be failed. */ -static int coroutine_fn do_alloc_cluster_offset(BlockDriverState *bs, - uint64_t guest_offset, - uint64_t *host_offset, - uint64_t *nb_clusters) +static int coroutine_fn GRAPH_RDLOCK +do_alloc_cluster_offset(BlockDriverState *bs, uint64_t guest_offset, + uint64_t *host_offset, uint64_t *nb_clusters) { BDRVQcow2State *s = bs->opaque; @@ -1658,9 +1657,9 @@ static int coroutine_fn do_alloc_cluster_offset(BlockDriverState *bs, * * -errno: in error cases */ -static int coroutine_fn handle_alloc(BlockDriverState *bs, - uint64_t guest_offset, uint64_t *host_offset, uint64_t *bytes, - QCowL2Meta **m) +static int coroutine_fn GRAPH_RDLOCK +handle_alloc(BlockDriverState *bs, uint64_t guest_offset, + uint64_t *host_offset, uint64_t *bytes, QCowL2Meta **m) { BDRVQcow2State *s = bs->opaque; int l2_index; @@ -1898,9 +1897,9 @@ again: * all clusters in the same L2 slice) and returns the number of discarded * clusters. */ -static int discard_in_l2_slice(BlockDriverState *bs, uint64_t offset, - uint64_t nb_clusters, - enum qcow2_discard_type type, bool full_discard) +static int GRAPH_RDLOCK +discard_in_l2_slice(BlockDriverState *bs, uint64_t offset, uint64_t nb_clusters, + enum qcow2_discard_type type, bool full_discard) { BDRVQcow2State *s = bs->opaque; uint64_t *l2_slice; @@ -2037,7 +2036,7 @@ fail: * all clusters in the same L2 slice) and returns the number of zeroed * clusters. */ -static int coroutine_fn +static int coroutine_fn GRAPH_RDLOCK zero_in_l2_slice(BlockDriverState *bs, uint64_t offset, uint64_t nb_clusters, int flags) { @@ -2093,7 +2092,7 @@ zero_in_l2_slice(BlockDriverState *bs, uint64_t offset, return nb_clusters; } -static int coroutine_fn +static int coroutine_fn GRAPH_RDLOCK zero_l2_subclusters(BlockDriverState *bs, uint64_t offset, unsigned nb_subclusters) { @@ -2231,11 +2230,12 @@ fail: * status_cb(). l1_entries contains the total number of L1 entries and * *visited_l1_entries counts all visited L1 entries. */ -static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, - int l1_size, int64_t *visited_l1_entries, - int64_t l1_entries, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque) +static int GRAPH_RDLOCK +expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table, + int l1_size, int64_t *visited_l1_entries, + int64_t l1_entries, + BlockDriverAmendStatusCB *status_cb, + void *cb_opaque) { BDRVQcow2State *s = bs->opaque; bool is_active_l1 = (l1_table == s->l1_table); diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index 996d1217d0..0266542cee 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -229,9 +229,9 @@ static void set_refcount_ro6(void *refcount_array, uint64_t index, } -static int load_refcount_block(BlockDriverState *bs, - int64_t refcount_block_offset, - void **refcount_block) +static int GRAPH_RDLOCK +load_refcount_block(BlockDriverState *bs, int64_t refcount_block_offset, + void **refcount_block) { BDRVQcow2State *s = bs->opaque; @@ -302,8 +302,9 @@ static int in_same_refcount_block(BDRVQcow2State *s, uint64_t offset_a, * * Returns 0 on success or -errno in error case */ -static int alloc_refcount_block(BlockDriverState *bs, - int64_t cluster_index, void **refcount_block) +static int GRAPH_RDLOCK +alloc_refcount_block(BlockDriverState *bs, int64_t cluster_index, + void **refcount_block) { BDRVQcow2State *s = bs->opaque; unsigned int refcount_table_index; @@ -806,12 +807,9 @@ found: /* XXX: cache several refcount block clusters ? */ /* @addend is the absolute value of the addend; if @decrease is set, @addend * will be subtracted from the current refcount, otherwise it will be added */ -static int update_refcount(BlockDriverState *bs, - int64_t offset, - int64_t length, - uint64_t addend, - bool decrease, - enum qcow2_discard_type type) +static int GRAPH_RDLOCK +update_refcount(BlockDriverState *bs, int64_t offset, int64_t length, + uint64_t addend, bool decrease, enum qcow2_discard_type type) { BDRVQcow2State *s = bs->opaque; int64_t start, last, cluster_offset; @@ -967,8 +965,8 @@ int qcow2_update_cluster_refcount(BlockDriverState *bs, /* return < 0 if error */ -static int64_t alloc_clusters_noref(BlockDriverState *bs, uint64_t size, - uint64_t max) +static int64_t GRAPH_RDLOCK +alloc_clusters_noref(BlockDriverState *bs, uint64_t size, uint64_t max) { BDRVQcow2State *s = bs->opaque; uint64_t i, nb_clusters, refcount; @@ -2302,7 +2300,7 @@ calculate_refcounts(BlockDriverState *bs, BdrvCheckResult *res, * Compares the actual reference count for each cluster in the image against the * refcount as reported by the refcount structures on-disk. */ -static void coroutine_fn +static void coroutine_fn GRAPH_RDLOCK compare_refcounts(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix, bool *rebuild, int64_t *highest_cluster, @@ -3103,20 +3101,22 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset, * * @allocated should be set to true if a new cluster has been allocated. */ -typedef int (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable, - uint64_t reftable_index, uint64_t *reftable_size, - void *refblock, bool refblock_empty, - bool *allocated, Error **errp); +typedef int /* GRAPH_RDLOCK_PTR */ + (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable, + uint64_t reftable_index, uint64_t *reftable_size, + void *refblock, bool refblock_empty, + bool *allocated, Error **errp); /** * This "operation" for walk_over_reftable() allocates the refblock on disk (if * it is not empty) and inserts its offset into the new reftable. The size of * this new reftable is increased as required. */ -static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable, - uint64_t reftable_index, uint64_t *reftable_size, - void *refblock, bool refblock_empty, bool *allocated, - Error **errp) +static int GRAPH_RDLOCK +alloc_refblock(BlockDriverState *bs, uint64_t **reftable, + uint64_t reftable_index, uint64_t *reftable_size, + void *refblock, bool refblock_empty, bool *allocated, + Error **errp) { BDRVQcow2State *s = bs->opaque; int64_t offset; @@ -3166,10 +3166,11 @@ static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable, * offset specified by the new reftable's entry. It does not modify the new * reftable or change any refcounts. */ -static int flush_refblock(BlockDriverState *bs, uint64_t **reftable, - uint64_t reftable_index, uint64_t *reftable_size, - void *refblock, bool refblock_empty, bool *allocated, - Error **errp) +static int GRAPH_RDLOCK +flush_refblock(BlockDriverState *bs, uint64_t **reftable, + uint64_t reftable_index, uint64_t *reftable_size, + void *refblock, bool refblock_empty, bool *allocated, + Error **errp) { BDRVQcow2State *s = bs->opaque; int64_t offset; @@ -3210,16 +3211,17 @@ static int flush_refblock(BlockDriverState *bs, uint64_t **reftable, * * @allocated is set to true if a new cluster has been allocated. */ -static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable, - uint64_t *new_reftable_index, - uint64_t *new_reftable_size, - void *new_refblock, int new_refblock_size, - int new_refcount_bits, - RefblockFinishOp *operation, bool *allocated, - Qcow2SetRefcountFunc *new_set_refcount, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque, int index, int total, - Error **errp) +static int GRAPH_RDLOCK +walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable, + uint64_t *new_reftable_index, + uint64_t *new_reftable_size, + void *new_refblock, int new_refblock_size, + int new_refcount_bits, + RefblockFinishOp *operation, bool *allocated, + Qcow2SetRefcountFunc *new_set_refcount, + BlockDriverAmendStatusCB *status_cb, + void *cb_opaque, int index, int total, + Error **errp) { BDRVQcow2State *s = bs->opaque; uint64_t reftable_index; @@ -3545,8 +3547,8 @@ done: return ret; } -static int64_t coroutine_fn get_refblock_offset(BlockDriverState *bs, - uint64_t offset) +static int64_t coroutine_fn GRAPH_RDLOCK +get_refblock_offset(BlockDriverState *bs, uint64_t offset) { BDRVQcow2State *s = bs->opaque; uint32_t index = offset_to_reftable_index(s, offset); @@ -3565,7 +3567,7 @@ static int64_t coroutine_fn get_refblock_offset(BlockDriverState *bs, return covering_refblock_offset; } -static int coroutine_fn +static int coroutine_fn GRAPH_RDLOCK qcow2_discard_refcount_block(BlockDriverState *bs, uint64_t discard_block_offs) { BDRVQcow2State *s = bs->opaque; diff --git a/block/qcow2.c b/block/qcow2.c index 5a3c537f14..aa01d9e7b5 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -536,7 +536,7 @@ int qcow2_mark_dirty(BlockDriverState *bs) * function when there are no pending requests, it does not guard against * concurrent requests dirtying the image. */ -static int qcow2_mark_clean(BlockDriverState *bs) +static int GRAPH_RDLOCK qcow2_mark_clean(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; @@ -570,7 +570,8 @@ int qcow2_mark_corrupt(BlockDriverState *bs) * Marks the image as consistent, i.e., unsets the corrupt bit, and flushes * before if necessary. */ -static int coroutine_fn qcow2_mark_consistent(BlockDriverState *bs) +static int coroutine_fn GRAPH_RDLOCK +qcow2_mark_consistent(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; @@ -980,10 +981,9 @@ typedef struct Qcow2ReopenState { QCryptoBlockOpenOptions *crypto_opts; /* Disk encryption runtime options */ } Qcow2ReopenState; -static int qcow2_update_options_prepare(BlockDriverState *bs, - Qcow2ReopenState *r, - QDict *options, int flags, - Error **errp) +static int GRAPH_RDLOCK +qcow2_update_options_prepare(BlockDriverState *bs, Qcow2ReopenState *r, + QDict *options, int flags, Error **errp) { BDRVQcow2State *s = bs->opaque; QemuOpts *opts = NULL; @@ -1260,7 +1260,7 @@ static void qcow2_update_options_abort(BlockDriverState *bs, qapi_free_QCryptoBlockOpenOptions(r->crypto_opts); } -static int coroutine_fn +static int coroutine_fn GRAPH_RDLOCK qcow2_update_options(BlockDriverState *bs, QDict *options, int flags, Error **errp) { @@ -1969,13 +1969,17 @@ static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp) bs->bl.pdiscard_alignment = s->cluster_size; } -static int qcow2_reopen_prepare(BDRVReopenState *state, - BlockReopenQueue *queue, Error **errp) +static int GRAPH_UNLOCKED +qcow2_reopen_prepare(BDRVReopenState *state,BlockReopenQueue *queue, + Error **errp) { BDRVQcow2State *s = state->bs->opaque; Qcow2ReopenState *r; int ret; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + r = g_new0(Qcow2ReopenState, 1); state->opaque = r; @@ -2038,6 +2042,8 @@ static void qcow2_reopen_commit(BDRVReopenState *state) static void qcow2_reopen_commit_post(BDRVReopenState *state) { + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (state->flags & BDRV_O_RDWR) { Error *local_err = NULL; @@ -2731,7 +2737,7 @@ fail_nometa: return ret; } -static int qcow2_inactivate(BlockDriverState *bs) +static int GRAPH_RDLOCK qcow2_inactivate(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; int ret, result = 0; @@ -2766,7 +2772,8 @@ static int qcow2_inactivate(BlockDriverState *bs) return result; } -static void qcow2_do_close(BlockDriverState *bs, bool close_data_file) +static void coroutine_mixed_fn GRAPH_RDLOCK +qcow2_do_close(BlockDriverState *bs, bool close_data_file) { BDRVQcow2State *s = bs->opaque; qemu_vfree(s->l1_table); @@ -2793,18 +2800,24 @@ static void qcow2_do_close(BlockDriverState *bs, bool close_data_file) g_free(s->image_backing_format); if (close_data_file && has_data_file(bs)) { + GLOBAL_STATE_CODE(); + bdrv_graph_rdunlock_main_loop(); bdrv_graph_wrlock(NULL); bdrv_unref_child(bs, s->data_file); bdrv_graph_wrunlock(); s->data_file = NULL; + bdrv_graph_rdlock_main_loop(); } qcow2_refcount_close(bs); qcow2_free_snapshots(bs); } -static void qcow2_close(BlockDriverState *bs) +static void GRAPH_UNLOCKED qcow2_close(BlockDriverState *bs) { + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + qcow2_do_close(bs, true); } @@ -3991,7 +4004,8 @@ finish: } -static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) +static bool coroutine_fn GRAPH_RDLOCK +is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) { int64_t nr; int res; @@ -4012,7 +4026,7 @@ static bool is_zero(BlockDriverState *bs, int64_t offset, int64_t bytes) * backing file. So, we need a loop. */ do { - res = bdrv_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); + res = bdrv_co_block_status_above(bs, NULL, offset, bytes, &nr, NULL, NULL); offset += nr; bytes -= nr; } while (res >= 0 && (res & BDRV_BLOCK_ZERO) && nr && bytes); @@ -4076,8 +4090,8 @@ qcow2_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int64_t bytes, return ret; } -static coroutine_fn int qcow2_co_pdiscard(BlockDriverState *bs, - int64_t offset, int64_t bytes) +static int coroutine_fn GRAPH_RDLOCK +qcow2_co_pdiscard(BlockDriverState *bs, int64_t offset, int64_t bytes) { int ret; BDRVQcow2State *s = bs->opaque; @@ -4822,7 +4836,7 @@ fail: return ret; } -static int make_completely_empty(BlockDriverState *bs) +static int GRAPH_RDLOCK make_completely_empty(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; Error *local_err = NULL; @@ -4973,7 +4987,7 @@ fail: return ret; } -static int qcow2_make_empty(BlockDriverState *bs) +static int GRAPH_RDLOCK qcow2_make_empty(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; uint64_t offset, end_offset; @@ -5017,7 +5031,7 @@ static int qcow2_make_empty(BlockDriverState *bs) return ret; } -static coroutine_fn int qcow2_co_flush_to_os(BlockDriverState *bs) +static coroutine_fn GRAPH_RDLOCK int qcow2_co_flush_to_os(BlockDriverState *bs) { BDRVQcow2State *s = bs->opaque; int ret; @@ -5366,7 +5380,7 @@ qcow2_co_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos) return bs->drv->bdrv_co_preadv_part(bs, offset, qiov->size, qiov, 0, 0); } -static int qcow2_has_compressed_clusters(BlockDriverState *bs) +static int GRAPH_RDLOCK qcow2_has_compressed_clusters(BlockDriverState *bs) { int64_t offset = 0; int64_t bytes = bdrv_getlength(bs); @@ -5402,9 +5416,10 @@ static int qcow2_has_compressed_clusters(BlockDriverState *bs) * Downgrades an image's version. To achieve this, any incompatible features * have to be removed. */ -static int qcow2_downgrade(BlockDriverState *bs, int target_version, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque, - Error **errp) +static int GRAPH_RDLOCK +qcow2_downgrade(BlockDriverState *bs, int target_version, + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + Error **errp) { BDRVQcow2State *s = bs->opaque; int current_version = s->qcow_version; @@ -5512,9 +5527,10 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version, * features of older versions, some things may have to be presented * differently. */ -static int qcow2_upgrade(BlockDriverState *bs, int target_version, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque, - Error **errp) +static int GRAPH_RDLOCK +qcow2_upgrade(BlockDriverState *bs, int target_version, + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + Error **errp) { BDRVQcow2State *s = bs->opaque; bool need_snapshot_update; @@ -5640,11 +5656,10 @@ static void qcow2_amend_helper_cb(BlockDriverState *bs, info->original_cb_opaque); } -static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque, - bool force, - Error **errp) +static int GRAPH_RDLOCK +qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts, + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + bool force, Error **errp) { BDRVQcow2State *s = bs->opaque; int old_version = s->qcow_version, new_version = old_version; diff --git a/block/qcow2.h b/block/qcow2.h index f789ce3ae0..29958c512b 100644 --- a/block/qcow2.h +++ b/block/qcow2.h @@ -838,9 +838,10 @@ int qcow2_mark_dirty(BlockDriverState *bs); int qcow2_mark_corrupt(BlockDriverState *bs); int qcow2_update_header(BlockDriverState *bs); -void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset, - int64_t size, const char *message_format, ...) - G_GNUC_PRINTF(5, 6); +void GRAPH_RDLOCK +qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset, + int64_t size, const char *message_format, ...) + G_GNUC_PRINTF(5, 6); int qcow2_validate_table(BlockDriverState *bs, uint64_t offset, uint64_t entries, size_t entry_len, @@ -851,33 +852,41 @@ int qcow2_validate_table(BlockDriverState *bs, uint64_t offset, int coroutine_fn GRAPH_RDLOCK qcow2_refcount_init(BlockDriverState *bs); void qcow2_refcount_close(BlockDriverState *bs); -int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index, - uint64_t *refcount); +int GRAPH_RDLOCK qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index, + uint64_t *refcount); -int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index, - uint64_t addend, bool decrease, - enum qcow2_discard_type type); +int GRAPH_RDLOCK +qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index, + uint64_t addend, bool decrease, + enum qcow2_discard_type type); -int64_t qcow2_refcount_area(BlockDriverState *bs, uint64_t offset, - uint64_t additional_clusters, bool exact_size, - int new_refblock_index, - uint64_t new_refblock_offset); +int64_t GRAPH_RDLOCK +qcow2_refcount_area(BlockDriverState *bs, uint64_t offset, + uint64_t additional_clusters, bool exact_size, + int new_refblock_index, + uint64_t new_refblock_offset); -int64_t qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size); -int64_t coroutine_fn qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset, - int64_t nb_clusters); -int64_t coroutine_fn GRAPH_RDLOCK qcow2_alloc_bytes(BlockDriverState *bs, int size); -void qcow2_free_clusters(BlockDriverState *bs, - int64_t offset, int64_t size, - enum qcow2_discard_type type); -void qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry, - enum qcow2_discard_type type); +int64_t GRAPH_RDLOCK +qcow2_alloc_clusters(BlockDriverState *bs, uint64_t size); -int qcow2_update_snapshot_refcount(BlockDriverState *bs, - int64_t l1_table_offset, int l1_size, int addend); +int64_t GRAPH_RDLOCK coroutine_fn +qcow2_alloc_clusters_at(BlockDriverState *bs, uint64_t offset, + int64_t nb_clusters); -int qcow2_flush_caches(BlockDriverState *bs); -int qcow2_write_caches(BlockDriverState *bs); +int64_t coroutine_fn GRAPH_RDLOCK qcow2_alloc_bytes(BlockDriverState *bs, int size); +void GRAPH_RDLOCK qcow2_free_clusters(BlockDriverState *bs, + int64_t offset, int64_t size, + enum qcow2_discard_type type); +void GRAPH_RDLOCK +qcow2_free_any_cluster(BlockDriverState *bs, uint64_t l2_entry, + enum qcow2_discard_type type); + +int GRAPH_RDLOCK +qcow2_update_snapshot_refcount(BlockDriverState *bs, int64_t l1_table_offset, + int l1_size, int addend); + +int GRAPH_RDLOCK qcow2_flush_caches(BlockDriverState *bs); +int GRAPH_RDLOCK qcow2_write_caches(BlockDriverState *bs); int coroutine_fn qcow2_check_refcounts(BlockDriverState *bs, BdrvCheckResult *res, BdrvCheckMode fix); @@ -885,39 +894,48 @@ void qcow2_process_discards(BlockDriverState *bs, int ret); int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset, int64_t size); -int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset, - int64_t size, bool data_file); +int GRAPH_RDLOCK +qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset, + int64_t size, bool data_file); + int coroutine_fn qcow2_inc_refcounts_imrt(BlockDriverState *bs, BdrvCheckResult *res, void **refcount_table, int64_t *refcount_table_size, int64_t offset, int64_t size); -int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque, Error **errp); +int GRAPH_RDLOCK +qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order, + BlockDriverAmendStatusCB *status_cb, + void *cb_opaque, Error **errp); int coroutine_fn GRAPH_RDLOCK qcow2_shrink_reftable(BlockDriverState *bs); -int64_t coroutine_fn qcow2_get_last_cluster(BlockDriverState *bs, int64_t size); + +int64_t coroutine_fn GRAPH_RDLOCK +qcow2_get_last_cluster(BlockDriverState *bs, int64_t size); int coroutine_fn GRAPH_RDLOCK qcow2_detect_metadata_preallocation(BlockDriverState *bs); /* qcow2-cluster.c functions */ -int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, - bool exact_size); +int GRAPH_RDLOCK +qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size, bool exact_size); int coroutine_fn GRAPH_RDLOCK qcow2_shrink_l1_table(BlockDriverState *bs, uint64_t max_size); -int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index); +int GRAPH_RDLOCK qcow2_write_l1_entry(BlockDriverState *bs, int l1_index); int qcow2_encrypt_sectors(BDRVQcow2State *s, int64_t sector_num, uint8_t *buf, int nb_sectors, bool enc, Error **errp); -int qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset, - unsigned int *bytes, uint64_t *host_offset, - QCow2SubclusterType *subcluster_type); -int coroutine_fn qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, - unsigned int *bytes, - uint64_t *host_offset, QCowL2Meta **m); +int GRAPH_RDLOCK +qcow2_get_host_offset(BlockDriverState *bs, uint64_t offset, + unsigned int *bytes, uint64_t *host_offset, + QCow2SubclusterType *subcluster_type); + +int coroutine_fn GRAPH_RDLOCK +qcow2_alloc_host_offset(BlockDriverState *bs, uint64_t offset, + unsigned int *bytes, uint64_t *host_offset, + QCowL2Meta **m); + int coroutine_fn GRAPH_RDLOCK qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs, uint64_t offset, int compressed_size, uint64_t *host_offset); @@ -927,26 +945,33 @@ void qcow2_parse_compressed_l2_entry(BlockDriverState *bs, uint64_t l2_entry, int coroutine_fn GRAPH_RDLOCK qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m); -void coroutine_fn qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m); -int qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset, - uint64_t bytes, enum qcow2_discard_type type, - bool full_discard); +void coroutine_fn GRAPH_RDLOCK +qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m); + +int GRAPH_RDLOCK +qcow2_cluster_discard(BlockDriverState *bs, uint64_t offset, uint64_t bytes, + enum qcow2_discard_type type, bool full_discard); int coroutine_fn GRAPH_RDLOCK qcow2_subcluster_zeroize(BlockDriverState *bs, uint64_t offset, uint64_t bytes, int flags); -int qcow2_expand_zero_clusters(BlockDriverState *bs, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque); +int GRAPH_RDLOCK +qcow2_expand_zero_clusters(BlockDriverState *bs, + BlockDriverAmendStatusCB *status_cb, + void *cb_opaque); /* qcow2-snapshot.c functions */ -int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info); -int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id); -int qcow2_snapshot_delete(BlockDriverState *bs, - const char *snapshot_id, - const char *name, - Error **errp); +int GRAPH_RDLOCK +qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info); + +int GRAPH_RDLOCK +qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id); + +int GRAPH_RDLOCK +qcow2_snapshot_delete(BlockDriverState *bs, const char *snapshot_id, + const char *name, Error **errp); + int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab); int qcow2_snapshot_load_tmp(BlockDriverState *bs, const char *snapshot_id, @@ -956,15 +981,15 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs, void qcow2_free_snapshots(BlockDriverState *bs); int coroutine_fn GRAPH_RDLOCK qcow2_read_snapshots(BlockDriverState *bs, Error **errp); -int qcow2_write_snapshots(BlockDriverState *bs); +int GRAPH_RDLOCK qcow2_write_snapshots(BlockDriverState *bs); int coroutine_fn GRAPH_RDLOCK qcow2_check_read_snapshot_table(BlockDriverState *bs, BdrvCheckResult *result, BdrvCheckMode fix); -int coroutine_fn qcow2_check_fix_snapshot_table(BlockDriverState *bs, - BdrvCheckResult *result, - BdrvCheckMode fix); +int coroutine_fn GRAPH_RDLOCK +qcow2_check_fix_snapshot_table(BlockDriverState *bs, BdrvCheckResult *result, + BdrvCheckMode fix); /* qcow2-cache.c functions */ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables, @@ -972,19 +997,23 @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables, int qcow2_cache_destroy(Qcow2Cache *c); void qcow2_cache_entry_mark_dirty(Qcow2Cache *c, void *table); -int qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c); -int qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c); -int qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c, - Qcow2Cache *dependency); +int GRAPH_RDLOCK qcow2_cache_flush(BlockDriverState *bs, Qcow2Cache *c); +int GRAPH_RDLOCK qcow2_cache_write(BlockDriverState *bs, Qcow2Cache *c); +int GRAPH_RDLOCK qcow2_cache_set_dependency(BlockDriverState *bs, Qcow2Cache *c, + Qcow2Cache *dependency); void qcow2_cache_depends_on_flush(Qcow2Cache *c); void qcow2_cache_clean_unused(Qcow2Cache *c); -int qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c); +int GRAPH_RDLOCK qcow2_cache_empty(BlockDriverState *bs, Qcow2Cache *c); + +int GRAPH_RDLOCK +qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, + void **table); + +int GRAPH_RDLOCK +qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, + void **table); -int qcow2_cache_get(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, - void **table); -int qcow2_cache_get_empty(BlockDriverState *bs, Qcow2Cache *c, uint64_t offset, - void **table); void qcow2_cache_put(Qcow2Cache *c, void **table); void *qcow2_cache_is_table_offset(Qcow2Cache *c, uint64_t offset); void qcow2_cache_discard(Qcow2Cache *c, void *table); @@ -998,18 +1027,22 @@ bool coroutine_fn GRAPH_RDLOCK qcow2_load_dirty_bitmaps(BlockDriverState *bs, bool *header_updated, Error **errp); bool qcow2_get_bitmap_info_list(BlockDriverState *bs, Qcow2BitmapInfoList **info_list, Error **errp); -int qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp); +int GRAPH_RDLOCK qcow2_reopen_bitmaps_rw(BlockDriverState *bs, Error **errp); +int GRAPH_RDLOCK qcow2_reopen_bitmaps_ro(BlockDriverState *bs, Error **errp); int coroutine_fn qcow2_truncate_bitmaps_check(BlockDriverState *bs, Error **errp); -bool qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, - bool release_stored, Error **errp); -int qcow2_reopen_bitmaps_ro(BlockDriverState *bs, Error **errp); -bool coroutine_fn qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, - const char *name, - uint32_t granularity, - Error **errp); -int coroutine_fn qcow2_co_remove_persistent_dirty_bitmap(BlockDriverState *bs, - const char *name, - Error **errp); + +bool GRAPH_RDLOCK +qcow2_store_persistent_dirty_bitmaps(BlockDriverState *bs, bool release_stored, + Error **errp); + +bool coroutine_fn GRAPH_RDLOCK +qcow2_co_can_store_new_dirty_bitmap(BlockDriverState *bs, const char *name, + uint32_t granularity, Error **errp); + +int coroutine_fn GRAPH_RDLOCK +qcow2_co_remove_persistent_dirty_bitmap(BlockDriverState *bs, const char *name, + Error **errp); + bool qcow2_supports_persistent_dirty_bitmap(BlockDriverState *bs); uint64_t qcow2_get_persistent_dirty_bitmap_size(BlockDriverState *bs, uint32_t cluster_size); diff --git a/block/quorum.c b/block/quorum.c index 05220cab7f..d3ffc2ee33 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -206,7 +206,7 @@ static void quorum_report_bad(QuorumOpType type, uint64_t offset, end_sector - start_sector); } -static void quorum_report_failure(QuorumAIOCB *acb) +static void GRAPH_RDLOCK quorum_report_failure(QuorumAIOCB *acb) { const char *reference = bdrv_get_device_or_node_name(acb->bs); int64_t start_sector = acb->offset / BDRV_SECTOR_SIZE; @@ -219,7 +219,7 @@ static void quorum_report_failure(QuorumAIOCB *acb) static int quorum_vote_error(QuorumAIOCB *acb); -static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb) +static bool GRAPH_RDLOCK quorum_has_too_much_io_failed(QuorumAIOCB *acb) { BDRVQuorumState *s = acb->bs->opaque; diff --git a/block/raw-format.c b/block/raw-format.c index a8bdee5279..8ff03adfa4 100644 --- a/block/raw-format.c +++ b/block/raw-format.c @@ -505,7 +505,9 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags, BDRV_REQ_ZERO_WRITE; if (bs->probed && !bdrv_is_read_only(bs)) { + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(bs->file->bs); + bdrv_graph_rdunlock_main_loop(); fprintf(stderr, "WARNING: Image format was not specified for '%s' and probing " "guessed raw.\n" diff --git a/block/rbd.c b/block/rbd.c index 472ca05cba..84bb2fa5d7 100644 --- a/block/rbd.c +++ b/block/rbd.c @@ -1168,7 +1168,9 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags, /* If we are using an rbd snapshot, we must be r/o, otherwise * leave as-is */ if (s->snap != NULL) { + bdrv_graph_rdlock_main_loop(); r = bdrv_apply_auto_read_only(bs, "rbd snapshots are read-only", errp); + bdrv_graph_rdunlock_main_loop(); if (r < 0) { goto failed_post_open; } @@ -1208,6 +1210,8 @@ static int qemu_rbd_reopen_prepare(BDRVReopenState *state, BDRVRBDState *s = state->bs->opaque; int ret = 0; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (s->snap && state->flags & BDRV_O_RDWR) { error_setg(errp, "Cannot change node '%s' to r/w when using RBD snapshot", diff --git a/block/replication.c b/block/replication.c index dd166d2d82..d522c7396f 100644 --- a/block/replication.c +++ b/block/replication.c @@ -276,10 +276,10 @@ replication_co_writev(BlockDriverState *bs, int64_t sector_num, while (remaining_sectors > 0) { int64_t count; - ret = bdrv_is_allocated_above(top->bs, base->bs, false, - sector_num * BDRV_SECTOR_SIZE, - remaining_sectors * BDRV_SECTOR_SIZE, - &count); + ret = bdrv_co_is_allocated_above(top->bs, base->bs, false, + sector_num * BDRV_SECTOR_SIZE, + remaining_sectors * BDRV_SECTOR_SIZE, + &count); if (ret < 0) { goto out1; } @@ -307,13 +307,16 @@ out: return ret; } -static void secondary_do_checkpoint(BlockDriverState *bs, Error **errp) +static void GRAPH_UNLOCKED +secondary_do_checkpoint(BlockDriverState *bs, Error **errp) { BDRVReplicationState *s = bs->opaque; BdrvChild *active_disk = bs->file; Error *local_err = NULL; int ret; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (!s->backup_job) { error_setg(errp, "Backup job was cancelled unexpectedly"); return; @@ -427,7 +430,8 @@ static void backup_job_completed(void *opaque, int ret) backup_job_cleanup(bs); } -static bool check_top_bs(BlockDriverState *top_bs, BlockDriverState *bs) +static bool GRAPH_RDLOCK +check_top_bs(BlockDriverState *top_bs, BlockDriverState *bs) { BdrvChild *child; @@ -458,6 +462,8 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, Error *local_err = NULL; BackupPerf perf = { .use_copy_range = true, .max_workers = 1 }; + GLOBAL_STATE_CODE(); + aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); s = bs->opaque; @@ -504,12 +510,15 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, return; } + bdrv_graph_rdlock_main_loop(); secondary_disk = hidden_disk->bs->backing; if (!secondary_disk->bs || !bdrv_has_blk(secondary_disk->bs)) { error_setg(errp, "The secondary disk doesn't have block backend"); + bdrv_graph_rdunlock_main_loop(); aio_context_release(aio_context); return; } + bdrv_graph_rdunlock_main_loop(); /* verify the length */ active_length = bdrv_getlength(active_disk->bs); @@ -526,13 +535,16 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, /* Must be true, or the bdrv_getlength() calls would have failed */ assert(active_disk->bs->drv && hidden_disk->bs->drv); + bdrv_graph_rdlock_main_loop(); if (!active_disk->bs->drv->bdrv_make_empty || !hidden_disk->bs->drv->bdrv_make_empty) { error_setg(errp, "Active disk or hidden disk doesn't support make_empty"); aio_context_release(aio_context); + bdrv_graph_rdunlock_main_loop(); return; } + bdrv_graph_rdunlock_main_loop(); /* reopen the backing file in r/w mode */ reopen_backing_file(bs, true, &local_err); @@ -566,8 +578,6 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, return; } - bdrv_graph_wrunlock(); - /* start backup job now */ error_setg(&s->blocker, "Block device is in use by internal backup job"); @@ -576,6 +586,7 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, if (!top_bs || !bdrv_is_root_node(top_bs) || !check_top_bs(top_bs, bs)) { error_setg(errp, "No top_bs or it is invalid"); + bdrv_graph_wrunlock(); reopen_backing_file(bs, false, NULL); aio_context_release(aio_context); return; @@ -583,6 +594,8 @@ static void replication_start(ReplicationState *rs, ReplicationMode mode, bdrv_op_block_all(top_bs, s->blocker); bdrv_op_unblock(top_bs, BLOCK_OP_TYPE_DATAPLANE, s->blocker); + bdrv_graph_wrunlock(); + s->backup_job = backup_job_create( NULL, s->secondary_disk->bs, s->hidden_disk->bs, 0, MIRROR_SYNC_MODE_NONE, NULL, 0, false, NULL, diff --git a/block/snapshot.c b/block/snapshot.c index b86b5b24ad..6e16eb803a 100644 --- a/block/snapshot.c +++ b/block/snapshot.c @@ -155,11 +155,15 @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs, * back if the given BDS does not support snapshots. * Return NULL if there is no BDS to (safely) fall back to. */ -static BdrvChild *bdrv_snapshot_fallback_child(BlockDriverState *bs) +static BdrvChild * GRAPH_RDLOCK +bdrv_snapshot_fallback_child(BlockDriverState *bs) { BdrvChild *fallback = bdrv_primary_child(bs); BdrvChild *child; + GLOBAL_STATE_CODE(); + assert_bdrv_graph_readable(); + /* We allow fallback only to primary child */ if (!fallback) { return NULL; @@ -182,8 +186,10 @@ static BdrvChild *bdrv_snapshot_fallback_child(BlockDriverState *bs) return fallback; } -static BlockDriverState *bdrv_snapshot_fallback(BlockDriverState *bs) +static BlockDriverState * GRAPH_RDLOCK +bdrv_snapshot_fallback(BlockDriverState *bs) { + GLOBAL_STATE_CODE(); return child_bs(bdrv_snapshot_fallback_child(bs)); } @@ -254,7 +260,10 @@ int bdrv_snapshot_goto(BlockDriverState *bs, return ret; } + bdrv_graph_rdlock_main_loop(); fallback = bdrv_snapshot_fallback_child(bs); + bdrv_graph_rdunlock_main_loop(); + if (fallback) { QDict *options; QDict *file_options; @@ -302,7 +311,10 @@ int bdrv_snapshot_goto(BlockDriverState *bs, * respective option (with the qdict_put_str() call above). * Assert that .bdrv_open() has attached the right BDS as primary child. */ + bdrv_graph_rdlock_main_loop(); assert(bdrv_primary_bs(bs) == fallback_bs); + bdrv_graph_rdunlock_main_loop(); + bdrv_unref(fallback_bs); return ret; } @@ -374,10 +386,12 @@ int bdrv_snapshot_delete(BlockDriverState *bs, int bdrv_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_info) { + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + BlockDriver *drv = bs->drv; BlockDriverState *fallback_bs = bdrv_snapshot_fallback(bs); - GLOBAL_STATE_CODE(); if (!drv) { return -ENOMEDIUM; } @@ -418,6 +432,7 @@ int bdrv_snapshot_load_tmp(BlockDriverState *bs, BlockDriver *drv = bs->drv; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (!drv) { error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs)); @@ -462,9 +477,9 @@ int bdrv_snapshot_load_tmp_by_id_or_name(BlockDriverState *bs, } -static int bdrv_all_get_snapshot_devices(bool has_devices, strList *devices, - GList **all_bdrvs, - Error **errp) +static int GRAPH_RDLOCK +bdrv_all_get_snapshot_devices(bool has_devices, strList *devices, + GList **all_bdrvs, Error **errp) { g_autoptr(GList) bdrvs = NULL; @@ -496,8 +511,11 @@ static int bdrv_all_get_snapshot_devices(bool has_devices, strList *devices, } -static bool bdrv_all_snapshots_includes_bs(BlockDriverState *bs) +static bool GRAPH_RDLOCK bdrv_all_snapshots_includes_bs(BlockDriverState *bs) { + GLOBAL_STATE_CODE(); + assert_bdrv_graph_readable(); + if (!bdrv_is_inserted(bs) || bdrv_is_read_only(bs)) { return false; } @@ -518,6 +536,7 @@ bool bdrv_all_can_snapshot(bool has_devices, strList *devices, GList *iterbdrvs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { return false; @@ -554,6 +573,7 @@ int bdrv_all_delete_snapshot(const char *name, GList *iterbdrvs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { return -1; @@ -593,10 +613,15 @@ int bdrv_all_goto_snapshot(const char *name, { g_autoptr(GList) bdrvs = NULL; GList *iterbdrvs; + int ret; GLOBAL_STATE_CODE(); - if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { + bdrv_graph_rdlock_main_loop(); + ret = bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp); + bdrv_graph_rdunlock_main_loop(); + + if (ret < 0) { return -1; } @@ -605,15 +630,22 @@ int bdrv_all_goto_snapshot(const char *name, BlockDriverState *bs = iterbdrvs->data; AioContext *ctx = bdrv_get_aio_context(bs); int ret = 0; + bool all_snapshots_includes_bs; aio_context_acquire(ctx); - if (devices || bdrv_all_snapshots_includes_bs(bs)) { + bdrv_graph_rdlock_main_loop(); + all_snapshots_includes_bs = bdrv_all_snapshots_includes_bs(bs); + bdrv_graph_rdunlock_main_loop(); + + if (devices || all_snapshots_includes_bs) { ret = bdrv_snapshot_goto(bs, name, errp); } aio_context_release(ctx); if (ret < 0) { + bdrv_graph_rdlock_main_loop(); error_prepend(errp, "Could not load snapshot '%s' on '%s': ", name, bdrv_get_device_or_node_name(bs)); + bdrv_graph_rdunlock_main_loop(); return -1; } @@ -631,6 +663,7 @@ int bdrv_all_has_snapshot(const char *name, GList *iterbdrvs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { return -1; @@ -673,7 +706,9 @@ int bdrv_all_create_snapshot(QEMUSnapshotInfo *sn, { g_autoptr(GList) bdrvs = NULL; GList *iterbdrvs; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { return -1; @@ -715,6 +750,7 @@ BlockDriverState *bdrv_all_find_vmstate_bs(const char *vmstate_bs, GList *iterbdrvs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (bdrv_all_get_snapshot_devices(has_devices, devices, &bdrvs, errp) < 0) { return NULL; diff --git a/block/stream.c b/block/stream.c index 133cb72fb4..ddaab7dbbd 100644 --- a/block/stream.c +++ b/block/stream.c @@ -172,7 +172,7 @@ static int coroutine_fn stream_run(Job *job, Error **errp) copy = false; WITH_GRAPH_RDLOCK_GUARD() { - ret = bdrv_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &n); + ret = bdrv_co_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &n); if (ret == 1) { /* Allocated in the top, no need to copy. */ } else if (ret >= 0) { @@ -180,9 +180,9 @@ static int coroutine_fn stream_run(Job *job, Error **errp) * Copy if allocated in the intermediate images. Limit to the * known-unallocated area [offset, offset+n*BDRV_SECTOR_SIZE). */ - ret = bdrv_is_allocated_above(bdrv_cow_bs(unfiltered_bs), - s->base_overlay, true, - offset, n, &n); + ret = bdrv_co_is_allocated_above(bdrv_cow_bs(unfiltered_bs), + s->base_overlay, true, + offset, n, &n); /* Finish early if end of backing file has been reached */ if (ret == 0 && n == 0) { n = len - offset; diff --git a/block/vdi.c b/block/vdi.c index 934e1b849b..3ed43b6f35 100644 --- a/block/vdi.c +++ b/block/vdi.c @@ -492,9 +492,12 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags, } /* Disable migration when vdi images are used */ + bdrv_graph_rdlock_main_loop(); error_setg(&s->migration_blocker, "The vdi format used by node '%s' " "does not support live migration", bdrv_get_device_or_node_name(bs)); + bdrv_graph_rdunlock_main_loop(); + ret = migrate_add_blocker(s->migration_blocker, errp); if (ret < 0) { error_free(s->migration_blocker); diff --git a/block/vhdx.c b/block/vhdx.c index a67edcc03e..73cb214fb4 100644 --- a/block/vhdx.c +++ b/block/vhdx.c @@ -1001,11 +1001,15 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags, uint64_t signature; Error *local_err = NULL; + GLOBAL_STATE_CODE(); + ret = bdrv_open_file_child(NULL, options, "file", bs, errp); if (ret < 0) { return ret; } + GRAPH_RDLOCK_GUARD_MAINLOOP(); + s->bat = NULL; s->first_visible_write = true; diff --git a/block/vhdx.h b/block/vhdx.h index 455a627a46..85594a5380 100644 --- a/block/vhdx.h +++ b/block/vhdx.h @@ -410,8 +410,9 @@ uint32_t vhdx_checksum_calc(uint32_t crc, uint8_t *buf, size_t size, bool vhdx_checksum_is_valid(uint8_t *buf, size_t size, int crc_offset); -int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed, - Error **errp); +int GRAPH_RDLOCK +vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed, + Error **errp); int coroutine_fn GRAPH_RDLOCK vhdx_log_write_and_flush(BlockDriverState *bs, BDRVVHDXState *s, diff --git a/block/vmdk.c b/block/vmdk.c index e90649c8bf..8a3b152798 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -578,8 +578,8 @@ static int vmdk_add_extent(BlockDriverState *bs, return 0; } -static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, - Error **errp) +static int GRAPH_RDLOCK +vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, Error **errp) { int ret; size_t l1_size; @@ -641,9 +641,9 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent, return ret; } -static int vmdk_open_vmfs_sparse(BlockDriverState *bs, - BdrvChild *file, - int flags, Error **errp) +static int GRAPH_RDLOCK +vmdk_open_vmfs_sparse(BlockDriverState *bs, BdrvChild *file, int flags, + Error **errp) { int ret; uint32_t magic; @@ -797,9 +797,9 @@ static int check_se_sparse_volatile_header(VMDKSESparseVolatileHeader *header, return 0; } -static int vmdk_open_se_sparse(BlockDriverState *bs, - BdrvChild *file, - int flags, Error **errp) +static int GRAPH_RDLOCK +vmdk_open_se_sparse(BlockDriverState *bs, BdrvChild *file, int flags, + Error **errp) { int ret; VMDKSESparseConstHeader const_header; @@ -913,9 +913,9 @@ static char *vmdk_read_desc(BdrvChild *file, uint64_t desc_offset, Error **errp) return buf; } -static int vmdk_open_vmdk4(BlockDriverState *bs, - BdrvChild *file, - int flags, QDict *options, Error **errp) +static int GRAPH_RDLOCK +vmdk_open_vmdk4(BlockDriverState *bs, BdrvChild *file, int flags, + QDict *options, Error **errp) { int ret; uint32_t magic; @@ -1095,8 +1095,9 @@ static int vmdk_parse_description(const char *desc, const char *opt_name, } /* Open an extent file and append to bs array */ -static int vmdk_open_sparse(BlockDriverState *bs, BdrvChild *file, int flags, - char *buf, QDict *options, Error **errp) +static int GRAPH_RDLOCK +vmdk_open_sparse(BlockDriverState *bs, BdrvChild *file, int flags, + char *buf, QDict *options, Error **errp) { uint32_t magic; @@ -1123,8 +1124,9 @@ static const char *next_line(const char *s) return s; } -static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, - QDict *options, Error **errp) +static int GRAPH_RDLOCK +vmdk_parse_extents(const char *desc, BlockDriverState *bs, QDict *options, + Error **errp) { int ret; int matches; @@ -1143,6 +1145,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, char extent_opt_prefix[32]; Error *local_err = NULL; + GLOBAL_STATE_CODE(); + for (p = desc; *p; p = next_line(p)) { /* parse extent line in one of below formats: * @@ -1223,9 +1227,11 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, ret = vmdk_add_extent(bs, extent_file, true, sectors, 0, 0, 0, 0, 0, &extent, errp); if (ret < 0) { + bdrv_graph_rdunlock_main_loop(); bdrv_graph_wrlock(NULL); bdrv_unref_child(bs, extent_file); bdrv_graph_wrunlock(); + bdrv_graph_rdlock_main_loop(); goto out; } extent->flat_start_offset = flat_offset << 9; @@ -1240,26 +1246,32 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs, } g_free(buf); if (ret) { + bdrv_graph_rdunlock_main_loop(); bdrv_graph_wrlock(NULL); bdrv_unref_child(bs, extent_file); bdrv_graph_wrunlock(); + bdrv_graph_rdlock_main_loop(); goto out; } extent = &s->extents[s->num_extents - 1]; } else if (!strcmp(type, "SESPARSE")) { ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp); if (ret) { + bdrv_graph_rdunlock_main_loop(); bdrv_graph_wrlock(NULL); bdrv_unref_child(bs, extent_file); bdrv_graph_wrunlock(); + bdrv_graph_rdlock_main_loop(); goto out; } extent = &s->extents[s->num_extents - 1]; } else { error_setg(errp, "Unsupported extent type '%s'", type); + bdrv_graph_rdunlock_main_loop(); bdrv_graph_wrlock(NULL); bdrv_unref_child(bs, extent_file); bdrv_graph_wrunlock(); + bdrv_graph_rdlock_main_loop(); ret = -ENOTSUP; goto out; } @@ -1283,8 +1295,9 @@ out: return ret; } -static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, - QDict *options, Error **errp) +static int GRAPH_RDLOCK +vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf, QDict *options, + Error **errp) { int ret; char ct[128]; @@ -2900,7 +2913,7 @@ static int vmdk_has_zero_init(BlockDriverState *bs) return 1; } -static VmdkExtentInfo *vmdk_get_extent_info(VmdkExtent *extent) +static VmdkExtentInfo * GRAPH_RDLOCK vmdk_get_extent_info(VmdkExtent *extent) { VmdkExtentInfo *info = g_new0(VmdkExtentInfo, 1); @@ -2977,8 +2990,8 @@ vmdk_co_check(BlockDriverState *bs, BdrvCheckResult *result, BdrvCheckMode fix) return ret; } -static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs, - Error **errp) +static ImageInfoSpecific * GRAPH_RDLOCK +vmdk_get_specific_info(BlockDriverState *bs, Error **errp) { int i; BDRVVmdkState *s = bs->opaque; diff --git a/block/vpc.c b/block/vpc.c index ceb87dd3d8..945847fe4a 100644 --- a/block/vpc.c +++ b/block/vpc.c @@ -446,9 +446,12 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags, } /* Disable migration when VHD images are used */ + bdrv_graph_rdlock_main_loop(); error_setg(&s->migration_blocker, "The vpc format used by node '%s' " "does not support live migration", bdrv_get_device_or_node_name(bs)); + bdrv_graph_rdunlock_main_loop(); + ret = migrate_add_blocker(s->migration_blocker, errp); if (ret < 0) { error_free(s->migration_blocker); diff --git a/block/vvfat.c b/block/vvfat.c index 856b479c91..b0415798c0 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -1144,6 +1144,8 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags, QemuOpts *opts; int ret; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + #ifdef DEBUG vvv = s; #endif @@ -1480,8 +1482,8 @@ vvfat_read(BlockDriverState *bs, int64_t sector_num, uint8_t *buf, int nb_sector if (s->qcow) { int64_t n; int ret; - ret = bdrv_is_allocated(s->qcow->bs, sector_num * BDRV_SECTOR_SIZE, - (nb_sectors - i) * BDRV_SECTOR_SIZE, &n); + ret = bdrv_co_is_allocated(s->qcow->bs, sector_num * BDRV_SECTOR_SIZE, + (nb_sectors - i) * BDRV_SECTOR_SIZE, &n); if (ret < 0) { return ret; } @@ -1806,10 +1808,10 @@ cluster_was_modified(BDRVVVFATState *s, uint32_t cluster_num) } for (i = 0; !was_modified && i < s->sectors_per_cluster; i++) { - was_modified = bdrv_is_allocated(s->qcow->bs, - (cluster2sector(s, cluster_num) + - i) * BDRV_SECTOR_SIZE, - BDRV_SECTOR_SIZE, NULL); + was_modified = bdrv_co_is_allocated(s->qcow->bs, + (cluster2sector(s, cluster_num) + + i) * BDRV_SECTOR_SIZE, + BDRV_SECTOR_SIZE, NULL); } /* @@ -1967,9 +1969,9 @@ get_cluster_count_for_direntry(BDRVVVFATState* s, direntry_t* direntry, const ch for (i = 0; i < s->sectors_per_cluster; i++) { int res; - res = bdrv_is_allocated(s->qcow->bs, - (offs + i) * BDRV_SECTOR_SIZE, - BDRV_SECTOR_SIZE, NULL); + res = bdrv_co_is_allocated(s->qcow->bs, + (offs + i) * BDRV_SECTOR_SIZE, + BDRV_SECTOR_SIZE, NULL); if (res < 0) { return -1; } diff --git a/blockdev.c b/blockdev.c index 325b7a3bef..a01c62596b 100644 --- a/blockdev.c +++ b/blockdev.c @@ -1041,6 +1041,8 @@ static BlockDriverState *qmp_get_root_bs(const char *name, Error **errp) BlockDriverState *bs; AioContext *aio_context; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_lookup_bs(name, name, errp); if (bs == NULL) { return NULL; @@ -1136,6 +1138,9 @@ SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device, SnapshotInfo *info = NULL; int ret; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = qmp_get_root_bs(device, errp); if (!bs) { return NULL; @@ -1221,6 +1226,9 @@ static void internal_snapshot_action(BlockdevSnapshotInternal *internal, AioContext *aio_context; int ret1; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + tran_add(tran, &internal_snapshot_drv, state); device = internal->device; @@ -1309,6 +1317,9 @@ static void internal_snapshot_abort(void *opaque) AioContext *aio_context; Error *local_error = NULL; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (!state->created) { return; } @@ -1654,6 +1665,8 @@ static void drive_backup_action(DriveBackup *backup, bool set_backing_hd = false; int ret; + GLOBAL_STATE_CODE(); + tran_add(tran, &drive_backup_drv, state); if (!backup->has_mode) { @@ -1683,9 +1696,12 @@ static void drive_backup_action(DriveBackup *backup, } /* Early check to avoid creating target */ + bdrv_graph_rdlock_main_loop(); if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) { + bdrv_graph_rdunlock_main_loop(); goto out; } + bdrv_graph_rdunlock_main_loop(); flags = bs->open_flags | BDRV_O_RDWR; @@ -1724,7 +1740,10 @@ static void drive_backup_action(DriveBackup *backup, BlockDriverState *explicit_backing = bdrv_skip_implicit_filters(source); + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(explicit_backing); + bdrv_graph_rdunlock_main_loop(); + bdrv_img_create(backup->target, format, explicit_backing->filename, explicit_backing->drv->format_name, NULL, @@ -2344,10 +2363,13 @@ void coroutine_fn qmp_block_resize(const char *device, const char *node_name, return; } + bdrv_graph_co_rdlock(); if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_RESIZE, NULL)) { error_setg(errp, QERR_DEVICE_IN_USE, device); + bdrv_graph_co_rdunlock(); return; } + bdrv_graph_co_rdunlock(); blk = blk_co_new_with_bs(bs, BLK_PERM_RESIZE, BLK_PERM_ALL, errp); if (!blk) { @@ -2387,6 +2409,8 @@ void qmp_block_stream(const char *job_id, const char *device, Error *local_err = NULL; int job_flags = JOB_DEFAULT; + GLOBAL_STATE_CODE(); + if (base && base_node) { error_setg(errp, "'base' and 'base-node' cannot be specified " "at the same time"); @@ -2437,7 +2461,10 @@ void qmp_block_stream(const char *job_id, const char *device, goto out; } assert(bdrv_get_aio_context(base_bs) == aio_context); + + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(base_bs); + bdrv_graph_rdunlock_main_loop(); } if (bottom) { @@ -2466,13 +2493,16 @@ void qmp_block_stream(const char *job_id, const char *device, * Check for op blockers in the whole chain between bs and base (or bottom) */ iter_end = bottom ? bdrv_filter_or_cow_bs(bottom_bs) : base_bs; + bdrv_graph_rdlock_main_loop(); for (iter = bs; iter && iter != iter_end; iter = bdrv_filter_or_cow_bs(iter)) { if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_STREAM, errp)) { + bdrv_graph_rdunlock_main_loop(); goto out; } } + bdrv_graph_rdunlock_main_loop(); /* if we are streaming the entire chain, the result will have no backing * file, and specifying one is therefore an error */ @@ -2835,6 +2865,8 @@ BlockDeviceInfoList *qmp_query_named_block_nodes(bool has_flat, XDbgBlockGraph *qmp_x_debug_query_block_graph(Error **errp) { + GRAPH_RDLOCK_GUARD_MAINLOOP(); + return bdrv_get_xdbg_block_graph(errp); } @@ -2998,9 +3030,12 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp) } /* Early check to avoid creating target */ + bdrv_graph_rdlock_main_loop(); if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR_SOURCE, errp)) { + bdrv_graph_rdunlock_main_loop(); return; } + bdrv_graph_rdunlock_main_loop(); aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); @@ -3063,7 +3098,10 @@ void qmp_drive_mirror(DriveMirror *arg, Error **errp) break; case NEW_IMAGE_MODE_ABSOLUTE_PATHS: /* create new image with backing file */ + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(explicit_backing); + bdrv_graph_rdunlock_main_loop(); + bdrv_img_create(arg->target, format, explicit_backing->filename, explicit_backing->drv->format_name, @@ -3383,9 +3421,12 @@ void qmp_change_backing_file(const char *device, /* even though we are not necessarily operating on bs, we need it to * determine if block ops are currently prohibited on the chain */ + bdrv_graph_rdlock_main_loop(); if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_CHANGE, errp)) { + bdrv_graph_rdunlock_main_loop(); goto out; } + bdrv_graph_rdunlock_main_loop(); /* final sanity check */ if (!bdrv_chain_contains(bs, image_bs)) { @@ -3509,6 +3550,7 @@ void qmp_blockdev_del(const char *node_name, Error **errp) BlockDriverState *bs; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); bs = bdrv_find_node(node_name); if (!bs) { @@ -3636,6 +3678,8 @@ void qmp_x_blockdev_set_iothread(const char *node_name, StrOrNull *iothread, AioContext *new_context; BlockDriverState *bs; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + bs = bdrv_find_node(node_name); if (!bs) { error_setg(errp, "Failed to find node with node-name='%s'", node_name); diff --git a/blockjob.c b/blockjob.c index 58c5d64539..807f992b59 100644 --- a/blockjob.c +++ b/blockjob.c @@ -485,6 +485,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver, BlockJob *job; int ret; GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); if (job_id == NULL && !(flags & JOB_INTERNAL)) { job_id = bdrv_get_device_name(bs); diff --git a/chardev/msmouse.c b/chardev/msmouse.c index ab8fe981d6..a774c397b4 100644 --- a/chardev/msmouse.c +++ b/chardev/msmouse.c @@ -171,7 +171,7 @@ static int msmouse_chr_write(struct Chardev *s, const uint8_t *buf, int len) return len; } -static QemuInputHandler msmouse_handler = { +static const QemuInputHandler msmouse_handler = { .name = "QEMU Microsoft Mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL, .event = msmouse_input_event, diff --git a/chardev/wctablet.c b/chardev/wctablet.c index 43bdf6b608..f4008bf35b 100644 --- a/chardev/wctablet.c +++ b/chardev/wctablet.c @@ -178,7 +178,7 @@ static void wctablet_input_sync(DeviceState *dev) } } -static QemuInputHandler wctablet_handler = { +static const QemuInputHandler wctablet_handler = { .name = "QEMU Wacom Pen Tablet", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS, .event = wctablet_input_event, diff --git a/configs/meson/windows.txt b/configs/meson/windows.txt new file mode 100644 index 0000000000..55b192e71b --- /dev/null +++ b/configs/meson/windows.txt @@ -0,0 +1,9 @@ +# target-specific defaults, can still be overridden on +# the command line + +[built-in options] +bindir = '' +prefix = '/qemu' + +[project options] +qemu_suffix = '' diff --git a/configure b/configure index 8fada85a71..b4ea78c77d 100755 --- a/configure +++ b/configure @@ -94,7 +94,7 @@ quote_sh() { printf "%s" "$1" | sed "s,','\\\\'',g; s,.*,'&'," } -print_error() { +error_exit() { (echo echo "ERROR: $1" while test -n "$2"; do @@ -102,10 +102,6 @@ print_error() { shift done echo) >&2 -} - -error_exit() { - print_error "$@" exit 1 } @@ -248,11 +244,8 @@ done default_cflags='-O2 -g' git_submodules_action="update" -git="git" docs="auto" EXESUF="" -prefix="/usr/local" -qemu_suffix="qemu" system="yes" linux_user="" bsd_user="" @@ -261,12 +254,10 @@ subdirs="" ninja="" python= download="enabled" -bindir="bin" skip_meson=no use_containers="yes" gdb_bin=$(command -v "gdb-multiarch" || command -v "gdb") gdb_arches="" -werror="" # Don't accept a target_list environment variable. unset target_list @@ -322,7 +313,6 @@ objcopy="${OBJCOPY-${cross_prefix}objcopy}" ld="${LD-${cross_prefix}ld}" ranlib="${RANLIB-${cross_prefix}ranlib}" nm="${NM-${cross_prefix}nm}" -smbd="$SMBD" strip="${STRIP-${cross_prefix}strip}" widl="${WIDL-${cross_prefix}widl}" windres="${WINDRES-${cross_prefix}windres}" @@ -373,18 +363,6 @@ else targetos=bogus fi -# OS specific - -case $targetos in -windows) - plugins="no" - pie="no" -;; -haiku) - pie="no" -;; -esac - if test ! -z "$cpu" ; then # command line argument : @@ -562,7 +540,8 @@ first_python= if test -z "${PYTHON}"; then # A bare 'python' is traditionally python 2.x, but some distros # have it as python 3.x, so check in both places. - for binary in python3 python python3.11 python3.10 python3.9 python3.8; do + for binary in python3 python python3.12 python3.11 \ + python3.10 python3.9 python3.8; do if has "$binary"; then python=$(command -v "$binary") if check_py_version "$python"; then @@ -599,9 +578,6 @@ done if test "$targetos" = "windows" ; then EXESUF=".exe" - prefix="/qemu" - bindir="" - qemu_suffix="" fi meson_option_build_array() { @@ -624,7 +600,10 @@ meson_option_build_array() { meson_options= meson_option_add() { - meson_options="$meson_options $(quote_sh "$1")" + local arg + for arg; do + meson_options="$meson_options $(quote_sh "$arg")" + done } meson_option_parse() { meson_options="$meson_options $(_meson_option_parse "$@")" @@ -635,6 +614,14 @@ meson_option_parse() { fi } +meson_add_machine_file() { + if test "$cross_compile" = "yes"; then + meson_option_add --cross-file "$1" + else + meson_option_add --native-file "$1" + fi +} + for opt do optarg=$(expr "x$opt" : 'x[^=]*=\(.*\)') case "$opt" in @@ -642,8 +629,6 @@ for opt do ;; --version|-V) exec cat "$source_path/VERSION" ;; - --prefix=*) prefix="$optarg" - ;; --cross-prefix=*) ;; --cc=*) @@ -664,8 +649,6 @@ for opt do ;; --ninja=*) ninja="$optarg" ;; - --smbd=*) smbd="$optarg" - ;; --extra-cflags=*) ;; --extra-cxxflags=*) @@ -714,10 +697,6 @@ for opt do ;; --static) static="yes" ;; - --bindir=*) bindir="$optarg" - ;; - --with-suffix=*) qemu_suffix="$optarg" - ;; --host=*|--build=*|\ --disable-dependency-tracking|\ --sbindir=*|--sharedstatedir=*|\ @@ -737,7 +716,6 @@ for opt do default_cflags='-O0 -g' ;; --disable-tcg) tcg="disabled" - plugins="no" ;; --enable-tcg) tcg="enabled" ;; @@ -762,25 +740,15 @@ for opt do ;; --disable-pie) pie="no" ;; - --enable-werror) werror="yes" + --enable-cfi) cfi=true ;; - --disable-werror) werror="no" - ;; - --enable-cfi) - cfi="true"; - meson_option_add -Db_lto=true - ;; - --disable-cfi) cfi="false" + --disable-cfi) cfi=false ;; --disable-download) download="disabled"; git_submodules_action=validate; ;; --enable-download) download="enabled"; git_submodules_action=update; ;; - --enable-plugins) if test "$targetos" = "windows"; then - error_exit "TCG plugins not currently supported on Windows platforms" - else - plugins="yes" - fi + --enable-plugins) plugins="yes" ;; --disable-plugins) plugins="no" ;; @@ -806,11 +774,6 @@ then git_submodules_action="validate" fi -# test for any invalid configuration combinations -if test "$plugins" = "yes" -a "$tcg" = "disabled"; then - error_exit "Can't enable plugins on non-TCG builds" -fi - if ! test -f "$source_path/subprojects/keycodemapdb/README" \ && test "$download" = disabled then @@ -886,7 +849,6 @@ Options: [defaults in brackets after descriptions] Standard options: --help print this message - --prefix=PREFIX install in PREFIX [$prefix] --target-list=LIST set target list (default: build all) $(echo Available targets: $default_target_list | \ fold -s -w 53 | sed -e 's/^/ /') @@ -909,20 +871,14 @@ Advanced options (experts only): --cross-prefix-ARCH=PREFIX cross compiler prefix when building ARCH guest test cases --python=PYTHON use specified python [$python] --ninja=NINJA use specified ninja [$ninja] - --smbd=SMBD use specified smbd [$smbd] --static enable static build [$static] - --bindir=PATH install binaries in PATH - --with-suffix=SUFFIX suffix for QEMU data inside datadir/libdir/sysconfdir/docdir [$qemu_suffix] --without-default-features default all --enable-* options to "disabled" --without-default-devices do not include any device that is not needed to start the emulator (only use if you are including desired devices in configs/devices/) --with-devices-ARCH=NAME override default configs/devices --enable-debug enable common debug build options - --disable-werror disable compilation abort on warning --cpu=CPU Build for host CPU [$cpu] - --enable-plugins - enable plugins via shared library loading --disable-containers don't use containers for cross-building --container-engine=TYPE which container engine to use [$container_engine] --gdb=GDB-path gdb to use for gdbstub tests [$gdb_bin] @@ -948,7 +904,7 @@ then # If first_python is set, there was a binary somewhere even though # it was not suitable. Use it for the error message. if test -n "$first_python"; then - error_exit "Cannot use '$first_python', Python >= 3.7 is required." \ + error_exit "Cannot use '$first_python', Python >= 3.8 is required." \ "Use --python=/path/to/python to specify a supported Python." else error_exit "Python not found. Use --python=/path/to/python" @@ -1045,17 +1001,6 @@ if test -z "$ninja"; then fi fi -# Consult white-list to determine whether to enable werror -# by default. Only enable by default for git builds -if test -z "$werror" ; then - if test -e "$source_path/.git" && \ - { test "$targetos" = linux || test "$targetos" = "windows"; }; then - werror="yes" - else - werror="no" - fi -fi - if test "$targetos" = "bogus"; then # Now that we know that we're not printing the help and that # the compiler works (so the results of the check_defines we used @@ -1064,15 +1009,27 @@ if test "$targetos" = "bogus"; then error_exit "Unrecognized host OS (uname -s reports '$(uname -s)')" fi +# test for any invalid configuration combinations +if test "$targetos" = "windows"; then + if test "$plugins" = "yes"; then + error_exit "TCG plugins not currently supported on Windows platforms" + fi + plugins="no" +fi +if test "$tcg" = "disabled" ; then + if test "$plugins" = "yes"; then + error_exit "Can't enable plugins on non-TCG builds" + fi + plugins="no" +fi if test "$static" = "yes" ; then if test "$plugins" = "yes"; then error_exit "static and plugins are mutually incompatible" - else - plugins="no" fi + plugins="no" fi -test "$plugins" = "" && plugins=yes -if test "$plugins" = "yes"; then +if test "$plugins" != "no"; then + plugins=yes subdirs="$subdirs contrib/plugins" fi @@ -1087,19 +1044,23 @@ static THREAD int tls_var; int main(void) { return tls_var; } EOF -if test "$static" = "yes"; then - if test "$pie" != "no" && compile_prog "-Werror -fPIE -DPIE" "-static-pie"; then - pie="yes" - elif test "$pie" = "yes"; then - error_exit "-static-pie not available due to missing toolchain support" +if test "$targetos" = windows || test "$targetos" = haiku; then + if test "$pie" = "yes"; then + error_exit "PIE not available due to missing OS support" + fi + pie=no +fi + +if test "$pie" != "no"; then + if test "$static" = "yes"; then + pie_ldflags=-static-pie else - pie="no" + pie_ldflags=-pie fi -elif test "$pie" != "no"; then - if compile_prog "-Werror -fPIE -DPIE" "-pie"; then + if compile_prog "-Werror -fPIE -DPIE" "$pie_ldflags"; then pie="yes" elif test "$pie" = "yes"; then - error_exit "PIE not available due to missing toolchain support" + error_exit "-static-pie not available due to missing toolchain support" else echo "Disabling PIE due to missing toolchain support" pie="no" @@ -1138,6 +1099,18 @@ if test "$tcg" = "auto"; then fi fi +######################################### +# gdb test + +if test -n "$gdb_bin"; then + gdb_version=$($gdb_bin --version | head -n 1) + if version_ge ${gdb_version##* } 9.1; then + gdb_arches=$($python "$source_path/scripts/probe-gdb-support.py" $gdb_bin) + else + gdb_bin="" + fi +fi + ########################################## # big/little endian test cat > $TMPC << EOF @@ -1165,34 +1138,6 @@ EOF fi fi -######################################## -# check if ccache is interfering with -# semantic analysis of macros - -unset CCACHE_CPP2 -ccache_cpp2=no -cat > $TMPC << EOF -static const int Z = 1; -#define fn() ({ Z; }) -#define TAUT(X) ((X) == Z) -#define PAREN(X, Y) (X == Y) -#define ID(X) (X) -int main(void) -{ - int x = 0, y = 0; - x = ID(x); - x = fn(); - fn(); - if (PAREN(x, y)) return 0; - if (TAUT(Z)) return 0; - return 0; -} -EOF - -if ! compile_object "-Werror"; then - ccache_cpp2=yes -fi - ########################################## # functions to probe cross compilers @@ -1336,10 +1281,6 @@ probe_target_compiler() { container_cross_prefix=aarch64-linux-gnu- container_cross_cc=${container_cross_prefix}gcc ;; - alpha) - container_image=debian-alpha-cross - container_cross_prefix=alpha-linux-gnu- - ;; arm) # We don't have any bigendian build tools so we only use this for ARM container_image=debian-armhf-cross @@ -1354,10 +1295,6 @@ probe_target_compiler() { container_cross_prefix=hexagon-unknown-linux-musl- container_cross_cc=${container_cross_prefix}clang ;; - hppa) - container_image=debian-hppa-cross - container_cross_prefix=hppa-linux-gnu- - ;; i386) container_image=fedora-i386-cross container_cross_prefix= @@ -1366,10 +1303,6 @@ probe_target_compiler() { container_image=debian-loongarch-cross container_cross_prefix=loongarch64-unknown-linux-gnu- ;; - m68k) - container_image=debian-m68k-cross - container_cross_prefix=m68k-linux-gnu- - ;; microblaze) container_image=debian-microblaze-cross container_cross_prefix=microblaze-linux-musl- @@ -1382,14 +1315,6 @@ probe_target_compiler() { container_image=debian-mips64-cross container_cross_prefix=mips64-linux-gnuabi64- ;; - mipsel) - container_image=debian-mipsel-cross - container_cross_prefix=mipsel-linux-gnu- - ;; - mips) - container_image=debian-mips-cross - container_cross_prefix=mips-linux-gnu- - ;; nios2) container_image=debian-nios2-cross container_cross_prefix=nios2-linux-gnu- @@ -1404,22 +1329,6 @@ probe_target_compiler() { container_cross_prefix=powerpc${target_arch#ppc}-linux-gnu- container_cross_cc=${container_cross_prefix}gcc-10 ;; - riscv64) - container_image=debian-riscv64-test-cross - container_cross_prefix=riscv64-linux-gnu- - ;; - s390x) - container_image=debian-s390x-cross - container_cross_prefix=s390x-linux-gnu- - ;; - sh4) - container_image=debian-sh4-cross - container_cross_prefix=sh4-linux-gnu- - ;; - sparc64) - container_image=debian-sparc64-cross - container_cross_prefix=sparc64-linux-gnu- - ;; tricore) container_image=debian-tricore-cross container_cross_prefix=tricore- @@ -1434,6 +1343,11 @@ probe_target_compiler() { # default to the dc232b cpu container_cross_prefix=/opt/2020.07/xtensa-dc232b-elf/bin/xtensa-dc232b-elf- ;; + *) + # Debian and GNU architecture names usually match + container_image=debian-$target_arch-cross + container_cross_prefix=$target_arch-linux-gnu- + ;; esac : ${container_cross_cc:=${container_cross_prefix}gcc} : ${container_cross_ar:=${container_cross_prefix}ar} @@ -1678,25 +1592,9 @@ echo >> $config_host_mak echo all: >> $config_host_mak -if test "$targetos" = "windows"; then - echo "QEMU_GA_MANUFACTURER=${QEMU_GA_MANUFACTURER-QEMU}" >> $config_host_mak - echo "QEMU_GA_DISTRO=${QEMU_GA_DISTRO-Linux}" >> $config_host_mak - echo "QEMU_GA_VERSION=${QEMU_GA_VERSION-$(cat "$source_path"/VERSION)}" >> $config_host_mak -fi - echo "SRC_PATH=$source_path" >> $config_host_mak echo "TARGET_DIRS=$target_list" >> $config_host_mak - -if test -n "$gdb_bin"; then - gdb_version=$($gdb_bin --version | head -n 1) - if version_ge ${gdb_version##* } 9.1; then - echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak - gdb_arches=$($python "$source_path/scripts/probe-gdb-support.py" $gdb_bin) - else - gdb_bin="" - fi -fi - +echo "GDB=$gdb_bin" >> $config_host_mak if test "$container" != no; then echo "RUNC=$runc" >> $config_host_mak fi @@ -1725,10 +1623,6 @@ if test "$default_targets" = "yes"; then echo "CONFIG_DEFAULT_TARGETS=y" >> $config_host_mak fi -if test "$ccache_cpp2" = "yes"; then - echo "export CCACHE_CPP2=y" >> $config_host_mak -fi - # contrib/plugins configuration echo "# Automatically generated by configure - do not modify" > contrib/plugins/$config_host_mak echo "SRC_PATH=$source_path/contrib/plugins" >> contrib/plugins/$config_host_mak @@ -1745,14 +1639,6 @@ mkdir -p tests/tcg echo "# Automatically generated by configure - do not modify" > $config_host_mak echo "SRC_PATH=$source_path" >> $config_host_mak -# versioned checked in the main config_host.mak above -if test -n "$gdb_bin"; then - echo "HAVE_GDB_BIN=$gdb_bin" >> $config_host_mak -fi -if test "$plugins" = "yes" ; then - echo "CONFIG_PLUGIN=y" >> $config_host_mak -fi - tcg_tests_targets= for target in $target_list; do arch=${target%%-*} @@ -1785,7 +1671,7 @@ for target in $target_list; do # will GDB work with these binaries? if test "${gdb_arches#*$arch}" != "$gdb_arches"; then - echo "HOST_GDB_SUPPORTS_ARCH=y" >> "$config_target_mak" + echo "GDB=$gdb_bin" >> $config_target_mak fi echo "run-tcg-tests-$target: $qemu\$(EXESUF)" >> Makefile.prereqs @@ -1820,6 +1706,29 @@ if test "$skip_meson" = no; then test -n "$objcc" && echo "objc_args = [$(meson_quote $OBJCFLAGS $EXTRA_OBJCFLAGS)]" >> $cross echo "c_link_args = [$(meson_quote $CFLAGS $LDFLAGS $EXTRA_CFLAGS $EXTRA_LDFLAGS)]" >> $cross echo "cpp_link_args = [$(meson_quote $CXXFLAGS $LDFLAGS $EXTRA_CXXFLAGS $EXTRA_LDFLAGS)]" >> $cross + + # Only enable by default for git builds and on select OSes + echo "# environment defaults, can still be overridden on " >> $cross + echo "# the command line" >> $cross + if test -e "$source_path/.git" && \ + { test "$targetos" = linux || test "$targetos" = "windows"; }; then + echo 'werror = true' >> $cross + fi + echo "[project options]" >> $cross + if test "$SMBD" != ''; then + echo "smbd = $(meson_quote "$SMBD")" >> $cross + fi + if test "${QEMU_GA_MANUFACTURER}" != ''; then + echo "qemu_ga_manufacturer = $(meson_quote "${QEMU_GA_MANUFACTURER}")" >> $cross + fi + if test "${QEMU_GA_DISTRO}" != ''; then + echo "qemu_ga_distro = $(meson_quote "${QEMU_GA_DISTRO}")" >> $cross + fi + if test "${QEMU_GA_VERSION}" != ''; then + echo "qemu_ga_version = $(meson_quote "${QEMU_GA_VERSION}")" >> $cross + fi + + echo >> $cross echo "[binaries]" >> $cross echo "c = [$(meson_quote $cc $CPU_CFLAGS)]" >> $cross test -n "$cxx" && echo "cpp = [$(meson_quote $cxx $CPU_CFLAGS)]" >> $cross @@ -1827,6 +1736,7 @@ if test "$skip_meson" = no; then echo "ar = [$(meson_quote $ar)]" >> $cross echo "nm = [$(meson_quote $nm)]" >> $cross echo "pkgconfig = [$(meson_quote $pkg_config)]" >> $cross + echo "pkg-config = [$(meson_quote $pkg_config)]" >> $cross echo "ranlib = [$(meson_quote $ranlib)]" >> $cross if has $sdl2_config; then echo "sdl2-config = [$(meson_quote $sdl2_config)]" >> $cross @@ -1852,39 +1762,36 @@ if test "$skip_meson" = no; then else echo "endian = 'little'" >> $cross fi - cross_arg="--cross-file config-meson.cross" native="config-meson.native.new" echo "# Automatically generated by configure - do not modify" > $native echo "[binaries]" >> $native echo "c = [$(meson_quote $host_cc)]" >> $native mv $native config-meson.native - cross_arg="$cross_arg --native-file config-meson.native" - else - cross_arg="--native-file config-meson.cross" + meson_option_add --native-file + meson_option_add config-meson.native fi mv $cross config-meson.cross + meson_add_machine_file config-meson.cross + if test -f "$source_path/configs/meson/$targetos.txt"; then + meson_add_machine_file $source_path/configs/meson/$targetos.txt + fi rm -rf meson-private meson-info meson-logs - # Built-in options test "$download" = "disabled" && meson_option_add "--wrap-mode=nodownload" - test "$bindir" != "bin" && meson_option_add "-Dbindir=$bindir" test "$default_feature" = no && meson_option_add -Dauto_features=disabled test "$static" = yes && meson_option_add -Dprefer_static=true test "$pie" = no && meson_option_add -Db_pie=false - test "$werror" = yes && meson_option_add -Dwerror=true # QEMU options - test "$cfi" != false && meson_option_add "-Dcfi=$cfi" + test "$cfi" != false && meson_option_add "-Dcfi=$cfi" "-Db_lto=$cfi" test "$docs" != auto && meson_option_add "-Ddocs=$docs" test -n "${LIB_FUZZING_ENGINE+xxx}" && meson_option_add "-Dfuzzing_engine=$LIB_FUZZING_ENGINE" test "$plugins" = yes && meson_option_add "-Dplugins=true" - test "$qemu_suffix" != qemu && meson_option_add "-Dqemu_suffix=$qemu_suffix" - test "$smbd" != '' && meson_option_add "-Dsmbd=$smbd" test "$tcg" != enabled && meson_option_add "-Dtcg=$tcg" run_meson() { - NINJA=$ninja $meson setup --prefix "$prefix" "$@" $cross_arg "$PWD" "$source_path" + NINJA=$ninja $meson setup "$@" "$PWD" "$source_path" } eval run_meson $meson_options if test "$?" -ne 0 ; then diff --git a/contrib/elf2dmp/addrspace.c b/contrib/elf2dmp/addrspace.c index 64b5d680ad..6f608a517b 100644 --- a/contrib/elf2dmp/addrspace.c +++ b/contrib/elf2dmp/addrspace.c @@ -72,10 +72,7 @@ int pa_space_create(struct pa_space *ps, QEMU_Elf *qemu_elf) } } - ps->block = malloc(sizeof(*ps->block) * ps->block_nr); - if (!ps->block) { - return 1; - } + ps->block = g_new(struct pa_block, ps->block_nr); for (i = 0; i < phdr_nr; i++) { if (phdr[i].p_type == PT_LOAD) { @@ -97,7 +94,7 @@ int pa_space_create(struct pa_space *ps, QEMU_Elf *qemu_elf) void pa_space_destroy(struct pa_space *ps) { ps->block_nr = 0; - free(ps->block); + g_free(ps->block); } void va_space_set_dtb(struct va_space *vs, uint64_t dtb) diff --git a/contrib/elf2dmp/main.c b/contrib/elf2dmp/main.c index 5db163bdbe..cbc38a7c10 100644 --- a/contrib/elf2dmp/main.c +++ b/contrib/elf2dmp/main.c @@ -120,14 +120,11 @@ static KDDEBUGGER_DATA64 *get_kdbg(uint64_t KernBase, struct pdb_reader *pdb, } } - kdbg = malloc(kdbg_hdr.Size); - if (!kdbg) { - return NULL; - } + kdbg = g_malloc(kdbg_hdr.Size); if (va_space_rw(vs, KdDebuggerDataBlock, kdbg, kdbg_hdr.Size, 0)) { eprintf("Failed to extract entire KDBG\n"); - free(kdbg); + g_free(kdbg); return NULL; } @@ -478,7 +475,7 @@ static bool pe_check_pdb_name(uint64_t base, void *start_addr, } if (memcmp(&rsds->Signature, sign_rsds, sizeof(sign_rsds))) { - eprintf("CodeView signature is \'%.4s\', \'%s\' expected\n", + eprintf("CodeView signature is \'%.4s\', \'%.4s\' expected\n", rsds->Signature, sign_rsds); return false; } @@ -643,7 +640,7 @@ int main(int argc, char *argv[]) } out_kdbg: - free(kdbg); + g_free(kdbg); out_pdb: pdb_exit(&pdb); out_pdb_file: diff --git a/contrib/elf2dmp/pdb.c b/contrib/elf2dmp/pdb.c index 6ca5086f02..40991f5f4c 100644 --- a/contrib/elf2dmp/pdb.c +++ b/contrib/elf2dmp/pdb.c @@ -25,6 +25,10 @@ static uint32_t pdb_get_file_size(const struct pdb_reader *r, unsigned idx) { + if (idx >= r->ds.toc->num_files) { + return 0; + } + return r->ds.toc->file_size[idx]; } @@ -90,18 +94,18 @@ uint64_t pdb_resolve(uint64_t img_base, struct pdb_reader *r, const char *name) static void pdb_reader_ds_exit(struct pdb_reader *r) { - free(r->ds.toc); + g_free(r->ds.toc); } static void pdb_exit_symbols(struct pdb_reader *r) { - free(r->modimage); - free(r->symbols); + g_free(r->modimage); + g_free(r->symbols); } static void pdb_exit_segments(struct pdb_reader *r) { - free(r->segs); + g_free(r->segs); } static void *pdb_ds_read(const PDB_DS_HEADER *header, @@ -116,10 +120,7 @@ static void *pdb_ds_read(const PDB_DS_HEADER *header, nBlocks = (size + header->block_size - 1) / header->block_size; - buffer = malloc(nBlocks * header->block_size); - if (!buffer) { - return NULL; - } + buffer = g_malloc(nBlocks * header->block_size); for (i = 0; i < nBlocks; i++) { memcpy(buffer + i * header->block_size, (const char *)header + @@ -159,16 +160,17 @@ static void *pdb_ds_read_file(struct pdb_reader* r, uint32_t file_number) static int pdb_init_segments(struct pdb_reader *r) { - char *segs; unsigned stream_idx = r->segments; - segs = pdb_ds_read_file(r, stream_idx); - if (!segs) { + r->segs = pdb_ds_read_file(r, stream_idx); + if (!r->segs) { return 1; } - r->segs = segs; r->segs_size = pdb_get_file_size(r, stream_idx); + if (!r->segs_size) { + return 1; + } return 0; } @@ -201,7 +203,7 @@ static int pdb_init_symbols(struct pdb_reader *r) return 0; out_symbols: - free(symbols); + g_free(symbols); return err; } @@ -258,7 +260,7 @@ static int pdb_reader_init(struct pdb_reader *r, void *data) out_sym: pdb_exit_symbols(r); out_root: - free(r->ds.root); + g_free(r->ds.root); out_ds: pdb_reader_ds_exit(r); @@ -269,7 +271,7 @@ static void pdb_reader_exit(struct pdb_reader *r) { pdb_exit_segments(r); pdb_exit_symbols(r); - free(r->ds.root); + g_free(r->ds.root); pdb_reader_ds_exit(r); } diff --git a/contrib/elf2dmp/qemu_elf.c b/contrib/elf2dmp/qemu_elf.c index de6ad744c6..055e6f8792 100644 --- a/contrib/elf2dmp/qemu_elf.c +++ b/contrib/elf2dmp/qemu_elf.c @@ -94,10 +94,7 @@ static int init_states(QEMU_Elf *qe) printf("%zu CPU states has been found\n", cpu_nr); - qe->state = malloc(sizeof(*qe->state) * cpu_nr); - if (!qe->state) { - return 1; - } + qe->state = g_new(QEMUCPUState*, cpu_nr); cpu_nr = 0; @@ -115,7 +112,7 @@ static int init_states(QEMU_Elf *qe) static void exit_states(QEMU_Elf *qe) { - free(qe->state); + g_free(qe->state); } static bool check_ehdr(QEMU_Elf *qe) diff --git a/contrib/vhost-user-gpu/vhost-user-gpu.c b/contrib/vhost-user-gpu/vhost-user-gpu.c index aa304475a0..bb41758e34 100644 --- a/contrib/vhost-user-gpu/vhost-user-gpu.c +++ b/contrib/vhost-user-gpu/vhost-user-gpu.c @@ -834,7 +834,7 @@ vg_resource_flush(VuGpu *g, .width = width, .height = height, }; - pixman_image_t *i = + pixman_image_t *img = pixman_image_create_bits(pixman_image_get_format(res->image), msg->payload.update.width, msg->payload.update.height, @@ -842,11 +842,11 @@ vg_resource_flush(VuGpu *g, payload.update.data), width * bpp); pixman_image_composite(PIXMAN_OP_SRC, - res->image, NULL, i, + res->image, NULL, img, extents->x1, extents->y1, 0, 0, 0, 0, width, height); - pixman_image_unref(i); + pixman_image_unref(img); vg_send_msg(g, msg, -1); g_free(msg); } diff --git a/contrib/vhost-user-gpu/vugpu.h b/contrib/vhost-user-gpu/vugpu.h index 509b679f03..654c392fbb 100644 --- a/contrib/vhost-user-gpu/vugpu.h +++ b/contrib/vhost-user-gpu/vugpu.h @@ -164,12 +164,12 @@ struct virtio_gpu_ctrl_command { }; #define VUGPU_FILL_CMD(out) do { \ - size_t s; \ - s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, 0, \ + size_t vugpufillcmd_s_ = \ + iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, 0, \ &out, sizeof(out)); \ - if (s != sizeof(out)) { \ + if (vugpufillcmd_s_ != sizeof(out)) { \ g_critical("%s: command size incorrect %zu vs %zu", \ - __func__, s, sizeof(out)); \ + __func__, vugpufillcmd_s_, sizeof(out)); \ return; \ } \ } while (0) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 1c4d7f36f0..2febd2d12f 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -363,6 +363,15 @@ recommending to switch to their stable counterparts: - "Zve64f" should be replaced with "zve64f" - "Zve64d" should be replaced with "zve64d" +``-device pvrdma`` and the rdma subsystem (since 8.2) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The pvrdma device and the whole rdma subsystem are in a bad shape and +without active maintenance. The QEMU project intends to remove this +device and subsystem from the code base in a future release without +replacement unless somebody steps up and improves the situation. + + Block device options '''''''''''''''''''' diff --git a/docs/devel/testing.rst b/docs/devel/testing.rst index f3e2472189..b0680cbb22 100644 --- a/docs/devel/testing.rst +++ b/docs/devel/testing.rst @@ -1014,8 +1014,8 @@ class. Here's a simple usage example: """ def test_qmp_human_info_version(self): self.vm.launch() - res = self.vm.command('human-monitor-command', - command_line='info version') + res = self.vm.cmd('human-monitor-command', + command_line='info version') self.assertRegexpMatches(res, r'^(\d+\.\d+\.\d)') To execute your test, run: @@ -1065,15 +1065,15 @@ and hypothetical example follows: first_machine.launch() second_machine.launch() - first_res = first_machine.command( + first_res = first_machine.cmd( 'human-monitor-command', command_line='info version') - second_res = second_machine.command( + second_res = second_machine.cmd( 'human-monitor-command', command_line='info version') - third_res = self.get_vm(name='third_machine').command( + third_res = self.get_vm(name='third_machine').cmd( 'human-monitor-command', command_line='info version') diff --git a/docs/sphinx/hxtool.py b/docs/sphinx/hxtool.py index fb0649a3d5..9f6b9d87dc 100644 --- a/docs/sphinx/hxtool.py +++ b/docs/sphinx/hxtool.py @@ -49,7 +49,7 @@ def serror(file, lnum, errtext): def parse_directive(line): """Return first word of line, if any""" - return re.split('\W', line)[0] + return re.split(r'\W', line)[0] def parse_defheading(file, lnum, line): """Handle a DEFHEADING directive""" diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 965cbf84c5..47fd648035 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -46,6 +46,7 @@ the following architecture extensions: - FEAT_HCX (Support for the HCRX_EL2 register) - FEAT_HPDS (Hierarchical permission disables) - FEAT_HPDS2 (Translation table page-based hardware attributes) +- FEAT_HPMN0 (Setting of MDCR_EL2.HPMN to zero) - FEAT_I8MM (AArch64 Int8 matrix multiplication instructions) - FEAT_IDST (ID space trap handling) - FEAT_IESB (Implicit error synchronization event) diff --git a/docs/system/device-emulation.rst b/docs/system/device-emulation.rst index 4491c4cbf7..1167f3a9f2 100644 --- a/docs/system/device-emulation.rst +++ b/docs/system/device-emulation.rst @@ -91,6 +91,7 @@ Emulated Devices devices/nvme.rst devices/usb.rst devices/vhost-user.rst + devices/virtio-gpu.rst devices/virtio-pmem.rst devices/vhost-user-rng.rst devices/canokey.rst diff --git a/docs/system/devices/virtio-gpu.rst b/docs/system/devices/virtio-gpu.rst new file mode 100644 index 0000000000..cb73dd7998 --- /dev/null +++ b/docs/system/devices/virtio-gpu.rst @@ -0,0 +1,112 @@ +.. + SPDX-License-Identifier: GPL-2.0-or-later + +virtio-gpu +========== + +This document explains the setup and usage of the virtio-gpu device. +The virtio-gpu device paravirtualizes the GPU and display controller. + +Linux kernel support +-------------------- + +virtio-gpu requires a guest Linux kernel built with the +``CONFIG_DRM_VIRTIO_GPU`` option. + +QEMU virtio-gpu variants +------------------------ + +QEMU virtio-gpu device variants come in the following form: + + * ``virtio-vga[-BACKEND]`` + * ``virtio-gpu[-BACKEND][-INTERFACE]`` + * ``vhost-user-vga`` + * ``vhost-user-pci`` + +**Backends:** QEMU provides a 2D virtio-gpu backend, and two accelerated +backends: virglrenderer ('gl' device label) and rutabaga_gfx ('rutabaga' +device label). There is a vhost-user backend that runs the graphics stack +in a separate process for improved isolation. + +**Interfaces:** QEMU further categorizes virtio-gpu device variants based +on the interface exposed to the guest. The interfaces can be classified +into VGA and non-VGA variants. The VGA ones are prefixed with virtio-vga +or vhost-user-vga while the non-VGA ones are prefixed with virtio-gpu or +vhost-user-gpu. + +The VGA ones always use the PCI interface, but for the non-VGA ones, the +user can further pick between MMIO or PCI. For MMIO, the user can suffix +the device name with -device, though vhost-user-gpu does not support MMIO. +For PCI, the user can suffix it with -pci. Without these suffixes, the +platform default will be chosen. + +virtio-gpu 2d +------------- + +The default 2D backend only performs 2D operations. The guest needs to +employ a software renderer for 3D graphics. + +Typically, the software renderer is provided by `Mesa`_ or `SwiftShader`_. +Mesa's implementations (LLVMpipe, Lavapipe and virgl below) work out of box +on typical modern Linux distributions. + +.. parsed-literal:: + -device virtio-gpu + +.. _Mesa: https://www.mesa3d.org/ +.. _SwiftShader: https://github.com/google/swiftshader + +virtio-gpu virglrenderer +------------------------ + +When using virgl accelerated graphics mode in the guest, OpenGL API calls +are translated into an intermediate representation (see `Gallium3D`_). The +intermediate representation is communicated to the host and the +`virglrenderer`_ library on the host translates the intermediate +representation back to OpenGL API calls. + +.. parsed-literal:: + -device virtio-gpu-gl + +.. _Gallium3D: https://www.freedesktop.org/wiki/Software/gallium/ +.. _virglrenderer: https://gitlab.freedesktop.org/virgl/virglrenderer/ + +virtio-gpu rutabaga +------------------- + +virtio-gpu can also leverage rutabaga_gfx to provide `gfxstream`_ +rendering and `Wayland display passthrough`_. With the gfxstream rendering +mode, GLES and Vulkan calls are forwarded to the host with minimal +modification. + +The crosvm book provides directions on how to build a `gfxstream-enabled +rutabaga`_ and launch a `guest Wayland proxy`_. + +This device does require host blob support (``hostmem`` field below). The +``hostmem`` field specifies the size of virtio-gpu host memory window. +This is typically between 256M and 8G. + +At least one virtio-gpu capability set ("capset") must be specified when +starting the device. The currently capsets supported are ``gfxstream-vulkan`` +and ``cross-domain`` for Linux guests. For Android guests, the experimental +``x-gfxstream-gles`` and ``x-gfxstream-composer`` capsets are also supported. + +The device will try to auto-detect the wayland socket path if the +``cross-domain`` capset name is set. The user may optionally specify +``wayland-socket-path`` for non-standard paths. + +The ``wsi`` option can be set to ``surfaceless`` or ``headless``. +Surfaceless doesn't create a native window surface, but does copy from the +render target to the Pixman buffer if a virtio-gpu 2D hypercall is issued. +Headless is like surfaceless, but doesn't copy to the Pixman buffer. +Surfaceless is the default if ``wsi`` is not specified. + +.. parsed-literal:: + -device virtio-gpu-rutabaga,gfxstream-vulkan=on,cross-domain=on, + hostmem=8G,wayland-socket-path=/tmp/nonstandard/mock_wayland.sock, + wsi=headless + +.. _gfxstream: https://android.googlesource.com/platform/hardware/google/gfxstream/ +.. _Wayland display passthrough: https://www.youtube.com/watch?v=OZJiHMtIQ2M +.. _gfxstream-enabled rutabaga: https://crosvm.dev/book/appendix/rutabaga_gfx.html +.. _guest Wayland proxy: https://crosvm.dev/book/devices/wayland.html diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c index cdd6f775a1..4f75c873e2 100644 --- a/hw/acpi/pcihp.c +++ b/hw/acpi/pcihp.c @@ -496,8 +496,7 @@ static const MemoryRegionOps acpi_pcihp_io_ops = { }; void acpi_pcihp_init(Object *owner, AcpiPciHpState *s, PCIBus *root_bus, - MemoryRegion *address_space_io, - uint16_t io_base) + MemoryRegion *io, uint16_t io_base) { s->io_len = ACPI_PCIHP_SIZE; s->io_base = io_base; @@ -506,7 +505,7 @@ void acpi_pcihp_init(Object *owner, AcpiPciHpState *s, PCIBus *root_bus, memory_region_init_io(&s->io, owner, &acpi_pcihp_io_ops, s, "acpi-pci-hotplug", s->io_len); - memory_region_add_subregion(address_space_io, s->io_base, &s->io); + memory_region_add_subregion(io, s->io_base, &s->io); object_property_add_uint16_ptr(owner, ACPI_PCIHP_IO_BASE_PROP, &s->io_base, OBJ_PROP_FLAG_READ); diff --git a/hw/arm/boot.c b/hw/arm/boot.c index 24fa169060..84ea6a807a 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -722,84 +722,35 @@ static void do_cpu_reset(void *opaque) cpu_set_pc(cs, entry); } else { - /* If we are booting Linux then we need to check whether we are - * booting into secure or non-secure state and adjust the state - * accordingly. Out of reset, ARM is defined to be in secure state - * (SCR.NS = 0), we change that here if non-secure boot has been - * requested. + /* + * If we are booting Linux then we might need to do so at: + * - AArch64 NS EL2 or NS EL1 + * - AArch32 Secure SVC (EL3) + * - AArch32 NS Hyp (EL2) + * - AArch32 NS SVC (EL1) + * Configure the CPU in the way boot firmware would do to + * drop us down to the appropriate level. */ - if (arm_feature(env, ARM_FEATURE_EL3)) { - /* AArch64 is defined to come out of reset into EL3 if enabled. - * If we are booting Linux then we need to adjust our EL as - * Linux expects us to be in EL2 or EL1. AArch32 resets into - * SVC, which Linux expects, so no privilege/exception level to - * adjust. - */ - if (env->aarch64) { - env->cp15.scr_el3 |= SCR_RW; - if (arm_feature(env, ARM_FEATURE_EL2)) { - env->cp15.hcr_el2 |= HCR_RW; - env->pstate = PSTATE_MODE_EL2h; - } else { - env->pstate = PSTATE_MODE_EL1h; - } - if (cpu_isar_feature(aa64_pauth, cpu)) { - env->cp15.scr_el3 |= SCR_API | SCR_APK; - } - if (cpu_isar_feature(aa64_mte, cpu)) { - env->cp15.scr_el3 |= SCR_ATA; - } - if (cpu_isar_feature(aa64_sve, cpu)) { - env->cp15.cptr_el[3] |= R_CPTR_EL3_EZ_MASK; - env->vfp.zcr_el[3] = 0xf; - } - if (cpu_isar_feature(aa64_sme, cpu)) { - env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK; - env->cp15.scr_el3 |= SCR_ENTP2; - env->vfp.smcr_el[3] = 0xf; - } - if (cpu_isar_feature(aa64_hcx, cpu)) { - env->cp15.scr_el3 |= SCR_HXEN; - } - if (cpu_isar_feature(aa64_fgt, cpu)) { - env->cp15.scr_el3 |= SCR_FGTEN; - } + int target_el = arm_feature(env, ARM_FEATURE_EL2) ? 2 : 1; - /* AArch64 kernels never boot in secure mode */ - assert(!info->secure_boot); - /* This hook is only supported for AArch32 currently: - * bootloader_aarch64[] will not call the hook, and - * the code above has already dropped us into EL2 or EL1. - */ - assert(!info->secure_board_setup); - } - - if (arm_feature(env, ARM_FEATURE_EL2)) { - /* If we have EL2 then Linux expects the HVC insn to work */ - env->cp15.scr_el3 |= SCR_HCE; - } - - /* Set to non-secure if not a secure boot */ - if (!info->secure_boot && - (cs != first_cpu || !info->secure_board_setup)) { - /* Linux expects non-secure state */ - env->cp15.scr_el3 |= SCR_NS; - /* Set NSACR.{CP11,CP10} so NS can access the FPU */ - env->cp15.nsacr |= 3 << 10; - } - } - - if (!env->aarch64 && !info->secure_boot && - arm_feature(env, ARM_FEATURE_EL2)) { + if (env->aarch64) { /* - * This is an AArch32 boot not to Secure state, and - * we have Hyp mode available, so boot the kernel into - * Hyp mode. This is not how the CPU comes out of reset, - * so we need to manually put it there. + * AArch64 kernels never boot in secure mode, and we don't + * support the secure_board_setup hook for AArch64. */ - cpsr_write(env, ARM_CPU_MODE_HYP, CPSR_M, CPSRWriteRaw); + assert(!info->secure_boot); + assert(!info->secure_board_setup); + } else { + if (arm_feature(env, ARM_FEATURE_EL3) && + (info->secure_boot || + (info->secure_board_setup && cs == first_cpu))) { + /* Start this CPU in Secure SVC */ + target_el = 3; + } } + arm_emulate_firmware_reset(cs, target_el); + if (cs == first_cpu) { AddressSpace *as = arm_boot_address_space(cpu, info); diff --git a/hw/arm/meson.build b/hw/arm/meson.build index 11eb9112f8..a6feaf1af9 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -64,7 +64,6 @@ arm_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c')) arm_ss.add(when: 'CONFIG_FSL_IMX6UL', if_true: files('fsl-imx6ul.c', 'mcimx6ul-evk.c')) arm_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_soc.c')) arm_ss.add(when: 'CONFIG_XEN', if_true: files('xen_arm.c')) -arm_ss.add_all(xen_ss) system_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmu-common.c')) system_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4_boards.c')) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index 3c7dfcd6dc..e8a82618f0 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -2,6 +2,7 @@ * ARM SBSA Reference Platform emulation * * Copyright (c) 2018 Linaro Limited + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. * Written by Hongbo Zhang <hongbo.zhang@linaro.org> * * This program is free software; you can redistribute it and/or modify it @@ -30,6 +31,7 @@ #include "exec/hwaddr.h" #include "kvm_arm.h" #include "hw/arm/boot.h" +#include "hw/arm/bsa.h" #include "hw/arm/fdt.h" #include "hw/arm/smmuv3.h" #include "hw/block/flash.h" @@ -55,14 +57,6 @@ #define NUM_SMMU_IRQS 4 #define NUM_SATA_PORTS 6 -#define VIRTUAL_PMU_IRQ 7 -#define ARCH_GIC_MAINT_IRQ 9 -#define ARCH_TIMER_VIRT_IRQ 11 -#define ARCH_TIMER_S_EL1_IRQ 13 -#define ARCH_TIMER_NS_EL1_IRQ 14 -#define ARCH_TIMER_NS_EL2_IRQ 10 -#define ARCH_TIMER_NS_EL2_VIRT_IRQ 12 - enum { SBSA_FLASH, SBSA_MEM, @@ -479,7 +473,7 @@ static void create_gic(SBSAMachineState *sms, MemoryRegion *mem) */ for (i = 0; i < smp_cpus; i++) { DeviceState *cpudev = DEVICE(qemu_get_cpu(i)); - int ppibase = NUM_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; + int intidbase = NUM_IRQS + i * GIC_INTERNAL; int irq; /* * Mapping from the output timer irq lines from the CPU to the @@ -496,14 +490,17 @@ static void create_gic(SBSAMachineState *sms, MemoryRegion *mem) for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { qdev_connect_gpio_out(cpudev, irq, qdev_get_gpio_in(sms->gic, - ppibase + timer_irq[irq])); + intidbase + timer_irq[irq])); } qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", 0, - qdev_get_gpio_in(sms->gic, ppibase + qdev_get_gpio_in(sms->gic, + intidbase + ARCH_GIC_MAINT_IRQ)); + qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, - qdev_get_gpio_in(sms->gic, ppibase + qdev_get_gpio_in(sms->gic, + intidbase + VIRTUAL_PMU_IRQ)); sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h index 648c2e37a2..6076025ad6 100644 --- a/hw/arm/smmuv3-internal.h +++ b/hw/arm/smmuv3-internal.h @@ -38,33 +38,71 @@ REG32(IDR0, 0x0) FIELD(IDR0, S1P, 1 , 1) FIELD(IDR0, TTF, 2 , 2) FIELD(IDR0, COHACC, 4 , 1) + FIELD(IDR0, BTM, 5 , 1) + FIELD(IDR0, HTTU, 6 , 2) + FIELD(IDR0, DORMHINT, 8 , 1) + FIELD(IDR0, HYP, 9 , 1) + FIELD(IDR0, ATS, 10, 1) + FIELD(IDR0, NS1ATS, 11, 1) FIELD(IDR0, ASID16, 12, 1) + FIELD(IDR0, MSI, 13, 1) + FIELD(IDR0, SEV, 14, 1) + FIELD(IDR0, ATOS, 15, 1) + FIELD(IDR0, PRI, 16, 1) + FIELD(IDR0, VMW, 17, 1) FIELD(IDR0, VMID16, 18, 1) + FIELD(IDR0, CD2L, 19, 1) + FIELD(IDR0, VATOS, 20, 1) FIELD(IDR0, TTENDIAN, 21, 2) + FIELD(IDR0, ATSRECERR, 23, 1) FIELD(IDR0, STALL_MODEL, 24, 2) FIELD(IDR0, TERM_MODEL, 26, 1) FIELD(IDR0, STLEVEL, 27, 2) + FIELD(IDR0, RME_IMPL, 30, 1) REG32(IDR1, 0x4) FIELD(IDR1, SIDSIZE, 0 , 6) + FIELD(IDR1, SSIDSIZE, 6 , 5) + FIELD(IDR1, PRIQS, 11, 5) FIELD(IDR1, EVENTQS, 16, 5) FIELD(IDR1, CMDQS, 21, 5) + FIELD(IDR1, ATTR_PERMS_OVR, 26, 1) + FIELD(IDR1, ATTR_TYPES_OVR, 27, 1) + FIELD(IDR1, REL, 28, 1) + FIELD(IDR1, QUEUES_PRESET, 29, 1) + FIELD(IDR1, TABLES_PRESET, 30, 1) + FIELD(IDR1, ECMDQ, 31, 1) #define SMMU_IDR1_SIDSIZE 16 #define SMMU_CMDQS 19 #define SMMU_EVENTQS 19 REG32(IDR2, 0x8) + FIELD(IDR2, BA_VATOS, 0, 10) + REG32(IDR3, 0xc) FIELD(IDR3, HAD, 2, 1); + FIELD(IDR3, PBHA, 3, 1); + FIELD(IDR3, XNX, 4, 1); + FIELD(IDR3, PPS, 5, 1); + FIELD(IDR3, MPAM, 7, 1); + FIELD(IDR3, FWB, 8, 1); + FIELD(IDR3, STT, 9, 1); FIELD(IDR3, RIL, 10, 1); FIELD(IDR3, BBML, 11, 2); + FIELD(IDR3, E0PD, 13, 1); + FIELD(IDR3, PTWNNC, 14, 1); + FIELD(IDR3, DPT, 15, 1); + REG32(IDR4, 0x10) + REG32(IDR5, 0x14) FIELD(IDR5, OAS, 0, 3); FIELD(IDR5, GRAN4K, 4, 1); FIELD(IDR5, GRAN16K, 5, 1); FIELD(IDR5, GRAN64K, 6, 1); + FIELD(IDR5, VAX, 10, 2); + FIELD(IDR5, STALL_MAX, 16, 16); #define SMMU_IDR5_OAS 4 diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index 6f2b2bd45f..c3871ae067 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -278,15 +278,19 @@ static void smmuv3_init_regs(SMMUv3State *s) s->idr[1] = FIELD_DP32(s->idr[1], IDR1, EVENTQS, SMMU_EVENTQS); s->idr[1] = FIELD_DP32(s->idr[1], IDR1, CMDQS, SMMU_CMDQS); - s->idr[3] = FIELD_DP32(s->idr[3], IDR3, RIL, 1); s->idr[3] = FIELD_DP32(s->idr[3], IDR3, HAD, 1); + if (FIELD_EX32(s->idr[0], IDR0, S2P)) { + /* XNX is a stage-2-specific feature */ + s->idr[3] = FIELD_DP32(s->idr[3], IDR3, XNX, 1); + } + s->idr[3] = FIELD_DP32(s->idr[3], IDR3, RIL, 1); s->idr[3] = FIELD_DP32(s->idr[3], IDR3, BBML, 2); + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, OAS, SMMU_IDR5_OAS); /* 44 bits */ /* 4K, 16K and 64K granule support */ s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN4K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN16K, 1); s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN64K, 1); - s->idr[5] = FIELD_DP32(s->idr[5], IDR5, OAS, SMMU_IDR5_OAS); /* 44 bits */ s->cmdq.base = deposit64(s->cmdq.base, 0, 5, SMMU_CMDQS); s->cmdq.prod = 0; diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 6b674231c2..9ce136cd88 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -601,21 +601,21 @@ build_gtdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) * The interrupt values are the same with the device tree when adding 16 */ /* Secure EL1 timer GSIV */ - build_append_int_noprefix(table_data, ARCH_TIMER_S_EL1_IRQ + 16, 4); + build_append_int_noprefix(table_data, ARCH_TIMER_S_EL1_IRQ, 4); /* Secure EL1 timer Flags */ build_append_int_noprefix(table_data, irqflags, 4); /* Non-Secure EL1 timer GSIV */ - build_append_int_noprefix(table_data, ARCH_TIMER_NS_EL1_IRQ + 16, 4); + build_append_int_noprefix(table_data, ARCH_TIMER_NS_EL1_IRQ, 4); /* Non-Secure EL1 timer Flags */ build_append_int_noprefix(table_data, irqflags | 1UL << 2, /* Always-on Capability */ 4); /* Virtual timer GSIV */ - build_append_int_noprefix(table_data, ARCH_TIMER_VIRT_IRQ + 16, 4); + build_append_int_noprefix(table_data, ARCH_TIMER_VIRT_IRQ, 4); /* Virtual Timer Flags */ build_append_int_noprefix(table_data, irqflags, 4); /* Non-Secure EL2 timer GSIV */ - build_append_int_noprefix(table_data, ARCH_TIMER_NS_EL2_IRQ + 16, 4); + build_append_int_noprefix(table_data, ARCH_TIMER_NS_EL2_IRQ, 4); /* Non-Secure EL2 timer Flags */ build_append_int_noprefix(table_data, irqflags, 4); /* CntReadBase Physical address */ @@ -729,9 +729,9 @@ build_madt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) for (i = 0; i < MACHINE(vms)->smp.cpus; i++) { ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(i)); uint64_t physical_base_address = 0, gich = 0, gicv = 0; - uint32_t vgic_interrupt = vms->virt ? PPI(ARCH_GIC_MAINT_IRQ) : 0; + uint32_t vgic_interrupt = vms->virt ? ARCH_GIC_MAINT_IRQ : 0; uint32_t pmu_interrupt = arm_feature(&armcpu->env, ARM_FEATURE_PMU) ? - PPI(VIRTUAL_PMU_IRQ) : 0; + VIRTUAL_PMU_IRQ : 0; if (vms->gic_version == VIRT_GIC_VERSION_2) { physical_base_address = memmap[VIRT_GIC_CPU].base; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 15e74249f9..529f1c089c 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -366,10 +366,14 @@ static void fdt_add_timer_nodes(const VirtMachineState *vms) } qemu_fdt_setprop(ms->fdt, "/timer", "always-on", NULL, 0); qemu_fdt_setprop_cells(ms->fdt, "/timer", "interrupts", - GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_S_EL1_IRQ, irqflags, - GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_NS_EL1_IRQ, irqflags, - GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_VIRT_IRQ, irqflags, - GIC_FDT_IRQ_TYPE_PPI, ARCH_TIMER_NS_EL2_IRQ, irqflags); + GIC_FDT_IRQ_TYPE_PPI, + INTID_TO_PPI(ARCH_TIMER_S_EL1_IRQ), irqflags, + GIC_FDT_IRQ_TYPE_PPI, + INTID_TO_PPI(ARCH_TIMER_NS_EL1_IRQ), irqflags, + GIC_FDT_IRQ_TYPE_PPI, + INTID_TO_PPI(ARCH_TIMER_VIRT_IRQ), irqflags, + GIC_FDT_IRQ_TYPE_PPI, + INTID_TO_PPI(ARCH_TIMER_NS_EL2_IRQ), irqflags); } static void fdt_add_cpu_nodes(const VirtMachineState *vms) @@ -647,13 +651,12 @@ static inline DeviceState *create_acpi_ged(VirtMachineState *vms) dev = qdev_new(TYPE_ACPI_GED); qdev_prop_set_uint32(dev, "ged-event", event); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_ACPI_GED].base); sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, vms->memmap[VIRT_PCDIMM_ACPI].base); sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, qdev_get_gpio_in(vms->gic, irq)); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - return dev; } @@ -691,10 +694,10 @@ static void create_v2m(VirtMachineState *vms) DeviceState *dev; dev = qdev_new("arm-gicv2m"); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_V2M].base); qdev_prop_set_uint32(dev, "base-spi", irq); qdev_prop_set_uint32(dev, "num-spi", NUM_GICV2M_SPIS); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_V2M].base); for (i = 0; i < NUM_GICV2M_SPIS; i++) { sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, @@ -800,7 +803,7 @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) */ for (i = 0; i < smp_cpus; i++) { DeviceState *cpudev = DEVICE(qemu_get_cpu(i)); - int ppibase = NUM_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; + int intidbase = NUM_IRQS + i * GIC_INTERNAL; /* Mapping from the output timer irq lines from the CPU to the * GIC PPI inputs we use for the virt board. */ @@ -814,22 +817,22 @@ static void create_gic(VirtMachineState *vms, MemoryRegion *mem) for (unsigned irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { qdev_connect_gpio_out(cpudev, irq, qdev_get_gpio_in(vms->gic, - ppibase + timer_irq[irq])); + intidbase + timer_irq[irq])); } if (vms->gic_version != VIRT_GIC_VERSION_2) { qemu_irq irq = qdev_get_gpio_in(vms->gic, - ppibase + ARCH_GIC_MAINT_IRQ); + intidbase + ARCH_GIC_MAINT_IRQ); qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", 0, irq); } else if (vms->virt) { qemu_irq irq = qdev_get_gpio_in(vms->gic, - ppibase + ARCH_GIC_MAINT_IRQ); + intidbase + ARCH_GIC_MAINT_IRQ); sysbus_connect_irq(gicbusdev, i + 4 * smp_cpus, irq); } qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, - qdev_get_gpio_in(vms->gic, ppibase + qdev_get_gpio_in(vms->gic, intidbase + VIRTUAL_PMU_IRQ)); sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); @@ -1989,7 +1992,7 @@ static void virt_cpu_post_init(VirtMachineState *vms, MemoryRegion *sysmem) if (pmu) { assert(arm_feature(&ARM_CPU(cpu)->env, ARM_FEATURE_PMU)); if (kvm_irqchip_in_kernel()) { - kvm_arm_pmu_set_irq(cpu, PPI(VIRTUAL_PMU_IRQ)); + kvm_arm_pmu_set_irq(cpu, VIRTUAL_PMU_IRQ); } kvm_arm_pmu_init(cpu); } diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index eecf3f7a81..4b37e26120 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -405,7 +405,7 @@ static void vhost_user_blk_event(void *opaque, QEMUChrEvent event) static int vhost_user_blk_realize_connect(VHostUserBlk *s, Error **errp) { - DeviceState *dev = &s->parent_obj.parent_obj; + DeviceState *dev = DEVICE(s); int ret; s->connected = false; @@ -423,7 +423,7 @@ static int vhost_user_blk_realize_connect(VHostUserBlk *s, Error **errp) assert(s->connected); ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg, - s->parent_obj.config_len, errp); + VIRTIO_DEVICE(s)->config_len, errp); if (ret < 0) { qemu_chr_fe_disconnect(&s->chardev); vhost_dev_cleanup(&s->dev); diff --git a/hw/char/escc.c b/hw/char/escc.c index 4be66053c1..48b30ee760 100644 --- a/hw/char/escc.c +++ b/hw/char/escc.c @@ -845,7 +845,7 @@ static void sunkbd_handle_event(DeviceState *dev, QemuConsole *src, put_queue(s, keycode); } -static QemuInputHandler sunkbd_handler = { +static const QemuInputHandler sunkbd_handler = { .name = "sun keyboard", .mask = INPUT_EVENT_MASK_KEY, .event = sunkbd_handle_event, diff --git a/hw/core/cpu-sysemu.c b/hw/core/cpu-sysemu.c index 5eaf2e79e6..d0d6a910f9 100644 --- a/hw/core/cpu-sysemu.c +++ b/hw/core/cpu-sysemu.c @@ -34,17 +34,17 @@ bool cpu_paging_enabled(const CPUState *cpu) return false; } -void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, +bool cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, Error **errp) { CPUClass *cc = CPU_GET_CLASS(cpu); if (cc->sysemu_ops->get_memory_mapping) { - cc->sysemu_ops->get_memory_mapping(cpu, list, errp); - return; + return cc->sysemu_ops->get_memory_mapping(cpu, list, errp); } error_setg(errp, "Obtaining memory mappings is unsupported on this CPU."); + return false; } hwaddr cpu_get_phys_page_attrs_debug(CPUState *cpu, vaddr addr, diff --git a/hw/core/machine.c b/hw/core/machine.c index cfd1edfe20..05aef2cf9f 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -34,6 +34,8 @@ GlobalProperty hw_compat_8_1[] = { { TYPE_PCI_BRIDGE, "x-pci-express-writeable-slt-bug", "true" }, + { "ramfb", "x-migrate", "off" }, + { "vfio-pci-nohotplug", "x-ramfb-migrate", "off" } }; const size_t hw_compat_8_1_len = G_N_ELEMENTS(hw_compat_8_1); diff --git a/hw/display/meson.build b/hw/display/meson.build index 05619c6968..2b64fd9f9d 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -80,6 +80,13 @@ if config_all_devices.has_key('CONFIG_VIRTIO_GPU') if_true: [files('virtio-gpu-gl.c', 'virtio-gpu-virgl.c'), pixman, virgl]) hw_display_modules += {'virtio-gpu-gl': virtio_gpu_gl_ss} endif + + if rutabaga.found() + virtio_gpu_rutabaga_ss = ss.source_set() + virtio_gpu_rutabaga_ss.add(when: ['CONFIG_VIRTIO_GPU', rutabaga], + if_true: [files('virtio-gpu-rutabaga.c'), pixman]) + hw_display_modules += {'virtio-gpu-rutabaga': virtio_gpu_rutabaga_ss} + endif endif if config_all_devices.has_key('CONFIG_VIRTIO_PCI') @@ -96,6 +103,12 @@ if config_all_devices.has_key('CONFIG_VIRTIO_PCI') if_true: [files('virtio-gpu-pci-gl.c'), pixman]) hw_display_modules += {'virtio-gpu-pci-gl': virtio_gpu_pci_gl_ss} endif + if rutabaga.found() + virtio_gpu_pci_rutabaga_ss = ss.source_set() + virtio_gpu_pci_rutabaga_ss.add(when: ['CONFIG_VIRTIO_GPU', 'CONFIG_VIRTIO_PCI', rutabaga], + if_true: [files('virtio-gpu-pci-rutabaga.c'), pixman]) + hw_display_modules += {'virtio-gpu-pci-rutabaga': virtio_gpu_pci_rutabaga_ss} + endif endif if config_all_devices.has_key('CONFIG_VIRTIO_VGA') @@ -114,6 +127,15 @@ if config_all_devices.has_key('CONFIG_VIRTIO_VGA') virtio_vga_gl_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-vga.c'), if_false: files('acpi-vga-stub.c')) hw_display_modules += {'virtio-vga-gl': virtio_vga_gl_ss} + + if rutabaga.found() + virtio_vga_rutabaga_ss = ss.source_set() + virtio_vga_rutabaga_ss.add(when: ['CONFIG_VIRTIO_VGA', rutabaga], + if_true: [files('virtio-vga-rutabaga.c'), pixman]) + virtio_vga_rutabaga_ss.add(when: 'CONFIG_ACPI', if_true: files('acpi-vga.c'), + if_false: files('acpi-vga-stub.c')) + hw_display_modules += {'virtio-vga-rutabaga': virtio_vga_rutabaga_ss} + endif endif system_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_lcdc.c')) diff --git a/hw/display/ramfb-standalone.c b/hw/display/ramfb-standalone.c index 8c0094397f..a96e7ebcd9 100644 --- a/hw/display/ramfb-standalone.c +++ b/hw/display/ramfb-standalone.c @@ -1,4 +1,5 @@ #include "qemu/osdep.h" +#include "migration/vmstate.h" #include "qapi/error.h" #include "qemu/module.h" #include "hw/loader.h" @@ -15,6 +16,7 @@ struct RAMFBStandaloneState { SysBusDevice parent_obj; QemuConsole *con; RAMFBState *state; + bool migrate; }; static void display_update_wrapper(void *dev) @@ -40,14 +42,39 @@ static void ramfb_realizefn(DeviceState *dev, Error **errp) ramfb->state = ramfb_setup(errp); } +static bool migrate_needed(void *opaque) +{ + RAMFBStandaloneState *ramfb = RAMFB(opaque); + + return ramfb->migrate; +} + +static const VMStateDescription ramfb_dev_vmstate = { + .name = "ramfb-dev", + .version_id = 1, + .minimum_version_id = 1, + .needed = migrate_needed, + .fields = (VMStateField[]) { + VMSTATE_STRUCT_POINTER(state, RAMFBStandaloneState, ramfb_vmstate, RAMFBState), + VMSTATE_END_OF_LIST() + } +}; + +static Property ramfb_properties[] = { + DEFINE_PROP_BOOL("x-migrate", RAMFBStandaloneState, migrate, true), + DEFINE_PROP_END_OF_LIST(), +}; + static void ramfb_class_initfn(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); + dc->vmsd = &ramfb_dev_vmstate; dc->realize = ramfb_realizefn; dc->desc = "ram framebuffer standalone device"; dc->user_creatable = true; + device_class_set_props(dc, ramfb_properties); } static const TypeInfo ramfb_info = { diff --git a/hw/display/ramfb.c b/hw/display/ramfb.c index c2b002d534..477ef7272a 100644 --- a/hw/display/ramfb.c +++ b/hw/display/ramfb.c @@ -28,6 +28,8 @@ struct QEMU_PACKED RAMFBCfg { uint32_t stride; }; +typedef struct RAMFBCfg RAMFBCfg; + struct RAMFBState { DisplaySurface *ds; uint32_t width, height; @@ -116,6 +118,23 @@ void ramfb_display_update(QemuConsole *con, RAMFBState *s) dpy_gfx_update_full(con); } +static int ramfb_post_load(void *opaque, int version_id) +{ + ramfb_fw_cfg_write(opaque, 0, 0); + return 0; +} + +const VMStateDescription ramfb_vmstate = { + .name = "ramfb", + .version_id = 1, + .minimum_version_id = 1, + .post_load = ramfb_post_load, + .fields = (VMStateField[]) { + VMSTATE_BUFFER_UNSAFE(cfg, RAMFBState, 0, sizeof(RAMFBCfg)), + VMSTATE_END_OF_LIST() + } +}; + RAMFBState *ramfb_setup(Error **errp) { FWCfgState *fw_cfg = fw_cfg_find(); diff --git a/hw/display/virtio-gpu-base.c b/hw/display/virtio-gpu-base.c index ca1fb7b16f..50c5373b65 100644 --- a/hw/display/virtio-gpu-base.c +++ b/hw/display/virtio-gpu-base.c @@ -223,7 +223,8 @@ virtio_gpu_base_get_features(VirtIODevice *vdev, uint64_t features, { VirtIOGPUBase *g = VIRTIO_GPU_BASE(vdev); - if (virtio_gpu_virgl_enabled(g->conf)) { + if (virtio_gpu_virgl_enabled(g->conf) || + virtio_gpu_rutabaga_enabled(g->conf)) { features |= (1 << VIRTIO_GPU_F_VIRGL); } if (virtio_gpu_edid_enabled(g->conf)) { @@ -232,6 +233,9 @@ virtio_gpu_base_get_features(VirtIODevice *vdev, uint64_t features, if (virtio_gpu_blob_enabled(g->conf)) { features |= (1 << VIRTIO_GPU_F_RESOURCE_BLOB); } + if (virtio_gpu_context_init_enabled(g->conf)) { + features |= (1 << VIRTIO_GPU_F_CONTEXT_INIT); + } return features; } diff --git a/hw/display/virtio-gpu-pci-rutabaga.c b/hw/display/virtio-gpu-pci-rutabaga.c new file mode 100644 index 0000000000..c96729e198 --- /dev/null +++ b/hw/display/virtio-gpu-pci-rutabaga.c @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/module.h" +#include "hw/pci/pci.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-gpu-pci.h" +#include "qom/object.h" + +#define TYPE_VIRTIO_GPU_RUTABAGA_PCI "virtio-gpu-rutabaga-pci" +OBJECT_DECLARE_SIMPLE_TYPE(VirtIOGPURutabagaPCI, VIRTIO_GPU_RUTABAGA_PCI) + +struct VirtIOGPURutabagaPCI { + VirtIOGPUPCIBase parent_obj; + + VirtIOGPURutabaga vdev; +}; + +static void virtio_gpu_rutabaga_initfn(Object *obj) +{ + VirtIOGPURutabagaPCI *dev = VIRTIO_GPU_RUTABAGA_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_GPU_RUTABAGA); + VIRTIO_GPU_PCI_BASE(obj)->vgpu = VIRTIO_GPU_BASE(&dev->vdev); +} + +static const TypeInfo virtio_gpu_rutabaga_pci_info[] = { + { + .name = TYPE_VIRTIO_GPU_RUTABAGA_PCI, + .parent = TYPE_VIRTIO_GPU_PCI_BASE, + .instance_size = sizeof(VirtIOGPURutabagaPCI), + .instance_init = virtio_gpu_rutabaga_initfn, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + } + }, +}; + +DEFINE_TYPES(virtio_gpu_rutabaga_pci_info) + +module_obj(TYPE_VIRTIO_GPU_RUTABAGA_PCI); +module_kconfig(VIRTIO_PCI); +module_dep("hw-display-virtio-gpu-pci"); diff --git a/hw/display/virtio-gpu-pci.c b/hw/display/virtio-gpu-pci.c index 93f214ff58..da6a99f038 100644 --- a/hw/display/virtio-gpu-pci.c +++ b/hw/display/virtio-gpu-pci.c @@ -33,6 +33,20 @@ static void virtio_gpu_pci_base_realize(VirtIOPCIProxy *vpci_dev, Error **errp) DeviceState *vdev = DEVICE(g); int i; + if (virtio_gpu_hostmem_enabled(g->conf)) { + vpci_dev->msix_bar_idx = 1; + vpci_dev->modern_mem_bar_idx = 2; + memory_region_init(&g->hostmem, OBJECT(g), "virtio-gpu-hostmem", + g->conf.hostmem); + pci_register_bar(&vpci_dev->pci_dev, 4, + PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_PREFETCH | + PCI_BASE_ADDRESS_MEM_TYPE_64, + &g->hostmem); + virtio_pci_add_shm_cap(vpci_dev, 4, 0, g->conf.hostmem, + VIRTIO_GPU_SHM_ID_HOST_VISIBLE); + } + virtio_pci_force_virtio_1(vpci_dev); if (!qdev_realize(vdev, BUS(&vpci_dev->bus), errp)) { return; diff --git a/hw/display/virtio-gpu-rutabaga.c b/hw/display/virtio-gpu-rutabaga.c new file mode 100644 index 0000000000..9e67f9bd51 --- /dev/null +++ b/hw/display/virtio-gpu-rutabaga.c @@ -0,0 +1,1120 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/iov.h" +#include "trace.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/virtio/virtio-gpu-pixman.h" +#include "hw/virtio/virtio-iommu.h" + +#include <glib/gmem.h> +#include <rutabaga_gfx/rutabaga_gfx_ffi.h> + +#define CHECK(condition, cmd) \ + do { \ + if (!(condition)) { \ + error_report("CHECK failed in %s() %s:" "%d", __func__, \ + __FILE__, __LINE__); \ + (cmd)->error = VIRTIO_GPU_RESP_ERR_UNSPEC; \ + return; \ + } \ + } while (0) + +struct rutabaga_aio_data { + struct VirtIOGPURutabaga *vr; + struct rutabaga_fence fence; +}; + +static void +virtio_gpu_rutabaga_update_cursor(VirtIOGPU *g, struct virtio_gpu_scanout *s, + uint32_t resource_id) +{ + struct virtio_gpu_simple_resource *res; + struct rutabaga_transfer transfer = { 0 }; + struct iovec transfer_iovec; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + res = virtio_gpu_find_resource(g, resource_id); + if (!res) { + return; + } + + if (res->width != s->current_cursor->width || + res->height != s->current_cursor->height) { + return; + } + + transfer.x = 0; + transfer.y = 0; + transfer.z = 0; + transfer.w = res->width; + transfer.h = res->height; + transfer.d = 1; + + transfer_iovec.iov_base = s->current_cursor->data; + transfer_iovec.iov_len = res->width * res->height * 4; + + rutabaga_resource_transfer_read(vr->rutabaga, 0, + resource_id, &transfer, + &transfer_iovec); +} + +static void +virtio_gpu_rutabaga_gl_flushed(VirtIOGPUBase *b) +{ + VirtIOGPU *g = VIRTIO_GPU(b); + virtio_gpu_process_cmdq(g); +} + +static void +rutabaga_cmd_create_resource_2d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct rutabaga_create_3d rc_3d = { 0 }; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_create_2d c2d; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(c2d); + trace_virtio_gpu_cmd_res_create_2d(c2d.resource_id, c2d.format, + c2d.width, c2d.height); + + rc_3d.target = 2; + rc_3d.format = c2d.format; + rc_3d.bind = (1 << 1); + rc_3d.width = c2d.width; + rc_3d.height = c2d.height; + rc_3d.depth = 1; + rc_3d.array_size = 1; + rc_3d.last_level = 0; + rc_3d.nr_samples = 0; + rc_3d.flags = VIRTIO_GPU_RESOURCE_FLAG_Y_0_TOP; + + result = rutabaga_resource_create_3d(vr->rutabaga, c2d.resource_id, &rc_3d); + CHECK(!result, cmd); + + res = g_new0(struct virtio_gpu_simple_resource, 1); + res->width = c2d.width; + res->height = c2d.height; + res->format = c2d.format; + res->resource_id = c2d.resource_id; + + QTAILQ_INSERT_HEAD(&g->reslist, res, next); +} + +static void +rutabaga_cmd_create_resource_3d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct rutabaga_create_3d rc_3d = { 0 }; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_create_3d c3d; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(c3d); + + trace_virtio_gpu_cmd_res_create_3d(c3d.resource_id, c3d.format, + c3d.width, c3d.height, c3d.depth); + + rc_3d.target = c3d.target; + rc_3d.format = c3d.format; + rc_3d.bind = c3d.bind; + rc_3d.width = c3d.width; + rc_3d.height = c3d.height; + rc_3d.depth = c3d.depth; + rc_3d.array_size = c3d.array_size; + rc_3d.last_level = c3d.last_level; + rc_3d.nr_samples = c3d.nr_samples; + rc_3d.flags = c3d.flags; + + result = rutabaga_resource_create_3d(vr->rutabaga, c3d.resource_id, &rc_3d); + CHECK(!result, cmd); + + res = g_new0(struct virtio_gpu_simple_resource, 1); + res->width = c3d.width; + res->height = c3d.height; + res->format = c3d.format; + res->resource_id = c3d.resource_id; + + QTAILQ_INSERT_HEAD(&g->reslist, res, next); +} + +static void +rutabaga_cmd_resource_unref(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_unref unref; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(unref); + + trace_virtio_gpu_cmd_res_unref(unref.resource_id); + + res = virtio_gpu_find_resource(g, unref.resource_id); + CHECK(res, cmd); + + result = rutabaga_resource_unref(vr->rutabaga, unref.resource_id); + CHECK(!result, cmd); + + if (res->image) { + pixman_image_unref(res->image); + } + + QTAILQ_REMOVE(&g->reslist, res, next); + g_free(res); +} + +static void +rutabaga_cmd_context_create(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_ctx_create cc; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(cc); + trace_virtio_gpu_cmd_ctx_create(cc.hdr.ctx_id, + cc.debug_name); + + result = rutabaga_context_create(vr->rutabaga, cc.hdr.ctx_id, + cc.context_init, cc.debug_name, cc.nlen); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_context_destroy(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_ctx_destroy cd; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(cd); + trace_virtio_gpu_cmd_ctx_destroy(cd.hdr.ctx_id); + + result = rutabaga_context_destroy(vr->rutabaga, cd.hdr.ctx_id); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_resource_flush(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result, i; + struct virtio_gpu_scanout *scanout = NULL; + struct virtio_gpu_simple_resource *res; + struct rutabaga_transfer transfer = { 0 }; + struct iovec transfer_iovec; + struct virtio_gpu_resource_flush rf; + bool found = false; + + VirtIOGPUBase *vb = VIRTIO_GPU_BASE(g); + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + if (vr->headless) { + return; + } + + VIRTIO_GPU_FILL_CMD(rf); + trace_virtio_gpu_cmd_res_flush(rf.resource_id, + rf.r.width, rf.r.height, rf.r.x, rf.r.y); + + res = virtio_gpu_find_resource(g, rf.resource_id); + CHECK(res, cmd); + + for (i = 0; i < vb->conf.max_outputs; i++) { + scanout = &vb->scanout[i]; + if (i == res->scanout_bitmask) { + found = true; + break; + } + } + + if (!found) { + return; + } + + transfer.x = 0; + transfer.y = 0; + transfer.z = 0; + transfer.w = res->width; + transfer.h = res->height; + transfer.d = 1; + + transfer_iovec.iov_base = pixman_image_get_data(res->image); + transfer_iovec.iov_len = res->width * res->height * 4; + + result = rutabaga_resource_transfer_read(vr->rutabaga, 0, + rf.resource_id, &transfer, + &transfer_iovec); + CHECK(!result, cmd); + dpy_gfx_update_full(scanout->con); +} + +static void +rutabaga_cmd_set_scanout(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_scanout *scanout = NULL; + struct virtio_gpu_set_scanout ss; + + VirtIOGPUBase *vb = VIRTIO_GPU_BASE(g); + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + if (vr->headless) { + return; + } + + VIRTIO_GPU_FILL_CMD(ss); + trace_virtio_gpu_cmd_set_scanout(ss.scanout_id, ss.resource_id, + ss.r.width, ss.r.height, ss.r.x, ss.r.y); + + CHECK(ss.scanout_id < VIRTIO_GPU_MAX_SCANOUTS, cmd); + scanout = &vb->scanout[ss.scanout_id]; + + if (ss.resource_id == 0) { + dpy_gfx_replace_surface(scanout->con, NULL); + dpy_gl_scanout_disable(scanout->con); + return; + } + + res = virtio_gpu_find_resource(g, ss.resource_id); + CHECK(res, cmd); + + if (!res->image) { + pixman_format_code_t pformat; + pformat = virtio_gpu_get_pixman_format(res->format); + CHECK(pformat, cmd); + + res->image = pixman_image_create_bits(pformat, + res->width, + res->height, + NULL, 0); + CHECK(res->image, cmd); + pixman_image_ref(res->image); + } + + vb->enable = 1; + + /* realloc the surface ptr */ + scanout->ds = qemu_create_displaysurface_pixman(res->image); + dpy_gfx_replace_surface(scanout->con, NULL); + dpy_gfx_replace_surface(scanout->con, scanout->ds); + res->scanout_bitmask = ss.scanout_id; +} + +static void +rutabaga_cmd_submit_3d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_cmd_submit cs; + struct rutabaga_command rutabaga_cmd = { 0 }; + g_autofree uint8_t *buf = NULL; + size_t s; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(cs); + trace_virtio_gpu_cmd_ctx_submit(cs.hdr.ctx_id, cs.size); + + buf = g_new0(uint8_t, cs.size); + s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, + sizeof(cs), buf, cs.size); + CHECK(s == cs.size, cmd); + + rutabaga_cmd.ctx_id = cs.hdr.ctx_id; + rutabaga_cmd.cmd = buf; + rutabaga_cmd.cmd_size = cs.size; + + result = rutabaga_submit_command(vr->rutabaga, &rutabaga_cmd); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_transfer_to_host_2d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct rutabaga_transfer transfer = { 0 }; + struct virtio_gpu_transfer_to_host_2d t2d; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(t2d); + trace_virtio_gpu_cmd_res_xfer_toh_2d(t2d.resource_id); + + transfer.x = t2d.r.x; + transfer.y = t2d.r.y; + transfer.z = 0; + transfer.w = t2d.r.width; + transfer.h = t2d.r.height; + transfer.d = 1; + + result = rutabaga_resource_transfer_write(vr->rutabaga, 0, t2d.resource_id, + &transfer); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_transfer_to_host_3d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct rutabaga_transfer transfer = { 0 }; + struct virtio_gpu_transfer_host_3d t3d; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(t3d); + trace_virtio_gpu_cmd_res_xfer_toh_3d(t3d.resource_id); + + transfer.x = t3d.box.x; + transfer.y = t3d.box.y; + transfer.z = t3d.box.z; + transfer.w = t3d.box.w; + transfer.h = t3d.box.h; + transfer.d = t3d.box.d; + transfer.level = t3d.level; + transfer.stride = t3d.stride; + transfer.layer_stride = t3d.layer_stride; + transfer.offset = t3d.offset; + + result = rutabaga_resource_transfer_write(vr->rutabaga, t3d.hdr.ctx_id, + t3d.resource_id, &transfer); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_transfer_from_host_3d(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct rutabaga_transfer transfer = { 0 }; + struct virtio_gpu_transfer_host_3d t3d; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(t3d); + trace_virtio_gpu_cmd_res_xfer_fromh_3d(t3d.resource_id); + + transfer.x = t3d.box.x; + transfer.y = t3d.box.y; + transfer.z = t3d.box.z; + transfer.w = t3d.box.w; + transfer.h = t3d.box.h; + transfer.d = t3d.box.d; + transfer.level = t3d.level; + transfer.stride = t3d.stride; + transfer.layer_stride = t3d.layer_stride; + transfer.offset = t3d.offset; + + result = rutabaga_resource_transfer_read(vr->rutabaga, t3d.hdr.ctx_id, + t3d.resource_id, &transfer, NULL); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_attach_backing(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + struct rutabaga_iovecs vecs = { 0 }; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_attach_backing att_rb; + int ret; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(att_rb); + trace_virtio_gpu_cmd_res_back_attach(att_rb.resource_id); + + res = virtio_gpu_find_resource(g, att_rb.resource_id); + CHECK(res, cmd); + CHECK(!res->iov, cmd); + + ret = virtio_gpu_create_mapping_iov(g, att_rb.nr_entries, sizeof(att_rb), + cmd, NULL, &res->iov, &res->iov_cnt); + CHECK(!ret, cmd); + + vecs.iovecs = res->iov; + vecs.num_iovecs = res->iov_cnt; + + ret = rutabaga_resource_attach_backing(vr->rutabaga, att_rb.resource_id, + &vecs); + if (ret != 0) { + virtio_gpu_cleanup_mapping(g, res); + } + + CHECK(!ret, cmd); +} + +static void +rutabaga_cmd_detach_backing(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_detach_backing detach_rb; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(detach_rb); + trace_virtio_gpu_cmd_res_back_detach(detach_rb.resource_id); + + res = virtio_gpu_find_resource(g, detach_rb.resource_id); + CHECK(res, cmd); + + rutabaga_resource_detach_backing(vr->rutabaga, + detach_rb.resource_id); + + virtio_gpu_cleanup_mapping(g, res); +} + +static void +rutabaga_cmd_ctx_attach_resource(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_ctx_resource att_res; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(att_res); + trace_virtio_gpu_cmd_ctx_res_attach(att_res.hdr.ctx_id, + att_res.resource_id); + + result = rutabaga_context_attach_resource(vr->rutabaga, att_res.hdr.ctx_id, + att_res.resource_id); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_ctx_detach_resource(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_ctx_resource det_res; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(det_res); + trace_virtio_gpu_cmd_ctx_res_detach(det_res.hdr.ctx_id, + det_res.resource_id); + + result = rutabaga_context_detach_resource(vr->rutabaga, det_res.hdr.ctx_id, + det_res.resource_id); + CHECK(!result, cmd); +} + +static void +rutabaga_cmd_get_capset_info(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_get_capset_info info; + struct virtio_gpu_resp_capset_info resp; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(info); + + result = rutabaga_get_capset_info(vr->rutabaga, info.capset_index, + &resp.capset_id, &resp.capset_max_version, + &resp.capset_max_size); + CHECK(!result, cmd); + + resp.hdr.type = VIRTIO_GPU_RESP_OK_CAPSET_INFO; + virtio_gpu_ctrl_response(g, cmd, &resp.hdr, sizeof(resp)); +} + +static void +rutabaga_cmd_get_capset(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + struct virtio_gpu_get_capset gc; + struct virtio_gpu_resp_capset *resp; + uint32_t capset_size, capset_version; + uint32_t current_id, i; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(gc); + for (i = 0; i < vr->num_capsets; i++) { + result = rutabaga_get_capset_info(vr->rutabaga, i, + ¤t_id, &capset_version, + &capset_size); + CHECK(!result, cmd); + + if (current_id == gc.capset_id) { + break; + } + } + + CHECK(i < vr->num_capsets, cmd); + + resp = g_malloc0(sizeof(*resp) + capset_size); + resp->hdr.type = VIRTIO_GPU_RESP_OK_CAPSET; + rutabaga_get_capset(vr->rutabaga, gc.capset_id, gc.capset_version, + resp->capset_data, capset_size); + + virtio_gpu_ctrl_response(g, cmd, &resp->hdr, sizeof(*resp) + capset_size); + g_free(resp); +} + +static void +rutabaga_cmd_resource_create_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int result; + struct rutabaga_iovecs vecs = { 0 }; + g_autofree struct virtio_gpu_simple_resource *res = NULL; + struct virtio_gpu_resource_create_blob cblob; + struct rutabaga_create_blob rc_blob = { 0 }; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(cblob); + trace_virtio_gpu_cmd_res_create_blob(cblob.resource_id, cblob.size); + + CHECK(cblob.resource_id != 0, cmd); + + res = g_new0(struct virtio_gpu_simple_resource, 1); + + res->resource_id = cblob.resource_id; + res->blob_size = cblob.size; + + if (cblob.blob_mem != VIRTIO_GPU_BLOB_MEM_HOST3D) { + result = virtio_gpu_create_mapping_iov(g, cblob.nr_entries, + sizeof(cblob), cmd, &res->addrs, + &res->iov, &res->iov_cnt); + CHECK(!result, cmd); + } + + rc_blob.blob_id = cblob.blob_id; + rc_blob.blob_mem = cblob.blob_mem; + rc_blob.blob_flags = cblob.blob_flags; + rc_blob.size = cblob.size; + + vecs.iovecs = res->iov; + vecs.num_iovecs = res->iov_cnt; + + result = rutabaga_resource_create_blob(vr->rutabaga, cblob.hdr.ctx_id, + cblob.resource_id, &rc_blob, &vecs, + NULL); + + if (result && cblob.blob_mem != VIRTIO_GPU_BLOB_MEM_HOST3D) { + virtio_gpu_cleanup_mapping(g, res); + } + + CHECK(!result, cmd); + + QTAILQ_INSERT_HEAD(&g->reslist, res, next); + res = NULL; +} + +static void +rutabaga_cmd_resource_map_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + uint32_t map_info = 0; + uint32_t slot = 0; + struct virtio_gpu_simple_resource *res; + struct rutabaga_mapping mapping = { 0 }; + struct virtio_gpu_resource_map_blob mblob; + struct virtio_gpu_resp_map_info resp = { 0 }; + + VirtIOGPUBase *vb = VIRTIO_GPU_BASE(g); + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(mblob); + + CHECK(mblob.resource_id != 0, cmd); + + res = virtio_gpu_find_resource(g, mblob.resource_id); + CHECK(res, cmd); + + result = rutabaga_resource_map_info(vr->rutabaga, mblob.resource_id, + &map_info); + CHECK(!result, cmd); + + /* + * RUTABAGA_MAP_ACCESS_* flags are not part of the virtio-gpu spec, but do + * exist to potentially allow the hypervisor to restrict write access to + * memory. QEMU does not need to use this functionality at the moment. + */ + resp.map_info = map_info & RUTABAGA_MAP_CACHE_MASK; + + result = rutabaga_resource_map(vr->rutabaga, mblob.resource_id, &mapping); + CHECK(!result, cmd); + + /* + * There is small risk of the MemoryRegion dereferencing the pointer after + * rutabaga unmaps it. Please see discussion here: + * + * https://lists.gnu.org/archive/html/qemu-devel/2023-09/msg05141.html + * + * It is highly unlikely to happen in practice and doesn't affect known + * use cases. However, it should be fixed and is noted here for posterity. + */ + for (slot = 0; slot < MAX_SLOTS; slot++) { + if (vr->memory_regions[slot].used) { + continue; + } + + MemoryRegion *mr = &(vr->memory_regions[slot].mr); + memory_region_init_ram_ptr(mr, OBJECT(vr), "blob", mapping.size, + mapping.ptr); + memory_region_add_subregion(&vb->hostmem, mblob.offset, mr); + vr->memory_regions[slot].resource_id = mblob.resource_id; + vr->memory_regions[slot].used = 1; + break; + } + + if (slot >= MAX_SLOTS) { + result = rutabaga_resource_unmap(vr->rutabaga, mblob.resource_id); + CHECK(!result, cmd); + } + + CHECK(slot < MAX_SLOTS, cmd); + + resp.hdr.type = VIRTIO_GPU_RESP_OK_MAP_INFO; + virtio_gpu_ctrl_response(g, cmd, &resp.hdr, sizeof(resp)); +} + +static void +rutabaga_cmd_resource_unmap_blob(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + int32_t result; + uint32_t slot = 0; + struct virtio_gpu_simple_resource *res; + struct virtio_gpu_resource_unmap_blob ublob; + + VirtIOGPUBase *vb = VIRTIO_GPU_BASE(g); + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(ublob); + + CHECK(ublob.resource_id != 0, cmd); + + res = virtio_gpu_find_resource(g, ublob.resource_id); + CHECK(res, cmd); + + for (slot = 0; slot < MAX_SLOTS; slot++) { + if (vr->memory_regions[slot].resource_id != ublob.resource_id) { + continue; + } + + MemoryRegion *mr = &(vr->memory_regions[slot].mr); + memory_region_del_subregion(&vb->hostmem, mr); + + vr->memory_regions[slot].resource_id = 0; + vr->memory_regions[slot].used = 0; + break; + } + + CHECK(slot < MAX_SLOTS, cmd); + result = rutabaga_resource_unmap(vr->rutabaga, res->resource_id); + CHECK(!result, cmd); +} + +static void +virtio_gpu_rutabaga_process_cmd(VirtIOGPU *g, + struct virtio_gpu_ctrl_command *cmd) +{ + struct rutabaga_fence fence = { 0 }; + int32_t result; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + VIRTIO_GPU_FILL_CMD(cmd->cmd_hdr); + + switch (cmd->cmd_hdr.type) { + case VIRTIO_GPU_CMD_CTX_CREATE: + rutabaga_cmd_context_create(g, cmd); + break; + case VIRTIO_GPU_CMD_CTX_DESTROY: + rutabaga_cmd_context_destroy(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_CREATE_2D: + rutabaga_cmd_create_resource_2d(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_CREATE_3D: + rutabaga_cmd_create_resource_3d(g, cmd); + break; + case VIRTIO_GPU_CMD_SUBMIT_3D: + rutabaga_cmd_submit_3d(g, cmd); + break; + case VIRTIO_GPU_CMD_TRANSFER_TO_HOST_2D: + rutabaga_cmd_transfer_to_host_2d(g, cmd); + break; + case VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D: + rutabaga_cmd_transfer_to_host_3d(g, cmd); + break; + case VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D: + rutabaga_cmd_transfer_from_host_3d(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_ATTACH_BACKING: + rutabaga_cmd_attach_backing(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_DETACH_BACKING: + rutabaga_cmd_detach_backing(g, cmd); + break; + case VIRTIO_GPU_CMD_SET_SCANOUT: + rutabaga_cmd_set_scanout(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_FLUSH: + rutabaga_cmd_resource_flush(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_UNREF: + rutabaga_cmd_resource_unref(g, cmd); + break; + case VIRTIO_GPU_CMD_CTX_ATTACH_RESOURCE: + rutabaga_cmd_ctx_attach_resource(g, cmd); + break; + case VIRTIO_GPU_CMD_CTX_DETACH_RESOURCE: + rutabaga_cmd_ctx_detach_resource(g, cmd); + break; + case VIRTIO_GPU_CMD_GET_CAPSET_INFO: + rutabaga_cmd_get_capset_info(g, cmd); + break; + case VIRTIO_GPU_CMD_GET_CAPSET: + rutabaga_cmd_get_capset(g, cmd); + break; + case VIRTIO_GPU_CMD_GET_DISPLAY_INFO: + virtio_gpu_get_display_info(g, cmd); + break; + case VIRTIO_GPU_CMD_GET_EDID: + virtio_gpu_get_edid(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB: + rutabaga_cmd_resource_create_blob(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_MAP_BLOB: + rutabaga_cmd_resource_map_blob(g, cmd); + break; + case VIRTIO_GPU_CMD_RESOURCE_UNMAP_BLOB: + rutabaga_cmd_resource_unmap_blob(g, cmd); + break; + default: + cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC; + break; + } + + if (cmd->finished) { + return; + } + if (cmd->error) { + error_report("%s: ctrl 0x%x, error 0x%x", __func__, + cmd->cmd_hdr.type, cmd->error); + virtio_gpu_ctrl_response_nodata(g, cmd, cmd->error); + return; + } + if (!(cmd->cmd_hdr.flags & VIRTIO_GPU_FLAG_FENCE)) { + virtio_gpu_ctrl_response_nodata(g, cmd, VIRTIO_GPU_RESP_OK_NODATA); + return; + } + + fence.flags = cmd->cmd_hdr.flags; + fence.ctx_id = cmd->cmd_hdr.ctx_id; + fence.fence_id = cmd->cmd_hdr.fence_id; + fence.ring_idx = cmd->cmd_hdr.ring_idx; + + trace_virtio_gpu_fence_ctrl(cmd->cmd_hdr.fence_id, cmd->cmd_hdr.type); + + result = rutabaga_create_fence(vr->rutabaga, &fence); + CHECK(!result, cmd); +} + +static void +virtio_gpu_rutabaga_aio_cb(void *opaque) +{ + struct rutabaga_aio_data *data = opaque; + VirtIOGPU *g = VIRTIO_GPU(data->vr); + struct rutabaga_fence fence_data = data->fence; + struct virtio_gpu_ctrl_command *cmd, *tmp; + + uint32_t signaled_ctx_specific = fence_data.flags & + RUTABAGA_FLAG_INFO_RING_IDX; + + QTAILQ_FOREACH_SAFE(cmd, &g->fenceq, next, tmp) { + /* + * Due to context specific timelines. + */ + uint32_t target_ctx_specific = cmd->cmd_hdr.flags & + RUTABAGA_FLAG_INFO_RING_IDX; + + if (signaled_ctx_specific != target_ctx_specific) { + continue; + } + + if (signaled_ctx_specific && + (cmd->cmd_hdr.ring_idx != fence_data.ring_idx)) { + continue; + } + + if (cmd->cmd_hdr.fence_id > fence_data.fence_id) { + continue; + } + + trace_virtio_gpu_fence_resp(cmd->cmd_hdr.fence_id); + virtio_gpu_ctrl_response_nodata(g, cmd, VIRTIO_GPU_RESP_OK_NODATA); + QTAILQ_REMOVE(&g->fenceq, cmd, next); + g_free(cmd); + } + + g_free(data); +} + +static void +virtio_gpu_rutabaga_fence_cb(uint64_t user_data, + const struct rutabaga_fence *fence) +{ + struct rutabaga_aio_data *data; + VirtIOGPU *g = (VirtIOGPU *)user_data; + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + /* + * gfxstream and both cross-domain (and even newer versions virglrenderer: + * see VIRGL_RENDERER_ASYNC_FENCE_CB) like to signal fence completion on + * threads ("callback threads") that are different from the thread that + * processes the command queue ("main thread"). + * + * crosvm and other virtio-gpu 1.1 implementations enable callback threads + * via locking. However, on QEMU a deadlock is observed if + * virtio_gpu_ctrl_response_nodata(..) [used in the fence callback] is used + * from a thread that is not the main thread. + * + * The reason is QEMU's internal locking is designed to work with QEMU + * threads (see rcu_register_thread()) and not generic C/C++/Rust threads. + * For now, we can workaround this by scheduling the return of the + * fence descriptors on the main thread. + */ + + data = g_new0(struct rutabaga_aio_data, 1); + data->vr = vr; + data->fence = *fence; + aio_bh_schedule_oneshot(qemu_get_aio_context(), + virtio_gpu_rutabaga_aio_cb, + data); +} + +static void +virtio_gpu_rutabaga_debug_cb(uint64_t user_data, + const struct rutabaga_debug *debug) +{ + switch (debug->debug_type) { + case RUTABAGA_DEBUG_ERROR: + error_report("%s", debug->message); + break; + case RUTABAGA_DEBUG_WARN: + warn_report("%s", debug->message); + break; + case RUTABAGA_DEBUG_INFO: + info_report("%s", debug->message); + break; + default: + error_report("unknown debug type: %u", debug->debug_type); + } +} + +static bool virtio_gpu_rutabaga_init(VirtIOGPU *g, Error **errp) +{ + int result; + struct rutabaga_builder builder = { 0 }; + struct rutabaga_channel channel = { 0 }; + struct rutabaga_channels channels = { 0 }; + + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + vr->rutabaga = NULL; + + builder.wsi = RUTABAGA_WSI_SURFACELESS; + /* + * Currently, if WSI is specified, the only valid strings are "surfaceless" + * or "headless". Surfaceless doesn't create a native window surface, but + * does copy from the render target to the Pixman buffer if a virtio-gpu + * 2D hypercall is issued. Surfacless is the default. + * + * Headless is like surfaceless, but doesn't copy to the Pixman buffer. The + * use case is automated testing environments where there is no need to view + * results. + * + * In the future, more performant virtio-gpu 2D UI integration may be added. + */ + if (vr->wsi) { + if (g_str_equal(vr->wsi, "surfaceless")) { + vr->headless = false; + } else if (g_str_equal(vr->wsi, "headless")) { + vr->headless = true; + } else { + error_setg(errp, "invalid wsi option selected"); + return false; + } + } + + builder.fence_cb = virtio_gpu_rutabaga_fence_cb; + builder.debug_cb = virtio_gpu_rutabaga_debug_cb; + builder.capset_mask = vr->capset_mask; + builder.user_data = (uint64_t)g; + + /* + * If the user doesn't specify the wayland socket path, we try to infer + * the socket via a process similar to the one used by libwayland. + * libwayland does the following: + * + * 1) If $WAYLAND_DISPLAY is set, attempt to connect to + * $XDG_RUNTIME_DIR/$WAYLAND_DISPLAY + * 2) Otherwise, attempt to connect to $XDG_RUNTIME_DIR/wayland-0 + * 3) Otherwise, don't pass a wayland socket to rutabaga. If a guest + * wayland proxy is launched, it will fail to work. + */ + channel.channel_type = RUTABAGA_CHANNEL_TYPE_WAYLAND; + g_autofree gchar *path = NULL; + if (!vr->wayland_socket_path) { + const gchar *runtime_dir = g_get_user_runtime_dir(); + const gchar *display = g_getenv("WAYLAND_DISPLAY"); + if (!display) { + display = "wayland-0"; + } + + if (runtime_dir) { + path = g_build_filename(runtime_dir, display, NULL); + channel.channel_name = path; + } + } else { + channel.channel_name = vr->wayland_socket_path; + } + + if ((builder.capset_mask & (1 << RUTABAGA_CAPSET_CROSS_DOMAIN))) { + if (channel.channel_name) { + channels.channels = &channel; + channels.num_channels = 1; + builder.channels = &channels; + } + } + + result = rutabaga_init(&builder, &vr->rutabaga); + if (result) { + error_setg_errno(errp, -result, "Failed to init rutabaga"); + return false; + } + + return true; +} + +static int virtio_gpu_rutabaga_get_num_capsets(VirtIOGPU *g) +{ + int result; + uint32_t num_capsets; + VirtIOGPURutabaga *vr = VIRTIO_GPU_RUTABAGA(g); + + result = rutabaga_get_num_capsets(vr->rutabaga, &num_capsets); + if (result) { + error_report("Failed to get capsets"); + return 0; + } + vr->num_capsets = num_capsets; + return num_capsets; +} + +static void virtio_gpu_rutabaga_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtIOGPU *g = VIRTIO_GPU(vdev); + struct virtio_gpu_ctrl_command *cmd; + + if (!virtio_queue_ready(vq)) { + return; + } + + cmd = virtqueue_pop(vq, sizeof(struct virtio_gpu_ctrl_command)); + while (cmd) { + cmd->vq = vq; + cmd->error = 0; + cmd->finished = false; + QTAILQ_INSERT_TAIL(&g->cmdq, cmd, next); + cmd = virtqueue_pop(vq, sizeof(struct virtio_gpu_ctrl_command)); + } + + virtio_gpu_process_cmdq(g); +} + +static void virtio_gpu_rutabaga_realize(DeviceState *qdev, Error **errp) +{ + int num_capsets; + VirtIOGPUBase *bdev = VIRTIO_GPU_BASE(qdev); + VirtIOGPU *gpudev = VIRTIO_GPU(qdev); + +#if HOST_BIG_ENDIAN + error_setg(errp, "rutabaga is not supported on bigendian platforms"); + return; +#endif + + if (!virtio_gpu_rutabaga_init(gpudev, errp)) { + return; + } + + num_capsets = virtio_gpu_rutabaga_get_num_capsets(gpudev); + if (!num_capsets) { + return; + } + + bdev->conf.flags |= (1 << VIRTIO_GPU_FLAG_RUTABAGA_ENABLED); + bdev->conf.flags |= (1 << VIRTIO_GPU_FLAG_BLOB_ENABLED); + bdev->conf.flags |= (1 << VIRTIO_GPU_FLAG_CONTEXT_INIT_ENABLED); + + bdev->virtio_config.num_capsets = num_capsets; + virtio_gpu_device_realize(qdev, errp); +} + +static Property virtio_gpu_rutabaga_properties[] = { + DEFINE_PROP_BIT64("gfxstream-vulkan", VirtIOGPURutabaga, capset_mask, + RUTABAGA_CAPSET_GFXSTREAM_VULKAN, false), + DEFINE_PROP_BIT64("cross-domain", VirtIOGPURutabaga, capset_mask, + RUTABAGA_CAPSET_CROSS_DOMAIN, false), + DEFINE_PROP_BIT64("x-gfxstream-gles", VirtIOGPURutabaga, capset_mask, + RUTABAGA_CAPSET_GFXSTREAM_GLES, false), + DEFINE_PROP_BIT64("x-gfxstream-composer", VirtIOGPURutabaga, capset_mask, + RUTABAGA_CAPSET_GFXSTREAM_COMPOSER, false), + DEFINE_PROP_STRING("wayland-socket-path", VirtIOGPURutabaga, + wayland_socket_path), + DEFINE_PROP_STRING("wsi", VirtIOGPURutabaga, wsi), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_gpu_rutabaga_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + VirtIOGPUBaseClass *vbc = VIRTIO_GPU_BASE_CLASS(klass); + VirtIOGPUClass *vgc = VIRTIO_GPU_CLASS(klass); + + vbc->gl_flushed = virtio_gpu_rutabaga_gl_flushed; + vgc->handle_ctrl = virtio_gpu_rutabaga_handle_ctrl; + vgc->process_cmd = virtio_gpu_rutabaga_process_cmd; + vgc->update_cursor_data = virtio_gpu_rutabaga_update_cursor; + + vdc->realize = virtio_gpu_rutabaga_realize; + device_class_set_props(dc, virtio_gpu_rutabaga_properties); +} + +static const TypeInfo virtio_gpu_rutabaga_info[] = { + { + .name = TYPE_VIRTIO_GPU_RUTABAGA, + .parent = TYPE_VIRTIO_GPU, + .instance_size = sizeof(VirtIOGPURutabaga), + .class_init = virtio_gpu_rutabaga_class_init, + }, +}; + +DEFINE_TYPES(virtio_gpu_rutabaga_info) + +module_obj(TYPE_VIRTIO_GPU_RUTABAGA); +module_kconfig(VIRTIO_GPU); +module_dep("hw-display-virtio-gpu"); diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c index 93857ad523..4265316cbb 100644 --- a/hw/display/virtio-gpu.c +++ b/hw/display/virtio-gpu.c @@ -33,15 +33,11 @@ #define VIRTIO_GPU_VM_VERSION 1 -static struct virtio_gpu_simple_resource* -virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id); static struct virtio_gpu_simple_resource * virtio_gpu_find_check_resource(VirtIOGPU *g, uint32_t resource_id, bool require_backing, const char *caller, uint32_t *error); -static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, - struct virtio_gpu_simple_resource *res); static void virtio_gpu_reset_bh(void *opaque); void virtio_gpu_update_cursor_data(VirtIOGPU *g, @@ -116,7 +112,7 @@ static void update_cursor(VirtIOGPU *g, struct virtio_gpu_update_cursor *cursor) cursor->resource_id ? 1 : 0); } -static struct virtio_gpu_simple_resource * +struct virtio_gpu_simple_resource * virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id) { struct virtio_gpu_simple_resource *res; @@ -904,8 +900,8 @@ void virtio_gpu_cleanup_mapping_iov(VirtIOGPU *g, g_free(iov); } -static void virtio_gpu_cleanup_mapping(VirtIOGPU *g, - struct virtio_gpu_simple_resource *res) +void virtio_gpu_cleanup_mapping(VirtIOGPU *g, + struct virtio_gpu_simple_resource *res) { virtio_gpu_cleanup_mapping_iov(g, res->iov, res->iov_cnt); res->iov = NULL; @@ -1132,7 +1128,7 @@ static void virtio_gpu_ctrl_bh(void *opaque) VirtIOGPU *g = opaque; VirtIOGPUClass *vgc = VIRTIO_GPU_GET_CLASS(g); - vgc->handle_ctrl(&g->parent_obj.parent_obj, g->ctrl_vq); + vgc->handle_ctrl(VIRTIO_DEVICE(g), g->ctrl_vq); } static void virtio_gpu_handle_cursor(VirtIODevice *vdev, VirtQueue *vq) @@ -1367,8 +1363,9 @@ void virtio_gpu_device_realize(DeviceState *qdev, Error **errp) VirtIOGPU *g = VIRTIO_GPU(qdev); if (virtio_gpu_blob_enabled(g->parent_obj.conf)) { - if (!virtio_gpu_have_udmabuf()) { - error_setg(errp, "cannot enable blob resources without udmabuf"); + if (!virtio_gpu_rutabaga_enabled(g->parent_obj.conf) && + !virtio_gpu_have_udmabuf()) { + error_setg(errp, "need rutabaga or udmabuf for blob resources"); return; } @@ -1511,6 +1508,7 @@ static Property virtio_gpu_properties[] = { 256 * MiB), DEFINE_PROP_BIT("blob", VirtIOGPU, parent_obj.conf.flags, VIRTIO_GPU_FLAG_BLOB_ENABLED, false), + DEFINE_PROP_SIZE("hostmem", VirtIOGPU, parent_obj.conf.hostmem, 0), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/display/virtio-vga-rutabaga.c b/hw/display/virtio-vga-rutabaga.c new file mode 100644 index 0000000000..a7bef6da24 --- /dev/null +++ b/hw/display/virtio-vga-rutabaga.c @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#include "qemu/osdep.h" +#include "hw/pci/pci.h" +#include "hw/qdev-properties.h" +#include "hw/virtio/virtio-gpu.h" +#include "hw/display/vga.h" +#include "qapi/error.h" +#include "qemu/module.h" +#include "virtio-vga.h" +#include "qom/object.h" + +#define TYPE_VIRTIO_VGA_RUTABAGA "virtio-vga-rutabaga" + +OBJECT_DECLARE_SIMPLE_TYPE(VirtIOVGARutabaga, VIRTIO_VGA_RUTABAGA) + +struct VirtIOVGARutabaga { + VirtIOVGABase parent_obj; + + VirtIOGPURutabaga vdev; +}; + +static void virtio_vga_rutabaga_inst_initfn(Object *obj) +{ + VirtIOVGARutabaga *dev = VIRTIO_VGA_RUTABAGA(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_GPU_RUTABAGA); + VIRTIO_VGA_BASE(dev)->vgpu = VIRTIO_GPU_BASE(&dev->vdev); +} + +static VirtioPCIDeviceTypeInfo virtio_vga_rutabaga_info = { + .generic_name = TYPE_VIRTIO_VGA_RUTABAGA, + .parent = TYPE_VIRTIO_VGA_BASE, + .instance_size = sizeof(VirtIOVGARutabaga), + .instance_init = virtio_vga_rutabaga_inst_initfn, +}; +module_obj(TYPE_VIRTIO_VGA_RUTABAGA); +module_kconfig(VIRTIO_VGA); + +static void virtio_vga_register_types(void) +{ + if (have_vga) { + virtio_pci_types_register(&virtio_vga_rutabaga_info); + } +} + +type_init(virtio_vga_register_types) + +module_dep("hw-display-virtio-vga"); diff --git a/hw/display/virtio-vga.c b/hw/display/virtio-vga.c index e6fb0aa876..c8552ff760 100644 --- a/hw/display/virtio-vga.c +++ b/hw/display/virtio-vga.c @@ -115,17 +115,32 @@ static void virtio_vga_base_realize(VirtIOPCIProxy *vpci_dev, Error **errp) pci_register_bar(&vpci_dev->pci_dev, 0, PCI_BASE_ADDRESS_MEM_PREFETCH, &vga->vram); - /* - * Configure virtio bar and regions - * - * We use bar #2 for the mmio regions, to be compatible with stdvga. - * virtio regions are moved to the end of bar #2, to make room for - * the stdvga mmio registers at the start of bar #2. - */ - vpci_dev->modern_mem_bar_idx = 2; - vpci_dev->msix_bar_idx = 4; vpci_dev->modern_io_bar_idx = 5; + if (!virtio_gpu_hostmem_enabled(g->conf)) { + /* + * Configure virtio bar and regions + * + * We use bar #2 for the mmio regions, to be compatible with stdvga. + * virtio regions are moved to the end of bar #2, to make room for + * the stdvga mmio registers at the start of bar #2. + */ + vpci_dev->modern_mem_bar_idx = 2; + vpci_dev->msix_bar_idx = 4; + } else { + vpci_dev->msix_bar_idx = 1; + vpci_dev->modern_mem_bar_idx = 2; + memory_region_init(&g->hostmem, OBJECT(g), "virtio-gpu-hostmem", + g->conf.hostmem); + pci_register_bar(&vpci_dev->pci_dev, 4, + PCI_BASE_ADDRESS_SPACE_MEMORY | + PCI_BASE_ADDRESS_MEM_PREFETCH | + PCI_BASE_ADDRESS_MEM_TYPE_64, + &g->hostmem); + virtio_pci_add_shm_cap(vpci_dev, 4, 0, g->conf.hostmem, + VIRTIO_GPU_SHM_ID_HOST_VISIBLE); + } + if (!(vpci_dev->flags & VIRTIO_PCI_FLAG_PAGE_PER_VQ)) { /* * with page-per-vq=off there is no padding space we can use diff --git a/hw/display/xenfb.c b/hw/display/xenfb.c index 0074a9b6f8..b2130a0d70 100644 --- a/hw/display/xenfb.c +++ b/hw/display/xenfb.c @@ -321,20 +321,20 @@ static void xenfb_mouse_sync(DeviceState *dev) xenfb->wheel = 0; } -static QemuInputHandler xenfb_keyboard = { +static const QemuInputHandler xenfb_keyboard = { .name = "Xen PV Keyboard", .mask = INPUT_EVENT_MASK_KEY, .event = xenfb_key_event, }; -static QemuInputHandler xenfb_abs_mouse = { +static const QemuInputHandler xenfb_abs_mouse = { .name = "Xen PV Mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS, .event = xenfb_mouse_event, .sync = xenfb_mouse_sync, }; -static QemuInputHandler xenfb_rel_mouse = { +static const QemuInputHandler xenfb_rel_mouse = { .name = "Xen PV Mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL, .event = xenfb_mouse_event, diff --git a/hw/dma/xilinx_axidma.c b/hw/dma/xilinx_axidma.c index 12c90267df..0ae056ed06 100644 --- a/hw/dma/xilinx_axidma.c +++ b/hw/dma/xilinx_axidma.c @@ -577,10 +577,6 @@ static void xilinx_axidma_init(Object *obj) object_initialize_child(OBJECT(s), "axistream-control-connected-target", &s->rx_control_dev, TYPE_XILINX_AXI_DMA_CONTROL_STREAM); - object_property_add_link(obj, "dma", TYPE_MEMORY_REGION, - (Object **)&s->dma_mr, - qdev_prop_allow_set_link_before_realize, - OBJ_PROP_LINK_STRONG); sysbus_init_irq(sbd, &s->streams[0].irq); sysbus_init_irq(sbd, &s->streams[1].irq); @@ -596,6 +592,8 @@ static Property axidma_properties[] = { tx_data_dev, TYPE_STREAM_SINK, StreamSink *), DEFINE_PROP_LINK("axistream-control-connected", XilinxAXIDMA, tx_control_dev, TYPE_STREAM_SINK, StreamSink *), + DEFINE_PROP_LINK("dma", XilinxAXIDMA, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index 4eb7f66e9f..84c0083013 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -795,11 +795,6 @@ static void zdma_init(Object *obj) TYPE_XLNX_ZDMA, ZDMA_R_MAX * 4); sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq_zdma_ch_imr); - - object_property_add_link(obj, "dma", TYPE_MEMORY_REGION, - (Object **)&s->dma_mr, - qdev_prop_allow_set_link_before_realize, - OBJ_PROP_LINK_STRONG); } static const VMStateDescription vmstate_zdma = { @@ -817,6 +812,8 @@ static const VMStateDescription vmstate_zdma = { static Property zdma_props[] = { DEFINE_PROP_UINT32("bus-width", XlnxZDMA, cfg.bus_width, 64), + DEFINE_PROP_LINK("dma", XlnxZDMA, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/dma/xlnx_csu_dma.c b/hw/dma/xlnx_csu_dma.c index 88002698a1..e89089821a 100644 --- a/hw/dma/xlnx_csu_dma.c +++ b/hw/dma/xlnx_csu_dma.c @@ -702,6 +702,10 @@ static Property xlnx_csu_dma_properties[] = { * which channel the device is connected to. */ DEFINE_PROP_BOOL("is-dst", XlnxCSUDMA, is_dst, true), + DEFINE_PROP_LINK("stream-connected-dma", XlnxCSUDMA, tx_dev, + TYPE_STREAM_SINK, StreamSink *), + DEFINE_PROP_LINK("dma", XlnxCSUDMA, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; @@ -728,15 +732,6 @@ static void xlnx_csu_dma_init(Object *obj) memory_region_init(&s->iomem, obj, TYPE_XLNX_CSU_DMA, XLNX_CSU_DMA_R_MAX * 4); - - object_property_add_link(obj, "stream-connected-dma", TYPE_STREAM_SINK, - (Object **)&s->tx_dev, - qdev_prop_allow_set_link_before_realize, - OBJ_PROP_LINK_STRONG); - object_property_add_link(obj, "dma", TYPE_MEMORY_REGION, - (Object **)&s->dma_mr, - qdev_prop_allow_set_link_before_realize, - OBJ_PROP_LINK_STRONG); } static const TypeInfo xlnx_csu_dma_info = { diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 8d0f2f99dd..7965415b47 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -1579,9 +1579,8 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) /* set up MMIO */ memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio", AMDVI_MMIO_SIZE); - - sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->mmio); - sysbus_mmio_map(SYS_BUS_DEVICE(s), 0, AMDVI_BASE_ADDR); + memory_region_add_subregion(get_system_memory(), AMDVI_BASE_ADDR, + &s->mmio); pci_setup_iommu(bus, amdvi_host_dma_iommu, s); amdvi_init(s); } diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 2c832ab68b..e4f6cedcb1 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -4134,6 +4134,8 @@ static void vtd_realize(DeviceState *dev, Error **errp) qemu_mutex_init(&s->iommu_lock); memory_region_init_io(&s->csrmem, OBJECT(s), &vtd_mem_ops, s, "intel_iommu", DMAR_REG_SIZE); + memory_region_add_subregion(get_system_memory(), + Q35_HOST_BRIDGE_IOMMU_ADDR, &s->csrmem); /* Create the shared memory regions by all devices */ memory_region_init(&s->mr_nodmar, OBJECT(s), "vtd-nodmar", @@ -4148,15 +4150,12 @@ static void vtd_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(&s->mr_nodmar, VTD_INTERRUPT_ADDR_FIRST, &s->mr_ir, 1); - - sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->csrmem); /* No corresponding destroy */ s->iotlb = g_hash_table_new_full(vtd_iotlb_hash, vtd_iotlb_equal, g_free, g_free); s->vtd_address_spaces = g_hash_table_new_full(vtd_as_hash, vtd_as_equal, g_free, g_free); vtd_init(s); - sysbus_mmio_map(SYS_BUS_DEVICE(s), 0, Q35_HOST_BRIDGE_IOMMU_ADDR); pci_setup_iommu(bus, vtd_host_dma_iommu, dev); /* Pseudo address space under root PCI bus. */ x86ms->ioapic_as = vtd_host_dma_iommu(bus, s, Q35_PSEUDO_DEVFN_IOAPIC); diff --git a/hw/i386/meson.build b/hw/i386/meson.build index ff879069c9..369c6bf823 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -32,6 +32,5 @@ subdir('kvm') subdir('xen') i386_ss.add_all(xenpv_ss) -i386_ss.add_all(xen_ss) hw_arch += {'i386': i386_ss} diff --git a/hw/i386/microvm.c b/hw/i386/microvm.c index b9c93039e2..ca55aecc3b 100644 --- a/hw/i386/microvm.c +++ b/hw/i386/microvm.c @@ -206,12 +206,12 @@ static void microvm_devices_init(MicrovmMachineState *mms) if (x86_machine_is_acpi_enabled(x86ms)) { DeviceState *dev = qdev_new(TYPE_ACPI_GED); qdev_prop_set_uint32(dev, "ged-event", ACPI_GED_PWR_DOWN_EVT); + sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, GED_MMIO_BASE); /* sysbus_mmio_map(SYS_BUS_DEVICE(dev), 1, GED_MMIO_BASE_MEMHP); */ sysbus_mmio_map(SYS_BUS_DEVICE(dev), 2, GED_MMIO_BASE_REGS); sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, x86ms->gsi[GED_MMIO_IRQ]); - sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); x86ms->acpi_dev = HOTPLUG_HANDLER(dev); } diff --git a/hw/i386/pc.c b/hw/i386/pc.c index bb3854d1d0..f7ee638bec 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -1283,7 +1283,9 @@ void pc_basic_device_init(struct PCMachineState *pcms, /* connect PIT to output control line of the HPET */ qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(DEVICE(pit), 0)); } - pcspk_init(pcms->pcspk, isa_bus, pit); + object_property_set_link(OBJECT(pcms->pcspk), "pit", + OBJECT(pit), &error_fatal); + isa_realize_and_unref(pcms->pcspk, isa_bus, &error_fatal); } /* Super I/O */ diff --git a/hw/input/adb-kbd.c b/hw/input/adb-kbd.c index a9088c910c..e21edf9acd 100644 --- a/hw/input/adb-kbd.c +++ b/hw/input/adb-kbd.c @@ -355,7 +355,7 @@ static void adb_kbd_reset(DeviceState *dev) s->count = 0; } -static QemuInputHandler adb_keyboard_handler = { +static const QemuInputHandler adb_keyboard_handler = { .name = "QEMU ADB Keyboard", .mask = INPUT_EVENT_MASK_KEY, .event = adb_keyboard_event, diff --git a/hw/input/hid.c b/hw/input/hid.c index a9c7dd1ce1..b8e85374ca 100644 --- a/hw/input/hid.c +++ b/hw/input/hid.c @@ -510,20 +510,20 @@ void hid_free(HIDState *hs) hid_del_idle_timer(hs); } -static QemuInputHandler hid_keyboard_handler = { +static const QemuInputHandler hid_keyboard_handler = { .name = "QEMU HID Keyboard", .mask = INPUT_EVENT_MASK_KEY, .event = hid_keyboard_event, }; -static QemuInputHandler hid_mouse_handler = { +static const QemuInputHandler hid_mouse_handler = { .name = "QEMU HID Mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL, .event = hid_pointer_event, .sync = hid_pointer_sync, }; -static QemuInputHandler hid_tablet_handler = { +static const QemuInputHandler hid_tablet_handler = { .name = "QEMU HID Tablet", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS, .event = hid_pointer_event, diff --git a/hw/input/ps2.c b/hw/input/ps2.c index 45af76a837..c8fd23cf36 100644 --- a/hw/input/ps2.c +++ b/hw/input/ps2.c @@ -1231,7 +1231,7 @@ static const VMStateDescription vmstate_ps2_mouse = { } }; -static QemuInputHandler ps2_keyboard_handler = { +static const QemuInputHandler ps2_keyboard_handler = { .name = "QEMU PS/2 Keyboard", .mask = INPUT_EVENT_MASK_KEY, .event = ps2_keyboard_event, @@ -1242,7 +1242,7 @@ static void ps2_kbd_realize(DeviceState *dev, Error **errp) qemu_input_handler_register(dev, &ps2_keyboard_handler); } -static QemuInputHandler ps2_mouse_handler = { +static const QemuInputHandler ps2_mouse_handler = { .name = "QEMU PS/2 Mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL, .event = ps2_mouse_event, diff --git a/hw/input/virtio-input-hid.c b/hw/input/virtio-input-hid.c index 7053ad72d4..45e4d4c75d 100644 --- a/hw/input/virtio-input-hid.c +++ b/hw/input/virtio-input-hid.c @@ -265,7 +265,7 @@ static const TypeInfo virtio_input_hid_info = { /* ----------------------------------------------------------------- */ -static QemuInputHandler virtio_keyboard_handler = { +static const QemuInputHandler virtio_keyboard_handler = { .name = VIRTIO_ID_NAME_KEYBOARD, .mask = INPUT_EVENT_MASK_KEY, .event = virtio_input_handle_event, @@ -322,7 +322,7 @@ static const TypeInfo virtio_keyboard_info = { /* ----------------------------------------------------------------- */ -static QemuInputHandler virtio_mouse_handler = { +static const QemuInputHandler virtio_mouse_handler = { .name = VIRTIO_ID_NAME_MOUSE, .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_REL, .event = virtio_input_handle_event, @@ -416,7 +416,7 @@ static const TypeInfo virtio_mouse_info = { /* ----------------------------------------------------------------- */ -static QemuInputHandler virtio_tablet_handler = { +static const QemuInputHandler virtio_tablet_handler = { .name = VIRTIO_ID_NAME_TABLET, .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS, .event = virtio_input_handle_event, @@ -541,7 +541,7 @@ static const TypeInfo virtio_tablet_info = { /* ----------------------------------------------------------------- */ -static QemuInputHandler virtio_multitouch_handler = { +static const QemuInputHandler virtio_multitouch_handler = { .name = VIRTIO_ID_NAME_MULTITOUCH, .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_MTT, .event = virtio_input_handle_event, diff --git a/hw/intc/apic_common.c b/hw/intc/apic_common.c index 68ad30e2f5..bccb4241c2 100644 --- a/hw/intc/apic_common.c +++ b/hw/intc/apic_common.c @@ -257,6 +257,7 @@ static const VMStateDescription vmstate_apic_common; static void apic_common_realize(DeviceState *dev, Error **errp) { + ERRP_GUARD(); APICCommonState *s = APIC_COMMON(dev); APICCommonClass *info; static DeviceState *vapic; @@ -267,6 +268,9 @@ static void apic_common_realize(DeviceState *dev, Error **errp) info = APIC_COMMON_GET_CLASS(s); info->realize(dev, errp); + if (*errp) { + return; + } /* Note: We need at least 1M to map the VAPIC option ROM */ if (!vapic && s->vapic_control & VAPIC_ENABLE_MASK && diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c index 7f701d414b..199c261b07 100644 --- a/hw/intc/spapr_xive.c +++ b/hw/intc/spapr_xive.c @@ -316,7 +316,6 @@ static void spapr_xive_realize(DeviceState *dev, Error **errp) if (!qdev_realize(DEVICE(xsrc), NULL, errp)) { return; } - sysbus_init_mmio(SYS_BUS_DEVICE(xive), &xsrc->esb_mmio); /* * Initialize the END ESB source @@ -328,7 +327,6 @@ static void spapr_xive_realize(DeviceState *dev, Error **errp) if (!qdev_realize(DEVICE(end_xsrc), NULL, errp)) { return; } - sysbus_init_mmio(SYS_BUS_DEVICE(xive), &end_xsrc->esb_mmio); /* Set the mapping address of the END ESB pages after the source ESBs */ xive->end_base = xive->vc_base + xive_source_esb_len(xsrc); @@ -347,15 +345,17 @@ static void spapr_xive_realize(DeviceState *dev, Error **errp) /* TIMA initialization */ memory_region_init_io(&xive->tm_mmio, OBJECT(xive), &spapr_xive_tm_ops, xive, "xive.tima", 4ull << TM_SHIFT); - sysbus_init_mmio(SYS_BUS_DEVICE(xive), &xive->tm_mmio); /* * Map all regions. These will be enabled or disabled at reset and * can also be overridden by KVM memory regions if active */ - sysbus_mmio_map(SYS_BUS_DEVICE(xive), 0, xive->vc_base); - sysbus_mmio_map(SYS_BUS_DEVICE(xive), 1, xive->end_base); - sysbus_mmio_map(SYS_BUS_DEVICE(xive), 2, xive->tm_base); + memory_region_add_subregion(get_system_memory(), xive->vc_base, + &xsrc->esb_mmio); + memory_region_add_subregion(get_system_memory(), xive->end_base, + &end_xsrc->esb_mmio); + memory_region_add_subregion(get_system_memory(), xive->tm_base, + &xive->tm_mmio); } static int spapr_xive_get_eas(XiveRouter *xrtr, uint8_t eas_blk, diff --git a/hw/isa/i82378.c b/hw/isa/i82378.c index 63e0857208..79ffbb52a0 100644 --- a/hw/isa/i82378.c +++ b/hw/isa/i82378.c @@ -67,6 +67,7 @@ static void i82378_realize(PCIDevice *pci, Error **errp) uint8_t *pci_conf; ISABus *isabus; ISADevice *pit; + ISADevice *pcspk; pci_conf = pci->config; pci_set_word(pci_conf + PCI_COMMAND, @@ -102,7 +103,9 @@ static void i82378_realize(PCIDevice *pci, Error **errp) pit = i8254_pit_init(isabus, 0x40, 0, NULL); /* speaker */ - pcspk_init(isa_new(TYPE_PC_SPEAKER), isabus, pit); + pcspk = isa_new(TYPE_PC_SPEAKER); + object_property_set_link(OBJECT(pcspk), "pit", OBJECT(pit), &error_fatal); + isa_realize_and_unref(pcspk, isabus, &error_fatal); /* 2 82C37 (dma) */ isa_create_simple(isabus, "i82374"); diff --git a/hw/isa/isa-bus.c b/hw/isa/isa-bus.c index a289eccfb1..f1e0f14007 100644 --- a/hw/isa/isa-bus.c +++ b/hw/isa/isa-bus.c @@ -52,18 +52,25 @@ static const TypeInfo isa_bus_info = { ISABus *isa_bus_new(DeviceState *dev, MemoryRegion* address_space, MemoryRegion *address_space_io, Error **errp) { + DeviceState *bridge = NULL; + if (isabus) { error_setg(errp, "Can't create a second ISA bus"); return NULL; } if (!dev) { - dev = qdev_new("isabus-bridge"); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + bridge = qdev_new("isabus-bridge"); + dev = bridge; } isabus = ISA_BUS(qbus_new(TYPE_ISA_BUS, dev, NULL)); isabus->address_space = address_space; isabus->address_space_io = address_space_io; + + if (bridge) { + sysbus_realize_and_unref(SYS_BUS_DEVICE(bridge), &error_fatal); + } + return isabus; } diff --git a/hw/loongarch/Kconfig b/hw/loongarch/Kconfig index 1e7c5b43c5..5727efed6d 100644 --- a/hw/loongarch/Kconfig +++ b/hw/loongarch/Kconfig @@ -5,9 +5,7 @@ config LOONGARCH_VIRT imply VIRTIO_VGA imply PCI_DEVICES imply NVDIMM - select ISA_BUS select SERIAL - select SERIAL_ISA select VIRTIO_PCI select PLATFORM_BUS select LOONGARCH_IPI diff --git a/hw/loongarch/virt.c b/hw/loongarch/virt.c index b0a004f860..4b7dc67a2d 100644 --- a/hw/loongarch/virt.c +++ b/hw/loongarch/virt.c @@ -47,6 +47,13 @@ #include "qemu/error-report.h" +struct loaderparams { + uint64_t ram_size; + const char *kernel_filename; + const char *kernel_cmdline; + const char *initrd_filename; +}; + static void virt_flash_create(LoongArchMachineState *lams) { DeviceState *dev = qdev_new(TYPE_PFLASH_CFI01); @@ -301,10 +308,6 @@ static void fdt_add_memory_node(MachineState *ms, g_free(nodename); } -#define PM_BASE 0x10080000 -#define PM_SIZE 0x100 -#define PM_CTRL 0x10 - static void virt_build_smbios(LoongArchMachineState *lams) { MachineState *ms = MACHINE(lams); @@ -373,62 +376,17 @@ static void memmap_add_entry(uint64_t address, uint64_t length, uint32_t type) memmap_entries++; } -/* - * This is a placeholder for missing ACPI, - * and will eventually be replaced. - */ -static uint64_t loongarch_virt_pm_read(void *opaque, hwaddr addr, unsigned size) -{ - return 0; -} - -static void loongarch_virt_pm_write(void *opaque, hwaddr addr, - uint64_t val, unsigned size) -{ - if (addr != PM_CTRL) { - return; - } - - switch (val) { - case 0x00: - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); - return; - case 0xff: - qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); - return; - default: - return; - } -} - -static const MemoryRegionOps loongarch_virt_pm_ops = { - .read = loongarch_virt_pm_read, - .write = loongarch_virt_pm_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid = { - .min_access_size = 1, - .max_access_size = 1 - } -}; - -static struct _loaderparams { - uint64_t ram_size; - const char *kernel_filename; - const char *kernel_cmdline; - const char *initrd_filename; -} loaderparams; - static uint64_t cpu_loongarch_virt_to_phys(void *opaque, uint64_t addr) { return addr & MAKE_64BIT_MASK(0, TARGET_PHYS_ADDR_SPACE_BITS); } -static int64_t load_kernel_info(void) +static int64_t load_kernel_info(const struct loaderparams *loaderparams) { uint64_t kernel_entry, kernel_low, kernel_high; ssize_t kernel_size; - kernel_size = load_elf(loaderparams.kernel_filename, NULL, + kernel_size = load_elf(loaderparams->kernel_filename, NULL, cpu_loongarch_virt_to_phys, NULL, &kernel_entry, &kernel_low, &kernel_high, NULL, 0, @@ -436,7 +394,7 @@ static int64_t load_kernel_info(void) if (kernel_size < 0) { error_report("could not load kernel '%s': %s", - loaderparams.kernel_filename, + loaderparams->kernel_filename, load_elf_strerror(kernel_size)); exit(1); } @@ -454,6 +412,7 @@ static DeviceState *create_acpi_ged(DeviceState *pch_pic, LoongArchMachineState } dev = qdev_new(TYPE_ACPI_GED); qdev_prop_set_uint32(dev, "ged-event", event); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); /* ged event */ sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, VIRT_GED_EVT_ADDR); @@ -464,7 +423,6 @@ static DeviceState *create_acpi_ged(DeviceState *pch_pic, LoongArchMachineState sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, qdev_get_gpio_in(pch_pic, VIRT_SCI_IRQ - VIRT_GSI_BASE)); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); return dev; } @@ -500,7 +458,7 @@ static void loongarch_devices_init(DeviceState *pch_pic, LoongArchMachineState * SysBusDevice *d; PCIBus *pci_bus; MemoryRegion *ecam_alias, *ecam_reg, *pio_alias, *pio_reg; - MemoryRegion *mmio_alias, *mmio_reg, *pm_mem; + MemoryRegion *mmio_alias, *mmio_reg; int i; gpex_dev = qdev_new(TYPE_GPEX_HOST); @@ -560,10 +518,6 @@ static void loongarch_devices_init(DeviceState *pch_pic, LoongArchMachineState * VIRT_RTC_IRQ - VIRT_GSI_BASE)); fdt_add_rtc_node(lams); - pm_mem = g_new(MemoryRegion, 1); - memory_region_init_io(pm_mem, NULL, &loongarch_virt_pm_ops, - NULL, "loongarch_virt_pm", PM_SIZE); - memory_region_add_subregion(get_system_memory(), PM_BASE, pm_mem); /* acpi ged */ lams->acpi_ged = create_acpi_ged(pch_pic, lams); /* platform bus */ @@ -728,7 +682,8 @@ static void reset_load_elf(void *opaque) } } -static void fw_cfg_add_kernel_info(FWCfgState *fw_cfg) +static void fw_cfg_add_kernel_info(const struct loaderparams *loaderparams, + FWCfgState *fw_cfg) { /* * Expose the kernel, the command line, and the initrd in fw_cfg. @@ -737,36 +692,38 @@ static void fw_cfg_add_kernel_info(FWCfgState *fw_cfg) */ load_image_to_fw_cfg(fw_cfg, FW_CFG_KERNEL_SIZE, FW_CFG_KERNEL_DATA, - loaderparams.kernel_filename, + loaderparams->kernel_filename, false); - if (loaderparams.initrd_filename) { + if (loaderparams->initrd_filename) { load_image_to_fw_cfg(fw_cfg, FW_CFG_INITRD_SIZE, FW_CFG_INITRD_DATA, - loaderparams.initrd_filename, false); + loaderparams->initrd_filename, false); } - if (loaderparams.kernel_cmdline) { + if (loaderparams->kernel_cmdline) { fw_cfg_add_i32(fw_cfg, FW_CFG_CMDLINE_SIZE, - strlen(loaderparams.kernel_cmdline) + 1); + strlen(loaderparams->kernel_cmdline) + 1); fw_cfg_add_string(fw_cfg, FW_CFG_CMDLINE_DATA, - loaderparams.kernel_cmdline); + loaderparams->kernel_cmdline); } } -static void loongarch_firmware_boot(LoongArchMachineState *lams) +static void loongarch_firmware_boot(LoongArchMachineState *lams, + const struct loaderparams *loaderparams) { - fw_cfg_add_kernel_info(lams->fw_cfg); + fw_cfg_add_kernel_info(loaderparams, lams->fw_cfg); } -static void loongarch_direct_kernel_boot(LoongArchMachineState *lams) +static void loongarch_direct_kernel_boot(LoongArchMachineState *lams, + const struct loaderparams *loaderparams) { MachineState *machine = MACHINE(lams); int64_t kernel_addr = 0; LoongArchCPU *lacpu; int i; - kernel_addr = load_kernel_info(); + kernel_addr = load_kernel_info(loaderparams); if (!machine->firmware) { for (i = 0; i < machine->smp.cpus; i++) { lacpu = LOONGARCH_CPU(qemu_get_cpu(i)); @@ -793,6 +750,7 @@ static void loongarch_init(MachineState *machine) MachineClass *mc = MACHINE_GET_CLASS(machine); CPUState *cpu; char *ramName = NULL; + struct loaderparams loaderparams = { }; if (!cpu_model) { cpu_model = LOONGARCH_CPU_TYPE_NAME("la464"); @@ -874,11 +832,6 @@ static void loongarch_init(MachineState *machine) machine_memory_devices_init(machine, device_mem_base, device_mem_size); } - /* Add isa io region */ - memory_region_init_alias(&lams->isa_io, NULL, "isa-io", - get_system_io(), 0, VIRT_ISA_IO_SIZE); - memory_region_add_subregion(address_space_mem, VIRT_ISA_IO_BASE, - &lams->isa_io); /* load the BIOS image. */ loongarch_firmware_init(lams); @@ -898,9 +851,9 @@ static void loongarch_init(MachineState *machine) /* load the kernel. */ if (loaderparams.kernel_filename) { if (lams->bios_loaded) { - loongarch_firmware_boot(lams); + loongarch_firmware_boot(lams, &loaderparams); } else { - loongarch_direct_kernel_boot(lams); + loongarch_direct_kernel_boot(lams, &loaderparams); } } fdt_add_flash_node(lams); diff --git a/hw/mem/memory-device.c b/hw/mem/memory-device.c index 667d56bd29..ae38f48f16 100644 --- a/hw/mem/memory-device.c +++ b/hw/mem/memory-device.c @@ -52,19 +52,135 @@ static int memory_device_build_list(Object *obj, void *opaque) return 0; } -static void memory_device_check_addable(MachineState *ms, MemoryRegion *mr, - Error **errp) +static unsigned int memory_device_get_memslots(MemoryDeviceState *md) { + const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + + if (mdc->get_memslots) { + return mdc->get_memslots(md); + } + return 1; +} + +/* + * Memslots that are reserved by memory devices (required but still reported + * as free from KVM / vhost). + */ +static unsigned int get_reserved_memslots(MachineState *ms) +{ + if (ms->device_memory->used_memslots > + ms->device_memory->required_memslots) { + /* This is unexpected, and we warned already in the memory notifier. */ + return 0; + } + return ms->device_memory->required_memslots - + ms->device_memory->used_memslots; +} + +unsigned int memory_devices_get_reserved_memslots(void) +{ + if (!current_machine->device_memory) { + return 0; + } + return get_reserved_memslots(current_machine); +} + +bool memory_devices_memslot_auto_decision_active(void) +{ + if (!current_machine->device_memory) { + return false; + } + + return current_machine->device_memory->memslot_auto_decision_active; +} + +static unsigned int memory_device_memslot_decision_limit(MachineState *ms, + MemoryRegion *mr) +{ + const unsigned int reserved = get_reserved_memslots(ms); + const uint64_t size = memory_region_size(mr); + unsigned int max = vhost_get_max_memslots(); + unsigned int free = vhost_get_free_memslots(); + uint64_t available_space; + unsigned int memslots; + + if (kvm_enabled()) { + max = MIN(max, kvm_get_max_memslots()); + free = MIN(free, kvm_get_free_memslots()); + } + + /* + * If we only have less overall memslots than what we consider reasonable, + * just keep it to a minimum. + */ + if (max < MEMORY_DEVICES_SAFE_MAX_MEMSLOTS) { + return 1; + } + + /* + * Consider our soft-limit across all memory devices. We don't really + * expect to exceed this limit in reasonable configurations. + */ + if (MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT <= + ms->device_memory->required_memslots) { + return 1; + } + memslots = MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT - + ms->device_memory->required_memslots; + + /* + * Consider the actually still free memslots. This is only relevant if + * other memslot consumers would consume *significantly* more memslots than + * what we prepared for (> 253). Unlikely, but let's just handle it + * cleanly. + */ + memslots = MIN(memslots, free - reserved); + if (memslots < 1 || unlikely(free < reserved)) { + return 1; + } + + /* We cannot have any other memory devices? So give all to this device. */ + if (size == ms->maxram_size - ms->ram_size) { + return memslots; + } + + /* + * Simple heuristic: equally distribute the memslots over the space + * still available for memory devices. + */ + available_space = ms->maxram_size - ms->ram_size - + ms->device_memory->used_region_size; + memslots = (double)memslots * size / available_space; + return memslots < 1 ? 1 : memslots; +} + +static void memory_device_check_addable(MachineState *ms, MemoryDeviceState *md, + MemoryRegion *mr, Error **errp) +{ + const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); const uint64_t used_region_size = ms->device_memory->used_region_size; const uint64_t size = memory_region_size(mr); + const unsigned int reserved_memslots = get_reserved_memslots(ms); + unsigned int required_memslots, memslot_limit; + + /* + * Instruct the device to decide how many memslots to use, if applicable, + * before we query the number of required memslots the first time. + */ + if (mdc->decide_memslots) { + memslot_limit = memory_device_memslot_decision_limit(ms, mr); + mdc->decide_memslots(md, memslot_limit); + } + required_memslots = memory_device_get_memslots(md); - /* we will need a new memory slot for kvm and vhost */ - if (kvm_enabled() && !kvm_has_free_slot(ms)) { - error_setg(errp, "hypervisor has no free memory slots left"); + /* we will need memory slots for kvm and vhost */ + if (kvm_enabled() && + kvm_get_free_memslots() < required_memslots + reserved_memslots) { + error_setg(errp, "hypervisor has not enough free memory slots left"); return; } - if (!vhost_has_free_slot()) { - error_setg(errp, "a used vhost backend has no free memory slots left"); + if (vhost_get_free_memslots() < required_memslots + reserved_memslots) { + error_setg(errp, "a used vhost backend has not enough free memory slots left"); return; } @@ -233,7 +349,7 @@ void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms, goto out; } - memory_device_check_addable(ms, mr, &local_err); + memory_device_check_addable(ms, md, mr, &local_err); if (local_err) { goto out; } @@ -264,6 +380,7 @@ out: void memory_device_plug(MemoryDeviceState *md, MachineState *ms) { const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + const unsigned int memslots = memory_device_get_memslots(md); const uint64_t addr = mdc->get_addr(md); MemoryRegion *mr; @@ -275,6 +392,11 @@ void memory_device_plug(MemoryDeviceState *md, MachineState *ms) g_assert(ms->device_memory); ms->device_memory->used_region_size += memory_region_size(mr); + ms->device_memory->required_memslots += memslots; + if (mdc->decide_memslots && memslots > 1) { + ms->device_memory->memslot_auto_decision_active++; + } + memory_region_add_subregion(&ms->device_memory->mr, addr - ms->device_memory->base, mr); trace_memory_device_plug(DEVICE(md)->id ? DEVICE(md)->id : "", addr); @@ -283,6 +405,7 @@ void memory_device_plug(MemoryDeviceState *md, MachineState *ms) void memory_device_unplug(MemoryDeviceState *md, MachineState *ms) { const MemoryDeviceClass *mdc = MEMORY_DEVICE_GET_CLASS(md); + const unsigned int memslots = memory_device_get_memslots(md); MemoryRegion *mr; /* @@ -293,7 +416,12 @@ void memory_device_unplug(MemoryDeviceState *md, MachineState *ms) g_assert(ms->device_memory); memory_region_del_subregion(&ms->device_memory->mr, mr); + + if (mdc->decide_memslots && memslots > 1) { + ms->device_memory->memslot_auto_decision_active--; + } ms->device_memory->used_region_size -= memory_region_size(mr); + ms->device_memory->required_memslots -= memslots; trace_memory_device_unplug(DEVICE(md)->id ? DEVICE(md)->id : "", mdc->get_addr(md)); } @@ -313,6 +441,50 @@ uint64_t memory_device_get_region_size(const MemoryDeviceState *md, return memory_region_size(mr); } +static void memory_devices_region_mod(MemoryListener *listener, + MemoryRegionSection *mrs, bool add) +{ + DeviceMemoryState *dms = container_of(listener, DeviceMemoryState, + listener); + + if (!memory_region_is_ram(mrs->mr)) { + warn_report("Unexpected memory region mapped into device memory region."); + return; + } + + /* + * The expectation is that each distinct RAM memory region section in + * our region for memory devices consumes exactly one memslot in KVM + * and in vhost. For vhost, this is true, except: + * * ROM memory regions don't consume a memslot. These get used very + * rarely for memory devices (R/O NVDIMMs). + * * Memslots without a fd (memory-backend-ram) don't necessarily + * consume a memslot. Such setups are quite rare and possibly bogus: + * the memory would be inaccessible by such vhost devices. + * + * So for vhost, in corner cases we might over-estimate the number of + * memslots that are currently used or that might still be reserved + * (required - used). + */ + dms->used_memslots += add ? 1 : -1; + + if (dms->used_memslots > dms->required_memslots) { + warn_report("Memory devices use more memory slots than indicated as required."); + } +} + +static void memory_devices_region_add(MemoryListener *listener, + MemoryRegionSection *mrs) +{ + return memory_devices_region_mod(listener, mrs, true); +} + +static void memory_devices_region_del(MemoryListener *listener, + MemoryRegionSection *mrs) +{ + return memory_devices_region_mod(listener, mrs, false); +} + void machine_memory_devices_init(MachineState *ms, hwaddr base, uint64_t size) { g_assert(size); @@ -322,8 +494,16 @@ void machine_memory_devices_init(MachineState *ms, hwaddr base, uint64_t size) memory_region_init(&ms->device_memory->mr, OBJECT(ms), "device-memory", size); + address_space_init(&ms->device_memory->as, &ms->device_memory->mr, + "device-memory"); memory_region_add_subregion(get_system_memory(), ms->device_memory->base, &ms->device_memory->mr); + + /* Track the number of memslots used by memory devices. */ + ms->device_memory->listener.region_add = memory_devices_region_add; + ms->device_memory->listener.region_del = memory_devices_region_del; + memory_listener_register(&ms->device_memory->listener, + &ms->device_memory->as); } static const TypeInfo memory_device_info = { diff --git a/hw/mips/cps.c b/hw/mips/cps.c index 2b5269ebf1..b6612c1762 100644 --- a/hw/mips/cps.c +++ b/hw/mips/cps.c @@ -24,7 +24,6 @@ #include "hw/mips/mips.h" #include "hw/qdev-clock.h" #include "hw/qdev-properties.h" -#include "hw/mips/cpudevs.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" diff --git a/hw/mips/fuloong2e.c b/hw/mips/fuloong2e.c index c6109633fe..97b2c8ed8e 100644 --- a/hw/mips/fuloong2e.c +++ b/hw/mips/fuloong2e.c @@ -30,7 +30,6 @@ #include "hw/block/flash.h" #include "hw/mips/mips.h" #include "hw/mips/bootloader.h" -#include "hw/mips/cpudevs.h" #include "hw/pci/pci.h" #include "hw/loader.h" #include "hw/ide/pci.h" diff --git a/hw/mips/jazz.c b/hw/mips/jazz.c index c32d2b0b0a..d33a76ad4d 100644 --- a/hw/mips/jazz.c +++ b/hw/mips/jazz.c @@ -26,7 +26,6 @@ #include "qemu/datadir.h" #include "hw/clock.h" #include "hw/mips/mips.h" -#include "hw/mips/cpudevs.h" #include "hw/intc/i8259.h" #include "hw/dma/i8257.h" #include "hw/char/serial.h" @@ -177,6 +176,7 @@ static void mips_jazz_init(MachineState *machine, SysBusDevice *sysbus; ISABus *isa_bus; ISADevice *pit; + ISADevice *pcspk; DriveInfo *fds[MAX_FD]; MemoryRegion *bios = g_new(MemoryRegion, 1); MemoryRegion *bios2 = g_new(MemoryRegion, 1); @@ -279,7 +279,9 @@ static void mips_jazz_init(MachineState *machine, isa_bus_register_input_irqs(isa_bus, i8259); i8257_dma_init(isa_bus, 0); pit = i8254_pit_init(isa_bus, 0x40, 0, NULL); - pcspk_init(isa_new(TYPE_PC_SPEAKER), isa_bus, pit); + pcspk = isa_new(TYPE_PC_SPEAKER); + object_property_set_link(OBJECT(pcspk), "pit", OBJECT(pit), &error_fatal); + isa_realize_and_unref(pcspk, isa_bus, &error_fatal); /* Video card */ switch (jazz_model) { diff --git a/hw/mips/loongson3_virt.c b/hw/mips/loongson3_virt.c index b74b358874..33eae01eca 100644 --- a/hw/mips/loongson3_virt.c +++ b/hw/mips/loongson3_virt.c @@ -32,7 +32,6 @@ #include "hw/char/serial.h" #include "hw/intc/loongson_liointc.h" #include "hw/mips/mips.h" -#include "hw/mips/cpudevs.h" #include "hw/mips/fw_cfg.h" #include "hw/mips/loongson3_bootp.h" #include "hw/misc/unimp.h" diff --git a/hw/mips/malta.c b/hw/mips/malta.c index dac27fad9d..4fa5b33fd9 100644 --- a/hw/mips/malta.c +++ b/hw/mips/malta.c @@ -37,7 +37,6 @@ #include "hw/block/flash.h" #include "hw/mips/mips.h" #include "hw/mips/bootloader.h" -#include "hw/mips/cpudevs.h" #include "hw/pci/pci.h" #include "hw/pci/pci_bus.h" #include "qemu/log.h" @@ -206,7 +205,7 @@ static eeprom24c0x_t spd_eeprom = { static void generate_eeprom_spd(uint8_t *eeprom, ram_addr_t ram_size) { - enum { SDR = 0x4, DDR2 = 0x8 } type; + enum sdram_type type; uint8_t *spd = spd_eeprom.contents; uint8_t nbanks = 0; uint16_t density = 0; diff --git a/hw/mips/mips_int.c b/hw/mips/mips_int.c index 73437cd90f..6c32e466a3 100644 --- a/hw/mips/mips_int.c +++ b/hw/mips/mips_int.c @@ -23,7 +23,6 @@ #include "qemu/osdep.h" #include "qemu/main-loop.h" #include "hw/irq.h" -#include "hw/mips/cpudevs.h" #include "sysemu/kvm.h" #include "kvm_mips.h" diff --git a/hw/mips/mipssim.c b/hw/mips/mipssim.c index 2f951f7fc6..4f743f37eb 100644 --- a/hw/mips/mipssim.c +++ b/hw/mips/mipssim.c @@ -30,7 +30,6 @@ #include "qemu/datadir.h" #include "hw/clock.h" #include "hw/mips/mips.h" -#include "hw/mips/cpudevs.h" #include "hw/char/serial.h" #include "hw/isa/isa.h" #include "net/net.h" diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index 858277bb60..dba41afe67 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -34,6 +34,11 @@ config PCA9552 bool depends on I2C +config I2C_ECHO + bool + default y if TEST_DEVICES + depends on I2C + config PL310 bool diff --git a/hw/misc/allwinner-r40-dramc.c b/hw/misc/allwinner-r40-dramc.c index 6944f84455..3d81ddb2e1 100644 --- a/hw/misc/allwinner-r40-dramc.c +++ b/hw/misc/allwinner-r40-dramc.c @@ -421,19 +421,23 @@ static void allwinner_r40_dramc_realize(DeviceState *dev, Error **errp) exit(1); } - /* detect_cells */ - sysbus_mmio_map_overlap(SYS_BUS_DEVICE(s), 3, s->ram_addr, 10); + /* R40 support max 2G memory but we only support up to 1G now. */ + memory_region_init_io(&s->detect_cells, OBJECT(s), + &allwinner_r40_detect_ops, s, + "DRAMCELLS", 1 * GiB); + memory_region_add_subregion_overlap(get_system_memory(), s->ram_addr, + &s->detect_cells, 10); memory_region_set_enabled(&s->detect_cells, false); /* * We only support DRAM size up to 1G now, so prepare a high memory page - * after 1G for dualrank detect. index = 4 + * after 1G for dualrank detect. */ memory_region_init_io(&s->dram_high, OBJECT(s), &allwinner_r40_dualrank_detect_ops, s, "DRAMHIGH", KiB); - sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->dram_high); - sysbus_mmio_map(SYS_BUS_DEVICE(s), 4, s->ram_addr + GiB); + memory_region_add_subregion(get_system_memory(), s->ram_addr + GiB, + &s->dram_high); } static void allwinner_r40_dramc_init(Object *obj) @@ -458,12 +462,6 @@ static void allwinner_r40_dramc_init(Object *obj) &allwinner_r40_dramphy_ops, s, "DRAMPHY", 4 * KiB); sysbus_init_mmio(sbd, &s->dramphy_iomem); - - /* R40 support max 2G memory but we only support up to 1G now. index 3 */ - memory_region_init_io(&s->detect_cells, OBJECT(s), - &allwinner_r40_detect_ops, s, - "DRAMCELLS", 1 * GiB); - sysbus_init_mmio(sbd, &s->detect_cells); } static Property allwinner_r40_dramc_properties[] = { diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index 4ed9faa54a..ff55a4e2cd 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -12,7 +12,7 @@ #include "migration/vmstate.h" #include "hw/irq.h" #include "hw/misc/bcm2835_mbox_defs.h" -#include "hw/misc/raspberrypi-fw-defs.h" +#include "hw/arm/raspberrypi-fw-defs.h" #include "sysemu/dma.h" #include "qemu/log.h" #include "qemu/module.h" diff --git a/hw/misc/i2c-echo.c b/hw/misc/i2c-echo.c index 5705ab5d73..5ae3d0817e 100644 --- a/hw/misc/i2c-echo.c +++ b/hw/misc/i2c-echo.c @@ -1,3 +1,13 @@ +/* + * Example I2C device using asynchronous I2C send. + * + * Copyright (C) 2023 Samsung Electronics Co., Ltd. All Rights Reserved. + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + #include "qemu/osdep.h" #include "qemu/timer.h" #include "qemu/main-loop.h" diff --git a/hw/misc/meson.build b/hw/misc/meson.build index 33659313b4..f60de33f9a 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -138,7 +138,7 @@ system_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('nrf51_rng.c')) system_ss.add(when: 'CONFIG_GRLIB', if_true: files('grlib_ahb_apb_pnp.c')) -system_ss.add(when: 'CONFIG_I2C', if_true: files('i2c-echo.c')) +system_ss.add(when: 'CONFIG_I2C_ECHO', if_true: files('i2c-echo.c')) specific_ss.add(when: 'CONFIG_AVR_POWER', if_true: files('avr_power.c')) diff --git a/hw/misc/mips_itu.c b/hw/misc/mips_itu.c index 0eda302db4..5a83ccc4e8 100644 --- a/hw/misc/mips_itu.c +++ b/hw/misc/mips_itu.c @@ -532,7 +532,7 @@ static void mips_itu_realize(DeviceState *dev, Error **errp) return; } - env = &s->cpu0->env; + env = &MIPS_CPU(s->cpu0)->env; if (env->saarp) { s->saar = env->CP0_SAAR; } @@ -563,7 +563,7 @@ static Property mips_itu_properties[] = { ITC_FIFO_NUM_MAX), DEFINE_PROP_UINT32("num-semaphores", MIPSITUState, num_semaphores, ITC_SEMAPH_NUM_MAX), - DEFINE_PROP_LINK("cpu[0]", MIPSITUState, cpu0, TYPE_MIPS_CPU, MIPSCPU *), + DEFINE_PROP_LINK("cpu[0]", MIPSITUState, cpu0, TYPE_MIPS_CPU, ArchCPU *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index f445d8bb5e..37e209cda6 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -1654,11 +1654,6 @@ static void gem_init(Object *obj) "enet", sizeof(s->regs)); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); - - object_property_add_link(obj, "dma", TYPE_MEMORY_REGION, - (Object **)&s->dma_mr, - qdev_prop_allow_set_link_before_realize, - OBJ_PROP_LINK_STRONG); } static const VMStateDescription vmstate_cadence_gem = { @@ -1691,6 +1686,8 @@ static Property gem_properties[] = { num_type2_screeners, 4), DEFINE_PROP_UINT16("jumbo-max-len", CadenceGEMState, jumbo_max_len, 10240), + DEFINE_PROP_LINK("dma", CadenceGEMState, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/nvram/xlnx-bbram.c b/hw/nvram/xlnx-bbram.c index c6b484cc85..e18e7770e1 100644 --- a/hw/nvram/xlnx-bbram.c +++ b/hw/nvram/xlnx-bbram.c @@ -2,6 +2,7 @@ * QEMU model of the Xilinx BBRAM Battery Backed RAM * * Copyright (c) 2014-2021 Xilinx Inc. + * Copyright (c) 2023 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -416,9 +417,9 @@ static RegisterAccessInfo bbram_ctrl_regs_info[] = { } }; -static void bbram_ctrl_reset(DeviceState *dev) +static void bbram_ctrl_reset_hold(Object *obj) { - XlnxBBRam *s = XLNX_BBRAM(dev); + XlnxBBRam *s = XLNX_BBRAM(obj); unsigned int i; for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { @@ -522,8 +523,9 @@ static Property bbram_ctrl_props[] = { static void bbram_ctrl_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); - dc->reset = bbram_ctrl_reset; + rc->phases.hold = bbram_ctrl_reset_hold; dc->realize = bbram_ctrl_realize; dc->vmsd = &vmstate_bbram_ctrl; device_class_set_props(dc, bbram_ctrl_props); diff --git a/hw/nvram/xlnx-versal-efuse-ctrl.c b/hw/nvram/xlnx-versal-efuse-ctrl.c index b35ba65ab5..beb5661c35 100644 --- a/hw/nvram/xlnx-versal-efuse-ctrl.c +++ b/hw/nvram/xlnx-versal-efuse-ctrl.c @@ -2,6 +2,7 @@ * QEMU model of the Versal eFuse controller * * Copyright (c) 2020 Xilinx Inc. + * Copyright (c) 2023 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -657,9 +658,9 @@ static void efuse_ctrl_register_reset(RegisterInfo *reg) register_reset(reg); } -static void efuse_ctrl_reset(DeviceState *dev) +static void efuse_ctrl_reset_hold(Object *obj) { - XlnxVersalEFuseCtrl *s = XLNX_VERSAL_EFUSE_CTRL(dev); + XlnxVersalEFuseCtrl *s = XLNX_VERSAL_EFUSE_CTRL(obj); unsigned int i; for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { @@ -749,8 +750,9 @@ static Property efuse_ctrl_props[] = { static void efuse_ctrl_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); - dc->reset = efuse_ctrl_reset; + rc->phases.hold = efuse_ctrl_reset_hold; dc->realize = efuse_ctrl_realize; dc->vmsd = &vmstate_efuse_ctrl; device_class_set_props(dc, efuse_ctrl_props); diff --git a/hw/nvram/xlnx-zynqmp-efuse.c b/hw/nvram/xlnx-zynqmp-efuse.c index 228ba0bbfa..3db5f98ec1 100644 --- a/hw/nvram/xlnx-zynqmp-efuse.c +++ b/hw/nvram/xlnx-zynqmp-efuse.c @@ -2,6 +2,7 @@ * QEMU model of the ZynqMP eFuse * * Copyright (c) 2015 Xilinx Inc. + * Copyright (c) 2023 Advanced Micro Devices, Inc. * * Written by Edgar E. Iglesias <edgari@xilinx.com> * @@ -769,9 +770,9 @@ static void zynqmp_efuse_register_reset(RegisterInfo *reg) register_reset(reg); } -static void zynqmp_efuse_reset(DeviceState *dev) +static void zynqmp_efuse_reset_hold(Object *obj) { - XlnxZynqMPEFuse *s = XLNX_ZYNQMP_EFUSE(dev); + XlnxZynqMPEFuse *s = XLNX_ZYNQMP_EFUSE(obj); unsigned int i; for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { @@ -837,8 +838,9 @@ static Property zynqmp_efuse_props[] = { static void zynqmp_efuse_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); - dc->reset = zynqmp_efuse_reset; + rc->phases.hold = zynqmp_efuse_reset_hold; dc->realize = zynqmp_efuse_realize; dc->vmsd = &vmstate_efuse; device_class_set_props(dc, zynqmp_efuse_props); diff --git a/hw/pci-host/bonito.c b/hw/pci-host/bonito.c index ee6cb85e97..bab661f3ce 100644 --- a/hw/pci-host/bonito.c +++ b/hw/pci-host/bonito.c @@ -654,7 +654,7 @@ static void bonito_host_realize(DeviceState *dev, Error **errp) static void bonito_pci_realize(PCIDevice *dev, Error **errp) { PCIBonitoState *s = PCI_BONITO(dev); - SysBusDevice *sysbus = SYS_BUS_DEVICE(s->pcihost); + MemoryRegion *host_mem = get_system_memory(); PCIHostState *phb = PCI_HOST_BRIDGE(s->pcihost); BonitoState *bs = s->pcihost; MemoryRegion *pcimem_alias = g_new(MemoryRegion, 1); @@ -668,48 +668,45 @@ static void bonito_pci_realize(PCIDevice *dev, Error **errp) /* set the north bridge register mapping */ memory_region_init_io(&s->iomem, OBJECT(s), &bonito_ops, s, "north-bridge-register", BONITO_INTERNAL_REG_SIZE); - sysbus_init_mmio(sysbus, &s->iomem); - sysbus_mmio_map(sysbus, 0, BONITO_INTERNAL_REG_BASE); + memory_region_add_subregion(host_mem, BONITO_INTERNAL_REG_BASE, &s->iomem); /* set the north bridge pci configure mapping */ memory_region_init_io(&phb->conf_mem, OBJECT(s), &bonito_pciconf_ops, s, "north-bridge-pci-config", BONITO_PCICONFIG_SIZE); - sysbus_init_mmio(sysbus, &phb->conf_mem); - sysbus_mmio_map(sysbus, 1, BONITO_PCICONFIG_BASE); + memory_region_add_subregion(host_mem, BONITO_PCICONFIG_BASE, + &phb->conf_mem); /* set the south bridge pci configure mapping */ memory_region_init_io(&phb->data_mem, OBJECT(s), &bonito_spciconf_ops, s, "south-bridge-pci-config", BONITO_SPCICONFIG_SIZE); - sysbus_init_mmio(sysbus, &phb->data_mem); - sysbus_mmio_map(sysbus, 2, BONITO_SPCICONFIG_BASE); + memory_region_add_subregion(host_mem, BONITO_SPCICONFIG_BASE, + &phb->data_mem); create_unimplemented_device("bonito", BONITO_REG_BASE, BONITO_REG_SIZE); memory_region_init_io(&s->iomem_ldma, OBJECT(s), &bonito_ldma_ops, s, "ldma", 0x100); - sysbus_init_mmio(sysbus, &s->iomem_ldma); - sysbus_mmio_map(sysbus, 3, 0x1fe00200); + memory_region_add_subregion(host_mem, 0x1fe00200, &s->iomem_ldma); /* PCI copier */ memory_region_init_io(&s->iomem_cop, OBJECT(s), &bonito_cop_ops, s, "cop", 0x100); - sysbus_init_mmio(sysbus, &s->iomem_cop); - sysbus_mmio_map(sysbus, 4, 0x1fe00300); + memory_region_add_subregion(host_mem, 0x1fe00300, &s->iomem_cop); create_unimplemented_device("ROMCS", BONITO_FLASH_BASE, 60 * MiB); /* Map PCI IO Space 0x1fd0 0000 - 0x1fd1 0000 */ memory_region_init_alias(&s->bonito_pciio, OBJECT(s), "isa_mmio", get_system_io(), 0, BONITO_PCIIO_SIZE); - sysbus_init_mmio(sysbus, &s->bonito_pciio); - sysbus_mmio_map(sysbus, 5, BONITO_PCIIO_BASE); + memory_region_add_subregion(host_mem, BONITO_PCIIO_BASE, + &s->bonito_pciio); /* add pci local io mapping */ memory_region_init_alias(&s->bonito_localio, OBJECT(s), "IOCS[0]", get_system_io(), 0, 256 * KiB); - sysbus_init_mmio(sysbus, &s->bonito_localio); - sysbus_mmio_map(sysbus, 6, BONITO_DEV_BASE); + memory_region_add_subregion(host_mem, BONITO_DEV_BASE, + &s->bonito_localio); create_unimplemented_device("IOCS[1]", BONITO_DEV_BASE + 1 * 256 * KiB, 256 * KiB); create_unimplemented_device("IOCS[2]", BONITO_DEV_BASE + 2 * 256 * KiB, @@ -719,8 +716,7 @@ static void bonito_pci_realize(PCIDevice *dev, Error **errp) memory_region_init_alias(pcimem_alias, NULL, "pci.mem.alias", &bs->pci_mem, 0, BONITO_PCIHI_SIZE); - memory_region_add_subregion(get_system_memory(), - BONITO_PCIHI_BASE, pcimem_alias); + memory_region_add_subregion(host_mem, BONITO_PCIHI_BASE, pcimem_alias); create_unimplemented_device("PCI_2", (hwaddr)BONITO_PCIHI_BASE + BONITO_PCIHI_SIZE, 2 * GiB); diff --git a/hw/pci-host/sh_pci.c b/hw/pci-host/sh_pci.c index 77e7bbc65f..4edebced5e 100644 --- a/hw/pci-host/sh_pci.c +++ b/hw/pci-host/sh_pci.c @@ -40,7 +40,7 @@ struct SHPCIState { PCIHostState parent_obj; PCIDevice *dev; - qemu_irq irq[4]; + qemu_irq irq[PCI_NUM_PINS]; MemoryRegion memconfig_p4; MemoryRegion memconfig_a7; MemoryRegion isa; @@ -116,7 +116,7 @@ static void sh_pci_set_irq(void *opaque, int irq_num, int level) qemu_set_irq(pic[irq_num], level); } -static void sh_pci_device_realize(DeviceState *dev, Error **errp) +static void sh_pcic_host_realize(DeviceState *dev, Error **errp) { SysBusDevice *sbd = SYS_BUS_DEVICE(dev); SHPCIState *s = SH_PCI_HOST_BRIDGE(dev); @@ -131,7 +131,8 @@ static void sh_pci_device_realize(DeviceState *dev, Error **errp) s->irq, get_system_memory(), get_system_io(), - PCI_DEVFN(0, 0), 4, TYPE_PCI_BUS); + PCI_DEVFN(0, 0), PCI_NUM_PINS, + TYPE_PCI_BUS); memory_region_init_io(&s->memconfig_p4, OBJECT(s), &sh_pci_reg_ops, s, "sh_pci", 0x224); memory_region_init_alias(&s->memconfig_a7, OBJECT(s), "sh_pci.2", @@ -145,19 +146,19 @@ static void sh_pci_device_realize(DeviceState *dev, Error **errp) s->dev = pci_create_simple(phb->bus, PCI_DEVFN(0, 0), "sh_pci_host"); } -static void sh_pci_host_realize(PCIDevice *d, Error **errp) +static void sh_pcic_pci_realize(PCIDevice *d, Error **errp) { pci_set_word(d->config + PCI_COMMAND, PCI_COMMAND_WAIT); pci_set_word(d->config + PCI_STATUS, PCI_STATUS_CAP_LIST | PCI_STATUS_FAST_BACK | PCI_STATUS_DEVSEL_MEDIUM); } -static void sh_pci_host_class_init(ObjectClass *klass, void *data) +static void sh_pcic_pci_class_init(ObjectClass *klass, void *data) { PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); DeviceClass *dc = DEVICE_CLASS(klass); - k->realize = sh_pci_host_realize; + k->realize = sh_pcic_pci_realize; k->vendor_id = PCI_VENDOR_ID_HITACHI; k->device_id = PCI_DEVICE_ID_HITACHI_SH7751R; /* @@ -167,35 +168,29 @@ static void sh_pci_host_class_init(ObjectClass *klass, void *data) dc->user_creatable = false; } -static const TypeInfo sh_pci_host_info = { - .name = "sh_pci_host", - .parent = TYPE_PCI_DEVICE, - .instance_size = sizeof(PCIDevice), - .class_init = sh_pci_host_class_init, - .interfaces = (InterfaceInfo[]) { - { INTERFACE_CONVENTIONAL_PCI_DEVICE }, - { }, - }, -}; - -static void sh_pci_device_class_init(ObjectClass *klass, void *data) +static void sh_pcic_host_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); - dc->realize = sh_pci_device_realize; + dc->realize = sh_pcic_host_realize; } -static const TypeInfo sh_pci_device_info = { - .name = TYPE_SH_PCI_HOST_BRIDGE, - .parent = TYPE_PCI_HOST_BRIDGE, - .instance_size = sizeof(SHPCIState), - .class_init = sh_pci_device_class_init, +static const TypeInfo sh_pcic_types[] = { + { + .name = TYPE_SH_PCI_HOST_BRIDGE, + .parent = TYPE_PCI_HOST_BRIDGE, + .instance_size = sizeof(SHPCIState), + .class_init = sh_pcic_host_class_init, + }, { + .name = "sh_pci_host", + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(PCIDevice), + .class_init = sh_pcic_pci_class_init, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, + }, }; -static void sh_pci_register_types(void) -{ - type_register_static(&sh_pci_device_info); - type_register_static(&sh_pci_host_info); -} - -type_init(sh_pci_register_types) +DEFINE_TYPES(sh_pcic_types) diff --git a/hw/pci/pci.c b/hw/pci/pci.c index b0d21bf43a..7d09e1a39d 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -500,15 +500,14 @@ bool pci_bus_bypass_iommu(PCIBus *bus) } static void pci_root_bus_internal_init(PCIBus *bus, DeviceState *parent, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min) { assert(PCI_FUNC(devfn_min) == 0); bus->devfn_min = devfn_min; bus->slot_reserved_mask = 0x0; - bus->address_space_mem = address_space_mem; - bus->address_space_io = address_space_io; + bus->address_space_mem = mem; + bus->address_space_io = io; bus->flags |= PCI_BUS_IS_ROOT; /* host bridge */ @@ -529,25 +528,21 @@ bool pci_bus_is_express(const PCIBus *bus) void pci_root_bus_init(PCIBus *bus, size_t bus_size, DeviceState *parent, const char *name, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, const char *typename) { qbus_init(bus, bus_size, typename, parent, name); - pci_root_bus_internal_init(bus, parent, address_space_mem, - address_space_io, devfn_min); + pci_root_bus_internal_init(bus, parent, mem, io, devfn_min); } PCIBus *pci_root_bus_new(DeviceState *parent, const char *name, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, const char *typename) { PCIBus *bus; bus = PCI_BUS(qbus_new(typename, parent, name)); - pci_root_bus_internal_init(bus, parent, address_space_mem, - address_space_io, devfn_min); + pci_root_bus_internal_init(bus, parent, mem, io, devfn_min); return bus; } @@ -586,15 +581,13 @@ void pci_bus_irqs_cleanup(PCIBus *bus) PCIBus *pci_register_root_bus(DeviceState *parent, const char *name, pci_set_irq_fn set_irq, pci_map_irq_fn map_irq, void *irq_opaque, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, int nirq, const char *typename) { PCIBus *bus; - bus = pci_root_bus_new(parent, name, address_space_mem, - address_space_io, devfn_min, typename); + bus = pci_root_bus_new(parent, name, mem, io, devfn_min, typename); pci_bus_irqs(bus, set_irq, irq_opaque, nirq); pci_bus_map_irqs(bus, map_irq); return bus; diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index eb54f93986..c0e34fffbc 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -1217,10 +1217,9 @@ static void pnv_chip_icp_realize(Pnv8Chip *chip8, Error **errp) name = g_strdup_printf("icp-%x", chip->chip_id); memory_region_init(&chip8->icp_mmio, OBJECT(chip), name, PNV_ICP_SIZE); - sysbus_init_mmio(SYS_BUS_DEVICE(chip), &chip8->icp_mmio); g_free(name); - - sysbus_mmio_map(SYS_BUS_DEVICE(chip), 1, PNV_ICP_BASE(chip)); + memory_region_add_subregion(get_system_memory(), PNV_ICP_BASE(chip), + &chip8->icp_mmio); /* Map the ICP registers for each thread */ for (i = 0; i < chip->nr_cores; i++) { @@ -1249,12 +1248,7 @@ static void pnv_chip_power8_realize(DeviceState *dev, Error **errp) assert(chip8->xics); /* XSCOM bridge is first */ - pnv_xscom_realize(chip, PNV_XSCOM_SIZE, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - sysbus_mmio_map(SYS_BUS_DEVICE(chip), 0, PNV_XSCOM_BASE(chip)); + pnv_xscom_init(chip, PNV_XSCOM_SIZE, PNV_XSCOM_BASE(chip)); pcc->parent_realize(dev, &local_err); if (local_err) { @@ -1512,12 +1506,7 @@ static void pnv_chip_power9_realize(DeviceState *dev, Error **errp) Error *local_err = NULL; /* XSCOM bridge is first */ - pnv_xscom_realize(chip, PNV9_XSCOM_SIZE, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - sysbus_mmio_map(SYS_BUS_DEVICE(chip), 0, PNV9_XSCOM_BASE(chip)); + pnv_xscom_init(chip, PNV9_XSCOM_SIZE, PNV9_XSCOM_BASE(chip)); pcc->parent_realize(dev, &local_err); if (local_err) { @@ -1727,12 +1716,7 @@ static void pnv_chip_power10_realize(DeviceState *dev, Error **errp) Error *local_err = NULL; /* XSCOM bridge is first */ - pnv_xscom_realize(chip, PNV10_XSCOM_SIZE, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - sysbus_mmio_map(SYS_BUS_DEVICE(chip), 0, PNV10_XSCOM_BASE(chip)); + pnv_xscom_init(chip, PNV10_XSCOM_SIZE, PNV10_XSCOM_BASE(chip)); pcc->parent_realize(dev, &local_err); if (local_err) { diff --git a/hw/ppc/pnv_xscom.c b/hw/ppc/pnv_xscom.c index d820e05e40..805b1d0c87 100644 --- a/hw/ppc/pnv_xscom.c +++ b/hw/ppc/pnv_xscom.c @@ -221,15 +221,14 @@ const MemoryRegionOps pnv_xscom_ops = { .endianness = DEVICE_BIG_ENDIAN, }; -void pnv_xscom_realize(PnvChip *chip, uint64_t size, Error **errp) +void pnv_xscom_init(PnvChip *chip, uint64_t size, hwaddr addr) { - SysBusDevice *sbd = SYS_BUS_DEVICE(chip); char *name; name = g_strdup_printf("xscom-%x", chip->chip_id); memory_region_init_io(&chip->xscom_mmio, OBJECT(chip), &pnv_xscom_ops, chip, name, size); - sysbus_init_mmio(sbd, &chip->xscom_mmio); + memory_region_add_subregion(get_system_memory(), addr, &chip->xscom_mmio); memory_region_init(&chip->xscom, OBJECT(chip), name, size); address_space_init(&chip->xscom_as, &chip->xscom, name); diff --git a/hw/ppc/spapr_vio.c b/hw/ppc/spapr_vio.c index 9d4fec2c04..f8ef2b6fa8 100644 --- a/hw/ppc/spapr_vio.c +++ b/hw/ppc/spapr_vio.c @@ -574,13 +574,14 @@ SpaprVioBus *spapr_vio_bus_init(void) /* Create bridge device */ dev = qdev_new(TYPE_SPAPR_VIO_BRIDGE); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); /* Create bus on bridge device */ qbus = qbus_new(TYPE_SPAPR_VIO_BUS, dev, "spapr-vio"); bus = SPAPR_VIO_BUS(qbus); bus->next_reg = SPAPR_VIO_REG_BASE; + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + /* hcall-vio */ spapr_register_hypercall(H_VIO_SIGNAL, h_vio_signal); diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c index 4fc6712025..e735ff97eb 100644 --- a/hw/rdma/vmw/pvrdma_main.c +++ b/hw/rdma/vmw/pvrdma_main.c @@ -91,19 +91,33 @@ static int init_dev_ring(PvrdmaRing *ring, PvrdmaRingState **ring_state, dma_addr_t dir_addr, uint32_t num_pages) { uint64_t *dir, *tbl; - int rc = 0; + int max_pages, rc = 0; if (!num_pages) { rdma_error_report("Ring pages count must be strictly positive"); return -EINVAL; } + /* + * Make sure we can satisfy the requested number of pages in a single + * TARGET_PAGE_SIZE sized page table (taking into account that first entry + * is reserved for ring-state) + */ + max_pages = TARGET_PAGE_SIZE / sizeof(dma_addr_t) - 1; + if (num_pages > max_pages) { + rdma_error_report("Maximum pages on a single directory must not exceed %d\n", + max_pages); + return -EINVAL; + } + dir = rdma_pci_dma_map(pci_dev, dir_addr, TARGET_PAGE_SIZE); if (!dir) { rdma_error_report("Failed to map to page directory (ring %s)", name); rc = -ENOMEM; goto out; } + + /* We support only one page table for a ring */ tbl = rdma_pci_dma_map(pci_dev, dir[0], TARGET_PAGE_SIZE); if (!tbl) { rdma_error_report("Failed to map to page table (ring %s)", name); @@ -601,6 +615,8 @@ static void pvrdma_realize(PCIDevice *pdev, Error **errp) bool ram_shared = false; PCIDevice *func0; + warn_report_once("pvrdma is deprecated and will be removed in a future release"); + rdma_info_report("Initializing device %s %x.%x", pdev->name, PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); diff --git a/hw/remote/meson.build b/hw/remote/meson.build index a1e8708c73..a3aa29aaf1 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -7,9 +7,11 @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iommu.c')) -remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: files('vfio-user-obj.c')) remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: libvfio_user_dep) +remote_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_true: files('vfio-user-obj.c'), + if_false: files('vfio-user-obj-stub.c')) +remote_ss.add(when: 'CONFIG_ALL', if_true: files('vfio-user-obj-stub.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) diff --git a/stubs/vfio-user-obj.c b/hw/remote/vfio-user-obj-stub.c index 79100d768e..79100d768e 100644 --- a/stubs/vfio-user-obj.c +++ b/hw/remote/vfio-user-obj-stub.c diff --git a/hw/s390x/css-bridge.c b/hw/s390x/css-bridge.c index 4017081d49..15d26efc95 100644 --- a/hw/s390x/css-bridge.c +++ b/hw/s390x/css-bridge.c @@ -95,7 +95,6 @@ static const TypeInfo virtual_css_bus_info = { VirtualCssBus *virtual_css_bus_init(void) { - VirtualCssBus *cbus; BusState *bus; DeviceState *dev; @@ -103,19 +102,19 @@ VirtualCssBus *virtual_css_bus_init(void) dev = qdev_new(TYPE_VIRTUAL_CSS_BRIDGE); object_property_add_child(qdev_get_machine(), TYPE_VIRTUAL_CSS_BRIDGE, OBJECT(dev)); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); /* Create bus on bridge device */ bus = qbus_new(TYPE_VIRTUAL_CSS_BUS, dev, "virtual-css"); - cbus = VIRTUAL_CSS_BUS(bus); /* Enable hotplugging */ qbus_set_hotplug_handler(bus, OBJECT(dev)); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + css_register_io_adapters(CSS_IO_ADAPTER_VIRTIO, true, false, 0, &error_abort); - return cbus; + return VIRTUAL_CSS_BUS(bus); } /***************** Virtual-css Bus Bridge Device ********************/ diff --git a/hw/s390x/sclpquiesce.c b/hw/s390x/sclpquiesce.c index ce07b16884..a641089929 100644 --- a/hw/s390x/sclpquiesce.c +++ b/hw/s390x/sclpquiesce.c @@ -78,12 +78,10 @@ static const VMStateDescription vmstate_sclpquiesce = { } }; -typedef struct QuiesceNotifier QuiesceNotifier; - -static struct QuiesceNotifier { +typedef struct QuiesceNotifier { Notifier notifier; SCLPEvent *event; -} qn; +} QuiesceNotifier; static void quiesce_powerdown_req(Notifier *n, void *opaque) { @@ -97,6 +95,8 @@ static void quiesce_powerdown_req(Notifier *n, void *opaque) static int quiesce_init(SCLPEvent *event) { + static QuiesceNotifier qn; + qn.notifier.notify = quiesce_powerdown_req; qn.event = event; diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 45b95ea070..fa53f0902c 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -761,7 +761,7 @@ static void virtio_scsi_fail_cmd_req(VirtIOSCSIReq *req) static int virtio_scsi_handle_cmd_req_prepare(VirtIOSCSI *s, VirtIOSCSIReq *req) { - VirtIOSCSICommon *vs = &s->parent_obj; + VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s); SCSIDevice *d; int rc; diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c index 5564765a9b..40473b0db0 100644 --- a/hw/sd/sdhci.c +++ b/hw/sd/sdhci.c @@ -321,6 +321,8 @@ static void sdhci_poweron_reset(DeviceState *dev) static void sdhci_data_transfer(void *opaque); +#define BLOCK_SIZE_MASK (4 * KiB - 1) + static void sdhci_send_command(SDHCIState *s) { SDRequest request; @@ -371,7 +373,8 @@ static void sdhci_send_command(SDHCIState *s) sdhci_update_irq(s); - if (!timeout && s->blksize && (s->cmdreg & SDHC_CMD_DATA_PRESENT)) { + if (!timeout && (s->blksize & BLOCK_SIZE_MASK) && + (s->cmdreg & SDHC_CMD_DATA_PRESENT)) { s->data_count = 0; sdhci_data_transfer(s); } @@ -406,7 +409,6 @@ static void sdhci_end_transfer(SDHCIState *s) /* * Programmed i/o data transfer */ -#define BLOCK_SIZE_MASK (4 * KiB - 1) /* Fill host controller's read buffer with BLKSIZE bytes of data from card */ static void sdhci_read_block_from_card(SDHCIState *s) @@ -1154,7 +1156,8 @@ sdhci_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) s->sdmasysad = (s->sdmasysad & mask) | value; MASKED_WRITE(s->sdmasysad, mask, value); /* Writing to last byte of sdmasysad might trigger transfer */ - if (!(mask & 0xFF000000) && s->blkcnt && s->blksize && + if (!(mask & 0xFF000000) && s->blkcnt && + (s->blksize & BLOCK_SIZE_MASK) && SDHC_DMA_TYPE(s->hostctl1) == SDHC_CTRL_SDMA) { if (s->trnmod & SDHC_TRNS_MULTI) { sdhci_sdma_transfer_multi_blocks(s); @@ -1168,7 +1171,11 @@ sdhci_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) if (!TRANSFERRING_DATA(s->prnsts)) { uint16_t blksize = s->blksize; - MASKED_WRITE(s->blksize, mask, extract32(value, 0, 12)); + /* + * [14:12] SDMA Buffer Boundary + * [11:00] Transfer Block Size + */ + MASKED_WRITE(s->blksize, mask, extract32(value, 0, 15)); MASKED_WRITE(s->blkcnt, mask >> 16, value >> 16); /* Limit block size to the maximum buffer size */ diff --git a/hw/sparc64/sun4u.c b/hw/sparc64/sun4u.c index d908a38f73..c871170378 100644 --- a/hw/sparc64/sun4u.c +++ b/hw/sparc64/sun4u.c @@ -360,11 +360,11 @@ static void ebus_realize(PCIDevice *pci_dev, Error **errp) pci_dev->config[0x09] = 0x00; // programming i/f pci_dev->config[0x0D] = 0x0a; // latency_timer - memory_region_init_alias(&s->bar0, OBJECT(s), "bar0", get_system_io(), - 0, 0x1000000); + memory_region_init_alias(&s->bar0, OBJECT(s), "bar0", + pci_address_space_io(pci_dev), 0, 0x1000000); pci_register_bar(pci_dev, 0, PCI_BASE_ADDRESS_SPACE_MEMORY, &s->bar0); - memory_region_init_alias(&s->bar1, OBJECT(s), "bar1", get_system_io(), - 0, 0x8000); + memory_region_init_alias(&s->bar1, OBJECT(s), "bar1", + pci_address_space_io(pci_dev), 0, 0x8000); pci_register_bar(pci_dev, 1, PCI_BASE_ADDRESS_SPACE_IO, &s->bar1); } diff --git a/hw/timer/npcm7xx_timer.c b/hw/timer/npcm7xx_timer.c index 32f5e021f8..a8bd93aeb2 100644 --- a/hw/timer/npcm7xx_timer.c +++ b/hw/timer/npcm7xx_timer.c @@ -138,6 +138,9 @@ static int64_t npcm7xx_timer_count_to_ns(NPCM7xxTimer *t, uint32_t count) /* Convert a time interval in nanoseconds to a timer cycle count. */ static uint32_t npcm7xx_timer_ns_to_count(NPCM7xxTimer *t, int64_t ns) { + if (ns < 0) { + return 0; + } return clock_ns_to_ticks(t->ctrl->clock, ns) / npcm7xx_tcsr_prescaler(t->tcsr); } diff --git a/hw/ufs/lu.c b/hw/ufs/lu.c index e1c46bddb1..13b5e37b53 100644 --- a/hw/ufs/lu.c +++ b/hw/ufs/lu.c @@ -1345,13 +1345,12 @@ static void ufs_lu_realize(SCSIDevice *dev, Error **errp) return; } - if (lu->qdev.conf.blk) { - ctx = blk_get_aio_context(lu->qdev.conf.blk); - aio_context_acquire(ctx); - if (!blkconf_blocksizes(&lu->qdev.conf, errp)) { - goto out; - } + ctx = blk_get_aio_context(lu->qdev.conf.blk); + aio_context_acquire(ctx); + if (!blkconf_blocksizes(&lu->qdev.conf, errp)) { + goto out; } + lu->qdev.blocksize = UFS_BLOCK_SIZE; blk_get_geometry(lu->qdev.conf.blk, &nb_sectors); nb_blocks = nb_sectors / (lu->qdev.blocksize / BDRV_SECTOR_SIZE); @@ -1367,10 +1366,9 @@ static void ufs_lu_realize(SCSIDevice *dev, Error **errp) } ufs_lu_brdv_init(lu, errp); + out: - if (ctx) { - aio_context_release(ctx); - } + aio_context_release(ctx); } static void ufs_lu_unrealize(SCSIDevice *dev) diff --git a/hw/ufs/ufs.c b/hw/ufs/ufs.c index 0ecedb9aed..2e6d582cc3 100644 --- a/hw/ufs/ufs.c +++ b/hw/ufs/ufs.c @@ -258,7 +258,7 @@ static void ufs_irq_check(UfsHc *u) static void ufs_process_db(UfsHc *u, uint32_t val) { - unsigned long doorbell; + DECLARE_BITMAP(doorbell, UFS_MAX_NUTRS); uint32_t slot; uint32_t nutrs = u->params.nutrs; UfsRequest *req; @@ -268,8 +268,8 @@ static void ufs_process_db(UfsHc *u, uint32_t val) return; } - doorbell = val; - slot = find_first_bit(&doorbell, nutrs); + doorbell[0] = val; + slot = find_first_bit(doorbell, nutrs); while (slot < nutrs) { req = &u->req_list[slot]; @@ -285,7 +285,7 @@ static void ufs_process_db(UfsHc *u, uint32_t val) trace_ufs_process_db(slot); req->state = UFS_REQUEST_READY; - slot = find_next_bit(&doorbell, nutrs, slot + 1); + slot = find_next_bit(doorbell, nutrs, slot + 1); } qemu_bh_schedule(u->doorbell_bh); @@ -838,7 +838,7 @@ static QueryRespCode ufs_read_unit_desc(UfsRequest *req) uint8_t lun = req->req_upiu.qr.index; if (lun != UFS_UPIU_RPMB_WLUN && - (lun > UFS_MAX_LUS || u->lus[lun] == NULL)) { + (lun >= UFS_MAX_LUS || u->lus[lun] == NULL)) { trace_ufs_err_query_invalid_index(req->req_upiu.qr.opcode, lun); return UFS_QUERY_RESULT_INVALID_INDEX; } diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 6e21d1da5a..5f257bffb9 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -53,40 +53,6 @@ struct VFIODeviceOps vfio_ap_ops = { .vfio_compute_needs_reset = vfio_ap_compute_needs_reset, }; -static void vfio_ap_put_device(VFIOAPDevice *vapdev) -{ - g_free(vapdev->vdev.name); - vfio_put_base_device(&vapdev->vdev); -} - -static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp) -{ - GError *gerror = NULL; - char *symlink, *group_path; - int groupid; - - symlink = g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev); - group_path = g_file_read_link(symlink, &gerror); - g_free(symlink); - - if (!group_path) { - error_setg(errp, "%s: no iommu_group found for %s: %s", - TYPE_VFIO_AP_DEVICE, vapdev->vdev.sysfsdev, gerror->message); - g_error_free(gerror); - return NULL; - } - - if (sscanf(basename(group_path), "%d", &groupid) != 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - g_free(group_path); - return NULL; - } - - g_free(group_path); - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ap_req_notifier_handler(void *opaque) { VFIOAPDevice *vapdev = opaque; @@ -189,22 +155,14 @@ static void vfio_ap_unregister_irq_notifier(VFIOAPDevice *vapdev, static void vfio_ap_realize(DeviceState *dev, Error **errp) { int ret; - char *mdevid; Error *err = NULL; - VFIOGroup *vfio_group; - APDevice *apdev = AP_DEVICE(dev); - VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev); + VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev); + VFIODevice *vbasedev = &vapdev->vdev; - vfio_group = vfio_ap_get_group(vapdev, errp); - if (!vfio_group) { - return; - } - - vapdev->vdev.ops = &vfio_ap_ops; - vapdev->vdev.type = VFIO_DEVICE_TYPE_AP; - mdevid = basename(vapdev->vdev.sysfsdev); - vapdev->vdev.name = g_strdup_printf("%s", mdevid); - vapdev->vdev.dev = dev; + vbasedev->name = g_path_get_basename(vbasedev->sysfsdev); + vbasedev->ops = &vfio_ap_ops; + vbasedev->type = VFIO_DEVICE_TYPE_AP; + vbasedev->dev = dev; /* * vfio-ap devices operate in a way compatible with discarding of @@ -214,9 +172,10 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp) */ vapdev->vdev.ram_block_discard_allowed = true; - ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp); + ret = vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - goto out_get_dev_err; + goto error; } vfio_ap_register_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX, &err); @@ -230,20 +189,18 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp) return; -out_get_dev_err: - vfio_ap_put_device(vapdev); - vfio_put_group(vfio_group); +error: + error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name); + g_free(vbasedev->name); } static void vfio_ap_unrealize(DeviceState *dev) { - APDevice *apdev = AP_DEVICE(dev); - VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev); - VFIOGroup *group = vapdev->vdev.group; + VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev); vfio_ap_unregister_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX); - vfio_ap_put_device(vapdev); - vfio_put_group(group); + vfio_detach_device(&vapdev->vdev); + g_free(vapdev->vdev.name); } static Property vfio_ap_properties[] = { @@ -254,8 +211,7 @@ static Property vfio_ap_properties[] = { static void vfio_ap_reset(DeviceState *dev) { int ret; - APDevice *apdev = AP_DEVICE(dev); - VFIOAPDevice *vapdev = VFIO_AP_DEVICE(apdev); + VFIOAPDevice *vapdev = VFIO_AP_DEVICE(dev); ret = ioctl(vapdev->vdev.fd, VFIO_DEVICE_RESET); if (ret) { diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 1e2fce83b0..6623ae237b 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -572,88 +572,14 @@ static void vfio_ccw_put_region(VFIOCCWDevice *vcdev) g_free(vcdev->io_region); } -static void vfio_ccw_put_device(VFIOCCWDevice *vcdev) -{ - g_free(vcdev->vdev.name); - vfio_put_base_device(&vcdev->vdev); -} - -static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, - Error **errp) -{ - S390CCWDevice *cdev = S390_CCW_DEVICE(vcdev); - char *name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid, - cdev->hostid.ssid, - cdev->hostid.devid); - VFIODevice *vbasedev; - - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (strcmp(vbasedev->name, name) == 0) { - error_setg(errp, "vfio: subchannel %s has already been attached", - name); - goto out_err; - } - } - - /* - * All vfio-ccw devices are believed to operate in a way compatible with - * discarding of memory in RAM blocks, ie. pages pinned in the host are - * in the current working set of the guest driver and therefore never - * overlap e.g., with pages available to the guest balloon driver. This - * needs to be set before vfio_get_device() for vfio common to handle - * ram_block_discard_disable(). - */ - vcdev->vdev.ram_block_discard_allowed = true; - - if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) { - goto out_err; - } - - vcdev->vdev.ops = &vfio_ccw_ops; - vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW; - vcdev->vdev.name = name; - vcdev->vdev.dev = DEVICE(vcdev); - - return; - -out_err: - g_free(name); -} - -static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) -{ - char *tmp, group_path[PATH_MAX]; - ssize_t len; - int groupid; - - tmp = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/%s/iommu_group", - cdev->hostid.cssid, cdev->hostid.ssid, - cdev->hostid.devid, cdev->mdevid); - len = readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <= 0 || len >= sizeof(group_path)) { - error_setg(errp, "vfio: no iommu_group found"); - return NULL; - } - - group_path[len] = 0; - - if (sscanf(basename(group_path), "%d", &groupid) != 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - return NULL; - } - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ccw_realize(DeviceState *dev, Error **errp) { - VFIOGroup *group; S390CCWDevice *cdev = S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev = VFIO_CCW(cdev); S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); + VFIODevice *vbasedev = &vcdev->vdev; Error *err = NULL; + int ret; /* Call the class init function for subchannel. */ if (cdc->realize) { @@ -663,14 +589,27 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) } } - group = vfio_ccw_get_group(cdev, &err); - if (!group) { - goto out_group_err; - } + vbasedev->ops = &vfio_ccw_ops; + vbasedev->type = VFIO_DEVICE_TYPE_CCW; + vbasedev->name = g_strdup_printf("%x.%x.%04x", vcdev->cdev.hostid.cssid, + vcdev->cdev.hostid.ssid, + vcdev->cdev.hostid.devid); + vbasedev->dev = dev; - vfio_ccw_get_device(group, vcdev, &err); - if (err) { - goto out_device_err; + /* + * All vfio-ccw devices are believed to operate in a way compatible with + * discarding of memory in RAM blocks, ie. pages pinned in the host are + * in the current working set of the guest driver and therefore never + * overlap e.g., with pages available to the guest balloon driver. This + * needs to be set before vfio_get_device() for vfio common to handle + * ram_block_discard_disable(). + */ + vbasedev->ram_block_discard_allowed = true; + + ret = vfio_attach_device(cdev->mdevid, vbasedev, + &address_space_memory, errp); + if (ret) { + goto out_attach_dev_err; } vfio_ccw_get_region(vcdev, &err); @@ -708,10 +647,9 @@ out_irq_notifier_err: out_io_notifier_err: vfio_ccw_put_region(vcdev); out_region_err: - vfio_ccw_put_device(vcdev); -out_device_err: - vfio_put_group(group); -out_group_err: + vfio_detach_device(vbasedev); +out_attach_dev_err: + g_free(vbasedev->name); if (cdc->unrealize) { cdc->unrealize(cdev); } @@ -724,14 +662,13 @@ static void vfio_ccw_unrealize(DeviceState *dev) S390CCWDevice *cdev = S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev = VFIO_CCW(cdev); S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev); - VFIOGroup *group = vcdev->vdev.group; vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_IO_IRQ_INDEX); vfio_ccw_put_region(vcdev); - vfio_ccw_put_device(vcdev); - vfio_put_group(group); + vfio_detach_device(&vcdev->vdev); + g_free(vcdev->vdev.name); if (cdc->unrealize) { cdc->unrealize(cdev); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 134649226d..5ff5acf1d8 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -46,8 +46,8 @@ #include "migration/qemu-file.h" #include "sysemu/tpm.h" -VFIOGroupList vfio_group_list = - QLIST_HEAD_INITIALIZER(vfio_group_list); +VFIODeviceList vfio_device_list = + QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = QLIST_HEAD_INITIALIZER(vfio_address_spaces); @@ -59,304 +59,24 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces = * initialized, this file descriptor is only released on QEMU exit and * we'll re-use it should another vfio device be attached before then. */ -static int vfio_kvm_device_fd = -1; +int vfio_kvm_device_fd = -1; #endif /* - * Common VFIO interrupt disable - */ -void vfio_disable_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, - .index = index, - .start = 0, - .count = 0, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, - .index = index, - .start = 0, - .count = 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set = { - .argsz = sizeof(irq_set), - .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, - .index = index, - .start = 0, - .count = 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -static inline const char *action_to_str(int action) -{ - switch (action) { - case VFIO_IRQ_SET_ACTION_MASK: - return "MASK"; - case VFIO_IRQ_SET_ACTION_UNMASK: - return "UNMASK"; - case VFIO_IRQ_SET_ACTION_TRIGGER: - return "TRIGGER"; - default: - return "UNKNOWN ACTION"; - } -} - -static const char *index_to_str(VFIODevice *vbasedev, int index) -{ - if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { - return NULL; - } - - switch (index) { - case VFIO_PCI_INTX_IRQ_INDEX: - return "INTX"; - case VFIO_PCI_MSI_IRQ_INDEX: - return "MSI"; - case VFIO_PCI_MSIX_IRQ_INDEX: - return "MSIX"; - case VFIO_PCI_ERR_IRQ_INDEX: - return "ERR"; - case VFIO_PCI_REQ_IRQ_INDEX: - return "REQ"; - default: - return NULL; - } -} - -static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state) -{ - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - /* - * We support coordinated discarding of RAM via the RamDiscardManager. - */ - return ram_block_uncoordinated_discard_disable(state); - default: - /* - * VFIO_SPAPR_TCE_IOMMU most probably works just fine with - * RamDiscardManager, however, it is completely untested. - * - * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does - * completely the opposite of managing mapping/pinning dynamically as - * required by RamDiscardManager. We would have to special-case sections - * with a RamDiscardManager. - */ - return ram_block_discard_disable(state); - } -} - -int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp) -{ - struct vfio_irq_set *irq_set; - int argsz, ret = 0; - const char *name; - int32_t *pfd; - - argsz = sizeof(*irq_set) + sizeof(*pfd); - - irq_set = g_malloc0(argsz); - irq_set->argsz = argsz; - irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action; - irq_set->index = index; - irq_set->start = subindex; - irq_set->count = 1; - pfd = (int32_t *)&irq_set->data; - *pfd = fd; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { - ret = -errno; - } - g_free(irq_set); - - if (!ret) { - return 0; - } - - error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); - - name = index_to_str(vbasedev, index); - if (name) { - error_prepend(errp, "%s-%d: ", name, subindex); - } else { - error_prepend(errp, "index %d-%d: ", index, subindex); - } - error_prepend(errp, - "Failed to %s %s eventfd signaling for interrupt ", - fd < 0 ? "tear down" : "set up", action_to_str(action)); - return ret; -} - -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -void vfio_region_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) -{ - VFIORegion *region = opaque; - VFIODevice *vbasedev = region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - - switch (size) { - case 1: - buf.byte = data; - break; - case 2: - buf.word = cpu_to_le16(data); - break; - case 4: - buf.dword = cpu_to_le32(data); - break; - case 8: - buf.qword = cpu_to_le64(data); - break; - default: - hw_error("vfio: unsupported write size, %u bytes", size); - break; - } - - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ",%d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, data, size); - } - - trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); - - /* - * A read or write to a BAR always signals an INTx EOI. This will - * do nothing if not pending (including not in INTx mode). We assume - * that a BAR access is in response to an interrupt and that BAR - * accesses will service the interrupt. Unfortunately, we don't know - * which access will service the interrupt, so we're potentially - * getting quite a few host interrupts per guest interrupt. - */ - vbasedev->ops->vfio_eoi(vbasedev); -} - -uint64_t vfio_region_read(void *opaque, - hwaddr addr, unsigned size) -{ - VFIORegion *region = opaque; - VFIODevice *vbasedev = region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - uint64_t data = 0; - - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, size); - return (uint64_t)-1; - } - switch (size) { - case 1: - data = buf.byte; - break; - case 2: - data = le16_to_cpu(buf.word); - break; - case 4: - data = le32_to_cpu(buf.dword); - break; - case 8: - data = le64_to_cpu(buf.qword); - break; - default: - hw_error("vfio: unsupported read size, %u bytes", size); - break; - } - - trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); - - /* Same as write above */ - vbasedev->ops->vfio_eoi(vbasedev); - - return data; -} - -const MemoryRegionOps vfio_region_ops = { - .read = vfio_region_read, - .write = vfio_region_write, - .endianness = DEVICE_LITTLE_ENDIAN, - .valid = { - .min_access_size = 1, - .max_access_size = 8, - }, - .impl = { - .min_access_size = 1, - .max_access_size = 8, - }, -}; - -/* * Device state interfaces */ -typedef struct { - unsigned long *bitmap; - hwaddr size; - hwaddr pages; -} VFIOBitmap; - -static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) -{ - vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size(); - vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; - vbmap->bitmap = g_try_malloc0(vbmap->size); - if (!vbmap->bitmap) { - return -ENOMEM; - } - - return 0; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr); - bool vfio_mig_active(void) { - VFIOGroup *group; VFIODevice *vbasedev; - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_device_list)) { return false; } - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration_blocker) { - return false; - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration_blocker) { + return false; } } return true; @@ -371,19 +91,16 @@ static Error *multiple_devices_migration_blocker; */ static bool vfio_multiple_devices_migration_is_supported(void) { - VFIOGroup *group; VFIODevice *vbasedev; unsigned int device_num = 0; bool all_support_p2p = true; - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration) { - device_num++; + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration) { + device_num++; - if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { - all_support_p2p = false; - } + if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { + all_support_p2p = false; } } } @@ -435,7 +152,7 @@ void vfio_unblock_multiple_devices_migration(void) bool vfio_viommu_preset(VFIODevice *vbasedev) { - return vbasedev->group->container->space->as != &address_space_memory; + return vbasedev->container->space->as != &address_space_memory; } static void vfio_set_migration_error(int err) @@ -469,7 +186,6 @@ bool vfio_device_state_is_precopy(VFIODevice *vbasedev) static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; MigrationState *ms = migrate_get_current(); @@ -478,34 +194,29 @@ static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) return false; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration = vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration = vbasedev->migration; - if (!migration) { - return false; - } + if (!migration) { + return false; + } - if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF && - (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev))) { - return false; - } + if (vbasedev->pre_copy_dirty_page_tracking == ON_OFF_AUTO_OFF && + (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev))) { + return false; } } return true; } -static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_pages_supported) { - return false; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_pages_supported) { + return false; } } @@ -516,178 +227,33 @@ static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) * Check if all VFIO devices are running and migration is active, which is * essentially equivalent to the migration being in pre-copy phase. */ -static bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; if (!migration_is_active(migrate_get_current())) { return false; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration = vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration = vbasedev->migration; - if (!migration) { - return false; - } - - if (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev)) { - continue; - } else { - return false; - } + if (!migration) { + return false; } - } - return true; -} - -static int vfio_dma_unmap_bitmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap *unmap; - struct vfio_bitmap *bitmap; - VFIOBitmap vbmap; - int ret; - - ret = vfio_bitmap_alloc(&vbmap, size); - if (ret) { - return ret; - } - - unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); - - unmap->argsz = sizeof(*unmap) + sizeof(*bitmap); - unmap->iova = iova; - unmap->size = size; - unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; - bitmap = (struct vfio_bitmap *)&unmap->data; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize - * to qemu_real_host_page_size. - */ - bitmap->pgsize = qemu_real_host_page_size(); - bitmap->size = vbmap.size; - bitmap->data = (__u64 *)vbmap.bitmap; - - if (vbmap.size > container->max_dirty_bitmap_size) { - error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size); - ret = -E2BIG; - goto unmap_exit; - } - - ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); - if (!ret) { - cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, - iotlb->translated_addr, vbmap.pages); - } else { - error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); - } - -unmap_exit: - g_free(unmap); - g_free(vbmap.bitmap); - - return ret; -} -/* - * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 - */ -static int vfio_dma_unmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap unmap = { - .argsz = sizeof(unmap), - .flags = 0, - .iova = iova, - .size = size, - }; - bool need_dirty_sync = false; - int ret; - - if (iotlb && vfio_devices_all_running_and_mig_active(container)) { - if (!vfio_devices_all_device_dirty_tracking(container) && - container->dirty_pages_supported) { - return vfio_dma_unmap_bitmap(container, iova, size, iotlb); - } - - need_dirty_sync = true; - } - - while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - /* - * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c - * v4.15) where an overflow in its wrap-around check prevents us from - * unmapping the last page of the address space. Test for the error - * condition and re-try the unmap excluding the last page. The - * expectation is that we've never mapped the last page anyway and this - * unmap request comes via vIOMMU support which also makes it unlikely - * that this page is used. This bug was introduced well after type1 v2 - * support was introduced, so we shouldn't need to test for v1. A fix - * is queued for kernel v5.0 so this workaround can be removed once - * affected kernels are sufficiently deprecated. - */ - if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) && - container->iommu_type == VFIO_TYPE1v2_IOMMU) { - trace_vfio_dma_unmap_overflow_workaround(); - unmap.size -= 1ULL << ctz64(container->pgsizes); + if (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev)) { continue; - } - error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); - return -errno; - } - - if (need_dirty_sync) { - ret = vfio_get_dirty_bitmap(container, iova, size, - iotlb->translated_addr); - if (ret) { - return ret; + } else { + return false; } } - - return 0; -} - -static int vfio_dma_map(VFIOContainer *container, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) -{ - struct vfio_iommu_type1_dma_map map = { - .argsz = sizeof(map), - .flags = VFIO_DMA_MAP_FLAG_READ, - .vaddr = (__u64)(uintptr_t)vaddr, - .iova = iova, - .size = size, - }; - - if (!readonly) { - map.flags |= VFIO_DMA_MAP_FLAG_WRITE; - } - - /* - * Try the mapping, if it fails with EBUSY, unmap the region and try - * again. This shouldn't be necessary, but we sometimes see it in - * the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || - (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { - return 0; - } - - error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); - return -errno; + return true; } -static void vfio_host_win_add(VFIOContainer *container, - hwaddr min_iova, hwaddr max_iova, - uint64_t iova_pgsizes) +void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova, uint64_t iova_pgsizes) { VFIOHostDMAWindow *hostwin; @@ -708,8 +274,8 @@ static void vfio_host_win_add(VFIOContainer *container, QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next); } -static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, - hwaddr max_iova) +int vfio_host_win_del(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova) { VFIOHostDMAWindow *hostwin; @@ -1084,62 +650,8 @@ static void vfio_listener_region_add(MemoryListener *listener, return; } - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - hwaddr pgsize = 0; - - /* For now intersections are not allowed, we may relax this later */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(&err, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - goto fail; - } - } - - ret = vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(&err, -ret, "Failed to create SPAPR window"); - goto fail; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr = (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_next) { - param.groupfd = group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("vfio: failed to setup fd %d " - "for a group with fd %d: %s", - param.tablefd, param.groupfd, - strerror(errno)); - return; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tablefd); - } - } - } -#endif + if (vfio_container_add_section_window(container, section, &err)) { + goto fail; } hostwin = vfio_find_hostwin(container, iova, end); @@ -1251,7 +763,7 @@ static void vfio_listener_region_add(MemoryListener *listener, fail: if (memory_region_is_ram_device(section->mr)) { - error_report("failed to vfio_dma_map. pci p2p may not work"); + error_reportf_err(err, "PCI p2p may not work: "); return; } /* @@ -1356,44 +868,7 @@ static void vfio_listener_region_del(MemoryListener *listener, memory_region_unref(section->mr); - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } - } -} - -static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) -{ - int ret; - struct vfio_iommu_type1_dirty_bitmap dirty = { - .argsz = sizeof(dirty), - }; - - if (!container->dirty_pages_supported) { - return 0; - } - - if (start) { - dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START; - } else { - dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; - } - - ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); - if (ret) { - ret = -errno; - error_report("Failed to set dirty tracking flag 0x%x errno: %d", - dirty.flags, errno); - } - - return ret; + vfio_container_del_section_window(container, section); } typedef struct VFIODirtyRanges { @@ -1416,20 +891,17 @@ static bool vfio_section_is_vfio_pci(MemoryRegionSection *section, { VFIOPCIDevice *pcidev; VFIODevice *vbasedev; - VFIOGroup *group; Object *owner; owner = memory_region_owner(section->mr); - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { - continue; - } - pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev); - if (OBJECT(pcidev) == owner) { - return true; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { + continue; + } + pcidev = container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (OBJECT(pcidev) == owner) { + return true; } } @@ -1525,24 +997,21 @@ static void vfio_devices_dma_logging_stop(VFIOContainer *container) sizeof(uint64_t))] = {}; struct vfio_device_feature *feature = (struct vfio_device_feature *)buf; VFIODevice *vbasedev; - VFIOGroup *group; feature->argsz = sizeof(buf); feature->flags = VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_tracking) { + continue; + } - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { - warn_report("%s: Failed to stop DMA logging, err %d (%s)", - vbasedev->name, -errno, strerror(errno)); - } - vbasedev->dirty_tracking = false; + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + warn_report("%s: Failed to stop DMA logging, err %d (%s)", + vbasedev->name, -errno, strerror(errno)); } + vbasedev->dirty_tracking = false; } } @@ -1625,7 +1094,6 @@ static int vfio_devices_dma_logging_start(VFIOContainer *container) struct vfio_device_feature *feature; VFIODirtyRanges ranges; VFIODevice *vbasedev; - VFIOGroup *group; int ret = 0; vfio_dirty_tracking_init(container, &ranges); @@ -1635,21 +1103,19 @@ static int vfio_devices_dma_logging_start(VFIOContainer *container) return -errno; } - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->dirty_tracking) { + continue; + } - ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); - if (ret) { - ret = -errno; - error_report("%s: Failed to start DMA logging, err %d (%s)", - vbasedev->name, ret, strerror(errno)); - goto out; - } - vbasedev->dirty_tracking = true; + ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); + if (ret) { + ret = -errno; + error_report("%s: Failed to start DMA logging, err %d (%s)", + vbasedev->name, ret, strerror(errno)); + goto out; } + vbasedev->dirty_tracking = true; } out: @@ -1724,71 +1190,31 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova, return 0; } -static int vfio_devices_query_dirty_bitmap(VFIOContainer *container, - VFIOBitmap *vbmap, hwaddr iova, - hwaddr size) +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size) { VFIODevice *vbasedev; - VFIOGroup *group; int ret; - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - ret = vfio_device_dma_logging_report(vbasedev, iova, size, - vbmap->bitmap); - if (ret) { - error_report("%s: Failed to get DMA logging report, iova: " - "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx - ", err: %d (%s)", - vbasedev->name, iova, size, ret, strerror(-ret)); + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + ret = vfio_device_dma_logging_report(vbasedev, iova, size, + vbmap->bitmap); + if (ret) { + error_report("%s: Failed to get DMA logging report, iova: " + "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx + ", err: %d (%s)", + vbasedev->name, iova, size, ret, strerror(-ret)); - return ret; - } + return ret; } } return 0; } -static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, - hwaddr iova, hwaddr size) -{ - struct vfio_iommu_type1_dirty_bitmap *dbitmap; - struct vfio_iommu_type1_dirty_bitmap_get *range; - int ret; - - dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range)); - - dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range); - dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; - range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; - range->iova = iova; - range->size = size; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize - * to qemu_real_host_page_size. - */ - range->bitmap.pgsize = qemu_real_host_page_size(); - range->bitmap.size = vbmap->size; - range->bitmap.data = (__u64 *)vbmap->bitmap; - - ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); - if (ret) { - ret = -errno; - error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 - " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, - (uint64_t)range->size, errno); - } - - g_free(dbitmap); - - return ret; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr) +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr) { bool all_device_dirty_tracking = vfio_devices_all_device_dirty_tracking(container); @@ -1977,7 +1403,7 @@ static void vfio_listener_log_sync(MemoryListener *listener, } } -static const MemoryListener vfio_memory_listener = { +const MemoryListener vfio_memory_listener = { .name = "vfio", .region_add = vfio_listener_region_add, .region_del = vfio_listener_region_del, @@ -1986,338 +1412,34 @@ static const MemoryListener vfio_memory_listener = { .log_sync = vfio_listener_log_sync, }; -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->listener); - if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - memory_listener_unregister(&container->prereg_listener); - } -} - -static struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - - for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) { - if (hdr->id == id) { - return hdr; - } - } - - return NULL; -} - -struct vfio_info_cap_header * -vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -static struct vfio_info_cap_header * -vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -struct vfio_info_cap_header * -vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, - unsigned int *avail) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_dma_avail *cap; - - /* If the capability cannot be found, assume no DMA limiting */ - hdr = vfio_get_iommu_type1_info_cap(info, - VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); - if (hdr == NULL) { - return false; - } - - if (avail != NULL) { - cap = (void *) hdr; - *avail = cap->avail; - } - - return true; -} - -static int vfio_setup_region_sparse_mmaps(VFIORegion *region, - struct vfio_region_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_sparse_mmap *sparse; - int i, j; - - hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP); - if (!hdr) { - return -ENODEV; - } - - sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header); - - trace_vfio_region_sparse_mmap_header(region->vbasedev->name, - region->nr, sparse->nr_areas); - - region->mmaps = g_new0(VFIOMmap, sparse->nr_areas); - - for (i = 0, j = 0; i < sparse->nr_areas; i++) { - if (sparse->areas[i].size) { - trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, - sparse->areas[i].offset + - sparse->areas[i].size - 1); - region->mmaps[j].offset = sparse->areas[i].offset; - region->mmaps[j].size = sparse->areas[i].size; - j++; - } - } - - region->nr_mmaps = j; - region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap)); - - return 0; -} - -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, - int index, const char *name) -{ - struct vfio_region_info *info; - int ret; - - ret = vfio_get_region_info(vbasedev, index, &info); - if (ret) { - return ret; - } - - region->vbasedev = vbasedev; - region->flags = info->flags; - region->size = info->size; - region->fd_offset = info->offset; - region->nr = index; - - if (region->size) { - region->mem = g_new0(MemoryRegion, 1); - memory_region_init_io(region->mem, obj, &vfio_region_ops, - region, name, region->size); - - if (!vbasedev->no_mmap && - region->flags & VFIO_REGION_INFO_FLAG_MMAP) { - - ret = vfio_setup_region_sparse_mmaps(region, info); - - if (ret) { - region->nr_mmaps = 1; - region->mmaps = g_new0(VFIOMmap, region->nr_mmaps); - region->mmaps[0].offset = 0; - region->mmaps[0].size = region->size; - } - } - } - - g_free(info); - - trace_vfio_region_setup(vbasedev->name, index, name, - region->flags, region->fd_offset, region->size); - return 0; -} - -static void vfio_subregion_unmap(VFIORegion *region, int index) -{ - trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), - region->mmaps[index].offset, - region->mmaps[index].offset + - region->mmaps[index].size - 1); - memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); - munmap(region->mmaps[index].mmap, region->mmaps[index].size); - object_unparent(OBJECT(®ion->mmaps[index].mem)); - region->mmaps[index].mmap = NULL; -} - -int vfio_region_mmap(VFIORegion *region) -{ - int i, prot = 0; - char *name; - - if (!region->mem) { - return 0; - } - - prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; - prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; - - for (i = 0; i < region->nr_mmaps; i++) { - region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot, - MAP_SHARED, region->vbasedev->fd, - region->fd_offset + - region->mmaps[i].offset); - if (region->mmaps[i].mmap == MAP_FAILED) { - int ret = -errno; - - trace_vfio_region_mmap_fault(memory_region_name(region->mem), i, - region->fd_offset + - region->mmaps[i].offset, - region->fd_offset + - region->mmaps[i].offset + - region->mmaps[i].size - 1, ret); - - region->mmaps[i].mmap = NULL; - - for (i--; i >= 0; i--) { - vfio_subregion_unmap(region, i); - } - - return ret; - } - - name = g_strdup_printf("%s mmaps[%d]", - memory_region_name(region->mem), i); - memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, - memory_region_owner(region->mem), - name, region->mmaps[i].size, - region->mmaps[i].mmap); - g_free(name); - memory_region_add_subregion(region->mem, region->mmaps[i].offset, - ®ion->mmaps[i].mem); - - trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), - region->mmaps[i].offset, - region->mmaps[i].offset + - region->mmaps[i].size - 1); - } - - return 0; -} - -void vfio_region_unmap(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - vfio_subregion_unmap(region, i); - } - } -} - -void vfio_region_exit(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem); - } - } - - trace_vfio_region_exit(region->vbasedev->name, region->nr); -} - -void vfio_region_finalize(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - munmap(region->mmaps[i].mmap, region->mmaps[i].size); - object_unparent(OBJECT(®ion->mmaps[i].mem)); - } - } - - object_unparent(OBJECT(region->mem)); - - g_free(region->mem); - g_free(region->mmaps); - - trace_vfio_region_finalize(region->vbasedev->name, region->nr); - - region->mem = NULL; - region->mmaps = NULL; - region->nr_mmaps = 0; - region->size = 0; - region->flags = 0; - region->nr = 0; -} - -void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) -{ - int i; - - if (!region->mem) { - return; - } - - for (i = 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_set_enabled(®ion->mmaps[i].mem, enabled); - } - } - - trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), - enabled); -} - void vfio_reset_handler(void *opaque) { - VFIOGroup *group; VFIODevice *vbasedev; - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); } } - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized && vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); } } } -static void vfio_kvm_device_add_group(VFIOGroup *group) +int vfio_kvm_device_add_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_ADD, - .addr = (uint64_t)(unsigned long)&group->fd, + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_ADD, + .addr = (uint64_t)(unsigned long)&fd, }; if (!kvm_enabled()) { - return; + return 0; } if (vfio_kvm_device_fd < 0) { @@ -2326,41 +1448,46 @@ static void vfio_kvm_device_add_group(VFIOGroup *group) }; if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - error_report("Failed to create KVM VFIO device: %m"); - return; + error_setg_errno(errp, errno, "Failed to create KVM VFIO device"); + return -errno; } vfio_kvm_device_fd = cd.fd; } if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to add group %d to KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO device", + fd); + return -errno; } #endif + return 0; } -static void vfio_kvm_device_del_group(VFIOGroup *group) +int vfio_kvm_device_del_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr = { - .group = KVM_DEV_VFIO_GROUP, - .attr = KVM_DEV_VFIO_GROUP_DEL, - .addr = (uint64_t)(unsigned long)&group->fd, + .group = KVM_DEV_VFIO_FILE, + .attr = KVM_DEV_VFIO_FILE_DEL, + .addr = (uint64_t)(unsigned long)&fd, }; if (vfio_kvm_device_fd < 0) { - return; + error_setg(errp, "KVM VFIO device isn't created yet"); + return -EINVAL; } if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to remove group %d from KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, + "Failed to remove fd %d from KVM VFIO device", fd); + return -errno; } #endif + return 0; } -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) { VFIOAddressSpace *space; @@ -2375,516 +1502,22 @@ static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) space->as = as; QLIST_INIT(&space->containers); + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_register_reset(vfio_reset_handler, NULL); + } + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); return space; } -static void vfio_put_address_space(VFIOAddressSpace *space) +void vfio_put_address_space(VFIOAddressSpace *space) { if (QLIST_EMPTY(&space->containers)) { QLIST_REMOVE(space, list); g_free(space); } -} - -/* - * vfio_get_iommu_type - selects the richest iommu_type (v2 first) - */ -static int vfio_get_iommu_type(VFIOContainer *container, - Error **errp) -{ - int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, - VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; - int i; - - for (i = 0; i < ARRAY_SIZE(iommu_types); i++) { - if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { - return iommu_types[i]; - } - } - error_setg(errp, "No available IOMMU models"); - return -EINVAL; -} - -static int vfio_init_container(VFIOContainer *container, int group_fd, - Error **errp) -{ - int iommu_type, ret; - - iommu_type = vfio_get_iommu_type(container, errp); - if (iommu_type < 0) { - return iommu_type; - } - - ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); - if (ret) { - error_setg_errno(errp, errno, "Failed to set group container"); - return -errno; - } - - while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { - if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { - /* - * On sPAPR, despite the IOMMU subdriver always advertises v1 and - * v2, the running platform may not support v2 and there is no - * way to guess it until an IOMMU group gets added to the container. - * So in case it fails with v2, try v1 as a fallback. - */ - iommu_type = VFIO_SPAPR_TCE_IOMMU; - continue; - } - error_setg_errno(errp, errno, "Failed to set iommu for container"); - return -errno; - } - - container->iommu_type = iommu_type; - return 0; -} - -static int vfio_get_iommu_info(VFIOContainer *container, - struct vfio_iommu_type1_info **info) -{ - - size_t argsz = sizeof(struct vfio_iommu_type1_info); - - *info = g_new0(struct vfio_iommu_type1_info, 1); -again: - (*info)->argsz = argsz; - - if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { - g_free(*info); - *info = NULL; - return -errno; - } - - if (((*info)->argsz > argsz)) { - argsz = (*info)->argsz; - *info = g_realloc(*info, argsz); - goto again; - } - - return 0; -} - -static struct vfio_info_cap_header * -vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - void *ptr = info; - - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) { - if (hdr->id == id) { - return hdr; - } - } - - return NULL; -} - -static void vfio_get_iommu_info_migration(VFIOContainer *container, - struct vfio_iommu_type1_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_cap_migration *cap_mig; - - hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION); - if (!hdr) { - return; - } - - cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration, - header); - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. - */ - if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { - container->dirty_pages_supported = true; - container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size; - container->dirty_pgsizes = cap_mig->pgsize_bitmap; - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, - Error **errp) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space = vfio_get_address_space(as); - - /* - * VFIO is currently incompatible with discarding of RAM insofar as the - * madvise to purge (zap) the page from QEMU's address space does not - * interact with the memory API and therefore leaves stale virtual to - * physical mappings in the IOMMU if the page was previously pinned. We - * therefore set discarding broken for each group added to a container, - * whether the container is used individually or shared. This provides - * us with options to allow devices within a group to opt-in and allow - * discarding, so long as it is done consistently for a group (for instance - * if the device is an mdev device where it is known that the host vendor - * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be discarding candidates). - * - * The first opportunity to induce pinning occurs here where we attempt to - * attach the group to existing containers within the AddressSpace. If any - * pages are already zapped from the virtual address space, such as from - * previous discards, new pinning will cause valid mappings to be - * re-established. Likewise, when the overall MemoryListener for a new - * container is registered, a replay of mappings within the AddressSpace - * will occur, re-establishing any previously zapped pages as well. - * - * Especially virtio-balloon is currently only prevented from discarding - * new memory, it will not yet set ram_block_discard_set_required() and - * therefore, neither stops us here or deals with the sudden memory - * consumption of inflated memory. - * - * We do support discarding of memory coordinated via the RamDiscardManager - * with some IOMMU types. vfio_ram_block_discard_disable() handles the - * details once we know which type of IOMMU we are using. - */ - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - ret = vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, - "Cannot set discarding of RAM broken"); - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, - &container->fd)) { - error_report("vfio: error disconnecting group %d from" - " container", group->groupid); - } - return ret; - } - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - vfio_kvm_device_add_group(group); - return 0; - } - } - - fd = qemu_open_old("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); - ret = -errno; - goto put_space_exit; - } - - ret = ioctl(fd, VFIO_GET_API_VERSION); - if (ret != VFIO_API_VERSION) { - error_setg(errp, "supported vfio version: %d, " - "reported version: %d", VFIO_API_VERSION, ret); - ret = -EINVAL; - goto close_fd_exit; - } - - container = g_malloc0(sizeof(*container)); - container->space = space; - container->fd = fd; - container->error = NULL; - container->dirty_pages_supported = false; - container->dma_max_mappings = 0; - QLIST_INIT(&container->giommu_list); - QLIST_INIT(&container->hostwin_list); - QLIST_INIT(&container->vrdl_list); - - ret = vfio_init_container(container, group->fd, errp); - if (ret) { - goto free_container_exit; - } - - ret = vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); - goto free_container_exit; - } - - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - { - struct vfio_iommu_type1_info *info; - - ret = vfio_get_iommu_info(container, &info); - if (ret) { - error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); - goto enable_discards_exit; - } - - if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { - container->pgsizes = info->iova_pgsizes; - } else { - container->pgsizes = qemu_real_host_page_size(); - } - - if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { - container->dma_max_mappings = 65535; - } - vfio_get_iommu_info_migration(container, info); - g_free(info); - - /* - * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE - * information to get the actual window extent rather than assume - * a 64-bit IOVA address space. - */ - vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); - - break; - } - case VFIO_SPAPR_TCE_v2_IOMMU: - case VFIO_SPAPR_TCE_IOMMU: - { - struct vfio_iommu_spapr_tce_info info; - bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU; - - /* - * The host kernel code implementing VFIO_IOMMU_DISABLE is called - * when container fd is closed so we do not call it explicitly - * in this file. - */ - if (!v2) { - ret = ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_setg_errno(errp, errno, "failed to enable container"); - ret = -errno; - goto enable_discards_exit; - } - } else { - container->prereg_listener = vfio_prereg_listener; - - memory_listener_register(&container->prereg_listener, - &address_space_memory); - if (container->error) { - memory_listener_unregister(&container->prereg_listener); - ret = -1; - error_propagate_prepend(errp, container->error, - "RAM memory listener initialization failed: "); - goto enable_discards_exit; - } - } - - info.argsz = sizeof(info); - ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); - if (ret) { - error_setg_errno(errp, errno, - "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); - ret = -errno; - if (v2) { - memory_listener_unregister(&container->prereg_listener); - } - goto enable_discards_exit; - } - - if (v2) { - container->pgsizes = info.ddw.pgsizes; - /* - * There is a default window in just created container. - * To make region_add/del simpler, we better remove this - * window now and let those iommu_listener callbacks - * create/remove them when needed. - */ - ret = vfio_spapr_remove_window(container, info.dma32_window_start); - if (ret) { - error_setg_errno(errp, -ret, - "failed to remove existing window"); - goto enable_discards_exit; - } - } else { - /* The default table uses 4K pages */ - container->pgsizes = 0x1000; - vfio_host_win_add(container, info.dma32_window_start, - info.dma32_window_start + - info.dma32_window_size - 1, - 0x1000); - } - } - } - - vfio_kvm_device_add_group(group); - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container = container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - container->listener = vfio_memory_listener; - - memory_listener_register(&container->listener, container->space->as); - - if (container->error) { - ret = -1; - error_propagate_prepend(errp, container->error, - "memory listener initialization failed: "); - goto listener_release_exit; - } - - container->initialized = true; - - return 0; -listener_release_exit: - QLIST_REMOVE(group, container_next); - QLIST_REMOVE(container, next); - vfio_kvm_device_del_group(group); - vfio_listener_release(container); - -enable_discards_exit: - vfio_ram_block_discard_disable(container, false); - -free_container_exit: - g_free(container); - -close_fd_exit: - close(fd); - -put_space_exit: - vfio_put_address_space(space); - - return ret; -} - -static void vfio_disconnect_container(VFIOGroup *group) -{ - VFIOContainer *container = group->container; - - QLIST_REMOVE(group, container_next); - group->container = NULL; - - /* - * Explicitly release the listener first before unset container, - * since unset may destroy the backend container if it's the last - * group. - */ - if (QLIST_EMPTY(&container->group_list)) { - vfio_listener_release(container); - } - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space = container->space; - VFIOGuestIOMMU *giommu, *tmp; - VFIOHostDMAWindow *hostwin, *next; - - QLIST_REMOVE(container, next); - - QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) { - memory_region_unregister_iommu_notifier( - MEMORY_REGION(giommu->iommu_mr), &giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - } - - QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, - next) { - QLIST_REMOVE(hostwin, hostwin_next); - g_free(hostwin); - } - - trace_vfio_disconnect_container(container->fd); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); - } -} - -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp) -{ - VFIOGroup *group; - char path[32]; - struct vfio_group_status status = { .argsz = sizeof(status) }; - - QLIST_FOREACH(group, &vfio_group_list, next) { - if (group->groupid == groupid) { - /* Found it. Now is it already in the right context? */ - if (group->container->space->as == as) { - return group; - } else { - error_setg(errp, "group %d used in multiple address spaces", - group->groupid); - return NULL; - } - } - } - - group = g_malloc0(sizeof(*group)); - - snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); - group->fd = qemu_open_old(path, O_RDWR); - if (group->fd < 0) { - error_setg_errno(errp, errno, "failed to open %s", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_setg_errno(errp, errno, "failed to get group %d status", groupid); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_setg(errp, "group %d is not viable", groupid); - error_append_hint(errp, - "Please ensure all devices within the iommu_group " - "are bound to their vfio bus driver.\n"); - goto close_fd_exit; - } - - group->groupid = groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as, errp)) { - error_prepend(errp, "failed to setup container for group %d: ", - groupid); - goto close_fd_exit; - } - - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_register_reset(vfio_reset_handler, NULL); - } - - QLIST_INSERT_HEAD(&vfio_group_list, group, next); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -void vfio_put_group(VFIOGroup *group) -{ - if (!group || !QLIST_EMPTY(&group->device_list)) { - return; - } - - if (!group->ram_block_discard_allowed) { - vfio_ram_block_discard_disable(group->container, false); - } - vfio_kvm_device_del_group(group); - vfio_disconnect_container(group); - QLIST_REMOVE(group, next); - trace_vfio_put_group(group->fd); - close(group->fd); - g_free(group); - - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_address_spaces)) { qemu_unregister_reset(vfio_reset_handler, NULL); } } @@ -2912,245 +1545,3 @@ retry: return info; } - -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) -{ - g_autofree struct vfio_device_info *info = NULL; - int fd; - - fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (fd < 0) { - error_setg_errno(errp, errno, "error getting device from group %d", - group->groupid); - error_append_hint(errp, - "Verify all devices in group %d are bound to vfio-<bus> " - "or pci-stub and not already in use\n", group->groupid); - return fd; - } - - info = vfio_get_device_info(fd); - if (!info) { - error_setg_errno(errp, errno, "error getting device info"); - close(fd); - return -1; - } - - /* - * Set discarding of RAM as not broken for this group if the driver knows - * the device operates compatibly with discarding. Setting must be - * consistent per group, but since compatibility is really only possible - * with mdev currently, we expect singleton groups. - */ - if (vbasedev->ram_block_discard_allowed != - group->ram_block_discard_allowed) { - if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, "Inconsistent setting of support for discarding " - "RAM (e.g., balloon) within group"); - close(fd); - return -1; - } - - if (!group->ram_block_discard_allowed) { - group->ram_block_discard_allowed = true; - vfio_ram_block_discard_disable(group->container, false); - } - } - - vbasedev->fd = fd; - vbasedev->group = group; - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); - - vbasedev->num_irqs = info->num_irqs; - vbasedev->num_regions = info->num_regions; - vbasedev->flags = info->flags; - - trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs); - - vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET); - - return 0; -} - -void vfio_put_base_device(VFIODevice *vbasedev) -{ - if (!vbasedev->group) { - return; - } - QLIST_REMOVE(vbasedev, next); - vbasedev->group = NULL; - trace_vfio_put_base_device(vbasedev->fd); - close(vbasedev->fd); -} - -int vfio_get_region_info(VFIODevice *vbasedev, int index, - struct vfio_region_info **info) -{ - size_t argsz = sizeof(struct vfio_region_info); - - *info = g_malloc0(argsz); - - (*info)->index = index; -retry: - (*info)->argsz = argsz; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { - g_free(*info); - *info = NULL; - return -errno; - } - - if ((*info)->argsz > argsz) { - argsz = (*info)->argsz; - *info = g_realloc(*info, argsz); - - goto retry; - } - - return 0; -} - -int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, - uint32_t subtype, struct vfio_region_info **info) -{ - int i; - - for (i = 0; i < vbasedev->num_regions; i++) { - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_type *cap_type; - - if (vfio_get_region_info(vbasedev, i, info)) { - continue; - } - - hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); - if (!hdr) { - g_free(*info); - continue; - } - - cap_type = container_of(hdr, struct vfio_region_info_cap_type, header); - - trace_vfio_get_dev_region(vbasedev->name, i, - cap_type->type, cap_type->subtype); - - if (cap_type->type == type && cap_type->subtype == subtype) { - return 0; - } - - g_free(*info); - } - - *info = NULL; - return -ENODEV; -} - -bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type) -{ - struct vfio_region_info *info = NULL; - bool ret = false; - - if (!vfio_get_region_info(vbasedev, region, &info)) { - if (vfio_get_region_info_cap(info, cap_type)) { - ret = true; - } - g_free(info); - } - - return ret; -} - -/* - * Interfaces for IBM EEH (Enhanced Error Handling) - */ -static bool vfio_eeh_container_ok(VFIOContainer *container) -{ - /* - * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO - * implementation is broken if there are multiple groups in a - * container. The hardware works in units of Partitionable - * Endpoints (== IOMMU groups) and the EEH operations naively - * iterate across all groups in the container, without any logic - * to make sure the groups have their state synchronized. For - * certain operations (ENABLE) that might be ok, until an error - * occurs, but for others (GET_STATE) it's clearly broken. - */ - - /* - * XXX Once fixed kernels exist, test for them here - */ - - if (QLIST_EMPTY(&container->group_list)) { - return false; - } - - if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { - return false; - } - - return true; -} - -static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) -{ - struct vfio_eeh_pe_op pe_op = { - .argsz = sizeof(pe_op), - .op = op, - }; - int ret; - - if (!vfio_eeh_container_ok(container)) { - error_report("vfio/eeh: EEH_PE_OP 0x%x: " - "kernel requires a container with exactly one group", op); - return -EPERM; - } - - ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); - if (ret < 0) { - error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); - return -errno; - } - - return ret; -} - -static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) -{ - VFIOAddressSpace *space = vfio_get_address_space(as); - VFIOContainer *container = NULL; - - if (QLIST_EMPTY(&space->containers)) { - /* No containers to act on */ - goto out; - } - - container = QLIST_FIRST(&space->containers); - - if (QLIST_NEXT(container, next)) { - /* We don't yet have logic to synchronize EEH state across - * multiple containers */ - container = NULL; - goto out; - } - -out: - vfio_put_address_space(space); - return container; -} - -bool vfio_eeh_as_ok(AddressSpace *as) -{ - VFIOContainer *container = vfio_eeh_as_container(as); - - return (container != NULL) && vfio_eeh_container_ok(container); -} - -int vfio_eeh_as_op(AddressSpace *as, uint32_t op) -{ - VFIOContainer *container = vfio_eeh_as_container(as); - - if (!container) { - return -ENODEV; - } - return vfio_eeh_container_op(container, op); -} diff --git a/hw/vfio/container.c b/hw/vfio/container.c new file mode 100644 index 0000000000..adc467210f --- /dev/null +++ b/hw/vfio/container.c @@ -0,0 +1,1161 @@ +/* + * generic functions used by VFIO devices + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson <alex.williamson@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include <sys/ioctl.h> +#ifdef CONFIG_KVM +#include <linux/kvm.h> +#endif +#include <linux/vfio.h> + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "exec/ram_addr.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "qemu/range.h" +#include "sysemu/kvm.h" +#include "sysemu/reset.h" +#include "trace.h" +#include "qapi/error.h" +#include "migration/migration.h" + +VFIOGroupList vfio_group_list = + QLIST_HEAD_INITIALIZER(vfio_group_list); + +static int vfio_ram_block_discard_disable(VFIOContainer *container, bool state) +{ + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + /* + * We support coordinated discarding of RAM via the RamDiscardManager. + */ + return ram_block_uncoordinated_discard_disable(state); + default: + /* + * VFIO_SPAPR_TCE_IOMMU most probably works just fine with + * RamDiscardManager, however, it is completely untested. + * + * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does + * completely the opposite of managing mapping/pinning dynamically as + * required by RamDiscardManager. We would have to special-case sections + * with a RamDiscardManager. + */ + return ram_block_discard_disable(state); + } +} + +static int vfio_dma_unmap_bitmap(VFIOContainer *container, + hwaddr iova, ram_addr_t size, + IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap *unmap; + struct vfio_bitmap *bitmap; + VFIOBitmap vbmap; + int ret; + + ret = vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + + unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); + + unmap->argsz = sizeof(*unmap) + sizeof(*bitmap); + unmap->iova = iova; + unmap->size = size; + unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; + bitmap = (struct vfio_bitmap *)&unmap->data; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize + * to qemu_real_host_page_size. + */ + bitmap->pgsize = qemu_real_host_page_size(); + bitmap->size = vbmap.size; + bitmap->data = (__u64 *)vbmap.bitmap; + + if (vbmap.size > container->max_dirty_bitmap_size) { + error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size); + ret = -E2BIG; + goto unmap_exit; + } + + ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); + if (!ret) { + cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, + iotlb->translated_addr, vbmap.pages); + } else { + error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); + } + +unmap_exit: + g_free(unmap); + g_free(vbmap.bitmap); + + return ret; +} + +/* + * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 + */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap unmap = { + .argsz = sizeof(unmap), + .flags = 0, + .iova = iova, + .size = size, + }; + bool need_dirty_sync = false; + int ret; + + if (iotlb && vfio_devices_all_running_and_mig_active(container)) { + if (!vfio_devices_all_device_dirty_tracking(container) && + container->dirty_pages_supported) { + return vfio_dma_unmap_bitmap(container, iova, size, iotlb); + } + + need_dirty_sync = true; + } + + while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { + /* + * The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c + * v4.15) where an overflow in its wrap-around check prevents us from + * unmapping the last page of the address space. Test for the error + * condition and re-try the unmap excluding the last page. The + * expectation is that we've never mapped the last page anyway and this + * unmap request comes via vIOMMU support which also makes it unlikely + * that this page is used. This bug was introduced well after type1 v2 + * support was introduced, so we shouldn't need to test for v1. A fix + * is queued for kernel v5.0 so this workaround can be removed once + * affected kernels are sufficiently deprecated. + */ + if (errno == EINVAL && unmap.size && !(unmap.iova + unmap.size) && + container->iommu_type == VFIO_TYPE1v2_IOMMU) { + trace_vfio_dma_unmap_overflow_workaround(); + unmap.size -= 1ULL << ctz64(container->pgsizes); + continue; + } + error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); + return -errno; + } + + if (need_dirty_sync) { + ret = vfio_get_dirty_bitmap(container, iova, size, + iotlb->translated_addr); + if (ret) { + return ret; + } + } + + return 0; +} + +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly) +{ + struct vfio_iommu_type1_dma_map map = { + .argsz = sizeof(map), + .flags = VFIO_DMA_MAP_FLAG_READ, + .vaddr = (__u64)(uintptr_t)vaddr, + .iova = iova, + .size = size, + }; + + if (!readonly) { + map.flags |= VFIO_DMA_MAP_FLAG_WRITE; + } + + /* + * Try the mapping, if it fails with EBUSY, unmap the region and try + * again. This shouldn't be necessary, but we sometimes see it in + * the VGA ROM space. + */ + if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 || + (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 && + ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) { + return 0; + } + + error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); + return -errno; +} + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp) +{ + VFIOHostDMAWindow *hostwin; + hwaddr pgsize = 0; + int ret; + + if (container->iommu_type != VFIO_SPAPR_TCE_v2_IOMMU) { + return 0; + } + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + error_setg(errp, + "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" + "host DMA window [0x%"PRIx64",0x%"PRIx64"]", + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, + hostwin->min_iova, hostwin->max_iova); + return -EINVAL; + } + } + + ret = vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + error_setg_errno(errp, -ret, "Failed to create SPAPR window"); + return ret; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); +#ifdef CONFIG_KVM + if (kvm_enabled()) { + VFIOGroup *group; + IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); + struct kvm_vfio_spapr_tce param; + struct kvm_device_attr attr = { + .group = KVM_DEV_VFIO_GROUP, + .attr = KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, + .addr = (uint64_t)(unsigned long)¶m, + }; + + if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_FD, + ¶m.tablefd)) { + QLIST_FOREACH(group, &container->group_list, container_next) { + param.groupfd = group->fd; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { + error_setg_errno(errp, errno, + "vfio: failed GROUP_SET_SPAPR_TCE for " + "KVM VFIO device %d and group fd %d", + param.tablefd, param.groupfd); + return -errno; + } + trace_vfio_spapr_group_attach(param.groupfd, param.tablefd); + } + } + } +#endif + return 0; +} + +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section) +{ + if (container->iommu_type != VFIO_SPAPR_TCE_v2_IOMMU) { + return; + } + + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } +} + +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) +{ + int ret; + struct vfio_iommu_type1_dirty_bitmap dirty = { + .argsz = sizeof(dirty), + }; + + if (!container->dirty_pages_supported) { + return 0; + } + + if (start) { + dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_START; + } else { + dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; + } + + ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); + if (ret) { + ret = -errno; + error_report("Failed to set dirty tracking flag 0x%x errno: %d", + dirty.flags, errno); + } + + return ret; +} + +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size) +{ + struct vfio_iommu_type1_dirty_bitmap *dbitmap; + struct vfio_iommu_type1_dirty_bitmap_get *range; + int ret; + + dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range)); + + dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range); + dbitmap->flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; + range = (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; + range->iova = iova; + range->size = size; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pgsize + * to qemu_real_host_page_size. + */ + range->bitmap.pgsize = qemu_real_host_page_size(); + range->bitmap.size = vbmap->size; + range->bitmap.data = (__u64 *)vbmap->bitmap; + + ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); + if (ret) { + ret = -errno; + error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 + " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, + (uint64_t)range->size, errno); + } + + g_free(dbitmap); + + return ret; +} + +static void vfio_listener_release(VFIOContainer *container) +{ + memory_listener_unregister(&container->listener); + if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + memory_listener_unregister(&container->prereg_listener); + } +} + +static struct vfio_info_cap_header * +vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, + unsigned int *avail) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_dma_avail *cap; + + /* If the capability cannot be found, assume no DMA limiting */ + hdr = vfio_get_iommu_type1_info_cap(info, + VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); + if (hdr == NULL) { + return false; + } + + if (avail != NULL) { + cap = (void *) hdr; + *avail = cap->avail; + } + + return true; +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ + Error *err = NULL; + + if (vfio_kvm_device_add_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ + Error *err = NULL; + + if (vfio_kvm_device_del_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +/* + * vfio_get_iommu_type - selects the richest iommu_type (v2 first) + */ +static int vfio_get_iommu_type(VFIOContainer *container, + Error **errp) +{ + int iommu_types[] = { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, + VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; + int i; + + for (i = 0; i < ARRAY_SIZE(iommu_types); i++) { + if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { + return iommu_types[i]; + } + } + error_setg(errp, "No available IOMMU models"); + return -EINVAL; +} + +static int vfio_init_container(VFIOContainer *container, int group_fd, + Error **errp) +{ + int iommu_type, ret; + + iommu_type = vfio_get_iommu_type(container, errp); + if (iommu_type < 0) { + return iommu_type; + } + + ret = ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); + if (ret) { + error_setg_errno(errp, errno, "Failed to set group container"); + return -errno; + } + + while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { + if (iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + /* + * On sPAPR, despite the IOMMU subdriver always advertises v1 and + * v2, the running platform may not support v2 and there is no + * way to guess it until an IOMMU group gets added to the container. + * So in case it fails with v2, try v1 as a fallback. + */ + iommu_type = VFIO_SPAPR_TCE_IOMMU; + continue; + } + error_setg_errno(errp, errno, "Failed to set iommu for container"); + return -errno; + } + + container->iommu_type = iommu_type; + return 0; +} + +static int vfio_get_iommu_info(VFIOContainer *container, + struct vfio_iommu_type1_info **info) +{ + + size_t argsz = sizeof(struct vfio_iommu_type1_info); + + *info = g_new0(struct vfio_iommu_type1_info, 1); +again: + (*info)->argsz = argsz; + + if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { + g_free(*info); + *info = NULL; + return -errno; + } + + if (((*info)->argsz > argsz)) { + argsz = (*info)->argsz; + *info = g_realloc(*info, argsz); + goto again; + } + + return 0; +} + +static struct vfio_info_cap_header * +vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + void *ptr = info; + + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) { + if (hdr->id == id) { + return hdr; + } + } + + return NULL; +} + +static void vfio_get_iommu_info_migration(VFIOContainer *container, + struct vfio_iommu_type1_info *info) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_cap_migration *cap_mig; + + hdr = vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION); + if (!hdr) { + return; + } + + cap_mig = container_of(hdr, struct vfio_iommu_type1_info_cap_migration, + header); + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. + */ + if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { + container->dirty_pages_supported = true; + container->max_dirty_bitmap_size = cap_mig->max_dirty_bitmap_size; + container->dirty_pgsizes = cap_mig->pgsize_bitmap; + } +} + +static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, + Error **errp) +{ + VFIOContainer *container; + int ret, fd; + VFIOAddressSpace *space; + + space = vfio_get_address_space(as); + + /* + * VFIO is currently incompatible with discarding of RAM insofar as the + * madvise to purge (zap) the page from QEMU's address space does not + * interact with the memory API and therefore leaves stale virtual to + * physical mappings in the IOMMU if the page was previously pinned. We + * therefore set discarding broken for each group added to a container, + * whether the container is used individually or shared. This provides + * us with options to allow devices within a group to opt-in and allow + * discarding, so long as it is done consistently for a group (for instance + * if the device is an mdev device where it is known that the host vendor + * driver will never pin pages outside of the working set of the guest + * driver, which would thus not be discarding candidates). + * + * The first opportunity to induce pinning occurs here where we attempt to + * attach the group to existing containers within the AddressSpace. If any + * pages are already zapped from the virtual address space, such as from + * previous discards, new pinning will cause valid mappings to be + * re-established. Likewise, when the overall MemoryListener for a new + * container is registered, a replay of mappings within the AddressSpace + * will occur, re-establishing any previously zapped pages as well. + * + * Especially virtio-balloon is currently only prevented from discarding + * new memory, it will not yet set ram_block_discard_set_required() and + * therefore, neither stops us here or deals with the sudden memory + * consumption of inflated memory. + * + * We do support discarding of memory coordinated via the RamDiscardManager + * with some IOMMU types. vfio_ram_block_discard_disable() handles the + * details once we know which type of IOMMU we are using. + */ + + QLIST_FOREACH(container, &space->containers, next) { + if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + ret = vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, + "Cannot set discarding of RAM broken"); + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, + &container->fd)) { + error_report("vfio: error disconnecting group %d from" + " container", group->groupid); + } + return ret; + } + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + vfio_kvm_device_add_group(group); + return 0; + } + } + + fd = qemu_open_old("/dev/vfio/vfio", O_RDWR); + if (fd < 0) { + error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); + ret = -errno; + goto put_space_exit; + } + + ret = ioctl(fd, VFIO_GET_API_VERSION); + if (ret != VFIO_API_VERSION) { + error_setg(errp, "supported vfio version: %d, " + "reported version: %d", VFIO_API_VERSION, ret); + ret = -EINVAL; + goto close_fd_exit; + } + + container = g_malloc0(sizeof(*container)); + container->space = space; + container->fd = fd; + container->error = NULL; + container->dirty_pages_supported = false; + container->dma_max_mappings = 0; + QLIST_INIT(&container->giommu_list); + QLIST_INIT(&container->hostwin_list); + QLIST_INIT(&container->vrdl_list); + + ret = vfio_init_container(container, group->fd, errp); + if (ret) { + goto free_container_exit; + } + + ret = vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); + goto free_container_exit; + } + + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + { + struct vfio_iommu_type1_info *info; + + ret = vfio_get_iommu_info(container, &info); + if (ret) { + error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); + goto enable_discards_exit; + } + + if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { + container->pgsizes = info->iova_pgsizes; + } else { + container->pgsizes = qemu_real_host_page_size(); + } + + if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { + container->dma_max_mappings = 65535; + } + vfio_get_iommu_info_migration(container, info); + g_free(info); + + /* + * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE + * information to get the actual window extent rather than assume + * a 64-bit IOVA address space. + */ + vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); + + break; + } + case VFIO_SPAPR_TCE_v2_IOMMU: + case VFIO_SPAPR_TCE_IOMMU: + { + struct vfio_iommu_spapr_tce_info info; + bool v2 = container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU; + + /* + * The host kernel code implementing VFIO_IOMMU_DISABLE is called + * when container fd is closed so we do not call it explicitly + * in this file. + */ + if (!v2) { + ret = ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_setg_errno(errp, errno, "failed to enable container"); + ret = -errno; + goto enable_discards_exit; + } + } else { + container->prereg_listener = vfio_prereg_listener; + + memory_listener_register(&container->prereg_listener, + &address_space_memory); + if (container->error) { + memory_listener_unregister(&container->prereg_listener); + ret = -1; + error_propagate_prepend(errp, container->error, + "RAM memory listener initialization failed: "); + goto enable_discards_exit; + } + } + + info.argsz = sizeof(info); + ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); + if (ret) { + error_setg_errno(errp, errno, + "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); + ret = -errno; + if (v2) { + memory_listener_unregister(&container->prereg_listener); + } + goto enable_discards_exit; + } + + if (v2) { + container->pgsizes = info.ddw.pgsizes; + /* + * There is a default window in just created container. + * To make region_add/del simpler, we better remove this + * window now and let those iommu_listener callbacks + * create/remove them when needed. + */ + ret = vfio_spapr_remove_window(container, info.dma32_window_start); + if (ret) { + error_setg_errno(errp, -ret, + "failed to remove existing window"); + goto enable_discards_exit; + } + } else { + /* The default table uses 4K pages */ + container->pgsizes = 0x1000; + vfio_host_win_add(container, info.dma32_window_start, + info.dma32_window_start + + info.dma32_window_size - 1, + 0x1000); + } + } + } + + vfio_kvm_device_add_group(group); + + QLIST_INIT(&container->group_list); + QLIST_INSERT_HEAD(&space->containers, container, next); + + group->container = container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + + container->listener = vfio_memory_listener; + + memory_listener_register(&container->listener, container->space->as); + + if (container->error) { + ret = -1; + error_propagate_prepend(errp, container->error, + "memory listener initialization failed: "); + goto listener_release_exit; + } + + container->initialized = true; + + return 0; +listener_release_exit: + QLIST_REMOVE(group, container_next); + QLIST_REMOVE(container, next); + vfio_kvm_device_del_group(group); + vfio_listener_release(container); + +enable_discards_exit: + vfio_ram_block_discard_disable(container, false); + +free_container_exit: + g_free(container); + +close_fd_exit: + close(fd); + +put_space_exit: + vfio_put_address_space(space); + + return ret; +} + +static void vfio_disconnect_container(VFIOGroup *group) +{ + VFIOContainer *container = group->container; + + QLIST_REMOVE(group, container_next); + group->container = NULL; + + /* + * Explicitly release the listener first before unset container, + * since unset may destroy the backend container if it's the last + * group. + */ + if (QLIST_EMPTY(&container->group_list)) { + vfio_listener_release(container); + } + + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { + error_report("vfio: error disconnecting group %d from container", + group->groupid); + } + + if (QLIST_EMPTY(&container->group_list)) { + VFIOAddressSpace *space = container->space; + VFIOGuestIOMMU *giommu, *tmp; + VFIOHostDMAWindow *hostwin, *next; + + QLIST_REMOVE(container, next); + + QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, tmp) { + memory_region_unregister_iommu_notifier( + MEMORY_REGION(giommu->iommu_mr), &giommu->n); + QLIST_REMOVE(giommu, giommu_next); + g_free(giommu); + } + + QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, + next) { + QLIST_REMOVE(hostwin, hostwin_next); + g_free(hostwin); + } + + trace_vfio_disconnect_container(container->fd); + close(container->fd); + g_free(container); + + vfio_put_address_space(space); + } +} + +static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp) +{ + VFIOGroup *group; + char path[32]; + struct vfio_group_status status = { .argsz = sizeof(status) }; + + QLIST_FOREACH(group, &vfio_group_list, next) { + if (group->groupid == groupid) { + /* Found it. Now is it already in the right context? */ + if (group->container->space->as == as) { + return group; + } else { + error_setg(errp, "group %d used in multiple address spaces", + group->groupid); + return NULL; + } + } + } + + group = g_malloc0(sizeof(*group)); + + snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); + group->fd = qemu_open_old(path, O_RDWR); + if (group->fd < 0) { + error_setg_errno(errp, errno, "failed to open %s", path); + goto free_group_exit; + } + + if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { + error_setg_errno(errp, errno, "failed to get group %d status", groupid); + goto close_fd_exit; + } + + if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { + error_setg(errp, "group %d is not viable", groupid); + error_append_hint(errp, + "Please ensure all devices within the iommu_group " + "are bound to their vfio bus driver.\n"); + goto close_fd_exit; + } + + group->groupid = groupid; + QLIST_INIT(&group->device_list); + + if (vfio_connect_container(group, as, errp)) { + error_prepend(errp, "failed to setup container for group %d: ", + groupid); + goto close_fd_exit; + } + + QLIST_INSERT_HEAD(&vfio_group_list, group, next); + + return group; + +close_fd_exit: + close(group->fd); + +free_group_exit: + g_free(group); + + return NULL; +} + +static void vfio_put_group(VFIOGroup *group) +{ + if (!group || !QLIST_EMPTY(&group->device_list)) { + return; + } + + if (!group->ram_block_discard_allowed) { + vfio_ram_block_discard_disable(group->container, false); + } + vfio_kvm_device_del_group(group); + vfio_disconnect_container(group); + QLIST_REMOVE(group, next); + trace_vfio_put_group(group->fd); + close(group->fd); + g_free(group); +} + +static int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev, Error **errp) +{ + g_autofree struct vfio_device_info *info = NULL; + int fd; + + fd = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); + if (fd < 0) { + error_setg_errno(errp, errno, "error getting device from group %d", + group->groupid); + error_append_hint(errp, + "Verify all devices in group %d are bound to vfio-<bus> " + "or pci-stub and not already in use\n", group->groupid); + return fd; + } + + info = vfio_get_device_info(fd); + if (!info) { + error_setg_errno(errp, errno, "error getting device info"); + close(fd); + return -1; + } + + /* + * Set discarding of RAM as not broken for this group if the driver knows + * the device operates compatibly with discarding. Setting must be + * consistent per group, but since compatibility is really only possible + * with mdev currently, we expect singleton groups. + */ + if (vbasedev->ram_block_discard_allowed != + group->ram_block_discard_allowed) { + if (!QLIST_EMPTY(&group->device_list)) { + error_setg(errp, "Inconsistent setting of support for discarding " + "RAM (e.g., balloon) within group"); + close(fd); + return -1; + } + + if (!group->ram_block_discard_allowed) { + group->ram_block_discard_allowed = true; + vfio_ram_block_discard_disable(group->container, false); + } + } + + vbasedev->fd = fd; + vbasedev->group = group; + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); + + vbasedev->num_irqs = info->num_irqs; + vbasedev->num_regions = info->num_regions; + vbasedev->flags = info->flags; + + trace_vfio_get_device(name, info->flags, info->num_regions, info->num_irqs); + + vbasedev->reset_works = !!(info->flags & VFIO_DEVICE_FLAGS_RESET); + + return 0; +} + +static void vfio_put_base_device(VFIODevice *vbasedev) +{ + if (!vbasedev->group) { + return; + } + QLIST_REMOVE(vbasedev, next); + vbasedev->group = NULL; + trace_vfio_put_base_device(vbasedev->fd); + close(vbasedev->fd); +} + +/* + * Interfaces for IBM EEH (Enhanced Error Handling) + */ +static bool vfio_eeh_container_ok(VFIOContainer *container) +{ + /* + * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO + * implementation is broken if there are multiple groups in a + * container. The hardware works in units of Partitionable + * Endpoints (== IOMMU groups) and the EEH operations naively + * iterate across all groups in the container, without any logic + * to make sure the groups have their state synchronized. For + * certain operations (ENABLE) that might be ok, until an error + * occurs, but for others (GET_STATE) it's clearly broken. + */ + + /* + * XXX Once fixed kernels exist, test for them here + */ + + if (QLIST_EMPTY(&container->group_list)) { + return false; + } + + if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { + return false; + } + + return true; +} + +static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) +{ + struct vfio_eeh_pe_op pe_op = { + .argsz = sizeof(pe_op), + .op = op, + }; + int ret; + + if (!vfio_eeh_container_ok(container)) { + error_report("vfio/eeh: EEH_PE_OP 0x%x: " + "kernel requires a container with exactly one group", op); + return -EPERM; + } + + ret = ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); + if (ret < 0) { + error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); + return -errno; + } + + return ret; +} + +static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) +{ + VFIOAddressSpace *space = vfio_get_address_space(as); + VFIOContainer *container = NULL; + + if (QLIST_EMPTY(&space->containers)) { + /* No containers to act on */ + goto out; + } + + container = QLIST_FIRST(&space->containers); + + if (QLIST_NEXT(container, next)) { + /* + * We don't yet have logic to synchronize EEH state across + * multiple containers + */ + container = NULL; + goto out; + } + +out: + vfio_put_address_space(space); + return container; +} + +bool vfio_eeh_as_ok(AddressSpace *as) +{ + VFIOContainer *container = vfio_eeh_as_container(as); + + return (container != NULL) && vfio_eeh_container_ok(container); +} + +int vfio_eeh_as_op(AddressSpace *as, uint32_t op) +{ + VFIOContainer *container = vfio_eeh_as_container(as); + + if (!container) { + return -ENODEV; + } + return vfio_eeh_container_op(container, op); +} + +static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) +{ + char *tmp, group_path[PATH_MAX], *group_name; + int ret, groupid; + ssize_t len; + + tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); + len = readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <= 0 || len >= sizeof(group_path)) { + ret = len < 0 ? -errno : -ENAMETOOLONG; + error_setg_errno(errp, -ret, "no iommu_group found"); + return ret; + } + + group_path[len] = 0; + + group_name = basename(group_path); + if (sscanf(group_name, "%d", &groupid) != 1) { + error_setg_errno(errp, errno, "failed to read %s", group_path); + return -errno; + } + return groupid; +} + +/* + * vfio_attach_device: attach a device to a security context + * @name and @vbasedev->name are likely to be different depending + * on the type of the device, hence the need for passing @name + */ +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp) +{ + int groupid = vfio_device_groupid(vbasedev, errp); + VFIODevice *vbasedev_iter; + VFIOGroup *group; + VFIOContainer *container; + int ret; + + if (groupid < 0) { + return groupid; + } + + trace_vfio_attach_device(vbasedev->name, groupid); + + group = vfio_get_group(groupid, as, errp); + if (!group) { + return -ENOENT; + } + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) { + error_setg(errp, "device is already attached"); + vfio_put_group(group); + return -EBUSY; + } + } + ret = vfio_get_device(group, name, vbasedev, errp); + if (ret) { + vfio_put_group(group); + return ret; + } + + container = group->container; + vbasedev->container = container; + QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); + + return ret; +} + +void vfio_detach_device(VFIODevice *vbasedev) +{ + VFIOGroup *group = vbasedev->group; + + if (!vbasedev->container) { + return; + } + + QLIST_REMOVE(vbasedev, global_next); + QLIST_REMOVE(vbasedev, container_next); + vbasedev->container = NULL; + trace_vfio_detach_device(vbasedev->name, group->groupid); + vfio_put_base_device(vbasedev); + vfio_put_group(group); +} diff --git a/hw/vfio/display.c b/hw/vfio/display.c index 837d9e6a30..7a10fa8604 100644 --- a/hw/vfio/display.c +++ b/hw/vfio/display.c @@ -544,3 +544,24 @@ void vfio_display_finalize(VFIOPCIDevice *vdev) vfio_display_edid_exit(vdev->dpy); g_free(vdev->dpy); } + +static bool migrate_needed(void *opaque) +{ + VFIODisplay *dpy = opaque; + bool ramfb_exists = dpy->ramfb != NULL; + + /* see vfio_display_migration_needed() */ + assert(ramfb_exists); + return ramfb_exists; +} + +const VMStateDescription vfio_display_vmstate = { + .name = "VFIODisplay", + .version_id = 1, + .minimum_version_id = 1, + .needed = migrate_needed, + .fields = (VMStateField[]) { + VMSTATE_STRUCT_POINTER(ramfb, VFIODisplay, ramfb_vmstate, RAMFBState), + VMSTATE_END_OF_LIST(), + } +}; diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c new file mode 100644 index 0000000000..7e5da21b31 --- /dev/null +++ b/hw/vfio/helpers.c @@ -0,0 +1,612 @@ +/* + * low level and IOMMU backend agnostic helpers used by VFIO devices, + * related to regions, interrupts, capabilities + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson <alex.williamson@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include <sys/ioctl.h> + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "hw/hw.h" +#include "trace.h" +#include "qapi/error.h" +#include "qemu/error-report.h" + +/* + * Common VFIO interrupt disable + */ +void vfio_disable_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, + .index = index, + .start = 0, + .count = 0, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, + .index = index, + .start = 0, + .count = 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set = { + .argsz = sizeof(irq_set), + .flags = VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, + .index = index, + .start = 0, + .count = 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +static inline const char *action_to_str(int action) +{ + switch (action) { + case VFIO_IRQ_SET_ACTION_MASK: + return "MASK"; + case VFIO_IRQ_SET_ACTION_UNMASK: + return "UNMASK"; + case VFIO_IRQ_SET_ACTION_TRIGGER: + return "TRIGGER"; + default: + return "UNKNOWN ACTION"; + } +} + +static const char *index_to_str(VFIODevice *vbasedev, int index) +{ + if (vbasedev->type != VFIO_DEVICE_TYPE_PCI) { + return NULL; + } + + switch (index) { + case VFIO_PCI_INTX_IRQ_INDEX: + return "INTX"; + case VFIO_PCI_MSI_IRQ_INDEX: + return "MSI"; + case VFIO_PCI_MSIX_IRQ_INDEX: + return "MSIX"; + case VFIO_PCI_ERR_IRQ_INDEX: + return "ERR"; + case VFIO_PCI_REQ_IRQ_INDEX: + return "REQ"; + default: + return NULL; + } +} + +int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, + int action, int fd, Error **errp) +{ + struct vfio_irq_set *irq_set; + int argsz, ret = 0; + const char *name; + int32_t *pfd; + + argsz = sizeof(*irq_set) + sizeof(*pfd); + + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | action; + irq_set->index = index; + irq_set->start = subindex; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + *pfd = fd; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + ret = -errno; + } + g_free(irq_set); + + if (!ret) { + return 0; + } + + error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); + + name = index_to_str(vbasedev, index); + if (name) { + error_prepend(errp, "%s-%d: ", name, subindex); + } else { + error_prepend(errp, "index %d-%d: ", index, subindex); + } + error_prepend(errp, + "Failed to %s %s eventfd signaling for interrupt ", + fd < 0 ? "tear down" : "set up", action_to_str(action)); + return ret; +} + +/* + * IO Port/MMIO - Beware of the endians, VFIO is always little endian + */ +void vfio_region_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + VFIORegion *region = opaque; + VFIODevice *vbasedev = region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + + switch (size) { + case 1: + buf.byte = data; + break; + case 2: + buf.word = cpu_to_le16(data); + break; + case 4: + buf.dword = cpu_to_le32(data); + break; + case 8: + buf.qword = cpu_to_le64(data); + break; + default: + hw_error("vfio: unsupported write size, %u bytes", size); + break; + } + + if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 + ",%d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, data, size); + } + + trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); + + /* + * A read or write to a BAR always signals an INTx EOI. This will + * do nothing if not pending (including not in INTx mode). We assume + * that a BAR access is in response to an interrupt and that BAR + * accesses will service the interrupt. Unfortunately, we don't know + * which access will service the interrupt, so we're potentially + * getting quite a few host interrupts per guest interrupt. + */ + vbasedev->ops->vfio_eoi(vbasedev); +} + +uint64_t vfio_region_read(void *opaque, + hwaddr addr, unsigned size) +{ + VFIORegion *region = opaque; + VFIODevice *vbasedev = region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + uint64_t data = 0; + + if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) != size) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, size); + return (uint64_t)-1; + } + switch (size) { + case 1: + data = buf.byte; + break; + case 2: + data = le16_to_cpu(buf.word); + break; + case 4: + data = le32_to_cpu(buf.dword); + break; + case 8: + data = le64_to_cpu(buf.qword); + break; + default: + hw_error("vfio: unsupported read size, %u bytes", size); + break; + } + + trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); + + /* Same as write above */ + vbasedev->ops->vfio_eoi(vbasedev); + + return data; +} + +const MemoryRegionOps vfio_region_ops = { + .read = vfio_region_read, + .write = vfio_region_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 8, + }, + .impl = { + .min_access_size = 1, + .max_access_size = 8, + }, +}; + +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) +{ + vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size(); + vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / + BITS_PER_BYTE; + vbmap->bitmap = g_try_malloc0(vbmap->size); + if (!vbmap->bitmap) { + return -ENOMEM; + } + + return 0; +} + +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + + for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) { + if (hdr->id == id) { + return hdr; + } + } + + return NULL; +} + +struct vfio_info_cap_header * +vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +struct vfio_info_cap_header * +vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +static int vfio_setup_region_sparse_mmaps(VFIORegion *region, + struct vfio_region_info *info) +{ + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_sparse_mmap *sparse; + int i, j; + + hdr = vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMAP); + if (!hdr) { + return -ENODEV; + } + + sparse = container_of(hdr, struct vfio_region_info_cap_sparse_mmap, header); + + trace_vfio_region_sparse_mmap_header(region->vbasedev->name, + region->nr, sparse->nr_areas); + + region->mmaps = g_new0(VFIOMmap, sparse->nr_areas); + + for (i = 0, j = 0; i < sparse->nr_areas; i++) { + if (sparse->areas[i].size) { + trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, + sparse->areas[i].offset + + sparse->areas[i].size - 1); + region->mmaps[j].offset = sparse->areas[i].offset; + region->mmaps[j].size = sparse->areas[i].size; + j++; + } + } + + region->nr_mmaps = j; + region->mmaps = g_realloc(region->mmaps, j * sizeof(VFIOMmap)); + + return 0; +} + +int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, + int index, const char *name) +{ + struct vfio_region_info *info; + int ret; + + ret = vfio_get_region_info(vbasedev, index, &info); + if (ret) { + return ret; + } + + region->vbasedev = vbasedev; + region->flags = info->flags; + region->size = info->size; + region->fd_offset = info->offset; + region->nr = index; + + if (region->size) { + region->mem = g_new0(MemoryRegion, 1); + memory_region_init_io(region->mem, obj, &vfio_region_ops, + region, name, region->size); + + if (!vbasedev->no_mmap && + region->flags & VFIO_REGION_INFO_FLAG_MMAP) { + + ret = vfio_setup_region_sparse_mmaps(region, info); + + if (ret) { + region->nr_mmaps = 1; + region->mmaps = g_new0(VFIOMmap, region->nr_mmaps); + region->mmaps[0].offset = 0; + region->mmaps[0].size = region->size; + } + } + } + + g_free(info); + + trace_vfio_region_setup(vbasedev->name, index, name, + region->flags, region->fd_offset, region->size); + return 0; +} + +static void vfio_subregion_unmap(VFIORegion *region, int index) +{ + trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), + region->mmaps[index].offset, + region->mmaps[index].offset + + region->mmaps[index].size - 1); + memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); + munmap(region->mmaps[index].mmap, region->mmaps[index].size); + object_unparent(OBJECT(®ion->mmaps[index].mem)); + region->mmaps[index].mmap = NULL; +} + +int vfio_region_mmap(VFIORegion *region) +{ + int i, prot = 0; + char *name; + + if (!region->mem) { + return 0; + } + + prot |= region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; + prot |= region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; + + for (i = 0; i < region->nr_mmaps; i++) { + region->mmaps[i].mmap = mmap(NULL, region->mmaps[i].size, prot, + MAP_SHARED, region->vbasedev->fd, + region->fd_offset + + region->mmaps[i].offset); + if (region->mmaps[i].mmap == MAP_FAILED) { + int ret = -errno; + + trace_vfio_region_mmap_fault(memory_region_name(region->mem), i, + region->fd_offset + + region->mmaps[i].offset, + region->fd_offset + + region->mmaps[i].offset + + region->mmaps[i].size - 1, ret); + + region->mmaps[i].mmap = NULL; + + for (i--; i >= 0; i--) { + vfio_subregion_unmap(region, i); + } + + return ret; + } + + name = g_strdup_printf("%s mmaps[%d]", + memory_region_name(region->mem), i); + memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, + memory_region_owner(region->mem), + name, region->mmaps[i].size, + region->mmaps[i].mmap); + g_free(name); + memory_region_add_subregion(region->mem, region->mmaps[i].offset, + ®ion->mmaps[i].mem); + + trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), + region->mmaps[i].offset, + region->mmaps[i].offset + + region->mmaps[i].size - 1); + } + + return 0; +} + +void vfio_region_unmap(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i = 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + vfio_subregion_unmap(region, i); + } + } +} + +void vfio_region_exit(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i = 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem); + } + } + + trace_vfio_region_exit(region->vbasedev->name, region->nr); +} + +void vfio_region_finalize(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i = 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + munmap(region->mmaps[i].mmap, region->mmaps[i].size); + object_unparent(OBJECT(®ion->mmaps[i].mem)); + } + } + + object_unparent(OBJECT(region->mem)); + + g_free(region->mem); + g_free(region->mmaps); + + trace_vfio_region_finalize(region->vbasedev->name, region->nr); + + region->mem = NULL; + region->mmaps = NULL; + region->nr_mmaps = 0; + region->size = 0; + region->flags = 0; + region->nr = 0; +} + +void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) +{ + int i; + + if (!region->mem) { + return; + } + + for (i = 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_set_enabled(®ion->mmaps[i].mem, enabled); + } + } + + trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), + enabled); +} + +int vfio_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info) +{ + size_t argsz = sizeof(struct vfio_region_info); + + *info = g_malloc0(argsz); + + (*info)->index = index; +retry: + (*info)->argsz = argsz; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { + g_free(*info); + *info = NULL; + return -errno; + } + + if ((*info)->argsz > argsz) { + argsz = (*info)->argsz; + *info = g_realloc(*info, argsz); + + goto retry; + } + + return 0; +} + +int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **info) +{ + int i; + + for (i = 0; i < vbasedev->num_regions; i++) { + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_type *cap_type; + + if (vfio_get_region_info(vbasedev, i, info)) { + continue; + } + + hdr = vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); + if (!hdr) { + g_free(*info); + continue; + } + + cap_type = container_of(hdr, struct vfio_region_info_cap_type, header); + + trace_vfio_get_dev_region(vbasedev->name, i, + cap_type->type, cap_type->subtype); + + if (cap_type->type == type && cap_type->subtype == subtype) { + return 0; + } + + g_free(*info); + } + + *info = NULL; + return -ENODEV; +} + +bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type) +{ + struct vfio_region_info *info = NULL; + bool ret = false; + + if (!vfio_get_region_info(vbasedev, region, &info)) { + if (vfio_get_region_info_cap(info, cap_type)) { + ret = true; + } + g_free(info); + } + + return ret; +} diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build index da9af297a0..2a6912c940 100644 --- a/hw/vfio/meson.build +++ b/hw/vfio/meson.build @@ -1,6 +1,8 @@ vfio_ss = ss.source_set() vfio_ss.add(files( + 'helpers.c', 'common.c', + 'container.c', 'spapr.c', 'migration.c', )) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 898296fd54..b27011cee7 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2675,6 +2675,33 @@ static bool vfio_msix_present(void *opaque, int version_id) return msix_present(pdev); } +static bool vfio_display_migration_needed(void *opaque) +{ + VFIOPCIDevice *vdev = opaque; + + /* + * We need to migrate the VFIODisplay object if ramfb *migration* was + * explicitly requested (in which case we enforced both ramfb=on and + * display=on), or ramfb migration was left at the default "auto" + * setting, and *ramfb* was explicitly requested (in which case we + * enforced display=on). + */ + return vdev->ramfb_migrate == ON_OFF_AUTO_ON || + (vdev->ramfb_migrate == ON_OFF_AUTO_AUTO && vdev->enable_ramfb); +} + +const VMStateDescription vmstate_vfio_display = { + .name = "VFIOPCIDevice/VFIODisplay", + .version_id = 1, + .minimum_version_id = 1, + .needed = vfio_display_migration_needed, + .fields = (VMStateField[]){ + VMSTATE_STRUCT_POINTER(dpy, VFIOPCIDevice, vfio_display_vmstate, + VFIODisplay), + VMSTATE_END_OF_LIST() + } +}; + const VMStateDescription vmstate_vfio_pci_config = { .name = "VFIOPCIDevice", .version_id = 1, @@ -2683,6 +2710,10 @@ const VMStateDescription vmstate_vfio_pci_config = { VMSTATE_PCI_DEVICE(pdev, VFIOPCIDevice), VMSTATE_MSIX_TEST(pdev, VFIOPCIDevice, vfio_msix_present), VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription * []) { + &vmstate_vfio_display, + NULL } }; @@ -2895,10 +2926,10 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp) static void vfio_pci_put_device(VFIOPCIDevice *vdev) { + vfio_detach_device(&vdev->vbasedev); + g_free(vdev->vbasedev.name); g_free(vdev->msix); - - vfio_put_base_device(&vdev->vbasedev); } static void vfio_err_notifier_handler(void *opaque) @@ -3045,13 +3076,9 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) { VFIOPCIDevice *vdev = VFIO_PCI(pdev); VFIODevice *vbasedev = &vdev->vbasedev; - VFIODevice *vbasedev_iter; - VFIOGroup *group; - char *tmp, *subsys, group_path[PATH_MAX], *group_name; + char *tmp, *subsys; Error *err = NULL; - ssize_t len; struct stat st; - int groupid; int i, ret; bool is_mdev; char uuid[UUID_FMT_LEN]; @@ -3082,39 +3109,6 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) vbasedev->type = VFIO_DEVICE_TYPE_PCI; vbasedev->dev = DEVICE(vdev); - tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len = readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <= 0 || len >= sizeof(group_path)) { - error_setg_errno(errp, len < 0 ? errno : ENAMETOOLONG, - "no iommu_group found"); - goto error; - } - - group_path[len] = 0; - - group_name = basename(group_path); - if (sscanf(group_name, "%d", &groupid) != 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - goto error; - } - - trace_vfio_realize(vbasedev->name, groupid); - - group = vfio_get_group(groupid, pci_device_iommu_address_space(pdev), errp); - if (!group) { - goto error; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - goto error; - } - } - /* * Mediated devices *might* operate compatibly with discarding of RAM, but * we cannot know for certain, it depends on whether the mdev vendor driver @@ -3132,7 +3126,6 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) if (vbasedev->ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); - vfio_put_group(group); goto error; } @@ -3143,10 +3136,10 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) name = g_strdup(vbasedev->name); } - ret = vfio_get_device(group, name, vbasedev, errp); + ret = vfio_attach_device(name, vbasedev, + pci_device_iommu_address_space(pdev), errp); g_free(name); if (ret) { - vfio_put_group(group); goto error; } @@ -3338,6 +3331,20 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } } + if (vdev->ramfb_migrate == ON_OFF_AUTO_ON && !vdev->enable_ramfb) { + warn_report("x-ramfb-migrate=on but ramfb=off. " + "Forcing x-ramfb-migrate to off."); + vdev->ramfb_migrate = ON_OFF_AUTO_OFF; + } + if (vbasedev->enable_migration == ON_OFF_AUTO_OFF) { + if (vdev->ramfb_migrate == ON_OFF_AUTO_AUTO) { + vdev->ramfb_migrate = ON_OFF_AUTO_OFF; + } else if (vdev->ramfb_migrate == ON_OFF_AUTO_ON) { + error_setg(errp, "x-ramfb-migrate requires enable-migration"); + goto out_deregister; + } + } + if (!pdev->failover_pair_id) { if (!vfio_migration_realize(vbasedev, errp)) { goto out_deregister; @@ -3371,7 +3378,6 @@ error: static void vfio_instance_finalize(Object *obj) { VFIOPCIDevice *vdev = VFIO_PCI(obj); - VFIOGroup *group = vdev->vbasedev.group; vfio_display_finalize(vdev); vfio_bars_finalize(vdev); @@ -3385,7 +3391,6 @@ static void vfio_instance_finalize(Object *obj) * g_free(vdev->igd_opregion); */ vfio_pci_put_device(vdev); - vfio_put_group(group); } static void vfio_exitfn(PCIDevice *pdev) @@ -3551,6 +3556,8 @@ static const TypeInfo vfio_pci_dev_info = { static Property vfio_pci_dev_nohotplug_properties[] = { DEFINE_PROP_BOOL("ramfb", VFIOPCIDevice, enable_ramfb, false), + DEFINE_PROP_ON_OFF_AUTO("x-ramfb-migrate", VFIOPCIDevice, ramfb_migrate, + ON_OFF_AUTO_AUTO), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index 0d89eb761e..fba8737ab2 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -174,6 +174,7 @@ struct VFIOPCIDevice { bool no_kvm_ioeventfd; bool no_vfio_ioeventfd; bool enable_ramfb; + OnOffAuto ramfb_migrate; bool defer_kvm_irq_routing; bool clear_parent_atomics_on_exit; VFIODisplay *dpy; @@ -227,4 +228,6 @@ void vfio_display_reset(VFIOPCIDevice *vdev); int vfio_display_probe(VFIOPCIDevice *vdev, Error **errp); void vfio_display_finalize(VFIOPCIDevice *vdev); +extern const VMStateDescription vfio_display_vmstate; + #endif /* HW_VFIO_VFIO_PCI_H */ diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 5af73f9287..8e3d4ac458 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -529,12 +529,7 @@ static VFIODeviceOps vfio_platform_ops = { */ static int vfio_base_device_init(VFIODevice *vbasedev, Error **errp) { - VFIOGroup *group; - VFIODevice *vbasedev_iter; - char *tmp, group_path[PATH_MAX], *group_name; - ssize_t len; struct stat st; - int groupid; int ret; /* @sysfsdev takes precedence over @host */ @@ -557,47 +552,15 @@ static int vfio_base_device_init(VFIODevice *vbasedev, Error **errp) return -errno; } - tmp = g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len = readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len < 0 || len >= sizeof(group_path)) { - ret = len < 0 ? -errno : -ENAMETOOLONG; - error_setg_errno(errp, -ret, "no iommu_group found"); - return ret; - } - - group_path[len] = 0; - - group_name = basename(group_path); - if (sscanf(group_name, "%d", &groupid) != 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - return -errno; - } - - trace_vfio_platform_base_device_init(vbasedev->name, groupid); - - group = vfio_get_group(groupid, &address_space_memory, errp); - if (!group) { - return -ENOENT; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - return -EBUSY; - } - } - ret = vfio_get_device(group, vbasedev->name, vbasedev, errp); + ret = vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - vfio_put_group(group); return ret; } ret = vfio_populate_device(vbasedev, errp); if (ret) { - vfio_put_group(group); + vfio_detach_device(vbasedev); } return ret; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 0ba3c5a0e2..0eb2387cf2 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -37,7 +37,8 @@ vfio_pci_hot_reset_dep_devices(int domain, int bus, int slot, int function, int vfio_pci_hot_reset_result(const char *name, const char *result) "%s hot reset: %s" vfio_populate_device_config(const char *name, unsigned long size, unsigned long offset, unsigned long flags) "Device %s config:\n size: 0x%lx, offset: 0x%lx, flags: 0x%lx" vfio_populate_device_get_irq_info_failure(const char *errstr) "VFIO_DEVICE_GET_IRQ_INFO failure: %s" -vfio_realize(const char *name, int group_id) " (%s) group %d" +vfio_attach_device(const char *name, int group_id) " (%s) group %d" +vfio_detach_device(const char *name, int group_id) " (%s) group %d" vfio_mdev(const char *name, bool is_mdev) " (%s) is_mdev %d" vfio_add_ext_cap_dropped(const char *name, uint16_t cap, uint16_t offset) "%s 0x%x@0x%x" vfio_pci_reset(const char *name) " (%s)" @@ -120,7 +121,6 @@ vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64 # platform.c -vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d" vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = %s" vfio_platform_eoi(int pin, int fd) "EOI IRQ pin %d (fd=%d)" vfio_platform_intp_mmap_enable(int pin) "IRQ #%d still active, stay in slow path" diff --git a/hw/virtio/vhost-stub.c b/hw/virtio/vhost-stub.c index aa858ef3fb..52d42adab2 100644 --- a/hw/virtio/vhost-stub.c +++ b/hw/virtio/vhost-stub.c @@ -2,9 +2,14 @@ #include "hw/virtio/vhost.h" #include "hw/virtio/vhost-user.h" -bool vhost_has_free_slot(void) +unsigned int vhost_get_max_memslots(void) { - return true; + return UINT_MAX; +} + +unsigned int vhost_get_free_memslots(void) +{ + return UINT_MAX; } bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 3766b415f8..68eb1f0c99 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -2327,19 +2327,6 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr) return -ENOTSUP; } -static bool vhost_user_can_merge(struct vhost_dev *dev, - uint64_t start1, uint64_t size1, - uint64_t start2, uint64_t size2) -{ - ram_addr_t offset; - int mfd, rfd; - - (void)vhost_user_get_mr_data(start1, &offset, &mfd); - (void)vhost_user_get_mr_data(start2, &offset, &rfd); - - return mfd == rfd; -} - static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu) { VhostUserMsg msg; @@ -2622,10 +2609,9 @@ vhost_user_crypto_close_session(struct vhost_dev *dev, uint64_t session_id) return 0; } -static bool vhost_user_mem_section_filter(struct vhost_dev *dev, - MemoryRegionSection *section) +static bool vhost_user_no_private_memslots(struct vhost_dev *dev) { - return memory_region_get_fd(section->mr) >= 0; + return true; } static int vhost_user_get_inflight_fd(struct vhost_dev *dev, @@ -2868,6 +2854,7 @@ const VhostOps user_ops = { .vhost_backend_init = vhost_user_backend_init, .vhost_backend_cleanup = vhost_user_backend_cleanup, .vhost_backend_memslots_limit = vhost_user_memslots_limit, + .vhost_backend_no_private_memslots = vhost_user_no_private_memslots, .vhost_set_log_base = vhost_user_set_log_base, .vhost_set_mem_table = vhost_user_set_mem_table, .vhost_set_vring_addr = vhost_user_set_vring_addr, @@ -2886,7 +2873,6 @@ const VhostOps user_ops = { .vhost_set_vring_enable = vhost_user_set_vring_enable, .vhost_requires_shm_log = vhost_user_requires_shm_log, .vhost_migration_done = vhost_user_migration_done, - .vhost_backend_can_merge = vhost_user_can_merge, .vhost_net_set_mtu = vhost_user_net_set_mtu, .vhost_set_iotlb_callback = vhost_user_set_iotlb_callback, .vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg, @@ -2894,7 +2880,6 @@ const VhostOps user_ops = { .vhost_set_config = vhost_user_set_config, .vhost_crypto_create_session = vhost_user_crypto_create_session, .vhost_crypto_close_session = vhost_user_crypto_close_session, - .vhost_backend_mem_section_filter = vhost_user_mem_section_filter, .vhost_get_inflight_fd = vhost_user_get_inflight_fd, .vhost_set_inflight_fd = vhost_user_set_inflight_fd, .vhost_dev_start = vhost_user_dev_start, diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 89ff02a999..819b2d811a 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -1512,7 +1512,6 @@ const VhostOps vdpa_ops = { .vhost_set_config = vhost_vdpa_set_config, .vhost_requires_shm_log = NULL, .vhost_migration_done = NULL, - .vhost_backend_can_merge = NULL, .vhost_net_set_mtu = NULL, .vhost_set_iotlb_callback = NULL, .vhost_send_device_iotlb_msg = NULL, diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 9cfac40fde..9f37206ba0 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -23,6 +23,7 @@ #include "qemu/log.h" #include "standard-headers/linux/vhost_types.h" #include "hw/virtio/virtio-bus.h" +#include "hw/mem/memory-device.h" #include "migration/blocker.h" #include "migration/qemu-file-types.h" #include "sysemu/dma.h" @@ -45,20 +46,44 @@ static struct vhost_log *vhost_log; static struct vhost_log *vhost_log_shm; +/* Memslots used by backends that support private memslots (without an fd). */ static unsigned int used_memslots; + +/* Memslots used by backends that only support shared memslots (with an fd). */ +static unsigned int used_shared_memslots; + static QLIST_HEAD(, vhost_dev) vhost_devices = QLIST_HEAD_INITIALIZER(vhost_devices); -bool vhost_has_free_slot(void) +unsigned int vhost_get_max_memslots(void) +{ + unsigned int max = UINT_MAX; + struct vhost_dev *hdev; + + QLIST_FOREACH(hdev, &vhost_devices, entry) { + max = MIN(max, hdev->vhost_ops->vhost_backend_memslots_limit(hdev)); + } + return max; +} + +unsigned int vhost_get_free_memslots(void) { - unsigned int slots_limit = ~0U; + unsigned int free = UINT_MAX; struct vhost_dev *hdev; QLIST_FOREACH(hdev, &vhost_devices, entry) { unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev); - slots_limit = MIN(slots_limit, r); + unsigned int cur_free; + + if (hdev->vhost_ops->vhost_backend_no_private_memslots && + hdev->vhost_ops->vhost_backend_no_private_memslots(hdev)) { + cur_free = r - used_shared_memslots; + } else { + cur_free = r - used_memslots; + } + free = MIN(free, cur_free); } - return slots_limit > used_memslots; + return free; } static void vhost_dev_sync_region(struct vhost_dev *dev, @@ -474,8 +499,7 @@ static int vhost_verify_ring_mappings(struct vhost_dev *dev, * vhost_section: identify sections needed for vhost access * * We only care about RAM sections here (where virtqueue and guest - * internals accessed by virtio might live). If we find one we still - * allow the backend to potentially filter it out of our list. + * internals accessed by virtio might live). */ static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section) { @@ -502,8 +526,16 @@ static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section) return false; } - if (dev->vhost_ops->vhost_backend_mem_section_filter && - !dev->vhost_ops->vhost_backend_mem_section_filter(dev, section)) { + /* + * Some backends (like vhost-user) can only handle memory regions + * that have an fd (can be mapped into a different process). Filter + * the ones without an fd out, if requested. + * + * TODO: we might have to limit to MAP_SHARED as well. + */ + if (memory_region_get_fd(section->mr) < 0 && + dev->vhost_ops->vhost_backend_no_private_memslots && + dev->vhost_ops->vhost_backend_no_private_memslots(dev)) { trace_vhost_reject_section(mr->name, 2); return false; } @@ -568,7 +600,14 @@ static void vhost_commit(MemoryListener *listener) dev->n_mem_sections * sizeof dev->mem->regions[0]; dev->mem = g_realloc(dev->mem, regions_size); dev->mem->nregions = dev->n_mem_sections; - used_memslots = dev->mem->nregions; + + if (dev->vhost_ops->vhost_backend_no_private_memslots && + dev->vhost_ops->vhost_backend_no_private_memslots(dev)) { + used_shared_memslots = dev->mem->nregions; + } else { + used_memslots = dev->mem->nregions; + } + for (i = 0; i < dev->n_mem_sections; i++) { struct vhost_memory_region *cur_vmr = dev->mem->regions + i; struct MemoryRegionSection *mrs = dev->mem_sections + i; @@ -668,7 +707,7 @@ static void vhost_region_add_section(struct vhost_dev *dev, mrs_size, mrs_host); } - if (dev->n_tmp_sections) { + if (dev->n_tmp_sections && !section->unmergeable) { /* Since we already have at least one section, lets see if * this extends it; since we're scanning in order, we only * have to look at the last one, and the FlatView that calls @@ -701,11 +740,7 @@ static void vhost_region_add_section(struct vhost_dev *dev, size_t offset = mrs_gpa - prev_gpa_start; if (prev_host_start + offset == mrs_host && - section->mr == prev_sec->mr && - (!dev->vhost_ops->vhost_backend_can_merge || - dev->vhost_ops->vhost_backend_can_merge(dev, - mrs_host, mrs_size, - prev_host_start, prev_size))) { + section->mr == prev_sec->mr && !prev_sec->unmergeable) { uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size); need_add = false; prev_sec->offset_within_address_space = @@ -1400,6 +1435,7 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, VhostBackendType backend_type, uint32_t busyloop_timeout, Error **errp) { + unsigned int used, reserved, limit; uint64_t features; int i, r, n_initialized_vqs = 0; @@ -1426,6 +1462,19 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, goto fail; } + limit = hdev->vhost_ops->vhost_backend_memslots_limit(hdev); + if (limit < MEMORY_DEVICES_SAFE_MAX_MEMSLOTS && + memory_devices_memslot_auto_decision_active()) { + error_setg(errp, "some memory device (like virtio-mem)" + " decided how many memory slots to use based on the overall" + " number of memory slots; this vhost backend would further" + " restricts the overall number of memory slots"); + error_append_hint(errp, "Try plugging this vhost backend before" + " plugging such memory devices.\n"); + r = -EINVAL; + goto fail; + } + for (i = 0; i < hdev->nvqs; ++i, ++n_initialized_vqs) { r = vhost_virtqueue_init(hdev, hdev->vqs + i, hdev->vq_index + i); if (r < 0) { @@ -1495,9 +1544,27 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque, memory_listener_register(&hdev->memory_listener, &address_space_memory); QLIST_INSERT_HEAD(&vhost_devices, hdev, entry); - if (used_memslots > hdev->vhost_ops->vhost_backend_memslots_limit(hdev)) { - error_setg(errp, "vhost backend memory slots limit is less" - " than current number of present memory slots"); + /* + * The listener we registered properly updated the corresponding counter. + * So we can trust that these values are accurate. + */ + if (hdev->vhost_ops->vhost_backend_no_private_memslots && + hdev->vhost_ops->vhost_backend_no_private_memslots(hdev)) { + used = used_shared_memslots; + } else { + used = used_memslots; + } + /* + * We assume that all reserved memslots actually require a real memslot + * in our vhost backend. This might not be true, for example, if the + * memslot would be ROM. If ever relevant, we can optimize for that -- + * but we'll need additional information about the reservations. + */ + reserved = memory_devices_get_reserved_memslots(); + if (used + reserved > limit) { + error_setg(errp, "vhost backend memory slots limit (%d) is less" + " than current number of used (%d) and reserved (%d)" + " memory slots for memory devices.", limit, used, reserved); r = -EINVAL; goto fail_busyloop; } diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c index c4597e029e..1b4e9a3284 100644 --- a/hw/virtio/virtio-mem-pci.c +++ b/hw/virtio/virtio-mem-pci.c @@ -48,6 +48,25 @@ static MemoryRegion *virtio_mem_pci_get_memory_region(MemoryDeviceState *md, return vmc->get_memory_region(vmem, errp); } +static void virtio_mem_pci_decide_memslots(MemoryDeviceState *md, + unsigned int limit) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + vmc->decide_memslots(vmem, limit); +} + +static unsigned int virtio_mem_pci_get_memslots(MemoryDeviceState *md) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + return vmc->get_memslots(vmem); +} + static uint64_t virtio_mem_pci_get_plugged_size(const MemoryDeviceState *md, Error **errp) { @@ -150,6 +169,8 @@ static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) mdc->set_addr = virtio_mem_pci_set_addr; mdc->get_plugged_size = virtio_mem_pci_get_plugged_size; mdc->get_memory_region = virtio_mem_pci_get_memory_region; + mdc->decide_memslots = virtio_mem_pci_decide_memslots; + mdc->get_memslots = virtio_mem_pci_get_memslots; mdc->fill_device_info = virtio_mem_pci_fill_device_info; mdc->get_min_alignment = virtio_mem_pci_get_min_alignment; diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index da5b09cefc..9dc3c61b5a 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -67,6 +67,13 @@ static uint32_t virtio_mem_default_thp_size(void) } /* + * The minimum memslot size depends on this setting ("sane default"), the + * device block size, and the memory backend page size. The last (or single) + * memslot might be smaller than this constant. + */ +#define VIRTIO_MEM_MIN_MEMSLOT_SIZE (1 * GiB) + +/* * We want to have a reasonable default block size such that * 1. We avoid splitting THPs when unplugging memory, which degrades * performance. @@ -177,10 +184,10 @@ static bool virtio_mem_is_busy(void) return migration_in_incoming_postcopy() || !migration_is_idle(); } -typedef int (*virtio_mem_range_cb)(const VirtIOMEM *vmem, void *arg, +typedef int (*virtio_mem_range_cb)(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size); -static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_for_each_unplugged_range(VirtIOMEM *vmem, void *arg, virtio_mem_range_cb cb) { unsigned long first_zero_bit, last_zero_bit; @@ -204,7 +211,7 @@ static int virtio_mem_for_each_unplugged_range(const VirtIOMEM *vmem, void *arg, return ret; } -static int virtio_mem_for_each_plugged_range(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_for_each_plugged_range(VirtIOMEM *vmem, void *arg, virtio_mem_range_cb cb) { unsigned long first_bit, last_bit; @@ -483,6 +490,96 @@ static bool virtio_mem_valid_range(const VirtIOMEM *vmem, uint64_t gpa, return true; } +static void virtio_mem_activate_memslot(VirtIOMEM *vmem, unsigned int idx) +{ + const uint64_t memslot_offset = idx * vmem->memslot_size; + + assert(vmem->memslots); + + /* + * Instead of enabling/disabling memslots, we add/remove them. This should + * make address space updates faster, because we don't have to loop over + * many disabled subregions. + */ + if (memory_region_is_mapped(&vmem->memslots[idx])) { + return; + } + memory_region_add_subregion(vmem->mr, memslot_offset, &vmem->memslots[idx]); +} + +static void virtio_mem_deactivate_memslot(VirtIOMEM *vmem, unsigned int idx) +{ + assert(vmem->memslots); + + if (!memory_region_is_mapped(&vmem->memslots[idx])) { + return; + } + memory_region_del_subregion(vmem->mr, &vmem->memslots[idx]); +} + +static void virtio_mem_activate_memslots_to_plug(VirtIOMEM *vmem, + uint64_t offset, uint64_t size) +{ + const unsigned int start_idx = offset / vmem->memslot_size; + const unsigned int end_idx = (offset + size + vmem->memslot_size - 1) / + vmem->memslot_size; + unsigned int idx; + + if (!vmem->dynamic_memslots) { + return; + } + + /* Activate all involved memslots in a single transaction. */ + memory_region_transaction_begin(); + for (idx = start_idx; idx < end_idx; idx++) { + virtio_mem_activate_memslot(vmem, idx); + } + memory_region_transaction_commit(); +} + +static void virtio_mem_deactivate_unplugged_memslots(VirtIOMEM *vmem, + uint64_t offset, + uint64_t size) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + const unsigned int start_idx = offset / vmem->memslot_size; + const unsigned int end_idx = (offset + size + vmem->memslot_size - 1) / + vmem->memslot_size; + unsigned int idx; + + if (!vmem->dynamic_memslots) { + return; + } + + /* Deactivate all memslots with unplugged blocks in a single transaction. */ + memory_region_transaction_begin(); + for (idx = start_idx; idx < end_idx; idx++) { + const uint64_t memslot_offset = idx * vmem->memslot_size; + uint64_t memslot_size = vmem->memslot_size; + + /* The size of the last memslot might be smaller. */ + if (idx == vmem->nb_memslots - 1) { + memslot_size = region_size - memslot_offset; + } + + /* + * Partially covered memslots might still have some blocks plugged and + * have to remain active if that's the case. + */ + if (offset > memslot_offset || + offset + size < memslot_offset + memslot_size) { + const uint64_t gpa = vmem->addr + memslot_offset; + + if (!virtio_mem_is_range_unplugged(vmem, gpa, memslot_size)) { + continue; + } + } + + virtio_mem_deactivate_memslot(vmem, idx); + } + memory_region_transaction_commit(); +} + static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, uint64_t size, bool plug) { @@ -500,6 +597,8 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, } virtio_mem_notify_unplug(vmem, offset, size); virtio_mem_set_range_unplugged(vmem, start_gpa, size); + /* Deactivate completely unplugged memslots after updating the state. */ + virtio_mem_deactivate_unplugged_memslots(vmem, offset, size); return 0; } @@ -527,7 +626,20 @@ static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, } if (!ret) { + /* + * Activate before notifying and rollback in case of any errors. + * + * When activating a yet inactive memslot, memory notifiers will get + * notified about the added memory region and can register with the + * RamDiscardManager; this will traverse all plugged blocks and skip the + * blocks we are plugging here. The following notification will inform + * registered listeners about the blocks we're plugging. + */ + virtio_mem_activate_memslots_to_plug(vmem, offset, size); ret = virtio_mem_notify_plug(vmem, offset, size); + if (ret) { + virtio_mem_deactivate_unplugged_memslots(vmem, offset, size); + } } if (ret) { /* Could be preallocation or a notifier populated memory. */ @@ -620,6 +732,7 @@ static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, static int virtio_mem_unplug_all(VirtIOMEM *vmem) { + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); RAMBlock *rb = vmem->memdev->mr.ram_block; if (vmem->size) { @@ -634,6 +747,9 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem) bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); vmem->size = 0; notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + + /* Deactivate all memslots after updating the state. */ + virtio_mem_deactivate_unplugged_memslots(vmem, 0, region_size); } trace_virtio_mem_unplugged_all(); @@ -790,6 +906,49 @@ static void virtio_mem_system_reset(void *opaque) virtio_mem_unplug_all(vmem); } +static void virtio_mem_prepare_mr(VirtIOMEM *vmem) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + + assert(!vmem->mr && vmem->dynamic_memslots); + vmem->mr = g_new0(MemoryRegion, 1); + memory_region_init(vmem->mr, OBJECT(vmem), "virtio-mem", + region_size); + vmem->mr->align = memory_region_get_alignment(&vmem->memdev->mr); +} + +static void virtio_mem_prepare_memslots(VirtIOMEM *vmem) +{ + const uint64_t region_size = memory_region_size(&vmem->memdev->mr); + unsigned int idx; + + g_assert(!vmem->memslots && vmem->nb_memslots && vmem->dynamic_memslots); + vmem->memslots = g_new0(MemoryRegion, vmem->nb_memslots); + + /* Initialize our memslots, but don't map them yet. */ + for (idx = 0; idx < vmem->nb_memslots; idx++) { + const uint64_t memslot_offset = idx * vmem->memslot_size; + uint64_t memslot_size = vmem->memslot_size; + char name[20]; + + /* The size of the last memslot might be smaller. */ + if (idx == vmem->nb_memslots - 1) { + memslot_size = region_size - memslot_offset; + } + + snprintf(name, sizeof(name), "memslot-%u", idx); + memory_region_init_alias(&vmem->memslots[idx], OBJECT(vmem), name, + &vmem->memdev->mr, memslot_offset, + memslot_size); + /* + * We want to be able to atomically and efficiently activate/deactivate + * individual memslots without affecting adjacent memslots in memory + * notifiers. + */ + memory_region_set_unmergeable(&vmem->memslots[idx], true); + } +} + static void virtio_mem_device_realize(DeviceState *dev, Error **errp) { MachineState *ms = MACHINE(qdev_get_machine()); @@ -861,6 +1020,14 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) vmem->unplugged_inaccessible = ON_OFF_AUTO_ON; #endif /* VIRTIO_MEM_HAS_LEGACY_GUESTS */ + if (vmem->dynamic_memslots && + vmem->unplugged_inaccessible != ON_OFF_AUTO_ON) { + error_setg(errp, "'%s' property set to 'on' requires '%s' to be 'on'", + VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, + VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP); + return; + } + /* * If the block size wasn't configured by the user, use a sane default. This * allows using hugetlbfs backends of any page size without manual @@ -930,6 +1097,25 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) virtio_init(vdev, VIRTIO_ID_MEM, sizeof(struct virtio_mem_config)); vmem->vq = virtio_add_queue(vdev, 128, virtio_mem_handle_request); + /* + * With "dynamic-memslots=off" (old behavior) we always map the whole + * RAM memory region directly. + */ + if (vmem->dynamic_memslots) { + if (!vmem->mr) { + virtio_mem_prepare_mr(vmem); + } + if (vmem->nb_memslots <= 1) { + vmem->nb_memslots = 1; + vmem->memslot_size = memory_region_size(&vmem->memdev->mr); + } + if (!vmem->memslots) { + virtio_mem_prepare_memslots(vmem); + } + } else { + assert(!vmem->mr && !vmem->nb_memslots && !vmem->memslots); + } + host_memory_backend_set_mapped(vmem->memdev, true); vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); if (vmem->early_migration) { @@ -969,7 +1155,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev) ram_block_coordinated_discard_require(false); } -static int virtio_mem_discard_range_cb(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_discard_range_cb(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size) { RAMBlock *rb = vmem->memdev->mr.ram_block; @@ -984,13 +1170,32 @@ static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) virtio_mem_discard_range_cb); } -static int virtio_mem_post_load(void *opaque, int version_id) +static int virtio_mem_activate_memslot_range_cb(VirtIOMEM *vmem, void *arg, + uint64_t offset, uint64_t size) +{ + virtio_mem_activate_memslots_to_plug(vmem, offset, size); + return 0; +} + +static int virtio_mem_post_load_bitmap(VirtIOMEM *vmem) { - VirtIOMEM *vmem = VIRTIO_MEM(opaque); RamDiscardListener *rdl; int ret; /* + * We restored the bitmap and updated the requested size; activate all + * memslots (so listeners register) before notifying about plugged blocks. + */ + if (vmem->dynamic_memslots) { + /* + * We don't expect any active memslots at this point to deactivate: no + * memory was plugged on the migration destination. + */ + virtio_mem_for_each_plugged_range(vmem, NULL, + virtio_mem_activate_memslot_range_cb); + } + + /* * We started out with all memory discarded and our memory region is mapped * into an address space. Replay, now that we updated the bitmap. */ @@ -1001,6 +1206,20 @@ static int virtio_mem_post_load(void *opaque, int version_id) return ret; } } + return 0; +} + +static int virtio_mem_post_load(void *opaque, int version_id) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + int ret; + + if (!vmem->early_migration) { + ret = virtio_mem_post_load_bitmap(vmem); + if (ret) { + return ret; + } + } /* * If shared RAM is migrated using the file content and not using QEMU, @@ -1021,7 +1240,7 @@ static int virtio_mem_post_load(void *opaque, int version_id) return virtio_mem_restore_unplugged(vmem); } -static int virtio_mem_prealloc_range_cb(const VirtIOMEM *vmem, void *arg, +static int virtio_mem_prealloc_range_cb(VirtIOMEM *vmem, void *arg, uint64_t offset, uint64_t size) { void *area = memory_region_get_ram_ptr(&vmem->memdev->mr) + offset; @@ -1043,7 +1262,7 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) int ret; if (!vmem->prealloc) { - return 0; + goto post_load_bitmap; } /* @@ -1051,7 +1270,7 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) * don't mess with preallocation and postcopy. */ if (migrate_ram_is_ignored(rb)) { - return 0; + goto post_load_bitmap; } /* @@ -1084,7 +1303,10 @@ static int virtio_mem_post_load_early(void *opaque, int version_id) return -EBUSY; } } - return 0; + +post_load_bitmap: + /* Finally, update any other state to be consistent with the new bitmap. */ + return virtio_mem_post_load_bitmap(vmem); } typedef struct VirtIOMEMMigSanityChecks { @@ -1235,11 +1457,79 @@ static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) if (!vmem->memdev) { error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); return NULL; + } else if (vmem->dynamic_memslots) { + if (!vmem->mr) { + virtio_mem_prepare_mr(vmem); + } + return vmem->mr; } return &vmem->memdev->mr; } +static void virtio_mem_decide_memslots(VirtIOMEM *vmem, unsigned int limit) +{ + uint64_t region_size, memslot_size, min_memslot_size; + unsigned int memslots; + RAMBlock *rb; + + if (!vmem->dynamic_memslots) { + return; + } + + /* We're called exactly once, before realizing the device. */ + assert(!vmem->nb_memslots); + + /* If realizing the device will fail, just assume a single memslot. */ + if (limit <= 1 || !vmem->memdev || !vmem->memdev->mr.ram_block) { + vmem->nb_memslots = 1; + return; + } + + rb = vmem->memdev->mr.ram_block; + region_size = memory_region_size(&vmem->memdev->mr); + + /* + * Determine the default block size now, to determine the minimum memslot + * size. We want the minimum slot size to be at least the device block size. + */ + if (!vmem->block_size) { + vmem->block_size = virtio_mem_default_block_size(rb); + } + /* If realizing the device will fail, just assume a single memslot. */ + if (vmem->block_size < qemu_ram_pagesize(rb) || + !QEMU_IS_ALIGNED(region_size, vmem->block_size)) { + vmem->nb_memslots = 1; + return; + } + + /* + * All memslots except the last one have a reasonable minimum size, and + * and all memslot sizes are aligned to the device block size. + */ + memslot_size = QEMU_ALIGN_UP(region_size / limit, vmem->block_size); + min_memslot_size = MAX(vmem->block_size, VIRTIO_MEM_MIN_MEMSLOT_SIZE); + memslot_size = MAX(memslot_size, min_memslot_size); + + memslots = QEMU_ALIGN_UP(region_size, memslot_size) / memslot_size; + if (memslots != 1) { + vmem->memslot_size = memslot_size; + } + vmem->nb_memslots = memslots; +} + +static unsigned int virtio_mem_get_memslots(VirtIOMEM *vmem) +{ + if (!vmem->dynamic_memslots) { + /* Exactly one static RAM memory region. */ + return 1; + } + + /* We're called after instructed to make a decision. */ + g_assert(vmem->nb_memslots); + return vmem->nb_memslots; +} + static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem, Notifier *notifier) { @@ -1377,6 +1667,21 @@ static void virtio_mem_instance_init(Object *obj) NULL, NULL); } +static void virtio_mem_instance_finalize(Object *obj) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + + /* + * Note: the core already dropped the references on all memory regions + * (it's passed as the owner to memory_region_init_*()) and finalized + * these objects. We can simply free the memory. + */ + g_free(vmem->memslots); + vmem->memslots = NULL; + g_free(vmem->mr); + vmem->mr = NULL; +} + static Property virtio_mem_properties[] = { DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0), DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0), @@ -1389,6 +1694,8 @@ static Property virtio_mem_properties[] = { #endif DEFINE_PROP_BOOL(VIRTIO_MEM_EARLY_MIGRATION_PROP, VirtIOMEM, early_migration, true), + DEFINE_PROP_BOOL(VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP, VirtIOMEM, + dynamic_memslots, false), DEFINE_PROP_END_OF_LIST(), }; @@ -1556,6 +1863,8 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data) vmc->fill_device_info = virtio_mem_fill_device_info; vmc->get_memory_region = virtio_mem_get_memory_region; + vmc->decide_memslots = virtio_mem_decide_memslots; + vmc->get_memslots = virtio_mem_get_memslots; vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; vmc->unplug_request_check = virtio_mem_unplug_request_check; @@ -1573,6 +1882,7 @@ static const TypeInfo virtio_mem_info = { .parent = TYPE_VIRTIO_DEVICE, .instance_size = sizeof(VirtIOMEM), .instance_init = virtio_mem_instance_init, + .instance_finalize = virtio_mem_instance_finalize, .class_init = virtio_mem_class_init, .class_size = sizeof(VirtIOMEMClass), .interfaces = (InterfaceInfo[]) { diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index abebd0075a..af1f4bc187 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -1435,6 +1435,24 @@ static int virtio_pci_add_mem_cap(VirtIOPCIProxy *proxy, return offset; } +int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy, + uint8_t bar, uint64_t offset, uint64_t length, + uint8_t id) +{ + struct virtio_pci_cap64 cap = { + .cap.cap_len = sizeof cap, + .cap.cfg_type = VIRTIO_PCI_CAP_SHARED_MEMORY_CFG, + }; + + cap.cap.bar = bar; + cap.cap.length = cpu_to_le32(length); + cap.length_hi = cpu_to_le32(length >> 32); + cap.cap.offset = cpu_to_le32(offset); + cap.offset_hi = cpu_to_le32(offset >> 32); + cap.cap.id = id; + return virtio_pci_add_mem_cap(proxy, &cap.cap); +} + static uint64_t virtio_pci_common_read(void *opaque, hwaddr addr, unsigned size) { diff --git a/hw/virtio/virtio-pmem.c b/hw/virtio/virtio-pmem.c index c3512c2dae..cc24812d2e 100644 --- a/hw/virtio/virtio-pmem.c +++ b/hw/virtio/virtio-pmem.c @@ -147,10 +147,7 @@ static void virtio_pmem_fill_device_info(const VirtIOPMEM *pmem, static MemoryRegion *virtio_pmem_get_memory_region(VirtIOPMEM *pmem, Error **errp) { - if (!pmem->memdev) { - error_setg(errp, "'%s' property must be set", VIRTIO_PMEM_MEMDEV_PROP); - return NULL; - } + assert(pmem->memdev); return &pmem->memdev->mr; } diff --git a/hw/xen/meson.build b/hw/xen/meson.build index 277f9f292b..d887fa9ba4 100644 --- a/hw/xen/meson.build +++ b/hw/xen/meson.build @@ -12,6 +12,10 @@ system_ss.add(when: ['CONFIG_XEN', xen], if_true: files( )) xen_specific_ss = ss.source_set() +xen_specific_ss.add(files( + 'xen-mapcache.c', + 'xen-hvm-common.c', +)) if have_xen_pci_passthrough xen_specific_ss.add(files( 'xen-host-pci-device.c', @@ -26,10 +30,3 @@ else endif specific_ss.add_all(when: ['CONFIG_XEN', xen], if_true: xen_specific_ss) - -xen_ss = ss.source_set() - -xen_ss.add(when: 'CONFIG_XEN', if_true: files( - 'xen-mapcache.c', - 'xen-hvm-common.c', -)) diff --git a/include/block/block-common.h b/include/block/block-common.h index 2d2af7230d..d7599564db 100644 --- a/include/block/block-common.h +++ b/include/block/block-common.h @@ -66,13 +66,16 @@ * function. The coroutine yields after scheduling the BH and is reentered when * the wrapped function returns. * - * A no_co_wrapper_bdrv_wrlock function is a no_co_wrapper function that - * automatically takes the graph wrlock when calling the wrapped function. + * A no_co_wrapper_bdrv_rdlock function is a no_co_wrapper function that + * automatically takes the graph rdlock when calling the wrapped function. In + * the same way, no_co_wrapper_bdrv_wrlock functions automatically take the + * graph wrlock. * * If the first parameter of the function is a BlockDriverState, BdrvChild or * BlockBackend pointer, the AioContext lock for it is taken in the wrapper. */ #define no_co_wrapper +#define no_co_wrapper_bdrv_rdlock #define no_co_wrapper_bdrv_wrlock #include "block/blockjob.h" diff --git a/include/block/block-global-state.h b/include/block/block-global-state.h index 6061220a6c..6bfafe781d 100644 --- a/include/block/block-global-state.h +++ b/include/block/block-global-state.h @@ -132,13 +132,13 @@ int bdrv_reopen_set_read_only(BlockDriverState *bs, bool read_only, Error **errp); BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs, const char *backing_file); -void bdrv_refresh_filename(BlockDriverState *bs); +void GRAPH_RDLOCK bdrv_refresh_filename(BlockDriverState *bs); void GRAPH_RDLOCK bdrv_refresh_limits(BlockDriverState *bs, Transaction *tran, Error **errp); int bdrv_commit(BlockDriverState *bs); -int bdrv_make_empty(BdrvChild *c, Error **errp); +int GRAPH_RDLOCK bdrv_make_empty(BdrvChild *c, Error **errp); int bdrv_change_backing_file(BlockDriverState *bs, const char *backing_file, const char *backing_fmt, bool warn); void bdrv_register(BlockDriver *bdrv); @@ -160,19 +160,20 @@ void bdrv_unfreeze_backing_chain(BlockDriverState *bs, BlockDriverState *base); */ typedef void BlockDriverAmendStatusCB(BlockDriverState *bs, int64_t offset, int64_t total_work_size, void *opaque); -int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts, - BlockDriverAmendStatusCB *status_cb, void *cb_opaque, - bool force, - Error **errp); +int GRAPH_RDLOCK +bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts, + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + bool force, Error **errp); /* check if a named node can be replaced when doing drive-mirror */ BlockDriverState * GRAPH_RDLOCK check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp); -int no_coroutine_fn bdrv_activate(BlockDriverState *bs, Error **errp); +int no_coroutine_fn GRAPH_RDLOCK +bdrv_activate(BlockDriverState *bs, Error **errp); -int coroutine_fn no_co_wrapper +int coroutine_fn no_co_wrapper_bdrv_rdlock bdrv_co_activate(BlockDriverState *bs, Error **errp); void bdrv_activate_all(Error **errp); @@ -191,7 +192,7 @@ int bdrv_has_zero_init_1(BlockDriverState *bs); int bdrv_has_zero_init(BlockDriverState *bs); BlockDriverState *bdrv_find_node(const char *node_name); BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, Error **errp); -XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp); +XDbgBlockGraph * GRAPH_RDLOCK bdrv_get_xdbg_block_graph(Error **errp); BlockDriverState *bdrv_lookup_bs(const char *device, const char *node_name, Error **errp); @@ -208,15 +209,18 @@ typedef struct BdrvNextIterator { BlockDriverState *bs; } BdrvNextIterator; -BlockDriverState *bdrv_first(BdrvNextIterator *it); -BlockDriverState *bdrv_next(BdrvNextIterator *it); +BlockDriverState * GRAPH_RDLOCK bdrv_first(BdrvNextIterator *it); +BlockDriverState * GRAPH_RDLOCK bdrv_next(BdrvNextIterator *it); void bdrv_next_cleanup(BdrvNextIterator *it); BlockDriverState *bdrv_next_monitor_owned(BlockDriverState *bs); void bdrv_iterate_format(void (*it)(void *opaque, const char *name), void *opaque, bool read_only); -char *bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp); -char *bdrv_dirname(BlockDriverState *bs, Error **errp); + +char * GRAPH_RDLOCK +bdrv_get_full_backing_filename(BlockDriverState *bs, Error **errp); + +char * GRAPH_RDLOCK bdrv_dirname(BlockDriverState *bs, Error **errp); void bdrv_img_create(const char *filename, const char *fmt, const char *base_filename, const char *base_fmt, @@ -242,7 +246,9 @@ bdrv_attach_child(BlockDriverState *parent_bs, BdrvChildRole child_role, Error **errp); -bool bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp); +bool GRAPH_RDLOCK +bdrv_op_is_blocked(BlockDriverState *bs, BlockOpType op, Error **errp); + void bdrv_op_block(BlockDriverState *bs, BlockOpType op, Error *reason); void bdrv_op_unblock(BlockDriverState *bs, BlockOpType op, Error *reason); void bdrv_op_block_all(BlockDriverState *bs, Error *reason); diff --git a/include/block/block-io.h b/include/block/block-io.h index f1c796a1ce..ad270b6ad2 100644 --- a/include/block/block-io.h +++ b/include/block/block-io.h @@ -127,37 +127,46 @@ int coroutine_fn GRAPH_RDLOCK bdrv_co_zone_append(BlockDriverState *bs, BdrvRequestFlags flags); bool bdrv_can_write_zeroes_with_unmap(BlockDriverState *bs); -int bdrv_block_status(BlockDriverState *bs, int64_t offset, - int64_t bytes, int64_t *pnum, int64_t *map, - BlockDriverState **file); + +int coroutine_fn GRAPH_RDLOCK +bdrv_co_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, BlockDriverState **file); +int co_wrapper_mixed_bdrv_rdlock +bdrv_block_status(BlockDriverState *bs, int64_t offset, int64_t bytes, + int64_t *pnum, int64_t *map, BlockDriverState **file); int coroutine_fn GRAPH_RDLOCK bdrv_co_block_status_above(BlockDriverState *bs, BlockDriverState *base, int64_t offset, int64_t bytes, int64_t *pnum, int64_t *map, BlockDriverState **file); -int bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, - int64_t offset, int64_t bytes, int64_t *pnum, - int64_t *map, BlockDriverState **file); +int co_wrapper_mixed_bdrv_rdlock +bdrv_block_status_above(BlockDriverState *bs, BlockDriverState *base, + int64_t offset, int64_t bytes, int64_t *pnum, + int64_t *map, BlockDriverState **file); int coroutine_fn GRAPH_RDLOCK bdrv_co_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, int64_t *pnum); -int bdrv_is_allocated(BlockDriverState *bs, int64_t offset, int64_t bytes, - int64_t *pnum); +int co_wrapper_mixed_bdrv_rdlock +bdrv_is_allocated(BlockDriverState *bs, int64_t offset, + int64_t bytes, int64_t *pnum); int coroutine_fn GRAPH_RDLOCK bdrv_co_is_allocated_above(BlockDriverState *top, BlockDriverState *base, bool include_base, int64_t offset, int64_t bytes, int64_t *pnum); -int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base, - bool include_base, int64_t offset, int64_t bytes, - int64_t *pnum); +int co_wrapper_mixed_bdrv_rdlock +bdrv_is_allocated_above(BlockDriverState *bs, BlockDriverState *base, + bool include_base, int64_t offset, + int64_t bytes, int64_t *pnum); int coroutine_fn GRAPH_RDLOCK bdrv_co_is_zero_fast(BlockDriverState *bs, int64_t offset, int64_t bytes); -int bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, - Error **errp); +int GRAPH_RDLOCK +bdrv_apply_auto_read_only(BlockDriverState *bs, const char *errmsg, + Error **errp); + bool bdrv_is_read_only(BlockDriverState *bs); bool bdrv_is_writable(BlockDriverState *bs); bool bdrv_is_sg(BlockDriverState *bs); @@ -176,8 +185,12 @@ const char *bdrv_get_format_name(BlockDriverState *bs); bool bdrv_supports_compressed_writes(BlockDriverState *bs); const char *bdrv_get_node_name(const BlockDriverState *bs); -const char *bdrv_get_device_name(const BlockDriverState *bs); -const char *bdrv_get_device_or_node_name(const BlockDriverState *bs); + +const char * GRAPH_RDLOCK +bdrv_get_device_name(const BlockDriverState *bs); + +const char * GRAPH_RDLOCK +bdrv_get_device_or_node_name(const BlockDriverState *bs); int coroutine_fn GRAPH_RDLOCK bdrv_co_get_info(BlockDriverState *bs, BlockDriverInfo *bdi); @@ -185,8 +198,9 @@ bdrv_co_get_info(BlockDriverState *bs, BlockDriverInfo *bdi); int co_wrapper_mixed_bdrv_rdlock bdrv_get_info(BlockDriverState *bs, BlockDriverInfo *bdi); -ImageInfoSpecific *bdrv_get_specific_info(BlockDriverState *bs, - Error **errp); +ImageInfoSpecific * GRAPH_RDLOCK +bdrv_get_specific_info(BlockDriverState *bs, Error **errp); + BlockStatsSpecific *bdrv_get_specific_stats(BlockDriverState *bs); void bdrv_round_to_subclusters(BlockDriverState *bs, int64_t offset, int64_t bytes, @@ -363,7 +377,7 @@ bdrv_writev_vmstate(BlockDriverState *bs, QEMUIOVector *qiov, int64_t pos); * * Begin a quiesced section for the parent of @c. */ -void bdrv_parent_drained_begin_single(BdrvChild *c); +void GRAPH_RDLOCK bdrv_parent_drained_begin_single(BdrvChild *c); /** * bdrv_parent_drained_poll_single: @@ -371,14 +385,14 @@ void bdrv_parent_drained_begin_single(BdrvChild *c); * Returns true if there is any pending activity to cease before @c can be * called quiesced, false otherwise. */ -bool bdrv_parent_drained_poll_single(BdrvChild *c); +bool GRAPH_RDLOCK bdrv_parent_drained_poll_single(BdrvChild *c); /** * bdrv_parent_drained_end_single: * * End a quiesced section for the parent of @c. */ -void bdrv_parent_drained_end_single(BdrvChild *c); +void GRAPH_RDLOCK bdrv_parent_drained_end_single(BdrvChild *c); /** * bdrv_drain_poll: @@ -391,8 +405,9 @@ void bdrv_parent_drained_end_single(BdrvChild *c); * * This is part of bdrv_drained_begin. */ -bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, - bool ignore_bds_parents); +bool GRAPH_RDLOCK +bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, + bool ignore_bds_parents); /** * bdrv_drained_begin: @@ -400,6 +415,12 @@ bool bdrv_drain_poll(BlockDriverState *bs, BdrvChild *ignore_parent, * Begin a quiesced section for exclusive access to the BDS, by disabling * external request sources including NBD server, block jobs, and device model. * + * This function can only be invoked by the main loop or a coroutine + * (regardless of the AioContext where it is running). + * If the coroutine is running in an Iothread AioContext, this function will + * just schedule a BH to run in the main loop. + * However, it cannot be directly called by an Iothread. + * * This function can be recursive. */ void bdrv_drained_begin(BlockDriverState *bs); @@ -416,6 +437,12 @@ void bdrv_do_drained_begin_quiesce(BlockDriverState *bs, BdrvChild *parent); * bdrv_drained_end: * * End a quiescent section started by bdrv_drained_begin(). + * + * This function can only be invoked by the main loop or a coroutine + * (regardless of the AioContext where it is running). + * If the coroutine is running in an Iothread AioContext, this function will + * just schedule a BH to run in the main loop. + * However, it cannot be directly called by an Iothread. */ void bdrv_drained_end(BlockDriverState *bs); diff --git a/include/block/block_int-common.h b/include/block/block_int-common.h index 2ca3758cb8..b8d9d24f39 100644 --- a/include/block/block_int-common.h +++ b/include/block/block_int-common.h @@ -235,11 +235,14 @@ struct BlockDriver { Error **errp); /* For handling image reopen for split or non-split files. */ - int (*bdrv_reopen_prepare)(BDRVReopenState *reopen_state, - BlockReopenQueue *queue, Error **errp); - void (*bdrv_reopen_commit)(BDRVReopenState *reopen_state); - void (*bdrv_reopen_commit_post)(BDRVReopenState *reopen_state); - void (*bdrv_reopen_abort)(BDRVReopenState *reopen_state); + int GRAPH_UNLOCKED_PTR (*bdrv_reopen_prepare)( + BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp); + void GRAPH_UNLOCKED_PTR (*bdrv_reopen_commit)( + BDRVReopenState *reopen_state); + void GRAPH_UNLOCKED_PTR (*bdrv_reopen_commit_post)( + BDRVReopenState *reopen_state); + void GRAPH_UNLOCKED_PTR (*bdrv_reopen_abort)( + BDRVReopenState *reopen_state); void (*bdrv_join_options)(QDict *options, QDict *old_options); int GRAPH_UNLOCKED_PTR (*bdrv_open)( @@ -256,20 +259,18 @@ struct BlockDriver { int coroutine_fn GRAPH_UNLOCKED_PTR (*bdrv_co_create_opts)( BlockDriver *drv, const char *filename, QemuOpts *opts, Error **errp); - int (*bdrv_amend_options)(BlockDriverState *bs, - QemuOpts *opts, - BlockDriverAmendStatusCB *status_cb, - void *cb_opaque, - bool force, - Error **errp); + int GRAPH_RDLOCK_PTR (*bdrv_amend_options)( + BlockDriverState *bs, QemuOpts *opts, + BlockDriverAmendStatusCB *status_cb, void *cb_opaque, + bool force, Error **errp); - int (*bdrv_make_empty)(BlockDriverState *bs); + int GRAPH_RDLOCK_PTR (*bdrv_make_empty)(BlockDriverState *bs); /* * Refreshes the bs->exact_filename field. If that is impossible, * bs->exact_filename has to be left empty. */ - void (*bdrv_refresh_filename)(BlockDriverState *bs); + void GRAPH_RDLOCK_PTR (*bdrv_refresh_filename)(BlockDriverState *bs); /* * Gathers the open options for all children into @target. @@ -292,15 +293,15 @@ struct BlockDriver { * block driver which implements it is probably doing something * shady regarding its runtime option structure. */ - void (*bdrv_gather_child_options)(BlockDriverState *bs, QDict *target, - bool backing_overridden); + void GRAPH_RDLOCK_PTR (*bdrv_gather_child_options)( + BlockDriverState *bs, QDict *target, bool backing_overridden); /* * Returns an allocated string which is the directory name of this BDS: It * will be used to make relative filenames absolute by prepending this * function's return value to them. */ - char *(*bdrv_dirname)(BlockDriverState *bs, Error **errp); + char * GRAPH_RDLOCK_PTR (*bdrv_dirname)(BlockDriverState *bs, Error **errp); /* * This informs the driver that we are no longer interested in the result @@ -313,14 +314,16 @@ struct BlockDriver { int GRAPH_RDLOCK_PTR (*bdrv_inactivate)(BlockDriverState *bs); - int (*bdrv_snapshot_create)(BlockDriverState *bs, - QEMUSnapshotInfo *sn_info); - int (*bdrv_snapshot_goto)(BlockDriverState *bs, - const char *snapshot_id); - int (*bdrv_snapshot_delete)(BlockDriverState *bs, - const char *snapshot_id, - const char *name, - Error **errp); + int GRAPH_RDLOCK_PTR (*bdrv_snapshot_create)( + BlockDriverState *bs, QEMUSnapshotInfo *sn_info); + + int GRAPH_UNLOCKED_PTR (*bdrv_snapshot_goto)( + BlockDriverState *bs, const char *snapshot_id); + + int GRAPH_RDLOCK_PTR (*bdrv_snapshot_delete)( + BlockDriverState *bs, const char *snapshot_id, const char *name, + Error **errp); + int (*bdrv_snapshot_list)(BlockDriverState *bs, QEMUSnapshotInfo **psn_info); int (*bdrv_snapshot_load_tmp)(BlockDriverState *bs, @@ -725,8 +728,8 @@ struct BlockDriver { int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_get_info)( BlockDriverState *bs, BlockDriverInfo *bdi); - ImageInfoSpecific *(*bdrv_get_specific_info)(BlockDriverState *bs, - Error **errp); + ImageInfoSpecific * GRAPH_RDLOCK_PTR (*bdrv_get_specific_info)( + BlockDriverState *bs, Error **errp); BlockStatsSpecific *(*bdrv_get_specific_stats)(BlockDriverState *bs); int coroutine_fn GRAPH_RDLOCK_PTR (*bdrv_co_save_vmstate)( @@ -963,15 +966,15 @@ struct BdrvChildClass { * Note that this can be nested. If drained_begin() was called twice, new * I/O is allowed only after drained_end() was called twice, too. */ - void (*drained_begin)(BdrvChild *child); - void (*drained_end)(BdrvChild *child); + void GRAPH_RDLOCK_PTR (*drained_begin)(BdrvChild *child); + void GRAPH_RDLOCK_PTR (*drained_end)(BdrvChild *child); /* * Returns whether the parent has pending requests for the child. This * callback is polled after .drained_begin() has been called until all * activity on the child has stopped. */ - bool (*drained_poll)(BdrvChild *child); + bool GRAPH_RDLOCK_PTR (*drained_poll)(BdrvChild *child); /* * Notifies the parent that the filename of its child has changed (e.g. @@ -1039,8 +1042,8 @@ struct BdrvChild { */ bool quiesced_parent; - QLIST_ENTRY(BdrvChild) next; - QLIST_ENTRY(BdrvChild) next_parent; + QLIST_ENTRY(BdrvChild GRAPH_RDLOCK_PTR) next; + QLIST_ENTRY(BdrvChild GRAPH_RDLOCK_PTR) next_parent; }; /* @@ -1173,11 +1176,11 @@ struct BlockDriverState { * See also comment in include/block/block.h, to learn how backing and file * are connected with BdrvChildRole. */ - QLIST_HEAD(, BdrvChild) children; + QLIST_HEAD(, BdrvChild GRAPH_RDLOCK_PTR) children; BdrvChild *backing; BdrvChild *file; - QLIST_HEAD(, BdrvChild) parents; + QLIST_HEAD(, BdrvChild GRAPH_RDLOCK_PTR) parents; QDict *options; QDict *explicit_options; diff --git a/include/block/block_int-io.h b/include/block/block_int-io.h index eb0da7232e..34eac72d7a 100644 --- a/include/block/block_int-io.h +++ b/include/block/block_int-io.h @@ -99,7 +99,7 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size, */ void bdrv_wakeup(BlockDriverState *bs); -const char *bdrv_get_parent_name(const BlockDriverState *bs); +const char * GRAPH_RDLOCK bdrv_get_parent_name(const BlockDriverState *bs); bool blk_dev_has_tray(BlockBackend *blk); bool blk_dev_is_tray_open(BlockBackend *blk); @@ -133,7 +133,7 @@ bdrv_refresh_total_sectors(BlockDriverState *bs, int64_t hint); BdrvChild *bdrv_cow_child(BlockDriverState *bs); BdrvChild *bdrv_filter_child(BlockDriverState *bs); BdrvChild *bdrv_filter_or_cow_child(BlockDriverState *bs); -BdrvChild *bdrv_primary_child(BlockDriverState *bs); +BdrvChild * GRAPH_RDLOCK bdrv_primary_child(BlockDriverState *bs); BlockDriverState *bdrv_skip_filters(BlockDriverState *bs); BlockDriverState *bdrv_backing_chain_next(BlockDriverState *bs); @@ -155,7 +155,8 @@ static inline BlockDriverState *bdrv_filter_or_cow_bs(BlockDriverState *bs) return child_bs(bdrv_filter_or_cow_child(bs)); } -static inline BlockDriverState *bdrv_primary_bs(BlockDriverState *bs) +static inline BlockDriverState * GRAPH_RDLOCK +bdrv_primary_bs(BlockDriverState *bs) { IO_CODE(); return child_bs(bdrv_primary_child(bs)); diff --git a/include/block/graph-lock.h b/include/block/graph-lock.h index 7e04f98ff0..6f1cd12745 100644 --- a/include/block/graph-lock.h +++ b/include/block/graph-lock.h @@ -116,7 +116,8 @@ void unregister_aiocontext(AioContext *ctx); * This function polls. Callers must not hold the lock of any AioContext other * than the current one and the one of @bs. */ -void bdrv_graph_wrlock(BlockDriverState *bs) TSA_ACQUIRE(graph_lock) TSA_NO_TSA; +void no_coroutine_fn TSA_ACQUIRE(graph_lock) TSA_NO_TSA +bdrv_graph_wrlock(BlockDriverState *bs); /* * bdrv_graph_wrunlock: diff --git a/include/block/qapi.h b/include/block/qapi.h index 8663971c58..54c48de26a 100644 --- a/include/block/qapi.h +++ b/include/block/qapi.h @@ -29,18 +29,17 @@ #include "block/snapshot.h" #include "qapi/qapi-types-block-core.h" -BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, - BlockDriverState *bs, - bool flat, - Error **errp); -int bdrv_query_snapshot_info_list(BlockDriverState *bs, - SnapshotInfoList **p_list, - Error **errp); -void bdrv_query_image_info(BlockDriverState *bs, - ImageInfo **p_info, - bool flat, - bool skip_implicit_filters, - Error **errp); +BlockDeviceInfo * GRAPH_RDLOCK +bdrv_block_device_info(BlockBackend *blk, BlockDriverState *bs, + bool flat, Error **errp); + +int GRAPH_RDLOCK +bdrv_query_snapshot_info_list(BlockDriverState *bs, + SnapshotInfoList **p_list, + Error **errp); +void GRAPH_RDLOCK +bdrv_query_image_info(BlockDriverState *bs, ImageInfo **p_info, bool flat, + bool skip_implicit_filters, Error **errp); void GRAPH_RDLOCK bdrv_query_block_graph_info(BlockDriverState *bs, BlockGraphInfo **p_info, Error **errp); diff --git a/include/block/snapshot.h b/include/block/snapshot.h index 50ff924710..d49c5599d9 100644 --- a/include/block/snapshot.h +++ b/include/block/snapshot.h @@ -25,6 +25,7 @@ #ifndef SNAPSHOT_H #define SNAPSHOT_H +#include "block/graph-lock.h" #include "qapi/qapi-builtin-types.h" #define SNAPSHOT_OPT_BASE "snapshot." @@ -59,16 +60,19 @@ bool bdrv_snapshot_find_by_id_and_name(BlockDriverState *bs, const char *name, QEMUSnapshotInfo *sn_info, Error **errp); -int bdrv_can_snapshot(BlockDriverState *bs); -int bdrv_snapshot_create(BlockDriverState *bs, - QEMUSnapshotInfo *sn_info); -int bdrv_snapshot_goto(BlockDriverState *bs, - const char *snapshot_id, - Error **errp); -int bdrv_snapshot_delete(BlockDriverState *bs, - const char *snapshot_id, - const char *name, - Error **errp); + +int GRAPH_RDLOCK bdrv_can_snapshot(BlockDriverState *bs); + +int GRAPH_RDLOCK +bdrv_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info); + +int GRAPH_UNLOCKED +bdrv_snapshot_goto(BlockDriverState *bs, const char *snapshot_id, Error **errp); + +int GRAPH_RDLOCK +bdrv_snapshot_delete(BlockDriverState *bs, const char *snapshot_id, + const char *name, Error **errp); + int bdrv_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_info); int bdrv_snapshot_load_tmp(BlockDriverState *bs, diff --git a/include/block/ufs.h b/include/block/ufs.h index fd884eb8ce..7631a5af10 100644 --- a/include/block/ufs.h +++ b/include/block/ufs.h @@ -111,14 +111,14 @@ REG32(UECT, offsetof(UfsReg, uect)) REG32(UECDME, offsetof(UfsReg, uecdme)) REG32(UTRIACR, offsetof(UfsReg, utriacr)) REG32(UTRLBA, offsetof(UfsReg, utrlba)) - FIELD(UTRLBA, UTRLBA, 9, 22) + FIELD(UTRLBA, UTRLBA, 10, 22) REG32(UTRLBAU, offsetof(UfsReg, utrlbau)) REG32(UTRLDBR, offsetof(UfsReg, utrldbr)) REG32(UTRLCLR, offsetof(UfsReg, utrlclr)) REG32(UTRLRSR, offsetof(UfsReg, utrlrsr)) REG32(UTRLCNR, offsetof(UfsReg, utrlcnr)) REG32(UTMRLBA, offsetof(UfsReg, utmrlba)) - FIELD(UTMRLBA, UTMRLBA, 9, 22) + FIELD(UTMRLBA, UTMRLBA, 10, 22) REG32(UTMRLBAU, offsetof(UfsReg, utmrlbau)) REG32(UTMRLDBR, offsetof(UfsReg, utmrldbr)) REG32(UTMRLCLR, offsetof(UfsReg, utmrlclr)) diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index 605b160a7e..30c376a4de 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -83,6 +83,21 @@ void qemu_ram_remap(ram_addr_t addr, ram_addr_t length); ram_addr_t qemu_ram_addr_from_host(void *ptr); ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr); RAMBlock *qemu_ram_block_by_name(const char *name); + +/* + * Translates a host ptr back to a RAMBlock and an offset in that RAMBlock. + * + * @ptr: The host pointer to translate. + * @round_offset: Whether to round the result offset down to a target page + * @offset: Will be set to the offset within the returned RAMBlock. + * + * Returns: RAMBlock (or NULL if not found) + * + * By the time this function returns, the returned pointer is not protected + * by RCU anymore. If the caller is not within an RCU critical section and + * does not hold the iothread lock, it must have other means of protecting the + * pointer, such as a reference to the memory region that owns the RAMBlock. + */ RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset, ram_addr_t *offset); ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host); diff --git a/include/exec/memory.h b/include/exec/memory.h index c99842d2fc..653a32ea10 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -95,6 +95,7 @@ struct ReservedRegion { * relative to the region's address space * @readonly: writes to this section are ignored * @nonvolatile: this section is non-volatile + * @unmergeable: this section should not get merged with adjacent sections */ struct MemoryRegionSection { Int128 size; @@ -104,6 +105,7 @@ struct MemoryRegionSection { hwaddr offset_within_address_space; bool readonly; bool nonvolatile; + bool unmergeable; }; typedef struct IOMMUTLBEntry IOMMUTLBEntry; @@ -599,8 +601,9 @@ typedef void (*ReplayRamDiscard)(MemoryRegionSection *section, void *opaque); * populated (consuming memory), to be used/accessed by the VM. * * A #RamDiscardManager can only be set for a RAM #MemoryRegion while the - * #MemoryRegion isn't mapped yet; it cannot change while the #MemoryRegion is - * mapped. + * #MemoryRegion isn't mapped into an address space yet (either directly + * or via an alias); it cannot change while the #MemoryRegion is + * mapped into an address space. * * The #RamDiscardManager is intended to be used by technologies that are * incompatible with discarding of RAM (e.g., VFIO, which may pin all @@ -772,6 +775,7 @@ struct MemoryRegion { bool nonvolatile; bool rom_device; bool flush_coalesced_mmio; + bool unmergeable; uint8_t dirty_log_mask; bool is_iommu; RAMBlock *ram_block; @@ -2350,6 +2354,25 @@ void memory_region_set_size(MemoryRegion *mr, uint64_t size); void memory_region_set_alias_offset(MemoryRegion *mr, hwaddr offset); +/* + * memory_region_set_unmergeable: Set a memory region unmergeable + * + * Mark a memory region unmergeable, resulting in the memory region (or + * everything contained in a memory region container) not getting merged when + * simplifying the address space and notifying memory listeners. Consequently, + * memory listeners will never get notified about ranges that are larger than + * the original memory regions. + * + * This is primarily useful when multiple aliases to a RAM memory region are + * mapped into a memory region container, and updates (e.g., enable/disable or + * map/unmap) of individual memory region aliases are not supposed to affect + * other memory regions in the same container. + * + * @mr: the #MemoryRegion to be updated + * @unmergeable: whether to mark the #MemoryRegion unmergeable + */ +void memory_region_set_unmergeable(MemoryRegion *mr, bool unmergeable); + /** * memory_region_present: checks if an address relative to a @container * translates into #MemoryRegion within @container diff --git a/include/hw/acpi/pcihp.h b/include/hw/acpi/pcihp.h index ef59810c17..ac21a95913 100644 --- a/include/hw/acpi/pcihp.h +++ b/include/hw/acpi/pcihp.h @@ -56,7 +56,7 @@ typedef struct AcpiPciHpState { } AcpiPciHpState; void acpi_pcihp_init(Object *owner, AcpiPciHpState *, PCIBus *root, - MemoryRegion *address_space_io, uint16_t io_base); + MemoryRegion *io, uint16_t io_base); bool acpi_pcihp_is_hotpluggbale_bus(AcpiPciHpState *s, BusState *bus); void acpi_pcihp_device_pre_plug_cb(HotplugHandler *hotplug_dev, diff --git a/include/hw/arm/bsa.h b/include/hw/arm/bsa.h new file mode 100644 index 0000000000..8eaab603c0 --- /dev/null +++ b/include/hw/arm/bsa.h @@ -0,0 +1,35 @@ +/* + * Common definitions for Arm Base System Architecture (BSA) platforms. + * + * Copyright (c) 2015 Linaro Limited + * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2 or later, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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/>. + * + */ + +#ifndef QEMU_ARM_BSA_H +#define QEMU_ARM_BSA_H + +/* These are architectural INTID values */ +#define VIRTUAL_PMU_IRQ 23 +#define ARCH_GIC_MAINT_IRQ 25 +#define ARCH_TIMER_NS_EL2_IRQ 26 +#define ARCH_TIMER_VIRT_IRQ 27 +#define ARCH_TIMER_NS_EL2_VIRT_IRQ 28 +#define ARCH_TIMER_S_EL1_IRQ 29 +#define ARCH_TIMER_NS_EL1_IRQ 30 + +#define INTID_TO_PPI(irq) ((irq) - 16) + +#endif /* QEMU_ARM_BSA_H */ diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index 68db19f0cb..d33fe38586 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -30,7 +30,7 @@ #include "hw/intc/exynos4210_gic.h" #include "hw/intc/exynos4210_combiner.h" #include "hw/core/split-irq.h" -#include "target/arm/cpu-qom.h" +#include "hw/arm/boot.h" #include "qom/object.h" #define EXYNOS4210_NCPUS 2 diff --git a/include/hw/misc/raspberrypi-fw-defs.h b/include/hw/arm/raspberrypi-fw-defs.h index 4551fe7450..4551fe7450 100644 --- a/include/hw/misc/raspberrypi-fw-defs.h +++ b/include/hw/arm/raspberrypi-fw-defs.h diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index e1ddbea96b..f69239850e 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -34,6 +34,7 @@ #include "qemu/notify.h" #include "hw/boards.h" #include "hw/arm/boot.h" +#include "hw/arm/bsa.h" #include "hw/block/flash.h" #include "sysemu/kvm.h" #include "hw/intc/arm_gicv3_common.h" @@ -43,17 +44,6 @@ #define NUM_VIRTIO_TRANSPORTS 32 #define NUM_SMMU_IRQS 4 -#define ARCH_GIC_MAINT_IRQ 9 - -#define ARCH_TIMER_VIRT_IRQ 11 -#define ARCH_TIMER_S_EL1_IRQ 13 -#define ARCH_TIMER_NS_EL1_IRQ 14 -#define ARCH_TIMER_NS_EL2_IRQ 10 - -#define VIRTUAL_PMU_IRQ 7 - -#define PPI(irq) ((irq) + 16) - /* See Linux kernel arch/arm64/include/asm/pvclock-abi.h */ #define PVTIME_SIZE_PER_CPU 64 diff --git a/include/hw/audio/pcspk.h b/include/hw/audio/pcspk.h index 9506179587..6be75a6b86 100644 --- a/include/hw/audio/pcspk.h +++ b/include/hw/audio/pcspk.h @@ -25,16 +25,6 @@ #ifndef HW_PCSPK_H #define HW_PCSPK_H -#include "hw/isa/isa.h" -#include "hw/qdev-properties.h" -#include "qapi/error.h" - #define TYPE_PC_SPEAKER "isa-pcspk" -static inline void pcspk_init(ISADevice *isadev, ISABus *bus, ISADevice *pit) -{ - object_property_set_link(OBJECT(isadev), "pit", OBJECT(pit), NULL); - isa_realize_and_unref(isadev, bus, &error_fatal); -} - #endif /* HW_PCSPK_H */ diff --git a/include/hw/boards.h b/include/hw/boards.h index 55a64a13fd..43a56dc51e 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -297,15 +297,27 @@ struct MachineClass { * DeviceMemoryState: * @base: address in guest physical address space where the memory * address space for memory devices starts - * @mr: address space container for memory devices + * @mr: memory region container for memory devices + * @as: address space for memory devices + * @listener: memory listener used to track used memslots in the address space * @dimm_size: the sum of plugged DIMMs' sizes * @used_region_size: the part of @mr already used by memory devices + * @required_memslots: the number of memslots required by memory devices + * @used_memslots: the number of memslots currently used by memory devices + * @memslot_auto_decision_active: whether any plugged memory device + * automatically decided to use more than + * one memslot */ typedef struct DeviceMemoryState { hwaddr base; MemoryRegion mr; + AddressSpace as; + MemoryListener listener; uint64_t dimm_size; uint64_t used_region_size; + unsigned int required_memslots; + unsigned int used_memslots; + unsigned int memslot_auto_decision_active; } DeviceMemoryState; /** diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index 3968369554..18593db5b2 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -618,8 +618,10 @@ bool cpu_paging_enabled(const CPUState *cpu); * @cpu: The CPU whose memory mappings are to be obtained. * @list: Where to write the memory mappings to. * @errp: Pointer for reporting an #Error. + * + * Returns: %true on success, %false otherwise. */ -void cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, +bool cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, Error **errp); #if !defined(CONFIG_USER_ONLY) diff --git a/include/hw/core/sysemu-cpu-ops.h b/include/hw/core/sysemu-cpu-ops.h index ee169b872c..24d003fe04 100644 --- a/include/hw/core/sysemu-cpu-ops.h +++ b/include/hw/core/sysemu-cpu-ops.h @@ -19,7 +19,7 @@ typedef struct SysemuCPUOps { /** * @get_memory_mapping: Callback for obtaining the memory mappings. */ - void (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, + bool (*get_memory_mapping)(CPUState *cpu, MemoryMappingList *list, Error **errp); /** * @get_paging_enabled: Callback for inquiring whether paging is enabled. diff --git a/include/hw/display/ramfb.h b/include/hw/display/ramfb.h index b33a2c467b..a7e0019144 100644 --- a/include/hw/display/ramfb.h +++ b/include/hw/display/ramfb.h @@ -1,11 +1,15 @@ #ifndef RAMFB_H #define RAMFB_H +#include "migration/vmstate.h" + /* ramfb.c */ typedef struct RAMFBState RAMFBState; void ramfb_display_update(QemuConsole *con, RAMFBState *s); RAMFBState *ramfb_setup(Error **errp); +extern const VMStateDescription ramfb_vmstate; + /* ramfb-standalone.c */ #define TYPE_RAMFB_DEVICE "ramfb" diff --git a/include/hw/loongarch/virt.h b/include/hw/loongarch/virt.h index f1659655c6..674f4655e0 100644 --- a/include/hw/loongarch/virt.h +++ b/include/hw/loongarch/virt.h @@ -16,8 +16,6 @@ #define LOONGARCH_MAX_CPUS 256 -#define VIRT_ISA_IO_BASE 0x18000000UL -#define VIRT_ISA_IO_SIZE 0x0004000 #define VIRT_FWCFG_BASE 0x1e020000UL #define VIRT_BIOS_BASE 0x1c000000UL #define VIRT_BIOS_SIZE (4 * MiB) @@ -38,7 +36,6 @@ struct LoongArchMachineState { MemoryRegion lowmem; MemoryRegion highmem; - MemoryRegion isa_io; MemoryRegion bios; bool bios_loaded; /* State for other subsystems/APIs: */ diff --git a/include/hw/mem/memory-device.h b/include/hw/mem/memory-device.h index 48d2611fc5..3354d6c166 100644 --- a/include/hw/mem/memory-device.h +++ b/include/hw/mem/memory-device.h @@ -14,6 +14,7 @@ #define MEMORY_DEVICE_H #include "hw/qdev-core.h" +#include "qemu/typedefs.h" #include "qapi/qapi-types-machine.h" #include "qom/object.h" @@ -41,6 +42,17 @@ typedef struct MemoryDeviceState MemoryDeviceState; * successive memory regions are used, a covering memory region has to * be provided. Scattered memory regions are not supported for single * devices. + * + * The device memory region returned via @get_memory_region may either be a + * single RAM memory region or a memory region container with subregions + * that are RAM memory regions or aliases to RAM memory regions. Other + * memory regions or subregions are not supported. + * + * If the device memory region returned via @get_memory_region is a + * memory region container, it's supported to dynamically (un)map subregions + * as long as the number of memslots returned by @get_memslots() won't + * be exceeded and as long as all memory regions are of the same kind (e.g., + * all RAM or all ROM). */ struct MemoryDeviceClass { /* private */ @@ -89,6 +101,28 @@ struct MemoryDeviceClass { MemoryRegion *(*get_memory_region)(MemoryDeviceState *md, Error **errp); /* + * Optional: Instruct the memory device to decide how many memory slots + * it requires, not exceeding the given limit. + * + * Called exactly once when pre-plugging the memory device, before + * querying the number of memslots using @get_memslots the first time. + */ + void (*decide_memslots)(MemoryDeviceState *md, unsigned int limit); + + /* + * Optional for memory devices that require only a single memslot, + * required for all other memory devices: Return the number of memslots + * (distinct RAM memory regions in the device memory region) that are + * required by the device. + * + * If this function is not implemented, the assumption is "1". + * + * Called when (un)plugging the memory device, to check if the requirements + * can be satisfied, and to do proper accounting. + */ + unsigned int (*get_memslots)(MemoryDeviceState *md); + + /* * Optional: Return the desired minimum alignment of the device in guest * physical address space. The final alignment is computed based on this * alignment and the alignment requirements of the memory region. @@ -105,8 +139,31 @@ struct MemoryDeviceClass { MemoryDeviceInfo *info); }; +/* + * Traditionally, KVM/vhost in many setups supported 509 memslots, whereby + * 253 memslots were "reserved" for boot memory and other devices (such + * as PCI BARs, which can get mapped dynamically) and 256 memslots were + * dedicated for DIMMs. These magic numbers worked reliably in the past. + * + * Further, using many memslots can negatively affect performance, so setting + * the soft-limit of memslots used by memory devices to the traditional + * DIMM limit of 256 sounds reasonable. + * + * If we have less than 509 memslots, we will instruct memory devices that + * support automatically deciding how many memslots to use to only use a single + * one. + * + * Hotplugging vhost devices with at least 509 memslots is not expected to + * cause problems, not even when devices automatically decided how many memslots + * to use. + */ +#define MEMORY_DEVICES_SOFT_MEMSLOT_LIMIT 256 +#define MEMORY_DEVICES_SAFE_MAX_MEMSLOTS 509 + MemoryDeviceInfoList *qmp_memory_device_list(void); uint64_t get_plugged_memory_size(void); +unsigned int memory_devices_get_reserved_memslots(void); +bool memory_devices_memslot_auto_decision_active(void); void memory_device_pre_plug(MemoryDeviceState *md, MachineState *ms, const uint64_t *legacy_align, Error **errp); void memory_device_plug(MemoryDeviceState *md, MachineState *ms); diff --git a/include/hw/mips/cpudevs.h b/include/hw/mips/cpudevs.h deleted file mode 100644 index f7c9728fa9..0000000000 --- a/include/hw/mips/cpudevs.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef HW_MIPS_CPUDEVS_H -#define HW_MIPS_CPUDEVS_H - -#include "target/mips/cpu-qom.h" - -/* Definitions for MIPS CPU internal devices. */ - -/* mips_int.c */ -void cpu_mips_irq_init_cpu(MIPSCPU *cpu); - -/* mips_timer.c */ -void cpu_mips_clock_init(MIPSCPU *cpu); - -#endif diff --git a/include/hw/misc/mips_itu.h b/include/hw/misc/mips_itu.h index 35218b2d14..5caed6cc36 100644 --- a/include/hw/misc/mips_itu.h +++ b/include/hw/misc/mips_itu.h @@ -73,10 +73,12 @@ struct MIPSITUState { /* SAAR */ uint64_t *saar; - MIPSCPU *cpu0; + ArchCPU *cpu0; }; /* Get ITC Configuration Tag memory region. */ MemoryRegion *mips_itu_get_tag_region(MIPSITUState *itu); +void itc_reconfigure(struct MIPSITUState *tag); + #endif /* MIPS_ITU_H */ diff --git a/include/hw/nvram/xlnx-bbram.h b/include/hw/nvram/xlnx-bbram.h index 87d59ef3c0..6fc13f8cc1 100644 --- a/include/hw/nvram/xlnx-bbram.h +++ b/include/hw/nvram/xlnx-bbram.h @@ -34,7 +34,7 @@ #define RMAX_XLNX_BBRAM ((0x4c / 4) + 1) -#define TYPE_XLNX_BBRAM "xlnx,bbram-ctrl" +#define TYPE_XLNX_BBRAM "xlnx.bbram-ctrl" OBJECT_DECLARE_SIMPLE_TYPE(XlnxBBRam, XLNX_BBRAM); struct XlnxBBRam { diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index b70a0b95ff..ea5aff118b 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -279,12 +279,10 @@ bool pci_bus_is_express(const PCIBus *bus); void pci_root_bus_init(PCIBus *bus, size_t bus_size, DeviceState *parent, const char *name, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, const char *typename); PCIBus *pci_root_bus_new(DeviceState *parent, const char *name, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, const char *typename); void pci_root_bus_cleanup(PCIBus *bus); void pci_bus_irqs(PCIBus *bus, pci_set_irq_fn set_irq, @@ -304,8 +302,7 @@ int pci_swizzle_map_irq_fn(PCIDevice *pci_dev, int pin); PCIBus *pci_register_root_bus(DeviceState *parent, const char *name, pci_set_irq_fn set_irq, pci_map_irq_fn map_irq, void *irq_opaque, - MemoryRegion *address_space_mem, - MemoryRegion *address_space_io, + MemoryRegion *mem, MemoryRegion *io, uint8_t devfn_min, int nirq, const char *typename); void pci_unregister_root_bus(PCIBus *bus); diff --git a/include/hw/ppc/pnv_xscom.h b/include/hw/ppc/pnv_xscom.h index 9bc6463547..35b19610f7 100644 --- a/include/hw/ppc/pnv_xscom.h +++ b/include/hw/ppc/pnv_xscom.h @@ -170,7 +170,7 @@ struct PnvXScomInterfaceClass { #define PNV10_XSCOM_PEC_PCI_BASE 0x8010800 /* index goes upwards ... */ #define PNV10_XSCOM_PEC_PCI_SIZE 0x200 -void pnv_xscom_realize(PnvChip *chip, uint64_t size, Error **errp); +void pnv_xscom_init(PnvChip *chip, uint64_t size, hwaddr addr); int pnv_dt_xscom(PnvChip *chip, void *fdt, int root_offset, uint64_t xscom_base, uint64_t xscom_size, const char *compat, int compat_size); diff --git a/include/hw/s390x/vfio-ccw.h b/include/hw/s390x/vfio-ccw.h index 63a909eb7e..4209d27657 100644 --- a/include/hw/s390x/vfio-ccw.h +++ b/include/hw/s390x/vfio-ccw.h @@ -22,6 +22,4 @@ #define TYPE_VFIO_CCW "vfio-ccw" OBJECT_DECLARE_SIMPLE_TYPE(VFIOCCWDevice, VFIO_CCW) -#define TYPE_VFIO_CCW "vfio-ccw" - #endif diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index e9b8954595..7780b9073a 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -98,6 +98,7 @@ typedef struct VFIOContainer { QLIST_HEAD(, VFIOGroup) group_list; QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainer) next; + QLIST_HEAD(, VFIODevice) device_list; } VFIOContainer; typedef struct VFIOGuestIOMMU { @@ -129,7 +130,10 @@ typedef struct VFIODeviceOps VFIODeviceOps; typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; + QLIST_ENTRY(VFIODevice) container_next; + QLIST_ENTRY(VFIODevice) global_next; struct VFIOGroup *group; + VFIOContainer *container; char *sysfsdev; char *name; DeviceState *dev; @@ -196,7 +200,36 @@ typedef struct VFIODisplay { } dmabuf; } VFIODisplay; -void vfio_put_base_device(VFIODevice *vbasedev); +typedef struct { + unsigned long *bitmap; + hwaddr size; + hwaddr pages; +} VFIOBitmap; + +void vfio_host_win_add(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova, + uint64_t iova_pgsizes); +int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova); +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as); +void vfio_put_address_space(VFIOAddressSpace *space); +bool vfio_devices_all_running_and_saving(VFIOContainer *container); + +/* container->fd */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb); +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly); +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start); +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size); + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp); +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section); + void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); @@ -214,15 +247,22 @@ void vfio_region_unmap(VFIORegion *region); void vfio_region_exit(VFIORegion *region); void vfio_region_finalize(VFIORegion *region); void vfio_reset_handler(void *opaque); -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp); -void vfio_put_group(VFIOGroup *group); struct vfio_device_info *vfio_get_device_info(int fd); -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp); +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); +void vfio_detach_device(VFIODevice *vbasedev); + +int vfio_kvm_device_add_fd(int fd, Error **errp); +int vfio_kvm_device_del_fd(int fd, Error **errp); extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; +typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; extern VFIOGroupList vfio_group_list; +extern VFIODeviceList vfio_device_list; + +extern const MemoryListener vfio_memory_listener; +extern int vfio_kvm_device_fd; bool vfio_mig_active(void); int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **errp); @@ -245,6 +285,8 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, unsigned int *avail); struct vfio_info_cap_header * vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id); +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id); #endif extern const MemoryListener vfio_prereg_listener; @@ -257,4 +299,12 @@ int vfio_spapr_remove_window(VFIOContainer *container, bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); void vfio_migration_exit(VFIODevice *vbasedev); +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container); +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container); +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size); +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr); #endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h index 1860b541d8..96ccc18cd3 100644 --- a/include/hw/virtio/vhost-backend.h +++ b/include/hw/virtio/vhost-backend.h @@ -86,9 +86,6 @@ typedef int (*vhost_set_vring_enable_op)(struct vhost_dev *dev, typedef bool (*vhost_requires_shm_log_op)(struct vhost_dev *dev); typedef int (*vhost_migration_done_op)(struct vhost_dev *dev, char *mac_addr); -typedef bool (*vhost_backend_can_merge_op)(struct vhost_dev *dev, - uint64_t start1, uint64_t size1, - uint64_t start2, uint64_t size2); typedef int (*vhost_vsock_set_guest_cid_op)(struct vhost_dev *dev, uint64_t guest_cid); typedef int (*vhost_vsock_set_running_op)(struct vhost_dev *dev, int start); @@ -108,8 +105,7 @@ typedef int (*vhost_crypto_create_session_op)(struct vhost_dev *dev, typedef int (*vhost_crypto_close_session_op)(struct vhost_dev *dev, uint64_t session_id); -typedef bool (*vhost_backend_mem_section_filter_op)(struct vhost_dev *dev, - MemoryRegionSection *section); +typedef bool (*vhost_backend_no_private_memslots_op)(struct vhost_dev *dev); typedef int (*vhost_get_inflight_fd_op)(struct vhost_dev *dev, uint16_t queue_size, @@ -138,6 +134,7 @@ typedef struct VhostOps { vhost_backend_init vhost_backend_init; vhost_backend_cleanup vhost_backend_cleanup; vhost_backend_memslots_limit vhost_backend_memslots_limit; + vhost_backend_no_private_memslots_op vhost_backend_no_private_memslots; vhost_net_set_backend_op vhost_net_set_backend; vhost_net_set_mtu_op vhost_net_set_mtu; vhost_scsi_set_endpoint_op vhost_scsi_set_endpoint; @@ -163,7 +160,6 @@ typedef struct VhostOps { vhost_set_vring_enable_op vhost_set_vring_enable; vhost_requires_shm_log_op vhost_requires_shm_log; vhost_migration_done_op vhost_migration_done; - vhost_backend_can_merge_op vhost_backend_can_merge; vhost_vsock_set_guest_cid_op vhost_vsock_set_guest_cid; vhost_vsock_set_running_op vhost_vsock_set_running; vhost_set_iotlb_callback_op vhost_set_iotlb_callback; @@ -172,7 +168,6 @@ typedef struct VhostOps { vhost_set_config_op vhost_set_config; vhost_crypto_create_session_op vhost_crypto_create_session; vhost_crypto_close_session_op vhost_crypto_close_session; - vhost_backend_mem_section_filter_op vhost_backend_mem_section_filter; vhost_get_inflight_fd_op vhost_get_inflight_fd; vhost_set_inflight_fd_op vhost_set_inflight_fd; vhost_dev_start_op vhost_dev_start; diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h index 6a173cb9fa..c7e5467693 100644 --- a/include/hw/virtio/vhost.h +++ b/include/hw/virtio/vhost.h @@ -315,7 +315,8 @@ uint64_t vhost_get_features(struct vhost_dev *hdev, const int *feature_bits, */ void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits, uint64_t features); -bool vhost_has_free_slot(void); +unsigned int vhost_get_max_memslots(void); +unsigned int vhost_get_free_memslots(void); int vhost_net_set_backend(struct vhost_dev *hdev, struct vhost_vring_file *file); diff --git a/include/hw/virtio/virtio-gpu-bswap.h b/include/hw/virtio/virtio-gpu-bswap.h index 637a0585d0..dd1975e2d4 100644 --- a/include/hw/virtio/virtio-gpu-bswap.h +++ b/include/hw/virtio/virtio-gpu-bswap.h @@ -71,6 +71,21 @@ virtio_gpu_create_blob_bswap(struct virtio_gpu_resource_create_blob *cblob) } static inline void +virtio_gpu_map_blob_bswap(struct virtio_gpu_resource_map_blob *mblob) +{ + virtio_gpu_ctrl_hdr_bswap(&mblob->hdr); + le32_to_cpus(&mblob->resource_id); + le64_to_cpus(&mblob->offset); +} + +static inline void +virtio_gpu_unmap_blob_bswap(struct virtio_gpu_resource_unmap_blob *ublob) +{ + virtio_gpu_ctrl_hdr_bswap(&ublob->hdr); + le32_to_cpus(&ublob->resource_id); +} + +static inline void virtio_gpu_scanout_blob_bswap(struct virtio_gpu_set_scanout_blob *ssb) { virtio_gpu_bswap_32(ssb, sizeof(*ssb) - sizeof(ssb->offsets[3])); diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h index 390c4642b8..584ba2ed73 100644 --- a/include/hw/virtio/virtio-gpu.h +++ b/include/hw/virtio/virtio-gpu.h @@ -38,6 +38,9 @@ OBJECT_DECLARE_SIMPLE_TYPE(VirtIOGPUGL, VIRTIO_GPU_GL) #define TYPE_VHOST_USER_GPU "vhost-user-gpu" OBJECT_DECLARE_SIMPLE_TYPE(VhostUserGPU, VHOST_USER_GPU) +#define TYPE_VIRTIO_GPU_RUTABAGA "virtio-gpu-rutabaga-device" +OBJECT_DECLARE_SIMPLE_TYPE(VirtIOGPURutabaga, VIRTIO_GPU_RUTABAGA) + struct virtio_gpu_simple_resource { uint32_t resource_id; uint32_t width; @@ -93,6 +96,8 @@ enum virtio_gpu_base_conf_flags { VIRTIO_GPU_FLAG_EDID_ENABLED, VIRTIO_GPU_FLAG_DMABUF_ENABLED, VIRTIO_GPU_FLAG_BLOB_ENABLED, + VIRTIO_GPU_FLAG_CONTEXT_INIT_ENABLED, + VIRTIO_GPU_FLAG_RUTABAGA_ENABLED, }; #define virtio_gpu_virgl_enabled(_cfg) \ @@ -105,12 +110,19 @@ enum virtio_gpu_base_conf_flags { (_cfg.flags & (1 << VIRTIO_GPU_FLAG_DMABUF_ENABLED)) #define virtio_gpu_blob_enabled(_cfg) \ (_cfg.flags & (1 << VIRTIO_GPU_FLAG_BLOB_ENABLED)) +#define virtio_gpu_context_init_enabled(_cfg) \ + (_cfg.flags & (1 << VIRTIO_GPU_FLAG_CONTEXT_INIT_ENABLED)) +#define virtio_gpu_rutabaga_enabled(_cfg) \ + (_cfg.flags & (1 << VIRTIO_GPU_FLAG_RUTABAGA_ENABLED)) +#define virtio_gpu_hostmem_enabled(_cfg) \ + (_cfg.hostmem > 0) struct virtio_gpu_base_conf { uint32_t max_outputs; uint32_t flags; uint32_t xres; uint32_t yres; + uint64_t hostmem; }; struct virtio_gpu_ctrl_command { @@ -134,6 +146,8 @@ struct VirtIOGPUBase { int renderer_blocked; int enable; + MemoryRegion hostmem; + struct virtio_gpu_scanout scanout[VIRTIO_GPU_MAX_SCANOUTS]; int enabled_output_bitmask; @@ -224,14 +238,35 @@ struct VhostUserGPU { bool backend_blocked; }; +#define MAX_SLOTS 4096 + +struct MemoryRegionInfo { + int used; + MemoryRegion mr; + uint32_t resource_id; +}; + +struct rutabaga; + +struct VirtIOGPURutabaga { + VirtIOGPU parent_obj; + struct MemoryRegionInfo memory_regions[MAX_SLOTS]; + uint64_t capset_mask; + char *wayland_socket_path; + char *wsi; + bool headless; + uint32_t num_capsets; + struct rutabaga *rutabaga; +}; + #define VIRTIO_GPU_FILL_CMD(out) do { \ - size_t s; \ - s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, 0, \ + size_t virtiogpufillcmd_s_ = \ + iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num, 0, \ &out, sizeof(out)); \ - if (s != sizeof(out)) { \ + if (virtiogpufillcmd_s_ != sizeof(out)) { \ qemu_log_mask(LOG_GUEST_ERROR, \ "%s: command size incorrect %zu vs %zu\n", \ - __func__, s, sizeof(out)); \ + __func__, virtiogpufillcmd_s_, sizeof(out)); \ return; \ } \ } while (0) @@ -249,6 +284,9 @@ void virtio_gpu_base_fill_display_info(VirtIOGPUBase *g, void virtio_gpu_base_generate_edid(VirtIOGPUBase *g, int scanout, struct virtio_gpu_resp_edid *edid); /* virtio-gpu.c */ +struct virtio_gpu_simple_resource * +virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id); + void virtio_gpu_ctrl_response(VirtIOGPU *g, struct virtio_gpu_ctrl_command *cmd, struct virtio_gpu_ctrl_hdr *resp, @@ -267,6 +305,8 @@ int virtio_gpu_create_mapping_iov(VirtIOGPU *g, uint32_t *niov); void virtio_gpu_cleanup_mapping_iov(VirtIOGPU *g, struct iovec *iov, uint32_t count); +void virtio_gpu_cleanup_mapping(VirtIOGPU *g, + struct virtio_gpu_simple_resource *res); void virtio_gpu_process_cmdq(VirtIOGPU *g); void virtio_gpu_device_realize(DeviceState *qdev, Error **errp); void virtio_gpu_reset(VirtIODevice *vdev); diff --git a/include/hw/virtio/virtio-input.h b/include/hw/virtio/virtio-input.h index 08f1591424..a6c9703644 100644 --- a/include/hw/virtio/virtio-input.h +++ b/include/hw/virtio/virtio-input.h @@ -84,7 +84,7 @@ struct VirtIOInputHID { VirtIOInput parent_obj; char *display; uint32_t head; - QemuInputHandler *handler; + const QemuInputHandler *handler; QemuInputHandlerState *hs; int ledstate; bool wheel_axis; diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index ab0fe2b4f2..5f5b02b8f9 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -33,6 +33,7 @@ OBJECT_DECLARE_TYPE(VirtIOMEM, VirtIOMEMClass, #define VIRTIO_MEM_UNPLUGGED_INACCESSIBLE_PROP "unplugged-inaccessible" #define VIRTIO_MEM_EARLY_MIGRATION_PROP "x-early-migration" #define VIRTIO_MEM_PREALLOC_PROP "prealloc" +#define VIRTIO_MEM_DYNAMIC_MEMSLOTS_PROP "dynamic-memslots" struct VirtIOMEM { VirtIODevice parent_obj; @@ -44,7 +45,28 @@ struct VirtIOMEM { int32_t bitmap_size; unsigned long *bitmap; - /* assigned memory backend and memory region */ + /* + * With "dynamic-memslots=on": Device memory region in which we dynamically + * map the memslots. + */ + MemoryRegion *mr; + + /* + * With "dynamic-memslots=on": The individual memslots (aliases into the + * memory backend). + */ + MemoryRegion *memslots; + + /* With "dynamic-memslots=on": The total number of memslots. */ + uint16_t nb_memslots; + + /* + * With "dynamic-memslots=on": Size of one memslot (the size of the + * last one can differ). + */ + uint64_t memslot_size; + + /* Assigned memory backend with the RAM memory region. */ HostMemoryBackend *memdev; /* NUMA node */ @@ -82,6 +104,12 @@ struct VirtIOMEM { */ bool early_migration; + /* + * Whether we dynamically map (multiple, if possible) memslots instead of + * statically mapping the whole RAM memory region. + */ + bool dynamic_memslots; + /* notifiers to notify when "size" changes */ NotifierList size_change_notifiers; @@ -96,6 +124,8 @@ struct VirtIOMEMClass { /* public */ void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi); MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp); + void (*decide_memslots)(VirtIOMEM *vmem, unsigned int limit); + unsigned int (*get_memslots)(VirtIOMEM *vmem); void (*add_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); void (*remove_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); void (*unplug_request_check)(VirtIOMEM *vmem, Error **errp); diff --git a/include/hw/virtio/virtio-pci.h b/include/hw/virtio/virtio-pci.h index ab2051b64b..5a3f182f99 100644 --- a/include/hw/virtio/virtio-pci.h +++ b/include/hw/virtio/virtio-pci.h @@ -264,4 +264,8 @@ unsigned virtio_pci_optimal_num_queues(unsigned fixed_queues); void virtio_pci_set_guest_notifier_fd_handler(VirtIODevice *vdev, VirtQueue *vq, int n, bool assign, bool with_irqfd); + +int virtio_pci_add_shm_cap(VirtIOPCIProxy *proxy, uint8_t bar, uint64_t offset, + uint64_t length, uint8_t id); + #endif diff --git a/include/migration/register.h b/include/migration/register.h index 2b12c6adec..fed1d04a3c 100644 --- a/include/migration/register.h +++ b/include/migration/register.h @@ -25,6 +25,7 @@ typedef struct SaveVMHandlers { * used to perform early checks. */ int (*save_prepare)(void *opaque, Error **errp); + int (*save_setup)(QEMUFile *f, void *opaque); void (*save_cleanup)(void *opaque); int (*save_live_complete_postcopy)(QEMUFile *f, void *opaque); int (*save_live_complete_precopy)(QEMUFile *f, void *opaque); @@ -50,7 +51,6 @@ typedef struct SaveVMHandlers { int (*save_live_iterate)(QEMUFile *f, void *opaque); /* This runs outside the iothread lock! */ - int (*save_setup)(QEMUFile *f, void *opaque); /* Note for save_live_pending: * must_precopy: * - must be migrated in precopy or in stopped state diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h index 1109482a00..c797f0d457 100644 --- a/include/qemu/compiler.h +++ b/include/qemu/compiler.h @@ -212,4 +212,19 @@ # define QEMU_USED #endif +/* + * Ugly CPP trick that is like "defined FOO", but also works in C + * code. Useful to replace #ifdef with "if" statements; assumes + * the symbol was defined with Meson's "config.set()", so it is empty + * if defined. + */ +#define IS_ENABLED(x) IS_EMPTY(x) + +#define IS_EMPTY_JUNK_ junk, +#define IS_EMPTY(value) IS_EMPTY_(IS_EMPTY_JUNK_##value) + +/* Expands to either SECOND_ARG(junk, 1, 0) or SECOND_ARG(IS_EMPTY_JUNK_CONFIG_FOO 1, 0) */ +#define SECOND_ARG(first, second, ...) second +#define IS_EMPTY_(junk_maybecomma) SECOND_ARG(junk_maybecomma 1, 0) + #endif /* COMPILER_H */ diff --git a/include/sysemu/block-backend-global-state.h b/include/sysemu/block-backend-global-state.h index d5f675493a..49c12b0fa9 100644 --- a/include/sysemu/block-backend-global-state.h +++ b/include/sysemu/block-backend-global-state.h @@ -59,8 +59,8 @@ BlockBackend *blk_by_public(BlockBackendPublic *public); void blk_remove_bs(BlockBackend *blk); int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp); int blk_replace_bs(BlockBackend *blk, BlockDriverState *new_bs, Error **errp); -bool bdrv_has_blk(BlockDriverState *bs); -bool bdrv_is_root_node(BlockDriverState *bs); +bool GRAPH_RDLOCK bdrv_has_blk(BlockDriverState *bs); +bool GRAPH_RDLOCK bdrv_is_root_node(BlockDriverState *bs); int GRAPH_UNLOCKED blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm, Error **errp); void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm); diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index ee9025f8e9..97a8a4f201 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -215,7 +215,8 @@ typedef struct KVMRouteChange { /* external API */ -bool kvm_has_free_slot(MachineState *ms); +unsigned int kvm_get_max_memslots(void); +unsigned int kvm_get_free_memslots(void); bool kvm_has_sync_mmu(void); int kvm_has_vcpu_events(void); int kvm_has_robust_singlestep(void); @@ -552,7 +553,6 @@ int kvm_set_one_reg(CPUState *cs, uint64_t id, void *source); */ int kvm_get_one_reg(CPUState *cs, uint64_t id, void *target); struct ppc_radix_page_info *kvm_get_radix_page_info(void); -int kvm_get_max_memslots(void); /* Notify resamplefd for EOI of specific interrupts. */ void kvm_resample_fd_notify(int gsi); diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index a5b9122cb8..075939a3c4 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -40,6 +40,7 @@ typedef struct KVMMemoryUpdate { typedef struct KVMMemoryListener { MemoryListener listener; KVMSlot *slots; + unsigned int nr_used_slots; int as_id; QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_add; QSIMPLEQ_HEAD(, KVMMemoryUpdate) transaction_del; diff --git a/include/sysemu/memory_mapping.h b/include/sysemu/memory_mapping.h index 3bbeb1bcb4..021e0a6230 100644 --- a/include/sysemu/memory_mapping.h +++ b/include/sysemu/memory_mapping.h @@ -71,7 +71,7 @@ void guest_phys_blocks_free(GuestPhysBlockList *list); void guest_phys_blocks_init(GuestPhysBlockList *list); void guest_phys_blocks_append(GuestPhysBlockList *list); -void qemu_get_guest_memory_mapping(MemoryMappingList *list, +bool qemu_get_guest_memory_mapping(MemoryMappingList *list, const GuestPhysBlockList *guest_phys_blocks, Error **errp); diff --git a/include/ui/input.h b/include/ui/input.h index 24d8e4579e..8f9aac562e 100644 --- a/include/ui/input.h +++ b/include/ui/input.h @@ -30,7 +30,7 @@ struct QemuInputHandler { }; QemuInputHandlerState *qemu_input_handler_register(DeviceState *dev, - QemuInputHandler *handler); + const QemuInputHandler *handler); void qemu_input_handler_activate(QemuInputHandlerState *s); void qemu_input_handler_deactivate(QemuInputHandlerState *s); void qemu_input_handler_unregister(QemuInputHandlerState *s); diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h new file mode 100644 index 0000000000..218bf7ac98 --- /dev/null +++ b/linux-headers/linux/iommufd.h @@ -0,0 +1,444 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + */ +#ifndef _IOMMUFD_H +#define _IOMMUFD_H + +#include <linux/types.h> +#include <linux/ioctl.h> + +#define IOMMUFD_TYPE (';') + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility. Each + * ioctl is passed in a structure pointer as the argument providing the size of + * the structure in the first u32. The kernel checks that any structure space + * beyond what it understands is 0. This allows userspace to use the backward + * compatible portion while consistently using the newer, larger, structures. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: An ID or IOVA provided does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ +enum { + IOMMUFD_CMD_BASE = 0x80, + IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, + IOMMUFD_CMD_IOAS_ALLOC, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS, + IOMMUFD_CMD_IOAS_COPY, + IOMMUFD_CMD_IOAS_IOVA_RANGES, + IOMMUFD_CMD_IOAS_MAP, + IOMMUFD_CMD_IOAS_UNMAP, + IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, + IOMMUFD_CMD_HWPT_ALLOC, + IOMMUFD_CMD_GET_HW_INFO, +}; + +/** + * struct iommu_destroy - ioctl(IOMMU_DESTROY) + * @size: sizeof(struct iommu_destroy) + * @id: iommufd object ID to destroy. Can be any destroyable object type. + * + * Destroy any object held within iommufd. + */ +struct iommu_destroy { + __u32 size; + __u32 id; +}; +#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY) + +/** + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC) + * @size: sizeof(struct iommu_ioas_alloc) + * @flags: Must be 0 + * @out_ioas_id: Output IOAS ID for the allocated object + * + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA) + * to memory mapping. + */ +struct iommu_ioas_alloc { + __u32 size; + __u32 flags; + __u32 out_ioas_id; +}; +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC) + +/** + * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE) + * @start: First IOVA + * @last: Inclusive last IOVA + * + * An interval in IOVA space. + */ +struct iommu_iova_range { + __aligned_u64 start; + __aligned_u64 last; +}; + +/** + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES) + * @size: sizeof(struct iommu_ioas_iova_ranges) + * @ioas_id: IOAS ID to read ranges from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to the output array of struct iommu_iova_range + * @out_iova_alignment: Minimum alignment required for mapping IOVA + * + * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these ranges + * is not allowed. num_iovas will be set to the total number of iovas and + * the allowed_iovas[] will be filled in as space permits. + * + * The allowed ranges are dependent on the HW path the DMA operation takes, and + * can change during the lifetime of the IOAS. A fresh empty IOAS will have a + * full range, and each attached device will narrow the ranges based on that + * device's HW restrictions. Detaching a device can widen the ranges. Userspace + * should query ranges after every attach/detach to know what IOVAs are valid + * for mapping. + * + * On input num_iovas is the length of the allowed_iovas array. On output it is + * the total number of iovas filled in. The ioctl will return -EMSGSIZE and set + * num_iovas to the required value if num_iovas is too small. In this case the + * caller should allocate a larger output array and re-issue the ioctl. + * + * out_iova_alignment returns the minimum IOVA alignment that can be given + * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy:: + * + * starting_iova % out_iova_alignment == 0 + * (starting_iova + length) % out_iova_alignment == 0 + * + * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot + * be higher than the system PAGE_SIZE. + */ +struct iommu_ioas_iova_ranges { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; + __aligned_u64 out_iova_alignment; +}; +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES) + +/** + * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS) + * @size: sizeof(struct iommu_ioas_allow_iovas) + * @ioas_id: IOAS ID to allow IOVAs from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to array of struct iommu_iova_range + * + * Ensure a range of IOVAs are always available for allocation. If this call + * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA ranges + * that are narrower than the ranges provided here. This call will fail if + * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges. + * + * When an IOAS is first created the IOVA_RANGES will be maximally sized, and as + * devices are attached the IOVA will narrow based on the device restrictions. + * When an allowed range is specified any narrowing will be refused, ie device + * attachment can fail if the device requires limiting within the allowed range. + * + * Automatic IOVA allocation is also impacted by this call. MAP will only + * allocate within the allowed IOVAs if they are present. + * + * This call replaces the entire allowed list with the given list. + */ +struct iommu_ioas_allow_iovas { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; +}; +#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IOVAS) + +/** + * enum iommufd_ioas_map_flags - Flags for map and copy + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate + * IOVA to place the mapping at + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping + */ +enum iommufd_ioas_map_flags { + IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0, + IOMMU_IOAS_MAP_WRITEABLE = 1 << 1, + IOMMU_IOAS_MAP_READABLE = 1 << 2, +}; + +/** + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP) + * @size: sizeof(struct iommu_ioas_map) + * @flags: Combination of enum iommufd_ioas_map_flags + * @ioas_id: IOAS ID to change the mapping of + * @__reserved: Must be 0 + * @user_va: Userspace pointer to start mapping from + * @length: Number of bytes to map + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set + * then this must be provided as input. + * + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the + * mapping will be established at iova, otherwise a suitable location based on + * the reserved and allowed lists will be automatically selected and returned in + * iova. + * + * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must currently + * be unused, existing IOVA cannot be replaced. + */ +struct iommu_ioas_map { + __u32 size; + __u32 flags; + __u32 ioas_id; + __u32 __reserved; + __aligned_u64 user_va; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) + +/** + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) + * @size: sizeof(struct iommu_ioas_copy) + * @flags: Combination of enum iommufd_ioas_map_flags + * @dst_ioas_id: IOAS ID to change the mapping of + * @src_ioas_id: IOAS ID to copy from + * @length: Number of bytes to copy and map + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is + * set then this must be provided as input. + * @src_iova: IOVA to start the copy + * + * Copy an already existing mapping from src_ioas_id and establish it in + * dst_ioas_id. The src iova/length must exactly match a range used with + * IOMMU_IOAS_MAP. + * + * This may be used to efficiently clone a subset of an IOAS to another, or as a + * kind of 'cache' to speed up mapping. Copy has an efficiency advantage over + * establishing equivalent new mappings, as internal resources are shared, and + * the kernel will pin the user memory only once. + */ +struct iommu_ioas_copy { + __u32 size; + __u32 flags; + __u32 dst_ioas_id; + __u32 src_ioas_id; + __aligned_u64 length; + __aligned_u64 dst_iova; + __aligned_u64 src_iova; +}; +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY) + +/** + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP) + * @size: sizeof(struct iommu_ioas_unmap) + * @ioas_id: IOAS ID to change the mapping of + * @iova: IOVA to start the unmapping at + * @length: Number of bytes to unmap, and return back the bytes unmapped + * + * Unmap an IOVA range. The iova/length must be a superset of a previously + * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or + * truncating ranges is not allowed. The values 0 to U64_MAX will unmap + * everything. + */ +struct iommu_ioas_unmap { + __u32 size; + __u32 ioas_id; + __aligned_u64 iova; + __aligned_u64 length; +}; +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP) + +/** + * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and + * ioctl(IOMMU_OPTION_HUGE_PAGES) + * @IOMMU_OPTION_RLIMIT_MODE: + * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege + * to invoke this. Value 0 (default) is user based accouting, 1 uses process + * based accounting. Global option, object_id must be 0 + * @IOMMU_OPTION_HUGE_PAGES: + * Value 1 (default) allows contiguous pages to be combined when generating + * iommu mappings. Value 0 disables combining, everything is mapped to + * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS + * option, the object_id must be the IOAS ID. + */ +enum iommufd_option { + IOMMU_OPTION_RLIMIT_MODE = 0, + IOMMU_OPTION_HUGE_PAGES = 1, +}; + +/** + * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and + * ioctl(IOMMU_OPTION_OP_GET) + * @IOMMU_OPTION_OP_SET: Set the option's value + * @IOMMU_OPTION_OP_GET: Get the option's value + */ +enum iommufd_option_ops { + IOMMU_OPTION_OP_SET = 0, + IOMMU_OPTION_OP_GET = 1, +}; + +/** + * struct iommu_option - iommu option multiplexer + * @size: sizeof(struct iommu_option) + * @option_id: One of enum iommufd_option + * @op: One of enum iommufd_option_ops + * @__reserved: Must be 0 + * @object_id: ID of the object if required + * @val64: Option value to set or value returned on get + * + * Change a simple option value. This multiplexor allows controlling options + * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP_GET + * will return the current value. + */ +struct iommu_option { + __u32 size; + __u32 option_id; + __u16 op; + __u16 __reserved; + __u32 object_id; + __aligned_u64 val64; +}; +#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET = 0, + IOMMU_VFIO_IOAS_SET = 1, + IOMMU_VFIO_IOAS_CLEAR = 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do not + * support the ID field. Set or Get the IOAS that VFIO compatibility will use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creating + * one. From then on VFIO will continue to use that ioas and is not effected by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) + +/** + * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) + * @size: sizeof(struct iommu_hwpt_alloc) + * @flags: Must be 0 + * @dev_id: The device to allocate this HWPT for + * @pt_id: The IOAS to connect this HWPT to + * @out_hwpt_id: The ID of the new HWPT + * @__reserved: Must be 0 + * + * Explicitly allocate a hardware page table object. This is the same object + * type that is returned by iommufd_device_attach() and represents the + * underlying iommu driver's iommu_domain kernel object. + * + * A HWPT will be created with the IOVA mappings from the given IOAS. + */ +struct iommu_hwpt_alloc { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 pt_id; + __u32 out_hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) + +/** + * struct iommu_hw_info_vtd - Intel VT-d hardware information + * + * @flags: Must be 0 + * @__reserved: Must be 0 + * + * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.2 Capability Register. + * @ecap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.3 Extended Capability Register. + * + * User needs to understand the Intel VT-d specification to decode the + * register value. + */ +struct iommu_hw_info_vtd { + __u32 flags; + __u32 __reserved; + __aligned_u64 cap_reg; + __aligned_u64 ecap_reg; +}; + +/** + * enum iommu_hw_info_type - IOMMU Hardware Info Types + * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware + * info + * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type + */ +enum iommu_hw_info_type { + IOMMU_HW_INFO_TYPE_NONE, + IOMMU_HW_INFO_TYPE_INTEL_VTD, +}; + +/** + * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) + * @size: sizeof(struct iommu_hw_info) + * @flags: Must be 0 + * @dev_id: The device bound to the iommufd + * @data_len: Input the length of a user buffer in bytes. Output the length of + * data that kernel supports + * @data_uptr: User pointer to a user-space buffer used by the kernel to fill + * the iommu type specific hardware information data + * @out_data_type: Output the iommu hardware info type as defined in the enum + * iommu_hw_info_type. + * @__reserved: Must be 0 + * + * Query an iommu type specific hardware information data from an iommu behind + * a given device that has been bound to iommufd. This hardware info data will + * be used to sync capabilities between the virtual iommu and the physical + * iommu, e.g. a nested translation setup needs to check the hardware info, so + * a guest stage-1 page table can be compatible with the physical iommu. + * + * To capture an iommu type specific hardware information data, @data_uptr and + * its length @data_len must be provided. Trailing bytes will be zeroed if the + * user buffer is larger than the data that kernel has. Otherwise, kernel only + * fills the buffer using the given length in @data_len. If the ioctl succeeds, + * @data_len will be updated to the length that kernel actually supports, + * @out_data_type will be filled to decode the data filled in the buffer + * pointed by @data_uptr. Input @data_len == zero is allowed. + */ +struct iommu_hw_info { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 data_len; + __aligned_u64 data_uptr; + __u32 out_data_type; + __u32 __reserved; +}; +#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) +#endif diff --git a/linux-user/elfload.c b/linux-user/elfload.c index f21e2e0c3d..2e3809f03c 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -1237,6 +1237,14 @@ static uint32_t get_elf_hwcap(void) hwcaps |= HWCAP_LOONGARCH_LAM; } + if (FIELD_EX32(cpu->env.cpucfg[2], CPUCFG2, LSX)) { + hwcaps |= HWCAP_LOONGARCH_LSX; + } + + if (FIELD_EX32(cpu->env.cpucfg[2], CPUCFG2, LASX)) { + hwcaps |= HWCAP_LOONGARCH_LASX; + } + return hwcaps; } @@ -2362,31 +2370,58 @@ static abi_ulong setup_arg_pages(struct linux_binprm *bprm, * Map and zero the bss. We need to explicitly zero any fractional pages * after the data section (i.e. bss). Return false on mapping failure. */ -static bool zero_bss(abi_ulong start_bss, abi_ulong end_bss, int prot) +static bool zero_bss(abi_ulong start_bss, abi_ulong end_bss, + int prot, Error **errp) { abi_ulong align_bss; + /* We only expect writable bss; the code segment shouldn't need this. */ + if (!(prot & PROT_WRITE)) { + error_setg(errp, "PT_LOAD with non-writable bss"); + return false; + } + align_bss = TARGET_PAGE_ALIGN(start_bss); end_bss = TARGET_PAGE_ALIGN(end_bss); if (start_bss < align_bss) { int flags = page_get_flags(start_bss); - if (!(flags & PAGE_VALID)) { - /* Map the start of the bss. */ + if (!(flags & PAGE_BITS)) { + /* + * The whole address space of the executable was reserved + * at the start, therefore all pages will be VALID. + * But assuming there are no PROT_NONE PT_LOAD segments, + * a PROT_NONE page means no data all bss, and we can + * simply extend the new anon mapping back to the start + * of the page of bss. + */ align_bss -= TARGET_PAGE_SIZE; - } else if (flags & PAGE_WRITE) { - /* The page is already mapped writable. */ - memset(g2h_untagged(start_bss), 0, align_bss - start_bss); } else { - /* Read-only zeros? */ - g_assert_not_reached(); + /* + * The start of the bss shares a page with something. + * The only thing that we expect is the data section, + * which would already be marked writable. + * Overlapping the RX code segment seems malformed. + */ + if (!(flags & PAGE_WRITE)) { + error_setg(errp, "PT_LOAD with bss overlapping " + "non-writable page"); + return false; + } + + /* The page is already mapped and writable. */ + memset(g2h_untagged(start_bss), 0, align_bss - start_bss); } } - return align_bss >= end_bss || - target_mmap(align_bss, end_bss - align_bss, prot, - MAP_FIXED | MAP_PRIVATE | MAP_ANON, -1, 0) != -1; + if (align_bss < end_bss && + target_mmap(align_bss, end_bss - align_bss, prot, + MAP_FIXED | MAP_PRIVATE | MAP_ANON, -1, 0) == -1) { + error_setg_errno(errp, errno, "Error mapping bss"); + return false; + } + return true; } #if defined(TARGET_ARM) @@ -3410,8 +3445,8 @@ static void load_elf_image(const char *image_name, int image_fd, /* If the load segment requests extra zeros (e.g. bss), map it. */ if (vaddr_ef < vaddr_em && - !zero_bss(vaddr_ef, vaddr_em, elf_prot)) { - goto exit_mmap; + !zero_bss(vaddr_ef, vaddr_em, elf_prot, &err)) { + goto exit_errmsg; } /* Find the full program boundaries. */ diff --git a/linux-user/mips/cpu_loop.c b/linux-user/mips/cpu_loop.c index 8735e58bad..990b03e727 100644 --- a/linux-user/mips/cpu_loop.c +++ b/linux-user/mips/cpu_loop.c @@ -180,7 +180,9 @@ done_syscall: } force_sig_fault(TARGET_SIGFPE, si_code, env->active_tc.PC); break; - + case EXCP_OVERFLOW: + force_sig_fault(TARGET_SIGFPE, TARGET_FPE_INTOVF, env->active_tc.PC); + break; /* The code below was inspired by the MIPS Linux kernel trap * handling code in arch/mips/kernel/traps.c. */ diff --git a/linux-user/mmap.c b/linux-user/mmap.c index 8ccaab7859..7b44b9ff49 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -778,7 +778,7 @@ fail: return -1; } -static void mmap_reserve_or_unmap(abi_ulong start, abi_ulong len) +static int mmap_reserve_or_unmap(abi_ulong start, abi_ulong len) { abi_ulong real_start; abi_ulong real_last; @@ -807,7 +807,7 @@ static void mmap_reserve_or_unmap(abi_ulong start, abi_ulong len) prot |= page_get_flags(a + 1); } if (prot != 0) { - return; + return 0; } } else { for (prot = 0, a = real_start; a < start; a += TARGET_PAGE_SIZE) { @@ -825,7 +825,7 @@ static void mmap_reserve_or_unmap(abi_ulong start, abi_ulong len) } if (real_last < real_start) { - return; + return 0; } } @@ -836,32 +836,36 @@ static void mmap_reserve_or_unmap(abi_ulong start, abi_ulong len) void *ptr = mmap(host_start, real_len, PROT_NONE, MAP_FIXED | MAP_ANONYMOUS | MAP_PRIVATE | MAP_NORESERVE, -1, 0); - assert(ptr == host_start); - } else { - int ret = munmap(host_start, real_len); - assert(ret == 0); + return ptr == host_start ? 0 : -1; } + return munmap(host_start, real_len); } int target_munmap(abi_ulong start, abi_ulong len) { + int ret; + trace_target_munmap(start, len); if (start & ~TARGET_PAGE_MASK) { - return -TARGET_EINVAL; + errno = EINVAL; + return -1; } len = TARGET_PAGE_ALIGN(len); if (len == 0 || !guest_range_valid_untagged(start, len)) { - return -TARGET_EINVAL; + errno = EINVAL; + return -1; } mmap_lock(); - mmap_reserve_or_unmap(start, len); - page_set_flags(start, start + len - 1, 0); - shm_region_rm_complete(start, start + len - 1); + ret = mmap_reserve_or_unmap(start, len); + if (likely(ret == 0)) { + page_set_flags(start, start + len - 1, 0); + shm_region_rm_complete(start, start + len - 1); + } mmap_unlock(); - return 0; + return ret; } abi_long target_mremap(abi_ulong old_addr, abi_ulong old_size, diff --git a/linux-user/sh4/signal.c b/linux-user/sh4/signal.c index c4ba962708..c16c2c2d57 100644 --- a/linux-user/sh4/signal.c +++ b/linux-user/sh4/signal.c @@ -104,6 +104,14 @@ static void unwind_gusa(CPUSH4State *regs) /* Reset the SP to the saved version in R1. */ regs->gregs[15] = regs->gregs[1]; + } else if (regs->gregs[15] >= -128u && regs->pc == regs->gregs[0]) { + /* If we are on the last instruction of a gUSA region, we must reset + the SP, otherwise we would be pushing the signal context to + invalid memory. */ + regs->gregs[15] = regs->gregs[1]; + } else if (regs->flags & TB_FLAG_DELAY_SLOT) { + /* If we are in a delay slot, push the previous instruction. */ + regs->pc -= 2; } } diff --git a/linux-user/signal.c b/linux-user/signal.c index a67ab47d30..3b8efec89f 100644 --- a/linux-user/signal.c +++ b/linux-user/signal.c @@ -32,6 +32,7 @@ #include "signal-common.h" #include "host-signal.h" #include "user/safe-syscall.h" +#include "tcg/tcg.h" static struct target_sigaction sigact_table[TARGET_NSIG]; @@ -43,9 +44,8 @@ abi_ulong default_sigreturn; abi_ulong default_rt_sigreturn; /* - * System includes define _NSIG as SIGRTMAX + 1, - * but qemu (like the kernel) defines TARGET_NSIG as TARGET_SIGRTMAX - * and the first signal is SIGHUP defined as 1 + * System includes define _NSIG as SIGRTMAX + 1, but qemu (like the kernel) + * defines TARGET_NSIG as TARGET_SIGRTMAX and the first signal is 1. * Signal number 0 is reserved for use as kill(pid, 0), to test whether * a process exists without sending it a signal. */ @@ -56,7 +56,6 @@ static uint8_t host_to_target_signal_table[_NSIG] = { #define MAKE_SIG_ENTRY(sig) [sig] = TARGET_##sig, MAKE_SIGNAL_LIST #undef MAKE_SIG_ENTRY - /* next signals stay the same */ }; static uint8_t target_to_host_signal_table[TARGET_NSIG + 1]; @@ -64,18 +63,24 @@ static uint8_t target_to_host_signal_table[TARGET_NSIG + 1]; /* valid sig is between 1 and _NSIG - 1 */ int host_to_target_signal(int sig) { - if (sig < 1 || sig >= _NSIG) { + if (sig < 1) { return sig; } + if (sig >= _NSIG) { + return TARGET_NSIG + 1; + } return host_to_target_signal_table[sig]; } /* valid sig is between 1 and TARGET_NSIG */ int target_to_host_signal(int sig) { - if (sig < 1 || sig > TARGET_NSIG) { + if (sig < 1) { return sig; } + if (sig > TARGET_NSIG) { + return _NSIG; + } return target_to_host_signal_table[sig]; } @@ -487,26 +492,6 @@ void target_to_host_siginfo(siginfo_t *info, const target_siginfo_t *tinfo) info->si_value.sival_ptr = (void *)(long)sival_ptr; } -static int fatal_signal (int sig) -{ - switch (sig) { - case TARGET_SIGCHLD: - case TARGET_SIGURG: - case TARGET_SIGWINCH: - /* Ignored by default. */ - return 0; - case TARGET_SIGCONT: - case TARGET_SIGSTOP: - case TARGET_SIGTSTP: - case TARGET_SIGTTIN: - case TARGET_SIGTTOU: - /* Job control signals. */ - return 0; - default: - return 1; - } -} - /* returns 1 if given signal should dump core if not handled */ static int core_dump_signal(int sig) { @@ -526,57 +511,69 @@ static int core_dump_signal(int sig) static void signal_table_init(void) { - int host_sig, target_sig, count; + int hsig, tsig, count; /* * Signals are supported starting from TARGET_SIGRTMIN and going up - * until we run out of host realtime signals. - * glibc at least uses only the lower 2 rt signals and probably - * nobody's using the upper ones. - * it's why SIGRTMIN (34) is generally greater than __SIGRTMIN (32) - * To fix this properly we need to do manual signal delivery multiplexed - * over a single host signal. + * until we run out of host realtime signals. Glibc uses the lower 2 + * RT signals and (hopefully) nobody uses the upper ones. + * This is why SIGRTMIN (34) is generally greater than __SIGRTMIN (32). + * To fix this properly we would need to do manual signal delivery + * multiplexed over a single host signal. * Attempts for configure "missing" signals via sigaction will be * silently ignored. + * + * Remap the target SIGABRT, so that we can distinguish host abort + * from guest abort. When the guest registers a signal handler or + * calls raise(SIGABRT), the host will raise SIG_RTn. If the guest + * arrives at dump_core_and_abort(), we will map back to host SIGABRT + * so that the parent (native or emulated) sees the correct signal. + * Finally, also map host to guest SIGABRT so that the emulated + * parent sees the correct mapping from wait status. */ - for (host_sig = SIGRTMIN; host_sig <= SIGRTMAX; host_sig++) { - target_sig = host_sig - SIGRTMIN + TARGET_SIGRTMIN; - if (target_sig <= TARGET_NSIG) { - host_to_target_signal_table[host_sig] = target_sig; + + hsig = SIGRTMIN; + host_to_target_signal_table[SIGABRT] = 0; + host_to_target_signal_table[hsig++] = TARGET_SIGABRT; + + for (; hsig <= SIGRTMAX; hsig++) { + tsig = hsig - SIGRTMIN + TARGET_SIGRTMIN; + if (tsig <= TARGET_NSIG) { + host_to_target_signal_table[hsig] = tsig; } } - /* generate signal conversion tables */ - for (target_sig = 1; target_sig <= TARGET_NSIG; target_sig++) { - target_to_host_signal_table[target_sig] = _NSIG; /* poison */ - } - for (host_sig = 1; host_sig < _NSIG; host_sig++) { - if (host_to_target_signal_table[host_sig] == 0) { - host_to_target_signal_table[host_sig] = host_sig; - } - target_sig = host_to_target_signal_table[host_sig]; - if (target_sig <= TARGET_NSIG) { - target_to_host_signal_table[target_sig] = host_sig; + /* Invert the mapping that has already been assigned. */ + for (hsig = 1; hsig < _NSIG; hsig++) { + tsig = host_to_target_signal_table[hsig]; + if (tsig) { + assert(target_to_host_signal_table[tsig] == 0); + target_to_host_signal_table[tsig] = hsig; } } - if (trace_event_get_state_backends(TRACE_SIGNAL_TABLE_INIT)) { - for (target_sig = 1, count = 0; target_sig <= TARGET_NSIG; target_sig++) { - if (target_to_host_signal_table[target_sig] == _NSIG) { - count++; - } + host_to_target_signal_table[SIGABRT] = TARGET_SIGABRT; + + /* Map everything else out-of-bounds. */ + for (hsig = 1; hsig < _NSIG; hsig++) { + if (host_to_target_signal_table[hsig] == 0) { + host_to_target_signal_table[hsig] = TARGET_NSIG + 1; } - trace_signal_table_init(count); } + for (count = 0, tsig = 1; tsig <= TARGET_NSIG; tsig++) { + if (target_to_host_signal_table[tsig] == 0) { + target_to_host_signal_table[tsig] = _NSIG; + count++; + } + } + + trace_signal_table_init(count); } void signal_init(void) { TaskState *ts = (TaskState *)thread_cpu->opaque; - struct sigaction act; - struct sigaction oact; - int i; - int host_sig; + struct sigaction act, oact; /* initialize signal conversion tables */ signal_table_init(); @@ -587,22 +584,36 @@ void signal_init(void) sigfillset(&act.sa_mask); act.sa_flags = SA_SIGINFO; act.sa_sigaction = host_signal_handler; - for(i = 1; i <= TARGET_NSIG; i++) { - host_sig = target_to_host_signal(i); - sigaction(host_sig, NULL, &oact); - if (oact.sa_sigaction == (void *)SIG_IGN) { - sigact_table[i - 1]._sa_handler = TARGET_SIG_IGN; - } else if (oact.sa_sigaction == (void *)SIG_DFL) { - sigact_table[i - 1]._sa_handler = TARGET_SIG_DFL; + + /* + * A parent process may configure ignored signals, but all other + * signals are default. For any target signals that have no host + * mapping, set to ignore. For all core_dump_signal, install our + * host signal handler so that we may invoke dump_core_and_abort. + * This includes SIGSEGV and SIGBUS, which are also need our signal + * handler for paging and exceptions. + */ + for (int tsig = 1; tsig <= TARGET_NSIG; tsig++) { + int hsig = target_to_host_signal(tsig); + abi_ptr thand = TARGET_SIG_IGN; + + if (hsig >= _NSIG) { + continue; } - /* If there's already a handler installed then something has - gone horribly wrong, so don't even try to handle that case. */ - /* Install some handlers for our own use. We need at least - SIGSEGV and SIGBUS, to detect exceptions. We can not just - trap all signals because it affects syscall interrupt - behavior. But do trap all default-fatal signals. */ - if (fatal_signal (i)) - sigaction(host_sig, &act, NULL); + + /* As we force remap SIGABRT, cannot probe and install in one step. */ + if (tsig == TARGET_SIGABRT) { + sigaction(SIGABRT, NULL, &oact); + sigaction(hsig, &act, NULL); + } else { + struct sigaction *iact = core_dump_signal(tsig) ? &act : NULL; + sigaction(hsig, iact, &oact); + } + + if (oact.sa_sigaction != (void *)SIG_IGN) { + thand = TARGET_SIG_DFL; + } + sigact_table[tsig - 1]._sa_handler = thand; } } @@ -690,14 +701,45 @@ void cpu_loop_exit_sigbus(CPUState *cpu, target_ulong addr, /* abort execution with signal */ static G_NORETURN +void die_with_signal(int host_sig) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + }; + + /* + * The proper exit code for dying from an uncaught signal is -<signal>. + * The kernel doesn't allow exit() or _exit() to pass a negative value. + * To get the proper exit code we need to actually die from an uncaught + * signal. Here the default signal handler is installed, we send + * the signal and we wait for it to arrive. + */ + sigfillset(&act.sa_mask); + sigaction(host_sig, &act, NULL); + + kill(getpid(), host_sig); + + /* Make sure the signal isn't masked (reusing the mask inside of act). */ + sigdelset(&act.sa_mask, host_sig); + sigsuspend(&act.sa_mask); + + /* unreachable */ + _exit(EXIT_FAILURE); +} + +static G_NORETURN void dump_core_and_abort(CPUArchState *env, int target_sig) { CPUState *cpu = env_cpu(env); TaskState *ts = (TaskState *)cpu->opaque; int host_sig, core_dumped = 0; - struct sigaction act; - host_sig = target_to_host_signal(target_sig); + /* On exit, undo the remapping of SIGABRT. */ + if (target_sig == TARGET_SIGABRT) { + host_sig = SIGABRT; + } else { + host_sig = target_to_host_signal(target_sig); + } trace_user_dump_core_and_abort(env, target_sig, host_sig); gdb_signalled(env, target_sig); @@ -719,29 +761,7 @@ void dump_core_and_abort(CPUArchState *env, int target_sig) } preexit_cleanup(env, 128 + target_sig); - - /* The proper exit code for dying from an uncaught signal is - * -<signal>. The kernel doesn't allow exit() or _exit() to pass - * a negative value. To get the proper exit code we need to - * actually die from an uncaught signal. Here the default signal - * handler is installed, we send ourself a signal and we wait for - * it to arrive. */ - sigfillset(&act.sa_mask); - act.sa_handler = SIG_DFL; - act.sa_flags = 0; - sigaction(host_sig, &act, NULL); - - /* For some reason raise(host_sig) doesn't send the signal when - * statically linked on x86-64. */ - kill(getpid(), host_sig); - - /* Make sure the signal isn't masked (just reuse the mask inside - of act) */ - sigdelset(&act.sa_mask, host_sig); - sigsuspend(&act.sa_mask); - - /* unreachable */ - abort(); + die_with_signal(host_sig); } /* queue a signal so that it will be send to the virtual CPU as soon @@ -775,6 +795,161 @@ static inline void rewind_if_in_safe_syscall(void *puc) } } +static G_NORETURN +void die_from_signal(siginfo_t *info) +{ + char sigbuf[4], codebuf[12]; + const char *sig, *code = NULL; + + switch (info->si_signo) { + case SIGSEGV: + sig = "SEGV"; + switch (info->si_code) { + case SEGV_MAPERR: + code = "MAPERR"; + break; + case SEGV_ACCERR: + code = "ACCERR"; + break; + } + break; + case SIGBUS: + sig = "BUS"; + switch (info->si_code) { + case BUS_ADRALN: + code = "ADRALN"; + break; + case BUS_ADRERR: + code = "ADRERR"; + break; + } + break; + case SIGILL: + sig = "ILL"; + switch (info->si_code) { + case ILL_ILLOPC: + code = "ILLOPC"; + break; + case ILL_ILLOPN: + code = "ILLOPN"; + break; + case ILL_ILLADR: + code = "ILLADR"; + break; + case ILL_PRVOPC: + code = "PRVOPC"; + break; + case ILL_PRVREG: + code = "PRVREG"; + break; + case ILL_COPROC: + code = "COPROC"; + break; + } + break; + case SIGFPE: + sig = "FPE"; + switch (info->si_code) { + case FPE_INTDIV: + code = "INTDIV"; + break; + case FPE_INTOVF: + code = "INTOVF"; + break; + } + break; + case SIGTRAP: + sig = "TRAP"; + break; + default: + snprintf(sigbuf, sizeof(sigbuf), "%d", info->si_signo); + sig = sigbuf; + break; + } + if (code == NULL) { + snprintf(codebuf, sizeof(sigbuf), "%d", info->si_code); + code = codebuf; + } + + error_report("QEMU internal SIG%s {code=%s, addr=%p}", + sig, code, info->si_addr); + die_with_signal(info->si_signo); +} + +static void host_sigsegv_handler(CPUState *cpu, siginfo_t *info, + host_sigcontext *uc) +{ + uintptr_t host_addr = (uintptr_t)info->si_addr; + /* + * Convert forcefully to guest address space: addresses outside + * reserved_va are still valid to report via SEGV_MAPERR. + */ + bool is_valid = h2g_valid(host_addr); + abi_ptr guest_addr = h2g_nocheck(host_addr); + uintptr_t pc = host_signal_pc(uc); + bool is_write = host_signal_write(info, uc); + MMUAccessType access_type = adjust_signal_pc(&pc, is_write); + bool maperr; + + /* If this was a write to a TB protected page, restart. */ + if (is_write + && is_valid + && info->si_code == SEGV_ACCERR + && handle_sigsegv_accerr_write(cpu, host_signal_mask(uc), + pc, guest_addr)) { + return; + } + + /* + * If the access was not on behalf of the guest, within the executable + * mapping of the generated code buffer, then it is a host bug. + */ + if (access_type != MMU_INST_FETCH + && !in_code_gen_buffer((void *)(pc - tcg_splitwx_diff))) { + die_from_signal(info); + } + + maperr = true; + if (is_valid && info->si_code == SEGV_ACCERR) { + /* + * With reserved_va, the whole address space is PROT_NONE, + * which means that we may get ACCERR when we want MAPERR. + */ + if (page_get_flags(guest_addr) & PAGE_VALID) { + maperr = false; + } else { + info->si_code = SEGV_MAPERR; + } + } + + sigprocmask(SIG_SETMASK, host_signal_mask(uc), NULL); + cpu_loop_exit_sigsegv(cpu, guest_addr, access_type, maperr, pc); +} + +static void host_sigbus_handler(CPUState *cpu, siginfo_t *info, + host_sigcontext *uc) +{ + uintptr_t pc = host_signal_pc(uc); + bool is_write = host_signal_write(info, uc); + MMUAccessType access_type = adjust_signal_pc(&pc, is_write); + + /* + * If the access was not on behalf of the guest, within the executable + * mapping of the generated code buffer, then it is a host bug. + */ + if (!in_code_gen_buffer((void *)(pc - tcg_splitwx_diff))) { + die_from_signal(info); + } + + if (info->si_code == BUS_ADRALN) { + uintptr_t host_addr = (uintptr_t)info->si_addr; + abi_ptr guest_addr = h2g_nocheck(host_addr); + + sigprocmask(SIG_SETMASK, host_signal_mask(uc), NULL); + cpu_loop_exit_sigbus(cpu, guest_addr, access_type, pc); + } +} + static void host_signal_handler(int host_sig, siginfo_t *info, void *puc) { CPUState *cpu = thread_cpu; @@ -786,61 +961,28 @@ static void host_signal_handler(int host_sig, siginfo_t *info, void *puc) int guest_sig; uintptr_t pc = 0; bool sync_sig = false; - void *sigmask = host_signal_mask(uc); + void *sigmask; /* * Non-spoofed SIGSEGV and SIGBUS are synchronous, and need special - * handling wrt signal blocking and unwinding. + * handling wrt signal blocking and unwinding. Non-spoofed SIGILL, + * SIGFPE, SIGTRAP are always host bugs. */ - if ((host_sig == SIGSEGV || host_sig == SIGBUS) && info->si_code > 0) { - MMUAccessType access_type; - uintptr_t host_addr; - abi_ptr guest_addr; - bool is_write; - - host_addr = (uintptr_t)info->si_addr; - - /* - * Convert forcefully to guest address space: addresses outside - * reserved_va are still valid to report via SEGV_MAPERR. - */ - guest_addr = h2g_nocheck(host_addr); - - pc = host_signal_pc(uc); - is_write = host_signal_write(info, uc); - access_type = adjust_signal_pc(&pc, is_write); - - if (host_sig == SIGSEGV) { - bool maperr = true; - - if (info->si_code == SEGV_ACCERR && h2g_valid(host_addr)) { - /* If this was a write to a TB protected page, restart. */ - if (is_write && - handle_sigsegv_accerr_write(cpu, sigmask, pc, guest_addr)) { - return; - } - - /* - * With reserved_va, the whole address space is PROT_NONE, - * which means that we may get ACCERR when we want MAPERR. - */ - if (page_get_flags(guest_addr) & PAGE_VALID) { - maperr = false; - } else { - info->si_code = SEGV_MAPERR; - } - } - - sigprocmask(SIG_SETMASK, sigmask, NULL); - cpu_loop_exit_sigsegv(cpu, guest_addr, access_type, maperr, pc); - } else { - sigprocmask(SIG_SETMASK, sigmask, NULL); - if (info->si_code == BUS_ADRALN) { - cpu_loop_exit_sigbus(cpu, guest_addr, access_type, pc); - } + if (info->si_code > 0) { + switch (host_sig) { + case SIGSEGV: + /* Only returns on handle_sigsegv_accerr_write success. */ + host_sigsegv_handler(cpu, info, uc); + return; + case SIGBUS: + host_sigbus_handler(cpu, info, uc); + sync_sig = true; + break; + case SIGILL: + case SIGFPE: + case SIGTRAP: + die_from_signal(info); } - - sync_sig = true; } /* get target signal number */ @@ -881,6 +1023,7 @@ static void host_signal_handler(int host_sig, siginfo_t *info, void *puc) * would write 0xff bytes off the end of the structure and trash * data on the struct. */ + sigmask = host_signal_mask(uc); memset(sigmask, 0xff, SIGSET_T_SIZE); sigdelset(sigmask, SIGSEGV); sigdelset(sigmask, SIGBUS); @@ -936,7 +1079,6 @@ int do_sigaction(int sig, const struct target_sigaction *act, struct target_sigaction *oact, abi_ulong ka_restorer) { struct target_sigaction *k; - struct sigaction act1; int host_sig; int ret = 0; @@ -996,22 +1138,27 @@ int do_sigaction(int sig, const struct target_sigaction *act, return 0; } if (host_sig != SIGSEGV && host_sig != SIGBUS) { + struct sigaction act1; + sigfillset(&act1.sa_mask); act1.sa_flags = SA_SIGINFO; - if (k->sa_flags & TARGET_SA_RESTART) - act1.sa_flags |= SA_RESTART; - /* NOTE: it is important to update the host kernel signal - ignore state to avoid getting unexpected interrupted - syscalls */ if (k->_sa_handler == TARGET_SIG_IGN) { + /* + * It is important to update the host kernel signal ignore + * state to avoid getting unexpected interrupted syscalls. + */ act1.sa_sigaction = (void *)SIG_IGN; } else if (k->_sa_handler == TARGET_SIG_DFL) { - if (fatal_signal (sig)) + if (core_dump_signal(sig)) { act1.sa_sigaction = host_signal_handler; - else + } else { act1.sa_sigaction = (void *)SIG_DFL; + } } else { act1.sa_sigaction = host_signal_handler; + if (k->sa_flags & TARGET_SA_RESTART) { + act1.sa_flags |= SA_RESTART; + } } ret = sigaction(host_sig, &act1, NULL); } diff --git a/meson.build b/meson.build index bd65a111aa..4961c82a6b 100644 --- a/meson.build +++ b/meson.build @@ -1046,6 +1046,12 @@ if not get_option('virglrenderer').auto() or have_system or have_vhost_user_gpu dependencies: virgl)) endif endif +rutabaga = not_found +if not get_option('rutabaga_gfx').auto() or have_system or have_vhost_user_gpu + rutabaga = dependency('rutabaga_gfx_ffi', + method: 'pkg-config', + required: get_option('rutabaga_gfx')) +endif blkio = not_found if not get_option('blkio').auto() or have_block blkio = dependency('blkio', @@ -2111,6 +2117,7 @@ config_host_data.set('CONFIG_OPENGL', opengl.found()) config_host_data.set('CONFIG_PLUGIN', get_option('plugins')) config_host_data.set('CONFIG_RBD', rbd.found()) config_host_data.set('CONFIG_RDMA', rdma.found()) +config_host_data.set('CONFIG_RELOCATABLE', get_option('relocatable')) config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack')) config_host_data.set('CONFIG_SDL', sdl.found()) config_host_data.set('CONFIG_SDL_IMAGE', sdl_image.found()) @@ -2194,7 +2201,7 @@ if get_option('debug_stack_usage') and have_coroutine_pool message('Disabling coroutine pool to measure stack usage') have_coroutine_pool = false endif -config_host_data.set10('CONFIG_COROUTINE_POOL', have_coroutine_pool) +config_host_data.set('CONFIG_COROUTINE_POOL', have_coroutine_pool) config_host_data.set('CONFIG_DEBUG_GRAPH_LOCK', get_option('debug_graph_lock')) config_host_data.set('CONFIG_DEBUG_MUTEX', get_option('debug_mutex')) config_host_data.set('CONFIG_DEBUG_STACK_USAGE', get_option('debug_stack_usage')) @@ -4020,8 +4027,13 @@ summary(summary_info, bool_yn: true, section: 'Directories') summary_info = {} summary_info += {'python': '@0@ (version: @1@)'.format(python.full_path(), python.language_version())} summary_info += {'sphinx-build': sphinx_build} -if config_host.has_key('HAVE_GDB_BIN') - summary_info += {'gdb': config_host['HAVE_GDB_BIN']} + +# FIXME: the [binaries] section of machine files, which can be probed +# with find_program(), would be great for passing gdb and genisoimage +# paths from configure to Meson. However, there seems to be no way to +# hide a program (for example if gdb is too old). +if config_host.has_key('GDB') + summary_info += {'gdb': config_host['GDB']} endif summary_info += {'iasl': iasl} summary_info += {'genisoimage': config_host['GENISOIMAGE']} @@ -4054,6 +4066,7 @@ if 'simple' in get_option('trace_backends') endif summary_info += {'D-Bus display': dbus_display} summary_info += {'QOM debugging': get_option('qom_cast_debug')} +summary_info += {'Relocatable install': get_option('relocatable')} summary_info += {'vhost-kernel support': have_vhost_kernel} summary_info += {'vhost-net support': have_vhost_net} summary_info += {'vhost-user support': have_vhost_user} @@ -4074,8 +4087,10 @@ if 'cpp' in all_languages else summary_info += {'C++ compiler': false} endif -if targetos == 'darwin' +if 'objc' in all_languages summary_info += {'Objective-C compiler': ' '.join(meson.get_compiler('objc').cmd_array())} +else + summary_info += {'Objective-C compiler': false} endif option_cflags = (get_option('debug') ? ['-g'] : []) if get_option('optimization') != 'plain' @@ -4085,7 +4100,7 @@ summary_info += {'CFLAGS': ' '.join(get_option('c_args') + option_cfl if 'cpp' in all_languages summary_info += {'CXXFLAGS': ' '.join(get_option('cpp_args') + option_cflags)} endif -if targetos == 'darwin' +if 'objc' in all_languages summary_info += {'OBJCFLAGS': ' '.join(get_option('objc_args') + option_cflags)} endif link_args = get_option('c_link_args') @@ -4277,6 +4292,7 @@ summary_info += {'libtasn1': tasn1} summary_info += {'PAM': pam} summary_info += {'iconv support': iconv} summary_info += {'virgl support': virgl} +summary_info += {'rutabaga support': rutabaga} summary_info += {'blkio support': blkio} summary_info += {'curl support': curl} summary_info += {'Multipath support': mpathpersist} @@ -4356,3 +4372,21 @@ if host_arch == 'unknown' or not supported_oses.contains(targetos) message('If you want to help supporting QEMU on this platform, please') message('contact the developers at qemu-devel@nongnu.org.') endif + +actually_reloc = get_option('relocatable') +# check if get_relocated_path() is actually able to relocate paths +if get_option('relocatable') and \ + not (get_option('prefix') / get_option('bindir')).startswith(get_option('prefix') / '') + message() + warning('bindir not included within prefix, the installation will not be relocatable.') + actually_reloc = false +endif +if not actually_reloc and (targetos == 'windows' or get_option('relocatable')) + if targetos == 'windows' + message() + warning('Windows installs should usually be relocatable.') + endif + message() + message('QEMU will have to be installed under ' + get_option('prefix') + '.') + message('Use --disable-relocatable to remove this warning.') +endif diff --git a/meson_options.txt b/meson_options.txt index 6a17b90968..3c7398f3c6 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -101,6 +101,8 @@ option('cfi_debug', type: 'boolean', value: false, description: 'Verbose errors in case of CFI violation') option('multiprocess', type: 'feature', value: 'auto', description: 'Out of process device emulation support') +option('relocatable', type : 'boolean', value : 'true', + description: 'toggle relocatable install') option('vfio_user_server', type: 'feature', value: 'disabled', description: 'vfio-user server support') option('dbus_display', type: 'feature', value: 'auto', @@ -230,6 +232,8 @@ option('vmnet', type : 'feature', value : 'auto', description: 'vmnet.framework network backend support') option('virglrenderer', type : 'feature', value : 'auto', description: 'virgl rendering support') +option('rutabaga_gfx', type : 'feature', value : 'auto', + description: 'rutabaga_gfx support') option('png', type : 'feature', value : 'auto', description: 'PNG support with libpng') option('vnc', type : 'feature', value : 'auto', @@ -351,5 +355,12 @@ option('qom_cast_debug', type: 'boolean', value: true, option('slirp_smbd', type : 'feature', value : 'auto', description: 'use smbd (at path --smbd=*) in slirp networking') +option('qemu_ga_manufacturer', type: 'string', value: 'QEMU', + description: '"manufacturer" name for qemu-ga registry entries') +option('qemu_ga_distro', type: 'string', value: 'Linux', + description: 'second path element in qemu-ga registry entries') +option('qemu_ga_version', type: 'string', value: '', + description: 'version number for qemu-ga installer') + option('hexagon_idef_parser', type : 'boolean', value : true, description: 'use idef-parser to automatically generate TCG code for the Hexagon frontend') diff --git a/migration/block-dirty-bitmap.c b/migration/block-dirty-bitmap.c index 032fc5f405..03cb2e72ee 100644 --- a/migration/block-dirty-bitmap.c +++ b/migration/block-dirty-bitmap.c @@ -1214,9 +1214,7 @@ static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque) DBMSaveState *s = &((DBMState *)opaque)->save; SaveBitmapState *dbms = NULL; - qemu_mutex_lock_iothread(); if (init_dirty_bitmap_migration(s) < 0) { - qemu_mutex_unlock_iothread(); return -1; } @@ -1224,7 +1222,6 @@ static int dirty_bitmap_save_setup(QEMUFile *f, void *opaque) send_bitmap_start(f, s, dbms); } qemu_put_bitmap_flags(f, DIRTY_BITMAP_MIG_FLAG_EOS); - qemu_mutex_unlock_iothread(); return 0; } diff --git a/migration/block.c b/migration/block.c index 5f930870a5..b60698d6e2 100644 --- a/migration/block.c +++ b/migration/block.c @@ -388,6 +388,8 @@ static int init_blk_migration(QEMUFile *f) Error *local_err = NULL; int ret; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + block_mig_state.submitted = 0; block_mig_state.read_done = 0; block_mig_state.transferred = 0; @@ -729,18 +731,13 @@ static int block_save_setup(QEMUFile *f, void *opaque) trace_migration_block_save("setup", block_mig_state.submitted, block_mig_state.transferred); - qemu_mutex_lock_iothread(); ret = init_blk_migration(f); if (ret < 0) { - qemu_mutex_unlock_iothread(); return ret; } /* start track dirty blocks */ ret = set_dirty_tracking(); - - qemu_mutex_unlock_iothread(); - if (ret) { return ret; } diff --git a/migration/migration-hmp-cmds.c b/migration/migration-hmp-cmds.c index c115ef2d23..a82597f18e 100644 --- a/migration/migration-hmp-cmds.c +++ b/migration/migration-hmp-cmds.c @@ -30,6 +30,7 @@ #include "sysemu/runstate.h" #include "ui/qemu-spice.h" #include "sysemu/sysemu.h" +#include "options.h" #include "migration.h" static void migration_global_dump(Monitor *mon) @@ -321,6 +322,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: %" PRIu64 " bytes/second\n", MigrationParameter_str(MIGRATION_PARAMETER_MAX_BANDWIDTH), params->max_bandwidth); + assert(params->has_avail_switchover_bandwidth); + monitor_printf(mon, "%s: %" PRIu64 " bytes/second\n", + MigrationParameter_str(MIGRATION_PARAMETER_AVAIL_SWITCHOVER_BANDWIDTH), + params->avail_switchover_bandwidth); assert(params->has_downtime_limit); monitor_printf(mon, "%s: %" PRIu64 " ms\n", MigrationParameter_str(MIGRATION_PARAMETER_DOWNTIME_LIMIT), @@ -574,6 +579,16 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) } p->max_bandwidth = valuebw; break; + case MIGRATION_PARAMETER_AVAIL_SWITCHOVER_BANDWIDTH: + p->has_avail_switchover_bandwidth = true; + ret = qemu_strtosz_MiB(valuestr, NULL, &valuebw); + if (ret < 0 || valuebw > INT64_MAX + || (size_t)valuebw != valuebw) { + error_setg(&err, "Invalid size %s", valuestr); + break; + } + p->avail_switchover_bandwidth = valuebw; + break; case MIGRATION_PARAMETER_DOWNTIME_LIMIT: p->has_downtime_limit = true; visit_type_size(v, param, &p->downtime_limit, &err); @@ -682,7 +697,6 @@ void hmp_x_colo_lost_heartbeat(Monitor *mon, const QDict *qdict) typedef struct HMPMigrationStatus { QEMUTimer *timer; Monitor *mon; - bool is_block_migration; } HMPMigrationStatus; static void hmp_migrate_status_cb(void *opaque) @@ -708,7 +722,7 @@ static void hmp_migrate_status_cb(void *opaque) timer_mod(status->timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + 1000); } else { - if (status->is_block_migration) { + if (migrate_block()) { monitor_printf(status->mon, "\n"); } if (info->error_desc) { @@ -748,7 +762,6 @@ void hmp_migrate(Monitor *mon, const QDict *qdict) status = g_malloc0(sizeof(*status)); status->mon = mon; - status->is_block_migration = blk || inc; status->timer = timer_new_ms(QEMU_CLOCK_REALTIME, hmp_migrate_status_cb, status); timer_mod(status->timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME)); @@ -794,6 +807,8 @@ static void vm_completion(ReadLineState *rs, const char *str) BlockDriverState *bs; BdrvNextIterator it; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + len = strlen(str); readline_set_completion_index(rs, len); diff --git a/migration/migration-stats.c b/migration/migration-stats.c index 84e11e6dd8..4cc989d975 100644 --- a/migration/migration-stats.c +++ b/migration/migration-stats.c @@ -24,14 +24,15 @@ bool migration_rate_exceeded(QEMUFile *f) return true; } + uint64_t rate_limit_max = migration_rate_get(); + if (rate_limit_max == RATE_LIMIT_DISABLED) { + return false; + } + uint64_t rate_limit_start = stat64_get(&mig_stats.rate_limit_start); uint64_t rate_limit_current = migration_transferred_bytes(f); uint64_t rate_limit_used = rate_limit_current - rate_limit_start; - uint64_t rate_limit_max = stat64_get(&mig_stats.rate_limit_max); - if (rate_limit_max == RATE_LIMIT_DISABLED) { - return false; - } if (rate_limit_max > 0 && rate_limit_used > rate_limit_max) { return true; } diff --git a/migration/migration.c b/migration/migration.c index 1c6c81ad49..05c0b801ba 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -99,7 +99,7 @@ static int migration_maybe_pause(MigrationState *s, int *current_active_state, int new_state); static void migrate_fd_cancel(MigrationState *s); -static int await_return_path_close_on_source(MigrationState *s); +static int close_return_path_on_source(MigrationState *s); static bool migration_needs_multiple_sockets(void) { @@ -447,6 +447,18 @@ static void qemu_start_incoming_migration(const char *uri, Error **errp) socket_start_incoming_migration(p ? p : uri, errp); #ifdef CONFIG_RDMA } else if (strstart(uri, "rdma:", &p)) { + if (migrate_compress()) { + error_setg(errp, "RDMA and compression can't be used together"); + return; + } + if (migrate_xbzrle()) { + error_setg(errp, "RDMA and XBZRLE can't be used together"); + return; + } + if (migrate_multifd()) { + error_setg(errp, "RDMA and multifd can't be used together"); + return; + } rdma_start_incoming_migration(p, errp); #endif } else if (strstart(uri, "exec:", &p)) { @@ -962,16 +974,7 @@ static void populate_ram_info(MigrationInfo *info, MigrationState *s) info->xbzrle_cache->overflow = xbzrle_counters.overflow; } - if (migrate_compress()) { - info->compression = g_malloc0(sizeof(*info->compression)); - info->compression->pages = compression_counters.pages; - info->compression->busy = compression_counters.busy; - info->compression->busy_rate = compression_counters.busy_rate; - info->compression->compressed_size = - compression_counters.compressed_size; - info->compression->compression_rate = - compression_counters.compression_rate; - } + populate_compress(info); if (cpu_throttle_active()) { info->has_cpu_throttle_percentage = true; @@ -1191,7 +1194,7 @@ static void migrate_fd_cleanup(MigrationState *s) * We already cleaned up to_dst_file, so errors from the return * path might be due to that, ignore them. */ - await_return_path_close_on_source(s); + close_return_path_on_source(s); assert(!migration_is_active(s)); @@ -1442,6 +1445,7 @@ int migrate_init(MigrationState *s, Error **errp) error_free(s->error); s->error = NULL; s->hostname = NULL; + s->vmdesc = NULL; migrate_set_state(&s->state, MIGRATION_STATUS_NONE, MIGRATION_STATUS_SETUP); @@ -1451,12 +1455,11 @@ int migrate_init(MigrationState *s, Error **errp) s->iteration_initial_bytes = 0; s->threshold_size = 0; s->switchover_acked = false; + s->rdma_migration = false; /* - * set mig_stats compression_counters memory to zero for a - * new migration + * set mig_stats memory to zero for a new migration */ memset(&mig_stats, 0, sizeof(mig_stats)); - memset(&compression_counters, 0, sizeof(compression_counters)); migration_reset_vfio_bytes_transferred(); return 0; @@ -2049,8 +2052,7 @@ static int open_return_path_on_source(MigrationState *ms) return 0; } -/* Returns 0 if the RP was ok, otherwise there was an error on the RP */ -static int await_return_path_close_on_source(MigrationState *ms) +static int close_return_path_on_source(MigrationState *ms) { int ret; @@ -2317,70 +2319,111 @@ static int migration_maybe_pause(MigrationState *s, return s->state == new_state ? 0 : -EINVAL; } -/** - * migration_completion: Used by migration_thread when there's not much left. - * The caller 'breaks' the loop when this returns. - * - * @s: Current migration state - */ -static void migration_completion(MigrationState *s) +static int migration_completion_precopy(MigrationState *s, + int *current_active_state) { int ret; - int current_active_state = s->state; - if (s->state == MIGRATION_STATUS_ACTIVE) { - qemu_mutex_lock_iothread(); - s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); - qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL); + qemu_mutex_lock_iothread(); + s->downtime_start = qemu_clock_get_ms(QEMU_CLOCK_REALTIME); + qemu_system_wakeup_request(QEMU_WAKEUP_REASON_OTHER, NULL); - s->vm_old_state = runstate_get(); - global_state_store(); + s->vm_old_state = runstate_get(); + global_state_store(); - ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); - trace_migration_completion_vm_stop(ret); - if (ret >= 0) { - ret = migration_maybe_pause(s, ¤t_active_state, - MIGRATION_STATUS_DEVICE); - } - if (ret >= 0) { - /* - * Inactivate disks except in COLO, and track that we - * have done so in order to remember to reactivate - * them if migration fails or is cancelled. - */ - s->block_inactive = !migrate_colo(); - migration_rate_set(RATE_LIMIT_DISABLED); - ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false, - s->block_inactive); - } + ret = vm_stop_force_state(RUN_STATE_FINISH_MIGRATE); + trace_migration_completion_vm_stop(ret); + if (ret < 0) { + goto out_unlock; + } - qemu_mutex_unlock_iothread(); + ret = migration_maybe_pause(s, current_active_state, + MIGRATION_STATUS_DEVICE); + if (ret < 0) { + goto out_unlock; + } - if (ret < 0) { - goto fail; - } - } else if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { - trace_migration_completion_postcopy_end(); + /* + * Inactivate disks except in COLO, and track that we have done so in order + * to remember to reactivate them if migration fails or is cancelled. + */ + s->block_inactive = !migrate_colo(); + migration_rate_set(RATE_LIMIT_DISABLED); + ret = qemu_savevm_state_complete_precopy(s->to_dst_file, false, + s->block_inactive); +out_unlock: + qemu_mutex_unlock_iothread(); + return ret; +} - qemu_mutex_lock_iothread(); - qemu_savevm_state_complete_postcopy(s->to_dst_file); - qemu_mutex_unlock_iothread(); +static void migration_completion_postcopy(MigrationState *s) +{ + trace_migration_completion_postcopy_end(); + + qemu_mutex_lock_iothread(); + qemu_savevm_state_complete_postcopy(s->to_dst_file); + qemu_mutex_unlock_iothread(); + + /* + * Shutdown the postcopy fast path thread. This is only needed when dest + * QEMU binary is old (7.1/7.2). QEMU 8.0+ doesn't need this. + */ + if (migrate_postcopy_preempt() && s->preempt_pre_7_2) { + postcopy_preempt_shutdown_file(s); + } + trace_migration_completion_postcopy_end_after_complete(); +} + +static void migration_completion_failed(MigrationState *s, + int current_active_state) +{ + if (s->block_inactive && (s->state == MIGRATION_STATUS_ACTIVE || + s->state == MIGRATION_STATUS_DEVICE)) { /* - * Shutdown the postcopy fast path thread. This is only needed - * when dest QEMU binary is old (7.1/7.2). QEMU 8.0+ doesn't need - * this. + * If not doing postcopy, vm_start() will be called: let's + * regain control on images. */ - if (migrate_postcopy_preempt() && s->preempt_pre_7_2) { - postcopy_preempt_shutdown_file(s); + Error *local_err = NULL; + + qemu_mutex_lock_iothread(); + bdrv_activate_all(&local_err); + if (local_err) { + error_report_err(local_err); + } else { + s->block_inactive = false; } + qemu_mutex_unlock_iothread(); + } + + migrate_set_state(&s->state, current_active_state, + MIGRATION_STATUS_FAILED); +} - trace_migration_completion_postcopy_end_after_complete(); +/** + * migration_completion: Used by migration_thread when there's not much left. + * The caller 'breaks' the loop when this returns. + * + * @s: Current migration state + */ +static void migration_completion(MigrationState *s) +{ + int ret = 0; + int current_active_state = s->state; + + if (s->state == MIGRATION_STATUS_ACTIVE) { + ret = migration_completion_precopy(s, ¤t_active_state); + } else if (s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + migration_completion_postcopy(s); } else { + ret = -1; + } + + if (ret < 0) { goto fail; } - if (await_return_path_close_on_source(s)) { + if (close_return_path_on_source(s)) { goto fail; } @@ -2401,26 +2444,7 @@ static void migration_completion(MigrationState *s) return; fail: - if (s->block_inactive && (s->state == MIGRATION_STATUS_ACTIVE || - s->state == MIGRATION_STATUS_DEVICE)) { - /* - * If not doing postcopy, vm_start() will be called: let's - * regain control on images. - */ - Error *local_err = NULL; - - qemu_mutex_lock_iothread(); - bdrv_activate_all(&local_err); - if (local_err) { - error_report_err(local_err); - } else { - s->block_inactive = false; - } - qemu_mutex_unlock_iothread(); - } - - migrate_set_state(&s->state, current_active_state, - MIGRATION_STATUS_FAILED); + migration_completion_failed(s, current_active_state); } /** @@ -2563,7 +2587,7 @@ static MigThrError postcopy_pause(MigrationState *s) * path and just wait for the thread to finish. It will be * re-created when we resume. */ - await_return_path_close_on_source(s); + close_return_path_on_source(s); migrate_set_state(&s->state, s->state, MIGRATION_STATUS_POSTCOPY_PAUSED); @@ -2689,17 +2713,33 @@ static void migration_update_counters(MigrationState *s, { uint64_t transferred, transferred_pages, time_spent; uint64_t current_bytes; /* bytes transferred since the beginning */ + uint64_t switchover_bw; + /* Expected bandwidth when switching over to destination QEMU */ + double expected_bw_per_ms; double bandwidth; if (current_time < s->iteration_start_time + BUFFER_DELAY) { return; } + switchover_bw = migrate_avail_switchover_bandwidth(); current_bytes = migration_transferred_bytes(s->to_dst_file); transferred = current_bytes - s->iteration_initial_bytes; time_spent = current_time - s->iteration_start_time; bandwidth = (double)transferred / time_spent; - s->threshold_size = bandwidth * migrate_downtime_limit(); + + if (switchover_bw) { + /* + * If the user specified a switchover bandwidth, let's trust the + * user so that can be more accurate than what we estimated. + */ + expected_bw_per_ms = switchover_bw / 1000; + } else { + /* If the user doesn't specify bandwidth, we use the estimated */ + expected_bw_per_ms = bandwidth; + } + + s->threshold_size = expected_bw_per_ms * migrate_downtime_limit(); s->mbps = (((double) transferred * 8.0) / ((double) time_spent / 1000.0)) / 1000.0 / 1000.0; @@ -2716,7 +2756,7 @@ static void migration_update_counters(MigrationState *s, if (stat64_get(&mig_stats.dirty_pages_rate) && transferred > 10000) { s->expected_downtime = - stat64_get(&mig_stats.dirty_bytes_last_sync) / bandwidth; + stat64_get(&mig_stats.dirty_bytes_last_sync) / expected_bw_per_ms; } migration_rate_reset(s->to_dst_file); @@ -2724,7 +2764,9 @@ static void migration_update_counters(MigrationState *s, update_iteration_initial_status(s); trace_migrate_transferred(transferred, time_spent, - bandwidth, s->threshold_size); + /* Both in unit bytes/ms */ + bandwidth, switchover_bw / 1000, + s->threshold_size); } static bool migration_can_switchover(MigrationState *s) @@ -2980,7 +3022,9 @@ static void *migration_thread(void *opaque) object_ref(OBJECT(s)); update_iteration_initial_status(s); + qemu_mutex_lock_iothread(); qemu_savevm_state_header(s->to_dst_file); + qemu_mutex_unlock_iothread(); /* * If we opened the return path, we need to make sure dst has it @@ -3008,7 +3052,9 @@ static void *migration_thread(void *opaque) qemu_savevm_send_colo_enable(s->to_dst_file); } + qemu_mutex_lock_iothread(); qemu_savevm_state_setup(s->to_dst_file); + qemu_mutex_unlock_iothread(); qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE); @@ -3119,8 +3165,10 @@ static void *bg_migration_thread(void *opaque) ram_write_tracking_prepare(); #endif + qemu_mutex_lock_iothread(); qemu_savevm_state_header(s->to_dst_file); qemu_savevm_state_setup(s->to_dst_file); + qemu_mutex_unlock_iothread(); qemu_savevm_wait_unplug(s, MIGRATION_STATUS_SETUP, MIGRATION_STATUS_ACTIVE); diff --git a/migration/migration.h b/migration/migration.h index cd5534337c..ae82004892 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -294,7 +294,7 @@ struct MigrationState { /* * The final stage happens when the remaining data is smaller than * this threshold; it's calculated from the requested downtime and - * measured bandwidth + * measured bandwidth, or avail-switchover-bandwidth if specified. */ int64_t threshold_size; @@ -469,6 +469,8 @@ struct MigrationState { * switchover has been received. */ bool switchover_acked; + /* Is this a rdma migration */ + bool rdma_migration; }; void migrate_set_state(int *state, int old_state, int new_state); diff --git a/migration/multifd.c b/migration/multifd.c index 0f6b203877..1fe53d3b98 100644 --- a/migration/multifd.c +++ b/migration/multifd.c @@ -510,6 +510,11 @@ static void multifd_send_terminate_threads(Error *err) } } +static int multifd_send_channel_destroy(QIOChannel *send) +{ + return socket_send_channel_destroy(send); +} + void multifd_save_cleanup(void) { int i; @@ -532,7 +537,7 @@ void multifd_save_cleanup(void) if (p->registered_yank) { migration_ioc_unregister_yank(p->c); } - socket_send_channel_destroy(p->c); + multifd_send_channel_destroy(p->c); p->c = NULL; qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); @@ -714,8 +719,6 @@ static void *multifd_send_thread(void *opaque) if (ret != 0) { break; } - stat64_add(&mig_stats.multifd_bytes, p->packet_len); - stat64_add(&mig_stats.transferred, p->packet_len); } else { /* Send header using the same writev call */ p->iov[0].iov_len = p->packet_len; @@ -728,8 +731,11 @@ static void *multifd_send_thread(void *opaque) break; } - stat64_add(&mig_stats.multifd_bytes, p->next_packet_size); - stat64_add(&mig_stats.transferred, p->next_packet_size); + stat64_add(&mig_stats.multifd_bytes, + p->next_packet_size + p->packet_len); + stat64_add(&mig_stats.transferred, + p->next_packet_size + p->packet_len); + p->next_packet_size = 0; qemu_mutex_lock(&p->mutex); p->pending_job--; qemu_mutex_unlock(&p->mutex); @@ -747,19 +753,13 @@ static void *multifd_send_thread(void *opaque) } out: - if (local_err) { + if (ret) { + assert(local_err); trace_multifd_send_error(p->id); multifd_send_terminate_threads(local_err); - error_free(local_err); - } - - /* - * Error happen, I will exit, but I can't just leave, tell - * who pay attention to me. - */ - if (ret != 0) { qemu_sem_post(&p->sem_sync); qemu_sem_post(&multifd_send_state->channels_ready); + error_free(local_err); } qemu_mutex_lock(&p->mutex); @@ -775,7 +775,7 @@ out: static bool multifd_channel_connect(MultiFDSendParams *p, QIOChannel *ioc, - Error *error); + Error **errp); static void multifd_tls_outgoing_handshake(QIOTask *task, gpointer opaque) @@ -784,21 +784,22 @@ static void multifd_tls_outgoing_handshake(QIOTask *task, QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task)); Error *err = NULL; - if (qio_task_propagate_error(task, &err)) { - trace_multifd_tls_outgoing_handshake_error(ioc, error_get_pretty(err)); - } else { + if (!qio_task_propagate_error(task, &err)) { trace_multifd_tls_outgoing_handshake_complete(ioc); + if (multifd_channel_connect(p, ioc, &err)) { + return; + } } - if (!multifd_channel_connect(p, ioc, err)) { - /* - * Error happen, mark multifd_send_thread status as 'quit' although it - * is not created, and then tell who pay attention to me. - */ - p->quit = true; - qemu_sem_post(&multifd_send_state->channels_ready); - qemu_sem_post(&p->sem_sync); - } + trace_multifd_tls_outgoing_handshake_error(ioc, error_get_pretty(err)); + + /* + * Error happen, mark multifd_send_thread status as 'quit' although it + * is not created, and then tell who pay attention to me. + */ + p->quit = true; + qemu_sem_post(&multifd_send_state->channels_ready); + qemu_sem_post(&p->sem_sync); } static void *multifd_tls_handshake_thread(void *opaque) @@ -814,7 +815,7 @@ static void *multifd_tls_handshake_thread(void *opaque) return NULL; } -static void multifd_tls_channel_connect(MultiFDSendParams *p, +static bool multifd_tls_channel_connect(MultiFDSendParams *p, QIOChannel *ioc, Error **errp) { @@ -824,7 +825,7 @@ static void multifd_tls_channel_connect(MultiFDSendParams *p, tioc = migration_tls_client_create(ioc, hostname, errp); if (!tioc) { - return; + return false; } object_unref(OBJECT(ioc)); @@ -834,31 +835,25 @@ static void multifd_tls_channel_connect(MultiFDSendParams *p, qemu_thread_create(&p->thread, "multifd-tls-handshake-worker", multifd_tls_handshake_thread, p, QEMU_THREAD_JOINABLE); + return true; } static bool multifd_channel_connect(MultiFDSendParams *p, QIOChannel *ioc, - Error *error) + Error **errp) { trace_multifd_set_outgoing_channel( ioc, object_get_typename(OBJECT(ioc)), - migrate_get_current()->hostname, error); + migrate_get_current()->hostname); - if (error) { - return false; - } if (migrate_channel_requires_tls_upgrade(ioc)) { - multifd_tls_channel_connect(p, ioc, &error); - if (!error) { - /* - * tls_channel_connect will call back to this - * function after the TLS handshake, - * so we mustn't call multifd_send_thread until then - */ - return true; - } else { - return false; - } + /* + * tls_channel_connect will call back to this + * function after the TLS handshake, + * so we mustn't call multifd_send_thread until then + */ + return multifd_tls_channel_connect(p, ioc, errp); + } else { migration_ioc_register_yank(ioc); p->registered_yank = true; @@ -889,20 +884,26 @@ static void multifd_new_send_channel_cleanup(MultiFDSendParams *p, static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) { MultiFDSendParams *p = opaque; - QIOChannel *sioc = QIO_CHANNEL(qio_task_get_source(task)); + QIOChannel *ioc = QIO_CHANNEL(qio_task_get_source(task)); Error *local_err = NULL; trace_multifd_new_send_channel_async(p->id); if (!qio_task_propagate_error(task, &local_err)) { - p->c = sioc; + p->c = ioc; qio_channel_set_delay(p->c, false); p->running = true; - if (multifd_channel_connect(p, sioc, local_err)) { + if (multifd_channel_connect(p, ioc, &local_err)) { return; } } - multifd_new_send_channel_cleanup(p, sioc, local_err); + trace_multifd_new_send_channel_async_error(p->id, local_err); + multifd_new_send_channel_cleanup(p, ioc, local_err); +} + +static void multifd_new_send_channel_create(gpointer opaque) +{ + socket_send_channel_create(multifd_new_send_channel_async, opaque); } int multifd_save_setup(Error **errp) @@ -951,7 +952,7 @@ int multifd_save_setup(Error **errp) p->write_flags = 0; } - socket_send_channel_create(multifd_new_send_channel_async, p); + multifd_new_send_channel_create(p); } for (i = 0; i < thread_count; i++) { diff --git a/migration/options.c b/migration/options.c index 6bbfd4853d..42fb818956 100644 --- a/migration/options.c +++ b/migration/options.c @@ -125,6 +125,8 @@ Property migration_properties[] = { parameters.cpu_throttle_tailslow, false), DEFINE_PROP_SIZE("x-max-bandwidth", MigrationState, parameters.max_bandwidth, MAX_THROTTLE), + DEFINE_PROP_SIZE("avail-switchover-bandwidth", MigrationState, + parameters.avail_switchover_bandwidth, 0), DEFINE_PROP_UINT64("x-downtime-limit", MigrationState, parameters.downtime_limit, DEFAULT_MIGRATE_SET_DOWNTIME), @@ -376,6 +378,13 @@ bool migrate_postcopy(void) return migrate_postcopy_ram() || migrate_dirty_bitmaps(); } +bool migrate_rdma(void) +{ + MigrationState *s = migrate_get_current(); + + return s->rdma_migration; +} + bool migrate_tls(void) { MigrationState *s = migrate_get_current(); @@ -780,6 +789,13 @@ uint64_t migrate_max_bandwidth(void) return s->parameters.max_bandwidth; } +uint64_t migrate_avail_switchover_bandwidth(void) +{ + MigrationState *s = migrate_get_current(); + + return s->parameters.avail_switchover_bandwidth; +} + uint64_t migrate_max_postcopy_bandwidth(void) { MigrationState *s = migrate_get_current(); @@ -917,6 +933,8 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) s->parameters.tls_authz : ""); params->has_max_bandwidth = true; params->max_bandwidth = s->parameters.max_bandwidth; + params->has_avail_switchover_bandwidth = true; + params->avail_switchover_bandwidth = s->parameters.avail_switchover_bandwidth; params->has_downtime_limit = true; params->downtime_limit = s->parameters.downtime_limit; params->has_x_checkpoint_delay = true; @@ -1056,6 +1074,15 @@ bool migrate_params_check(MigrationParameters *params, Error **errp) return false; } + if (params->has_avail_switchover_bandwidth && + (params->avail_switchover_bandwidth > SIZE_MAX)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "avail_switchover_bandwidth", + "an integer in the range of 0 to "stringify(SIZE_MAX) + " bytes/second"); + return false; + } + if (params->has_downtime_limit && (params->downtime_limit > MAX_MIGRATE_DOWNTIME)) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, @@ -1225,6 +1252,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params, dest->max_bandwidth = params->max_bandwidth; } + if (params->has_avail_switchover_bandwidth) { + dest->avail_switchover_bandwidth = params->avail_switchover_bandwidth; + } + if (params->has_downtime_limit) { dest->downtime_limit = params->downtime_limit; } @@ -1341,6 +1372,10 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) } } + if (params->has_avail_switchover_bandwidth) { + s->parameters.avail_switchover_bandwidth = params->avail_switchover_bandwidth; + } + if (params->has_downtime_limit) { s->parameters.downtime_limit = params->downtime_limit; } diff --git a/migration/options.h b/migration/options.h index 045e2a41a2..237f2d6b4a 100644 --- a/migration/options.h +++ b/migration/options.h @@ -56,6 +56,7 @@ bool migrate_zero_copy_send(void); bool migrate_multifd_flush_after_each_section(void); bool migrate_postcopy(void); +bool migrate_rdma(void); bool migrate_tls(void); /* capabilities helpers */ @@ -80,6 +81,7 @@ int migrate_decompress_threads(void); uint64_t migrate_downtime_limit(void); uint8_t migrate_max_cpu_throttle(void); uint64_t migrate_max_bandwidth(void); +uint64_t migrate_avail_switchover_bandwidth(void); uint64_t migrate_max_postcopy_bandwidth(void); int migrate_multifd_channels(void); MultiFDCompression migrate_multifd_compression(void); diff --git a/migration/qemu-file.c b/migration/qemu-file.c index 7fb659296f..3fb25148d1 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -32,12 +32,12 @@ #include "trace.h" #include "options.h" #include "qapi/error.h" +#include "rdma.h" #define IO_BUF_SIZE 32768 #define MAX_IOV_SIZE MIN_CONST(IOV_MAX, 64) struct QEMUFile { - const QEMUFileHooks *hooks; QIOChannel *ioc; bool is_writable; @@ -132,11 +132,6 @@ QEMUFile *qemu_file_new_input(QIOChannel *ioc) return qemu_file_new_impl(ioc, false); } -void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks) -{ - f->hooks = hooks; -} - /* * Get last error for stream f with optional Error* * @@ -297,60 +292,6 @@ void qemu_fflush(QEMUFile *f) f->iovcnt = 0; } -void ram_control_before_iterate(QEMUFile *f, uint64_t flags) -{ - int ret = 0; - - if (f->hooks && f->hooks->before_ram_iterate) { - ret = f->hooks->before_ram_iterate(f, flags, NULL); - if (ret < 0) { - qemu_file_set_error(f, ret); - } - } -} - -void ram_control_after_iterate(QEMUFile *f, uint64_t flags) -{ - int ret = 0; - - if (f->hooks && f->hooks->after_ram_iterate) { - ret = f->hooks->after_ram_iterate(f, flags, NULL); - if (ret < 0) { - qemu_file_set_error(f, ret); - } - } -} - -void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data) -{ - if (f->hooks && f->hooks->hook_ram_load) { - int ret = f->hooks->hook_ram_load(f, flags, data); - if (ret < 0) { - qemu_file_set_error(f, ret); - } - } -} - -int ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size) -{ - if (f->hooks && f->hooks->save_page) { - int ret = f->hooks->save_page(f, block_offset, offset, size); - /* - * RAM_SAVE_CONTROL_* are negative values - */ - if (ret != RAM_SAVE_CONTROL_DELAYED && - ret != RAM_SAVE_CONTROL_NOT_SUPP) { - if (ret < 0) { - qemu_file_set_error(f, ret); - } - } - return ret; - } - - return RAM_SAVE_CONTROL_NOT_SUPP; -} - /* * Attempt to fill the buffer from the underlying file * Returns the number of bytes read, or negative value for an error. diff --git a/migration/qemu-file.h b/migration/qemu-file.h index 03e718c264..a29c37b0d0 100644 --- a/migration/qemu-file.h +++ b/migration/qemu-file.h @@ -29,41 +29,8 @@ #include "exec/cpu-common.h" #include "io/channel.h" -/* - * This function provides hooks around different - * stages of RAM migration. - * 'data' is call specific data associated with the 'flags' value - */ -typedef int (QEMURamHookFunc)(QEMUFile *f, uint64_t flags, void *data); - -/* - * Constants used by ram_control_* hooks - */ -#define RAM_CONTROL_SETUP 0 -#define RAM_CONTROL_ROUND 1 -#define RAM_CONTROL_HOOK 2 -#define RAM_CONTROL_FINISH 3 -#define RAM_CONTROL_BLOCK_REG 4 - -/* - * This function allows override of where the RAM page - * is saved (such as RDMA, for example.) - */ -typedef int (QEMURamSaveFunc)(QEMUFile *f, - ram_addr_t block_offset, - ram_addr_t offset, - size_t size); - -typedef struct QEMUFileHooks { - QEMURamHookFunc *before_ram_iterate; - QEMURamHookFunc *after_ram_iterate; - QEMURamHookFunc *hook_ram_load; - QEMURamSaveFunc *save_page; -} QEMUFileHooks; - QEMUFile *qemu_file_new_input(QIOChannel *ioc); QEMUFile *qemu_file_new_output(QIOChannel *ioc); -void qemu_file_set_hooks(QEMUFile *f, const QEMUFileHooks *hooks); int qemu_fclose(QEMUFile *f); /* @@ -127,22 +94,6 @@ void qemu_fflush(QEMUFile *f); void qemu_file_set_blocking(QEMUFile *f, bool block); int qemu_file_get_to_fd(QEMUFile *f, int fd, size_t size); -void ram_control_before_iterate(QEMUFile *f, uint64_t flags); -void ram_control_after_iterate(QEMUFile *f, uint64_t flags); -void ram_control_load_hook(QEMUFile *f, uint64_t flags, void *data); - -/* Whenever this is found in the data stream, the flags - * will be passed to ram_control_load_hook in the incoming-migration - * side. This lets before_ram_iterate/after_ram_iterate add - * transport-specific sections to the RAM migration data. - */ -#define RAM_SAVE_FLAG_HOOK 0x80 - -#define RAM_SAVE_CONTROL_NOT_SUPP -1000 -#define RAM_SAVE_CONTROL_DELAYED -2000 - -int ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, - ram_addr_t offset, size_t size); QIOChannel *qemu_file_get_ioc(QEMUFile *file); #endif diff --git a/migration/ram-compress.c b/migration/ram-compress.c index 06254d8c69..d037dfe6cf 100644 --- a/migration/ram-compress.c +++ b/migration/ram-compress.c @@ -32,11 +32,14 @@ #include "ram-compress.h" #include "qemu/error-report.h" +#include "qemu/stats64.h" #include "migration.h" #include "options.h" #include "io/channel-null.h" #include "exec/target_page.h" #include "exec/ramblock.h" +#include "ram.h" +#include "migration-stats.h" CompressionStats compression_counters; @@ -227,27 +230,25 @@ static inline void compress_reset_result(CompressParam *param) void flush_compressed_data(int (send_queued_data(CompressParam *))) { - int idx, thread_count; - - thread_count = migrate_compress_threads(); + int thread_count = migrate_compress_threads(); qemu_mutex_lock(&comp_done_lock); - for (idx = 0; idx < thread_count; idx++) { - while (!comp_param[idx].done) { + for (int i = 0; i < thread_count; i++) { + while (!comp_param[i].done) { qemu_cond_wait(&comp_done_cond, &comp_done_lock); } } qemu_mutex_unlock(&comp_done_lock); - for (idx = 0; idx < thread_count; idx++) { - qemu_mutex_lock(&comp_param[idx].mutex); - if (!comp_param[idx].quit) { - CompressParam *param = &comp_param[idx]; + for (int i = 0; i < thread_count; i++) { + qemu_mutex_lock(&comp_param[i].mutex); + if (!comp_param[i].quit) { + CompressParam *param = &comp_param[i]; send_queued_data(param); assert(qemu_file_buffer_empty(param->file)); compress_reset_result(param); } - qemu_mutex_unlock(&comp_param[idx].mutex); + qemu_mutex_unlock(&comp_param[i].mutex); } } @@ -262,15 +263,15 @@ static inline void set_compress_params(CompressParam *param, RAMBlock *block, int compress_page_with_multi_thread(RAMBlock *block, ram_addr_t offset, int (send_queued_data(CompressParam *))) { - int idx, thread_count, pages = -1; + int thread_count, pages = -1; bool wait = migrate_compress_wait_thread(); thread_count = migrate_compress_threads(); qemu_mutex_lock(&comp_done_lock); retry: - for (idx = 0; idx < thread_count; idx++) { - if (comp_param[idx].done) { - CompressParam *param = &comp_param[idx]; + for (int i = 0; i < thread_count; i++) { + if (comp_param[i].done) { + CompressParam *param = &comp_param[i]; qemu_mutex_lock(¶m->mutex); param->done = false; send_queued_data(param); @@ -364,16 +365,14 @@ static void *do_data_decompress(void *opaque) int wait_for_decompress_done(void) { - int idx, thread_count; - if (!migrate_compress()) { return 0; } - thread_count = migrate_decompress_threads(); + int thread_count = migrate_decompress_threads(); qemu_mutex_lock(&decomp_done_lock); - for (idx = 0; idx < thread_count; idx++) { - while (!decomp_param[idx].done) { + for (int i = 0; i < thread_count; i++) { + while (!decomp_param[i].done) { qemu_cond_wait(&decomp_done_cond, &decomp_done_lock); } } @@ -430,6 +429,11 @@ int compress_threads_load_setup(QEMUFile *f) return 0; } + /* + * set compression_counters memory to zero for a new migration + */ + memset(&compression_counters, 0, sizeof(compression_counters)); + thread_count = migrate_decompress_threads(); decompress_threads = g_new0(QemuThread, thread_count); decomp_param = g_new0(DecompressParam, thread_count); @@ -459,27 +463,54 @@ exit: void decompress_data_with_multi_threads(QEMUFile *f, void *host, int len) { - int idx, thread_count; - - thread_count = migrate_decompress_threads(); + int thread_count = migrate_decompress_threads(); QEMU_LOCK_GUARD(&decomp_done_lock); while (true) { - for (idx = 0; idx < thread_count; idx++) { - if (decomp_param[idx].done) { - decomp_param[idx].done = false; - qemu_mutex_lock(&decomp_param[idx].mutex); - qemu_get_buffer(f, decomp_param[idx].compbuf, len); - decomp_param[idx].des = host; - decomp_param[idx].len = len; - qemu_cond_signal(&decomp_param[idx].cond); - qemu_mutex_unlock(&decomp_param[idx].mutex); - break; + for (int i = 0; i < thread_count; i++) { + if (decomp_param[i].done) { + decomp_param[i].done = false; + qemu_mutex_lock(&decomp_param[i].mutex); + qemu_get_buffer(f, decomp_param[i].compbuf, len); + decomp_param[i].des = host; + decomp_param[i].len = len; + qemu_cond_signal(&decomp_param[i].cond); + qemu_mutex_unlock(&decomp_param[i].mutex); + return; } } - if (idx < thread_count) { - break; - } else { - qemu_cond_wait(&decomp_done_cond, &decomp_done_lock); - } + qemu_cond_wait(&decomp_done_cond, &decomp_done_lock); + } +} + +void populate_compress(MigrationInfo *info) +{ + if (!migrate_compress()) { + return; + } + info->compression = g_malloc0(sizeof(*info->compression)); + info->compression->pages = compression_counters.pages; + info->compression->busy = compression_counters.busy; + info->compression->busy_rate = compression_counters.busy_rate; + info->compression->compressed_size = compression_counters.compressed_size; + info->compression->compression_rate = compression_counters.compression_rate; +} + +uint64_t ram_compressed_pages(void) +{ + return compression_counters.pages; +} + +void update_compress_thread_counts(const CompressParam *param, int bytes_xmit) +{ + ram_transferred_add(bytes_xmit); + + if (param->result == RES_ZEROPAGE) { + stat64_add(&mig_stats.zero_pages, 1); + return; } + + /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */ + compression_counters.compressed_size += bytes_xmit - 8; + compression_counters.pages++; } + diff --git a/migration/ram-compress.h b/migration/ram-compress.h index 6f7fe2f472..e55d3b50bd 100644 --- a/migration/ram-compress.h +++ b/migration/ram-compress.h @@ -30,6 +30,7 @@ #define QEMU_MIGRATION_COMPRESS_H #include "qemu-file.h" +#include "qapi/qapi-types-migration.h" enum CompressResult { RES_NONE = 0, @@ -67,4 +68,8 @@ void compress_threads_load_cleanup(void); int compress_threads_load_setup(QEMUFile *f); void decompress_data_with_multi_threads(QEMUFile *f, void *host, int len); +void populate_compress(MigrationInfo *info); +uint64_t ram_compressed_pages(void); +void update_compress_thread_counts(const CompressParam *param, int bytes_xmit); + #endif diff --git a/migration/ram.c b/migration/ram.c index 2f5ce4d60b..16c30a9d7a 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -59,6 +59,7 @@ #include "qemu/iov.h" #include "multifd.h" #include "sysemu/runstate.h" +#include "rdma.h" #include "options.h" #include "sysemu/dirtylimit.h" #include "sysemu/kvm.h" @@ -88,7 +89,7 @@ #define RAM_SAVE_FLAG_EOS 0x10 #define RAM_SAVE_FLAG_CONTINUE 0x20 #define RAM_SAVE_FLAG_XBZRLE 0x40 -/* 0x80 is reserved in qemu-file.h for RAM_SAVE_FLAG_HOOK */ +/* 0x80 is reserved in rdma.h for RAM_SAVE_FLAG_HOOK */ #define RAM_SAVE_FLAG_COMPRESS_PAGE 0x100 #define RAM_SAVE_FLAG_MULTIFD_FLUSH 0x200 /* We can't use any flag that is bigger than 0x200 */ @@ -569,7 +570,6 @@ void mig_throttle_counter_reset(void) /** * xbzrle_cache_zero_page: insert a zero page in the XBZRLE cache * - * @rs: current RAM state * @current_addr: address for the zero page * * Update the xbzrle cache to reflect a page that's been sent as all 0. @@ -578,7 +578,7 @@ void mig_throttle_counter_reset(void) * As a bonus, if the page wasn't in the cache it gets added so that * when a small write is made into the 0'd page it gets XBZRLE sent. */ -static void xbzrle_cache_zero_page(RAMState *rs, ram_addr_t current_addr) +static void xbzrle_cache_zero_page(ram_addr_t current_addr) { /* We don't care if this fails to allocate a new cache page * as long as it updated an old one */ @@ -939,7 +939,7 @@ uint64_t ram_get_total_transferred_pages(void) { return stat64_get(&mig_stats.normal_pages) + stat64_get(&mig_stats.zero_pages) + - compression_counters.pages + xbzrle_counters.pages; + ram_compressed_pages() + xbzrle_counters.pages; } static void migration_update_rates(RAMState *rs, int64_t end_time) @@ -1138,50 +1138,44 @@ void ram_release_page(const char *rbname, uint64_t offset) } /** - * save_zero_page_to_file: send the zero page to the file + * save_zero_page: send the zero page to the stream * - * Returns the size of data written to the file, 0 means the page is not - * a zero page + * Returns the number of pages written. * + * @rs: current RAM state * @pss: current PSS channel - * @block: block that contains the page we want to send * @offset: offset inside the block for the page */ -static int save_zero_page_to_file(PageSearchStatus *pss, QEMUFile *file, - RAMBlock *block, ram_addr_t offset) +static int save_zero_page(RAMState *rs, PageSearchStatus *pss, + ram_addr_t offset) { - uint8_t *p = block->host + offset; + uint8_t *p = pss->block->host + offset; + QEMUFile *file = pss->pss_channel; int len = 0; - if (buffer_is_zero(p, TARGET_PAGE_SIZE)) { - len += save_page_header(pss, file, block, offset | RAM_SAVE_FLAG_ZERO); - qemu_put_byte(file, 0); - len += 1; - ram_release_page(block->idstr, offset); + if (!buffer_is_zero(p, TARGET_PAGE_SIZE)) { + return 0; } - return len; -} -/** - * save_zero_page: send the zero page to the stream - * - * Returns the number of pages written. - * - * @pss: current PSS channel - * @block: block that contains the page we want to send - * @offset: offset inside the block for the page - */ -static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block, - ram_addr_t offset) -{ - int len = save_zero_page_to_file(pss, f, block, offset); + len += save_page_header(pss, file, pss->block, offset | RAM_SAVE_FLAG_ZERO); + qemu_put_byte(file, 0); + len += 1; + ram_release_page(pss->block->idstr, offset); - if (len) { - stat64_add(&mig_stats.zero_pages, 1); - ram_transferred_add(len); - return 1; + stat64_add(&mig_stats.zero_pages, 1); + ram_transferred_add(len); + + /* + * Must let xbzrle know, otherwise a previous (now 0'd) cached + * page would be stale. + */ + if (rs->xbzrle_started) { + XBZRLE_cache_lock(); + xbzrle_cache_zero_page(pss->block->offset + offset); + XBZRLE_cache_unlock(); } - return -1; + + return len; } /* @@ -1191,13 +1185,13 @@ static int save_zero_page(PageSearchStatus *pss, QEMUFile *f, RAMBlock *block, * * Return true if the pages has been saved, otherwise false is returned. */ -static bool control_save_page(PageSearchStatus *pss, RAMBlock *block, +static bool control_save_page(PageSearchStatus *pss, ram_addr_t offset, int *pages) { int ret; - ret = ram_control_save_page(pss->pss_channel, block->offset, offset, - TARGET_PAGE_SIZE); + ret = rdma_control_save_page(pss->pss_channel, pss->block->offset, offset, + TARGET_PAGE_SIZE); if (ret == RAM_SAVE_CONTROL_NOT_SUPP) { return false; } @@ -1297,21 +1291,6 @@ static int ram_save_multifd_page(QEMUFile *file, RAMBlock *block, return 1; } -static void -update_compress_thread_counts(const CompressParam *param, int bytes_xmit) -{ - ram_transferred_add(bytes_xmit); - - if (param->result == RES_ZEROPAGE) { - stat64_add(&mig_stats.zero_pages, 1); - return; - } - - /* 8 means a header with RAM_SAVE_FLAG_CONTINUE. */ - compression_counters.compressed_size += bytes_xmit - 8; - compression_counters.pages++; -} - static bool save_page_use_compression(RAMState *rs); static int send_queued_data(CompressParam *param) @@ -1395,7 +1374,8 @@ static int find_dirty_block(RAMState *rs, PageSearchStatus *pss) pss->page = 0; pss->block = QLIST_NEXT_RCU(pss->block, next); if (!pss->block) { - if (!migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && + !migrate_multifd_flush_after_each_section()) { QEMUFile *f = rs->pss[RAM_CHANNEL_PRECOPY].pss_channel; int ret = multifd_send_sync_main(f); if (ret < 0) { @@ -2086,7 +2066,7 @@ static bool save_page_use_compression(RAMState *rs) * paths to handle it */ static bool save_compress_page(RAMState *rs, PageSearchStatus *pss, - RAMBlock *block, ram_addr_t offset) + ram_addr_t offset) { if (!save_page_use_compression(rs)) { return false; @@ -2102,12 +2082,13 @@ static bool save_compress_page(RAMState *rs, PageSearchStatus *pss, * We post the fist page as normal page as compression will take * much CPU resource. */ - if (block != pss->last_sent_block) { + if (pss->block != pss->last_sent_block) { ram_flush_compressed_data(rs); return false; } - if (compress_page_with_multi_thread(block, offset, send_queued_data) > 0) { + if (compress_page_with_multi_thread(pss->block, offset, + send_queued_data) > 0) { return true; } @@ -2129,25 +2110,16 @@ static int ram_save_target_page_legacy(RAMState *rs, PageSearchStatus *pss) ram_addr_t offset = ((ram_addr_t)pss->page) << TARGET_PAGE_BITS; int res; - if (control_save_page(pss, block, offset, &res)) { + if (control_save_page(pss, offset, &res)) { return res; } - if (save_compress_page(rs, pss, block, offset)) { + if (save_compress_page(rs, pss, offset)) { return 1; } - res = save_zero_page(pss, pss->pss_channel, block, offset); - if (res > 0) { - /* Must let xbzrle know, otherwise a previous (now 0'd) cached - * page would be stale - */ - if (rs->xbzrle_started) { - XBZRLE_cache_lock(); - xbzrle_cache_zero_page(rs, block->offset + offset); - XBZRLE_cache_unlock(); - } - return res; + if (save_zero_page(rs, pss, offset)) { + return 1; } /* @@ -2891,8 +2863,6 @@ static void migration_bitmap_clear_discarded_pages(RAMState *rs) static void ram_init_bitmaps(RAMState *rs) { - /* For memory_global_dirty_log_start below. */ - qemu_mutex_lock_iothread(); qemu_mutex_lock_ramlist(); WITH_RCU_READ_LOCK_GUARD() { @@ -2904,7 +2874,6 @@ static void ram_init_bitmaps(RAMState *rs) } } qemu_mutex_unlock_ramlist(); - qemu_mutex_unlock_iothread(); /* * After an eventual first bitmap sync, fixup the initial bitmap @@ -3062,17 +3031,27 @@ static int ram_save_setup(QEMUFile *f, void *opaque) } } - ram_control_before_iterate(f, RAM_CONTROL_SETUP); - ram_control_after_iterate(f, RAM_CONTROL_SETUP); + ret = rdma_registration_start(f, RAM_CONTROL_SETUP); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + + ret = rdma_registration_stop(f, RAM_CONTROL_SETUP); + if (ret < 0) { + qemu_file_set_error(f, ret); + } migration_ops = g_malloc0(sizeof(MigrationOps)); migration_ops->ram_save_target_page = ram_save_target_page_legacy; + + qemu_mutex_unlock_iothread(); ret = multifd_send_sync_main(f); + qemu_mutex_lock_iothread(); if (ret < 0) { return ret; } - if (!migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) { qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH); } @@ -3122,7 +3101,10 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) /* Read version before ram_list.blocks */ smp_rmb(); - ram_control_before_iterate(f, RAM_CONTROL_ROUND); + ret = rdma_registration_start(f, RAM_CONTROL_ROUND); + if (ret < 0) { + qemu_file_set_error(f, ret); + } t0 = qemu_clock_get_ns(QEMU_CLOCK_REALTIME); i = 0; @@ -3179,12 +3161,15 @@ static int ram_save_iterate(QEMUFile *f, void *opaque) * Must occur before EOS (or any QEMUFile operation) * because of RDMA protocol. */ - ram_control_after_iterate(f, RAM_CONTROL_ROUND); + ret = rdma_registration_stop(f, RAM_CONTROL_ROUND); + if (ret < 0) { + qemu_file_set_error(f, ret); + } out: if (ret >= 0 && migration_is_setup_or_active(migrate_get_current()->state)) { - if (migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && migrate_multifd_flush_after_each_section()) { ret = multifd_send_sync_main(rs->pss[RAM_CHANNEL_PRECOPY].pss_channel); if (ret < 0) { return ret; @@ -3227,7 +3212,10 @@ static int ram_save_complete(QEMUFile *f, void *opaque) migration_bitmap_sync_precopy(rs, true); } - ram_control_before_iterate(f, RAM_CONTROL_FINISH); + ret = rdma_registration_start(f, RAM_CONTROL_FINISH); + if (ret < 0) { + qemu_file_set_error(f, ret); + } /* try transferring iterative blocks of memory */ @@ -3249,7 +3237,11 @@ static int ram_save_complete(QEMUFile *f, void *opaque) qemu_mutex_unlock(&rs->bitmap_mutex); ram_flush_compressed_data(rs); - ram_control_after_iterate(f, RAM_CONTROL_FINISH); + + int ret = rdma_registration_stop(f, RAM_CONTROL_FINISH); + if (ret < 0) { + qemu_file_set_error(f, ret); + } } if (ret < 0) { @@ -3261,7 +3253,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque) return ret; } - if (!migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && !migrate_multifd_flush_after_each_section()) { qemu_put_be64(f, RAM_SAVE_FLAG_MULTIFD_FLUSH); } qemu_put_be64(f, RAM_SAVE_FLAG_EOS); @@ -3768,7 +3760,8 @@ int ram_load_postcopy(QEMUFile *f, int channel) break; case RAM_SAVE_FLAG_EOS: /* normal exit */ - if (migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && + migrate_multifd_flush_after_each_section()) { multifd_recv_sync_main(); } break; @@ -3861,6 +3854,85 @@ void colo_flush_ram_cache(void) trace_colo_flush_ram_cache_end(); } +static int parse_ramblock(QEMUFile *f, RAMBlock *block, ram_addr_t length) +{ + int ret = 0; + /* ADVISE is earlier, it shows the source has the postcopy capability on */ + bool postcopy_advised = migration_incoming_postcopy_advised(); + + assert(block); + + if (!qemu_ram_is_migratable(block)) { + error_report("block %s should not be migrated !", block->idstr); + return -EINVAL; + } + + if (length != block->used_length) { + Error *local_err = NULL; + + ret = qemu_ram_resize(block, length, &local_err); + if (local_err) { + error_report_err(local_err); + } + } + /* For postcopy we need to check hugepage sizes match */ + if (postcopy_advised && migrate_postcopy_ram() && + block->page_size != qemu_host_page_size) { + uint64_t remote_page_size = qemu_get_be64(f); + if (remote_page_size != block->page_size) { + error_report("Mismatched RAM page size %s " + "(local) %zd != %" PRId64, block->idstr, + block->page_size, remote_page_size); + ret = -EINVAL; + } + } + if (migrate_ignore_shared()) { + hwaddr addr = qemu_get_be64(f); + if (migrate_ram_is_ignored(block) && + block->mr->addr != addr) { + error_report("Mismatched GPAs for block %s " + "%" PRId64 "!= %" PRId64, block->idstr, + (uint64_t)addr, (uint64_t)block->mr->addr); + ret = -EINVAL; + } + } + ret = rdma_block_notification_handle(f, block->idstr); + if (ret < 0) { + qemu_file_set_error(f, ret); + } + + return ret; +} + +static int parse_ramblocks(QEMUFile *f, ram_addr_t total_ram_bytes) +{ + int ret = 0; + + /* Synchronize RAM block list */ + while (!ret && total_ram_bytes) { + RAMBlock *block; + char id[256]; + ram_addr_t length; + int len = qemu_get_byte(f); + + qemu_get_buffer(f, (uint8_t *)id, len); + id[len] = 0; + length = qemu_get_be64(f); + + block = qemu_ram_block_by_name(id); + if (block) { + ret = parse_ramblock(f, block, length); + } else { + error_report("Unknown ramblock \"%s\", cannot accept " + "migration", id); + ret = -EINVAL; + } + total_ram_bytes -= length; + } + + return ret; +} + /** * ram_load_precopy: load pages in precopy case * @@ -3875,14 +3947,13 @@ static int ram_load_precopy(QEMUFile *f) { MigrationIncomingState *mis = migration_incoming_get_current(); int flags = 0, ret = 0, invalid_flags = 0, len = 0, i = 0; - /* ADVISE is earlier, it shows the source has the postcopy capability on */ - bool postcopy_advised = migration_incoming_postcopy_advised(); + if (!migrate_compress()) { invalid_flags |= RAM_SAVE_FLAG_COMPRESS_PAGE; } while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) { - ram_addr_t addr, total_ram_bytes; + ram_addr_t addr; void *host = NULL, *host_bak = NULL; uint8_t ch; @@ -3953,65 +4024,7 @@ static int ram_load_precopy(QEMUFile *f) switch (flags & ~RAM_SAVE_FLAG_CONTINUE) { case RAM_SAVE_FLAG_MEM_SIZE: - /* Synchronize RAM block list */ - total_ram_bytes = addr; - while (!ret && total_ram_bytes) { - RAMBlock *block; - char id[256]; - ram_addr_t length; - - len = qemu_get_byte(f); - qemu_get_buffer(f, (uint8_t *)id, len); - id[len] = 0; - length = qemu_get_be64(f); - - block = qemu_ram_block_by_name(id); - if (block && !qemu_ram_is_migratable(block)) { - error_report("block %s should not be migrated !", id); - ret = -EINVAL; - } else if (block) { - if (length != block->used_length) { - Error *local_err = NULL; - - ret = qemu_ram_resize(block, length, - &local_err); - if (local_err) { - error_report_err(local_err); - } - } - /* For postcopy we need to check hugepage sizes match */ - if (postcopy_advised && migrate_postcopy_ram() && - block->page_size != qemu_host_page_size) { - uint64_t remote_page_size = qemu_get_be64(f); - if (remote_page_size != block->page_size) { - error_report("Mismatched RAM page size %s " - "(local) %zd != %" PRId64, - id, block->page_size, - remote_page_size); - ret = -EINVAL; - } - } - if (migrate_ignore_shared()) { - hwaddr addr2 = qemu_get_be64(f); - if (migrate_ram_is_ignored(block) && - block->mr->addr != addr2) { - error_report("Mismatched GPAs for block %s " - "%" PRId64 "!= %" PRId64, - id, (uint64_t)addr2, - (uint64_t)block->mr->addr); - ret = -EINVAL; - } - } - ram_control_load_hook(f, RAM_CONTROL_BLOCK_REG, - block->idstr); - } else { - error_report("Unknown ramblock \"%s\", cannot " - "accept migration", id); - ret = -EINVAL; - } - - total_ram_bytes -= length; - } + ret = parse_ramblocks(f, addr); break; case RAM_SAVE_FLAG_ZERO: @@ -4046,12 +4059,16 @@ static int ram_load_precopy(QEMUFile *f) break; case RAM_SAVE_FLAG_EOS: /* normal exit */ - if (migrate_multifd_flush_after_each_section()) { + if (migrate_multifd() && + migrate_multifd_flush_after_each_section()) { multifd_recv_sync_main(); } break; case RAM_SAVE_FLAG_HOOK: - ram_control_load_hook(f, RAM_CONTROL_HOOK, NULL); + ret = rdma_registration_handle(f); + if (ret < 0) { + qemu_file_set_error(f, ret); + } break; default: error_report("Unknown combination of migration flags: 0x%x", flags); @@ -4159,7 +4176,8 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block) int ret = -EINVAL; /* from_dst_file is always valid because we're within rp_thread */ QEMUFile *file = s->rp_state.from_dst_file; - unsigned long *le_bitmap, nbits = block->used_length >> TARGET_PAGE_BITS; + g_autofree unsigned long *le_bitmap = NULL; + unsigned long nbits = block->used_length >> TARGET_PAGE_BITS; uint64_t local_size = DIV_ROUND_UP(nbits, 8); uint64_t size, end_mark; RAMState *rs = ram_state; @@ -4188,8 +4206,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block) error_report("%s: ramblock '%s' bitmap size mismatch " "(0x%"PRIx64" != 0x%"PRIx64")", __func__, block->idstr, size, local_size); - ret = -EINVAL; - goto out; + return -EINVAL; } size = qemu_get_buffer(file, (uint8_t *)le_bitmap, local_size); @@ -4200,15 +4217,13 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block) error_report("%s: read bitmap failed for ramblock '%s': %d" " (size 0x%"PRIx64", got: 0x%"PRIx64")", __func__, block->idstr, ret, local_size, size); - ret = -EIO; - goto out; + return -EIO; } if (end_mark != RAMBLOCK_RECV_BITMAP_ENDING) { error_report("%s: ramblock '%s' end mark incorrect: 0x%"PRIx64, __func__, block->idstr, end_mark); - ret = -EINVAL; - goto out; + return -EINVAL; } /* @@ -4240,10 +4255,7 @@ int ram_dirty_bitmap_reload(MigrationState *s, RAMBlock *block) */ migration_rp_kick(s); - ret = 0; -out: - g_free(le_bitmap); - return ret; + return 0; } static int ram_resume_prepare(MigrationState *s, void *opaque) @@ -4290,6 +4302,11 @@ static void ram_mig_ram_block_resized(RAMBlockNotifier *n, void *host, RAMBlock *rb = qemu_ram_block_from_host(host, false, &offset); Error *err = NULL; + if (!rb) { + error_report("RAM block not found"); + return; + } + if (migrate_ram_is_ignored(rb)) { return; } diff --git a/migration/rdma.c b/migration/rdma.c index f6fc226c9b..2a1852ec7f 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -559,10 +559,8 @@ static void rdma_add_block(RDMAContext *rdma, const char *block_name, local->block = g_new0(RDMALocalBlock, local->nb_blocks + 1); if (local->nb_blocks) { - int x; - if (rdma->blockmap) { - for (x = 0; x < local->nb_blocks; x++) { + for (int x = 0; x < local->nb_blocks; x++) { g_hash_table_remove(rdma->blockmap, (void *)(uintptr_t)old[x].offset); g_hash_table_insert(rdma->blockmap, @@ -649,15 +647,12 @@ static void rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) { RDMALocalBlocks *local = &rdma->local_ram_blocks; RDMALocalBlock *old = local->block; - int x; if (rdma->blockmap) { g_hash_table_remove(rdma->blockmap, (void *)(uintptr_t)block->offset); } if (block->pmr) { - int j; - - for (j = 0; j < block->nb_chunks; j++) { + for (int j = 0; j < block->nb_chunks; j++) { if (!block->pmr[j]) { continue; } @@ -687,7 +682,7 @@ static void rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) block->block_name = NULL; if (rdma->blockmap) { - for (x = 0; x < local->nb_blocks; x++) { + for (int x = 0; x < local->nb_blocks; x++) { g_hash_table_remove(rdma->blockmap, (void *)(uintptr_t)old[x].offset); } @@ -705,7 +700,7 @@ static void rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) memcpy(local->block + block->index, old + (block->index + 1), sizeof(RDMALocalBlock) * (local->nb_blocks - (block->index + 1))); - for (x = block->index; x < local->nb_blocks - 1; x++) { + for (int x = block->index; x < local->nb_blocks - 1; x++) { local->block[x].index--; } } @@ -725,7 +720,7 @@ static void rdma_delete_block(RDMAContext *rdma, RDMALocalBlock *block) local->nb_blocks--; if (local->nb_blocks && rdma->blockmap) { - for (x = 0; x < local->nb_blocks; x++) { + for (int x = 0; x < local->nb_blocks; x++) { g_hash_table_insert(rdma->blockmap, (void *)(uintptr_t)local->block[x].offset, &local->block[x]); @@ -828,12 +823,12 @@ static int qemu_rdma_broken_ipv6_kernel(struct ibv_context *verbs, Error **errp) * Otherwise, there are no guarantees until the bug is fixed in linux. */ if (!verbs) { - int num_devices, x; + int num_devices; struct ibv_device **dev_list = ibv_get_device_list(&num_devices); bool roce_found = false; bool ib_found = false; - for (x = 0; x < num_devices; x++) { + for (int x = 0; x < num_devices; x++) { verbs = ibv_open_device(dev_list[x]); /* * ibv_open_device() is not documented to set errno. If @@ -925,7 +920,6 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) char port_str[16]; struct rdma_cm_event *cm_event; char ip[40] = "unknown"; - struct rdma_addrinfo *e; if (rdma->host == NULL || !strcmp(rdma->host, "")) { error_setg(errp, "RDMA ERROR: RDMA hostname has not been set"); @@ -957,7 +951,7 @@ static int qemu_rdma_resolve_host(RDMAContext *rdma, Error **errp) } /* Try all addresses, saving the first error in @err */ - for (e = res; e != NULL; e = e->ai_next) { + for (struct rdma_addrinfo *e = res; e != NULL; e = e->ai_next) { Error **local_errp = err ? NULL : &err; inet_ntop(e->ai_family, @@ -1113,7 +1107,6 @@ err_alloc_pd_cq: static int qemu_rdma_alloc_qp(RDMAContext *rdma) { struct ibv_qp_init_attr attr = { 0 }; - int ret; attr.cap.max_send_wr = RDMA_SIGNALED_SEND_MAX; attr.cap.max_recv_wr = 3; @@ -1123,8 +1116,7 @@ static int qemu_rdma_alloc_qp(RDMAContext *rdma) attr.recv_cq = rdma->recv_cq; attr.qp_type = IBV_QPT_RC; - ret = rdma_create_qp(rdma->cm_id, rdma->pd, &attr); - if (ret < 0) { + if (rdma_create_qp(rdma->cm_id, rdma->pd, &attr) < 0) { return -1; } @@ -1136,8 +1128,8 @@ static int qemu_rdma_alloc_qp(RDMAContext *rdma) static bool rdma_support_odp(struct ibv_context *dev) { struct ibv_device_attr_ex attr = {0}; - int ret = ibv_query_device_ex(dev, NULL, &attr); - if (ret) { + + if (ibv_query_device_ex(dev, NULL, &attr)) { return false; } @@ -1514,7 +1506,6 @@ static int qemu_rdma_wait_comp_channel(RDMAContext *rdma, struct ibv_comp_channel *comp_channel) { struct rdma_cm_event *cm_event; - int ret; /* * Coroutine doesn't start until migration_fd_process_incoming() @@ -1550,8 +1541,7 @@ static int qemu_rdma_wait_comp_channel(RDMAContext *rdma, } if (pfds[1].revents) { - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { + if (rdma_get_cm_event(rdma->channel, &cm_event) < 0) { return -1; } @@ -2323,12 +2313,10 @@ static int qemu_rdma_write(RDMAContext *rdma, uint64_t current_addr = block_offset + offset; uint64_t index = rdma->current_index; uint64_t chunk = rdma->current_chunk; - int ret; /* If we cannot merge it, we flush the current buffer first. */ if (!qemu_rdma_buffer_mergeable(rdma, current_addr, len)) { - ret = qemu_rdma_write_flush(rdma, errp); - if (ret < 0) { + if (qemu_rdma_write_flush(rdma, errp) < 0) { return -1; } rdma->current_length = 0; @@ -2354,7 +2342,6 @@ static int qemu_rdma_write(RDMAContext *rdma, static void qemu_rdma_cleanup(RDMAContext *rdma) { Error *err = NULL; - int idx; if (rdma->cm_id && rdma->connected) { if ((rdma->errored || @@ -2381,12 +2368,12 @@ static void qemu_rdma_cleanup(RDMAContext *rdma) g_free(rdma->dest_blocks); rdma->dest_blocks = NULL; - for (idx = 0; idx < RDMA_WRID_MAX; idx++) { - if (rdma->wr_data[idx].control_mr) { + for (int i = 0; i < RDMA_WRID_MAX; i++) { + if (rdma->wr_data[i].control_mr) { rdma->total_registrations--; - ibv_dereg_mr(rdma->wr_data[idx].control_mr); + ibv_dereg_mr(rdma->wr_data[i].control_mr); } - rdma->wr_data[idx].control_mr = NULL; + rdma->wr_data[i].control_mr = NULL; } if (rdma->local_ram_blocks.block) { @@ -2452,7 +2439,7 @@ static void qemu_rdma_cleanup(RDMAContext *rdma) static int qemu_rdma_source_init(RDMAContext *rdma, bool pin_all, Error **errp) { - int ret, idx; + int ret; /* * Will be validated against destination's actual capabilities @@ -2480,18 +2467,17 @@ static int qemu_rdma_source_init(RDMAContext *rdma, bool pin_all, Error **errp) /* Build the hash that maps from offset to RAMBlock */ rdma->blockmap = g_hash_table_new(g_direct_hash, g_direct_equal); - for (idx = 0; idx < rdma->local_ram_blocks.nb_blocks; idx++) { + for (int i = 0; i < rdma->local_ram_blocks.nb_blocks; i++) { g_hash_table_insert(rdma->blockmap, - (void *)(uintptr_t)rdma->local_ram_blocks.block[idx].offset, - &rdma->local_ram_blocks.block[idx]); + (void *)(uintptr_t)rdma->local_ram_blocks.block[i].offset, + &rdma->local_ram_blocks.block[i]); } - for (idx = 0; idx < RDMA_WRID_MAX; idx++) { - ret = qemu_rdma_reg_control(rdma, idx); + for (int i = 0; i < RDMA_WRID_MAX; i++) { + ret = qemu_rdma_reg_control(rdma, i); if (ret < 0) { - error_setg(errp, - "RDMA ERROR: rdma migration: error registering %d control!", - idx); + error_setg(errp, "RDMA ERROR: rdma migration: error " + "registering %d control!", i); goto err_rdma_source_init; } } @@ -2625,16 +2611,16 @@ err_rdma_source_connect: static int qemu_rdma_dest_init(RDMAContext *rdma, Error **errp) { Error *err = NULL; - int ret, idx; + int ret; struct rdma_cm_id *listen_id; char ip[40] = "unknown"; struct rdma_addrinfo *res, *e; char port_str[16]; int reuse = 1; - for (idx = 0; idx < RDMA_WRID_MAX; idx++) { - rdma->wr_data[idx].control_len = 0; - rdma->wr_data[idx].control_curr = NULL; + for (int i = 0; i < RDMA_WRID_MAX; i++) { + rdma->wr_data[i].control_len = 0; + rdma->wr_data[i].control_curr = NULL; } if (!rdma->host || !rdma->host[0]) { @@ -2723,11 +2709,9 @@ err_dest_init_create_listen_id: static void qemu_rdma_return_path_dest_init(RDMAContext *rdma_return_path, RDMAContext *rdma) { - int idx; - - for (idx = 0; idx < RDMA_WRID_MAX; idx++) { - rdma_return_path->wr_data[idx].control_len = 0; - rdma_return_path->wr_data[idx].control_curr = NULL; + for (int i = 0; i < RDMA_WRID_MAX; i++) { + rdma_return_path->wr_data[i].control_len = 0; + rdma_return_path->wr_data[i].control_curr = NULL; } /*the CM channel and CM id is shared*/ @@ -2781,7 +2765,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, RDMAContext *rdma; int ret; ssize_t done = 0; - size_t i, len; + size_t len; RCU_READ_LOCK_GUARD(); rdma = qatomic_rcu_read(&rioc->rdmaout); @@ -2807,7 +2791,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, return -1; } - for (i = 0; i < niov; i++) { + for (int i = 0; i < niov; i++) { size_t remaining = iov[i].iov_len; uint8_t * data = (void *)iov[i].iov_base; while (remaining) { @@ -2870,7 +2854,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, RDMAControlHeader head; int ret; ssize_t done = 0; - size_t i, len; + size_t len; RCU_READ_LOCK_GUARD(); rdma = qatomic_rcu_read(&rioc->rdmain); @@ -2886,7 +2870,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, return -1; } - for (i = 0; i < niov; i++) { + for (int i = 0; i < niov; i++) { size_t want = iov[i].iov_len; uint8_t *data = (void *)iov[i].iov_base; @@ -2946,7 +2930,6 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, static int qemu_rdma_drain_cq(RDMAContext *rdma) { Error *err = NULL; - int ret; if (qemu_rdma_write_flush(rdma, &err) < 0) { error_report_err(err); @@ -2954,8 +2937,7 @@ static int qemu_rdma_drain_cq(RDMAContext *rdma) } while (rdma->nb_sent) { - ret = qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL); - if (ret < 0) { + if (qemu_rdma_block_for_wrid(rdma, RDMA_WRID_RDMA_WRITE, NULL) < 0) { error_report("rdma migration: complete polling error!"); return -1; } @@ -3240,10 +3222,6 @@ static int qemu_rdma_save_page(QEMUFile *f, ram_addr_t block_offset, RDMAContext *rdma; int ret; - if (migration_in_postcopy()) { - return RAM_SAVE_CONTROL_NOT_SUPP; - } - RCU_READ_LOCK_GUARD(); rdma = qatomic_rcu_read(&rioc->rdmaout); @@ -3314,17 +3292,33 @@ err: return -1; } +int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, + ram_addr_t offset, size_t size) +{ + if (!migrate_rdma() || migration_in_postcopy()) { + return RAM_SAVE_CONTROL_NOT_SUPP; + } + + int ret = qemu_rdma_save_page(f, block_offset, offset, size); + + if (ret != RAM_SAVE_CONTROL_DELAYED && + ret != RAM_SAVE_CONTROL_NOT_SUPP) { + if (ret < 0) { + qemu_file_set_error(f, ret); + } + } + return ret; +} + static void rdma_accept_incoming_migration(void *opaque); static void rdma_cm_poll_handler(void *opaque) { RDMAContext *rdma = opaque; - int ret; struct rdma_cm_event *cm_event; MigrationIncomingState *mis = migration_incoming_get_current(); - ret = rdma_get_cm_event(rdma->channel, &cm_event); - if (ret < 0) { + if (rdma_get_cm_event(rdma->channel, &cm_event) < 0) { error_report("get_cm_event failed %d", errno); return; } @@ -3362,7 +3356,6 @@ static int qemu_rdma_accept(RDMAContext *rdma) struct rdma_cm_event *cm_event; struct ibv_context *verbs; int ret; - int idx; ret = rdma_get_cm_event(rdma->channel, &cm_event); if (ret < 0) { @@ -3448,10 +3441,10 @@ static int qemu_rdma_accept(RDMAContext *rdma) qemu_rdma_init_ram_blocks(rdma); - for (idx = 0; idx < RDMA_WRID_MAX; idx++) { - ret = qemu_rdma_reg_control(rdma, idx); + for (int i = 0; i < RDMA_WRID_MAX; i++) { + ret = qemu_rdma_reg_control(rdma, i); if (ret < 0) { - error_report("rdma: error registering %d control", idx); + error_report("rdma: error registering %d control", i); goto err_rdma_dest_wait; } } @@ -3522,7 +3515,7 @@ static int dest_ram_sort_func(const void *a, const void *b) * * Keep doing this until the source tells us to stop. */ -static int qemu_rdma_registration_handle(QEMUFile *f) +int rdma_registration_handle(QEMUFile *f) { RDMAControlHeader reg_resp = { .len = sizeof(RDMARegisterResult), .type = RDMA_CONTROL_REGISTER_RESULT, @@ -3534,7 +3527,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) }; RDMAControlHeader blocks = { .type = RDMA_CONTROL_RAM_BLOCKS_RESULT, .repeat = 1 }; - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); + QIOChannelRDMA *rioc; Error *err = NULL; RDMAContext *rdma; RDMALocalBlocks *local; @@ -3547,10 +3540,13 @@ static int qemu_rdma_registration_handle(QEMUFile *f) void *host_addr; int ret; int idx = 0; - int count = 0; - int i = 0; + + if (!migrate_rdma()) { + return 0; + } RCU_READ_LOCK_GUARD(); + rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); rdma = qatomic_rcu_read(&rioc->rdmain); if (!rdma) { @@ -3563,7 +3559,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) local = &rdma->local_ram_blocks; do { - trace_qemu_rdma_registration_handle_wait(); + trace_rdma_registration_handle_wait(); ret = qemu_rdma_exchange_recv(rdma, &head, RDMA_CONTROL_NONE, &err); @@ -3583,9 +3579,9 @@ static int qemu_rdma_registration_handle(QEMUFile *f) comp = (RDMACompress *) rdma->wr_data[idx].control_curr; network_to_compress(comp); - trace_qemu_rdma_registration_handle_compress(comp->length, - comp->block_idx, - comp->offset); + trace_rdma_registration_handle_compress(comp->length, + comp->block_idx, + comp->offset); if (comp->block_idx >= rdma->local_ram_blocks.nb_blocks) { error_report("rdma: 'compress' bad block index %u (vs %d)", (unsigned int)comp->block_idx, @@ -3601,11 +3597,11 @@ static int qemu_rdma_registration_handle(QEMUFile *f) break; case RDMA_CONTROL_REGISTER_FINISHED: - trace_qemu_rdma_registration_handle_finished(); + trace_rdma_registration_handle_finished(); return 0; case RDMA_CONTROL_RAM_BLOCKS_REQUEST: - trace_qemu_rdma_registration_handle_ram_blocks(); + trace_rdma_registration_handle_ram_blocks(); /* Sort our local RAM Block list so it's the same as the source, * we can do this since we've filled in a src_index in the list @@ -3614,7 +3610,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) qsort(rdma->local_ram_blocks.block, rdma->local_ram_blocks.nb_blocks, sizeof(RDMALocalBlock), dest_ram_sort_func); - for (i = 0; i < local->nb_blocks; i++) { + for (int i = 0; i < local->nb_blocks; i++) { local->block[i].index = i; } @@ -3632,7 +3628,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) * Both sides use the "remote" structure to communicate and update * their "local" descriptions with what was sent. */ - for (i = 0; i < local->nb_blocks; i++) { + for (int i = 0; i < local->nb_blocks; i++) { rdma->dest_blocks[i].remote_host_addr = (uintptr_t)(local->block[i].local_host_addr); @@ -3644,7 +3640,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) rdma->dest_blocks[i].length = local->block[i].length; dest_block_to_network(&rdma->dest_blocks[i]); - trace_qemu_rdma_registration_handle_ram_blocks_loop( + trace_rdma_registration_handle_ram_blocks_loop( local->block[i].block_name, local->block[i].offset, local->block[i].length, @@ -3667,12 +3663,12 @@ static int qemu_rdma_registration_handle(QEMUFile *f) break; case RDMA_CONTROL_REGISTER_REQUEST: - trace_qemu_rdma_registration_handle_register(head.repeat); + trace_rdma_registration_handle_register(head.repeat); reg_resp.repeat = head.repeat; registers = (RDMARegister *) rdma->wr_data[idx].control_curr; - for (count = 0; count < head.repeat; count++) { + for (int count = 0; count < head.repeat; count++) { uint64_t chunk; uint8_t *chunk_start, *chunk_end; @@ -3681,7 +3677,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) reg_result = &results[count]; - trace_qemu_rdma_registration_handle_register_loop(count, + trace_rdma_registration_handle_register_loop(count, reg->current_index, reg->key.current_addr, reg->chunks); if (reg->current_index >= rdma->local_ram_blocks.nb_blocks) { @@ -3729,8 +3725,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) reg_result->host_addr = (uintptr_t)block->local_host_addr; - trace_qemu_rdma_registration_handle_register_rkey( - reg_result->rkey); + trace_rdma_registration_handle_register_rkey(reg_result->rkey); result_to_network(reg_result); } @@ -3744,15 +3739,15 @@ static int qemu_rdma_registration_handle(QEMUFile *f) } break; case RDMA_CONTROL_UNREGISTER_REQUEST: - trace_qemu_rdma_registration_handle_unregister(head.repeat); + trace_rdma_registration_handle_unregister(head.repeat); unreg_resp.repeat = head.repeat; registers = (RDMARegister *) rdma->wr_data[idx].control_curr; - for (count = 0; count < head.repeat; count++) { + for (int count = 0; count < head.repeat; count++) { reg = ®isters[count]; network_to_register(reg); - trace_qemu_rdma_registration_handle_unregister_loop(count, + trace_rdma_registration_handle_unregister_loop(count, reg->current_index, reg->key.chunk); block = &(rdma->local_ram_blocks.block[reg->current_index]); @@ -3768,8 +3763,7 @@ static int qemu_rdma_registration_handle(QEMUFile *f) rdma->total_registrations--; - trace_qemu_rdma_registration_handle_unregister_success( - reg->key.chunk); + trace_rdma_registration_handle_unregister_success(reg->key.chunk); } ret = qemu_rdma_post_send_control(rdma, NULL, &unreg_resp, &err); @@ -3794,22 +3788,23 @@ err: } /* Destination: - * Called via a ram_control_load_hook during the initial RAM load section which - * lists the RAMBlocks by name. This lets us know the order of the RAMBlocks - * on the source. - * We've already built our local RAMBlock list, but not yet sent the list to - * the source. + * Called during the initial RAM load section which lists the + * RAMBlocks by name. This lets us know the order of the RAMBlocks on + * the source. We've already built our local RAMBlock list, but not + * yet sent the list to the source. */ -static int -rdma_block_notification_handle(QEMUFile *f, const char *name) +int rdma_block_notification_handle(QEMUFile *f, const char *name) { - RDMAContext *rdma; - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); int curr; int found = -1; + if (!migrate_rdma()) { + return 0; + } + RCU_READ_LOCK_GUARD(); - rdma = qatomic_rcu_read(&rioc->rdmain); + QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); + RDMAContext *rdma = qatomic_rcu_read(&rioc->rdmain); if (!rdma) { return -1; @@ -3835,33 +3830,15 @@ rdma_block_notification_handle(QEMUFile *f, const char *name) return 0; } -static int rdma_load_hook(QEMUFile *f, uint64_t flags, void *data) -{ - switch (flags) { - case RAM_CONTROL_BLOCK_REG: - return rdma_block_notification_handle(f, data); - - case RAM_CONTROL_HOOK: - return qemu_rdma_registration_handle(f); - - default: - /* Shouldn't be called with any other values */ - abort(); - } -} - -static int qemu_rdma_registration_start(QEMUFile *f, - uint64_t flags, void *data) +int rdma_registration_start(QEMUFile *f, uint64_t flags) { - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); - RDMAContext *rdma; - - if (migration_in_postcopy()) { + if (!migrate_rdma() || migration_in_postcopy()) { return 0; } + QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); RCU_READ_LOCK_GUARD(); - rdma = qatomic_rcu_read(&rioc->rdmaout); + RDMAContext *rdma = qatomic_rcu_read(&rioc->rdmaout); if (!rdma) { return -1; } @@ -3870,7 +3847,7 @@ static int qemu_rdma_registration_start(QEMUFile *f, return -1; } - trace_qemu_rdma_registration_start(flags); + trace_rdma_registration_start(flags); qemu_put_be64(f, RAM_SAVE_FLAG_HOOK); qemu_fflush(f); @@ -3881,20 +3858,20 @@ static int qemu_rdma_registration_start(QEMUFile *f, * Inform dest that dynamic registrations are done for now. * First, flush writes, if any. */ -static int qemu_rdma_registration_stop(QEMUFile *f, - uint64_t flags, void *data) +int rdma_registration_stop(QEMUFile *f, uint64_t flags) { - QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); + QIOChannelRDMA *rioc; Error *err = NULL; RDMAContext *rdma; RDMAControlHeader head = { .len = 0, .repeat = 1 }; int ret; - if (migration_in_postcopy()) { + if (!migrate_rdma() || migration_in_postcopy()) { return 0; } RCU_READ_LOCK_GUARD(); + rioc = QIO_CHANNEL_RDMA(qemu_file_get_ioc(f)); rdma = qatomic_rcu_read(&rioc->rdmaout); if (!rdma) { return -1; @@ -3914,10 +3891,10 @@ static int qemu_rdma_registration_stop(QEMUFile *f, if (flags == RAM_CONTROL_SETUP) { RDMAControlHeader resp = {.type = RDMA_CONTROL_RAM_BLOCKS_RESULT }; RDMALocalBlocks *local = &rdma->local_ram_blocks; - int reg_result_idx, i, nb_dest_blocks; + int reg_result_idx, nb_dest_blocks; head.type = RDMA_CONTROL_RAM_BLOCKS_REQUEST; - trace_qemu_rdma_registration_stop_ram(); + trace_rdma_registration_stop_ram(); /* * Make sure that we parallelize the pinning on both sides. @@ -3962,7 +3939,7 @@ static int qemu_rdma_registration_stop(QEMUFile *f, qemu_rdma_move_header(rdma, reg_result_idx, &resp); memcpy(rdma->dest_blocks, rdma->wr_data[reg_result_idx].control_curr, resp.len); - for (i = 0; i < nb_dest_blocks; i++) { + for (int i = 0; i < nb_dest_blocks; i++) { network_to_dest_block(&rdma->dest_blocks[i]); /* We require that the blocks are in the same order */ @@ -3981,7 +3958,7 @@ static int qemu_rdma_registration_stop(QEMUFile *f, } } - trace_qemu_rdma_registration_stop(flags); + trace_rdma_registration_stop(flags); head.type = RDMA_CONTROL_REGISTER_FINISHED; ret = qemu_rdma_exchange_send(rdma, &head, NULL, NULL, NULL, NULL, &err); @@ -3997,17 +3974,6 @@ err: return -1; } -static const QEMUFileHooks rdma_read_hooks = { - .hook_ram_load = rdma_load_hook, -}; - -static const QEMUFileHooks rdma_write_hooks = { - .before_ram_iterate = qemu_rdma_registration_start, - .after_ram_iterate = qemu_rdma_registration_stop, - .save_page = qemu_rdma_save_page, -}; - - static void qio_channel_rdma_finalize(Object *obj) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(obj); @@ -4059,7 +4025,6 @@ static QEMUFile *rdma_new_input(RDMAContext *rdma) rioc->file = qemu_file_new_input(QIO_CHANNEL(rioc)); rioc->rdmain = rdma; rioc->rdmaout = rdma->return_path; - qemu_file_set_hooks(rioc->file, &rdma_read_hooks); return rioc->file; } @@ -4071,7 +4036,6 @@ static QEMUFile *rdma_new_output(RDMAContext *rdma) rioc->file = qemu_file_new_output(QIO_CHANNEL(rioc)); rioc->rdmaout = rdma; rioc->rdmain = rdma->return_path; - qemu_file_set_hooks(rioc->file, &rdma_write_hooks); return rioc->file; } @@ -4079,14 +4043,11 @@ static QEMUFile *rdma_new_output(RDMAContext *rdma) static void rdma_accept_incoming_migration(void *opaque) { RDMAContext *rdma = opaque; - int ret; QEMUFile *f; Error *local_err = NULL; trace_qemu_rdma_accept_incoming_migration(); - ret = qemu_rdma_accept(rdma); - - if (ret < 0) { + if (qemu_rdma_accept(rdma) < 0) { error_report("RDMA ERROR: Migration initialization failed"); return; } @@ -4113,6 +4074,7 @@ static void rdma_accept_incoming_migration(void *opaque) void rdma_start_incoming_migration(const char *host_port, Error **errp) { + MigrationState *s = migrate_get_current(); int ret; RDMAContext *rdma; @@ -4144,7 +4106,7 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp) } trace_rdma_start_incoming_migration_after_rdma_listen(); - + s->rdma_migration = true; qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, NULL, (void *)(intptr_t)rdma); return; @@ -4220,6 +4182,7 @@ void rdma_start_outgoing_migration(void *opaque, trace_rdma_start_outgoing_migration_after_rdma_connect(); s->to_dst_file = rdma_new_output(rdma); + s->rdma_migration = true; migrate_fd_connect(s, NULL); return; return_path_err: diff --git a/migration/rdma.h b/migration/rdma.h index de2ba09dc5..30b15b4466 100644 --- a/migration/rdma.h +++ b/migration/rdma.h @@ -17,9 +17,51 @@ #ifndef QEMU_MIGRATION_RDMA_H #define QEMU_MIGRATION_RDMA_H +#include "exec/memory.h" + void rdma_start_outgoing_migration(void *opaque, const char *host_port, Error **errp); void rdma_start_incoming_migration(const char *host_port, Error **errp); +/* + * Constants used by rdma return codes + */ +#define RAM_CONTROL_SETUP 0 +#define RAM_CONTROL_ROUND 1 +#define RAM_CONTROL_FINISH 3 + +/* + * Whenever this is found in the data stream, the flags + * will be passed to rdma functions in the incoming-migration + * side. + */ +#define RAM_SAVE_FLAG_HOOK 0x80 + +#define RAM_SAVE_CONTROL_NOT_SUPP -1000 +#define RAM_SAVE_CONTROL_DELAYED -2000 + +#ifdef CONFIG_RDMA +int rdma_registration_handle(QEMUFile *f); +int rdma_registration_start(QEMUFile *f, uint64_t flags); +int rdma_registration_stop(QEMUFile *f, uint64_t flags); +int rdma_block_notification_handle(QEMUFile *f, const char *name); +int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, + ram_addr_t offset, size_t size); +#else +static inline +int rdma_registration_handle(QEMUFile *f) { return 0; } +static inline +int rdma_registration_start(QEMUFile *f, uint64_t flags) { return 0; } +static inline +int rdma_registration_stop(QEMUFile *f, uint64_t flags) { return 0; } +static inline +int rdma_block_notification_handle(QEMUFile *f, const char *name) { return 0; } +static inline +int rdma_control_save_page(QEMUFile *f, ram_addr_t block_offset, + ram_addr_t offset, size_t size) +{ + return RAM_SAVE_CONTROL_NOT_SUPP; +} +#endif #endif diff --git a/migration/savevm.c b/migration/savevm.c index 497ce02bd7..8622f229e5 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1217,13 +1217,27 @@ void qemu_savevm_non_migratable_list(strList **reasons) void qemu_savevm_state_header(QEMUFile *f) { + MigrationState *s = migrate_get_current(); + + s->vmdesc = json_writer_new(false); + trace_savevm_state_header(); qemu_put_be32(f, QEMU_VM_FILE_MAGIC); qemu_put_be32(f, QEMU_VM_FILE_VERSION); - if (migrate_get_current()->send_configuration) { + if (s->send_configuration) { qemu_put_byte(f, QEMU_VM_CONFIGURATION); - vmstate_save_state(f, &vmstate_configuration, &savevm_state, 0); + + /* + * This starts the main json object and is paired with the + * json_writer_end_object in + * qemu_savevm_state_complete_precopy_non_iterable + */ + json_writer_start_object(s->vmdesc, NULL); + + json_writer_start_object(s->vmdesc, "configuration"); + vmstate_save_state(f, &vmstate_configuration, &savevm_state, s->vmdesc); + json_writer_end_object(s->vmdesc); } } @@ -1272,8 +1286,6 @@ void qemu_savevm_state_setup(QEMUFile *f) Error *local_err = NULL; int ret; - ms->vmdesc = json_writer_new(false); - json_writer_start_object(ms->vmdesc, NULL); json_writer_int64(ms->vmdesc, "page_size", qemu_target_page_size()); json_writer_start_array(ms->vmdesc, "devices"); @@ -1660,10 +1672,8 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp) } ms->to_dst_file = f; - qemu_mutex_unlock_iothread(); qemu_savevm_state_header(f); qemu_savevm_state_setup(f); - qemu_mutex_lock_iothread(); while (qemu_file_get_error(f) == 0) { if (qemu_savevm_state_iterate(f, false) > 0) { diff --git a/migration/trace-events b/migration/trace-events index ee9c8f4d63..fa9486dffe 100644 --- a/migration/trace-events +++ b/migration/trace-events @@ -125,6 +125,7 @@ postcopy_preempt_reset_channel(void) "" # multifd.c multifd_new_send_channel_async(uint8_t id) "channel %u" +multifd_new_send_channel_async_error(uint8_t id, void *err) "channel=%u err=%p" multifd_recv(uint8_t id, uint64_t packet_num, uint32_t used, uint32_t flags, uint32_t next_packet_size) "channel %u packet_num %" PRIu64 " pages %u flags 0x%x next packet size %u" multifd_recv_new_channel(uint8_t id) "channel %u" multifd_recv_sync_main(long packet_num) "packet num %ld" @@ -144,7 +145,7 @@ multifd_send_thread_start(uint8_t id) "%u" multifd_tls_outgoing_handshake_start(void *ioc, void *tioc, const char *hostname) "ioc=%p tioc=%p hostname=%s" multifd_tls_outgoing_handshake_error(void *ioc, const char *err) "ioc=%p err=%s" multifd_tls_outgoing_handshake_complete(void *ioc) "ioc=%p" -multifd_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname, void *err) "ioc=%p ioctype=%s hostname=%s err=%p" +multifd_set_outgoing_channel(void *ioc, const char *ioctype, const char *hostname) "ioc=%p ioctype=%s hostname=%s" # migration.c await_return_path_close_on_source_close(void) "" @@ -186,7 +187,7 @@ source_return_path_thread_shut(uint32_t val) "0x%x" source_return_path_thread_resume_ack(uint32_t v) "%"PRIu32 source_return_path_thread_switchover_acked(void) "" migration_thread_low_pending(uint64_t pending) "%" PRIu64 -migrate_transferred(uint64_t transferred, uint64_t time_spent, uint64_t bandwidth, uint64_t size) "transferred %" PRIu64 " time_spent %" PRIu64 " bandwidth %" PRIu64 " max_size %" PRId64 +migrate_transferred(uint64_t transferred, uint64_t time_spent, uint64_t bandwidth, uint64_t avail_bw, uint64_t size) "transferred %" PRIu64 " time_spent %" PRIu64 " bandwidth %" PRIu64 " switchover_bw %" PRIu64 " max_size %" PRId64 process_incoming_migration_co_end(int ret, int ps) "ret=%d postcopy-state=%d" process_incoming_migration_co_postcopy_end_main(void) "" postcopy_preempt_enabled(bool value) "%d" @@ -231,20 +232,6 @@ qemu_rdma_post_send_control(const char *desc) "CONTROL: sending %s.." qemu_rdma_register_and_get_keys(uint64_t len, void *start) "Registering %" PRIu64 " bytes @ %p" qemu_rdma_register_odp_mr(const char *name) "Try to register On-Demand Paging memory region: %s" qemu_rdma_advise_mr(const char *name, uint32_t len, uint64_t addr, const char *res) "Try to advise block %s prefetch at %" PRIu32 "@0x%" PRIx64 ": %s" -qemu_rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64 -qemu_rdma_registration_handle_finished(void) "" -qemu_rdma_registration_handle_ram_blocks(void) "" -qemu_rdma_registration_handle_ram_blocks_loop(const char *name, uint64_t offset, uint64_t length, void *local_host_addr, unsigned int src_index) "%s: @0x%" PRIx64 "/%" PRIu64 " host:@%p src_index: %u" -qemu_rdma_registration_handle_register(int requests) "%d requests" -qemu_rdma_registration_handle_register_loop(int req, int index, uint64_t addr, uint64_t chunks) "Registration request (%d): index %d, current_addr %" PRIu64 " chunks: %" PRIu64 -qemu_rdma_registration_handle_register_rkey(int rkey) "0x%x" -qemu_rdma_registration_handle_unregister(int requests) "%d requests" -qemu_rdma_registration_handle_unregister_loop(int count, int index, uint64_t chunk) "Unregistration request (%d): index %d, chunk %" PRIu64 -qemu_rdma_registration_handle_unregister_success(uint64_t chunk) "%" PRIu64 -qemu_rdma_registration_handle_wait(void) "" -qemu_rdma_registration_start(uint64_t flags) "%" PRIu64 -qemu_rdma_registration_stop(uint64_t flags) "%" PRIu64 -qemu_rdma_registration_stop_ram(void) "" qemu_rdma_resolve_host_trying(const char *host, const char *ip) "Trying %s => %s" qemu_rdma_signal_unregister_append(uint64_t chunk, int pos) "Appending unregister chunk %" PRIu64 " at position %d" qemu_rdma_signal_unregister_already(uint64_t chunk) "Unregister chunk %" PRIu64 " already in queue" @@ -263,6 +250,20 @@ qemu_rdma_write_one_zero(uint64_t chunk, int len, int index, int64_t offset) "En rdma_add_block(const char *block_name, int block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Added Block: '%s':%d, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d" rdma_block_notification_handle(const char *name, int index) "%s at %d" rdma_delete_block(void *block, uint64_t addr, uint64_t offset, uint64_t len, uint64_t end, uint64_t bits, int chunks) "Deleted Block: %p, addr: %" PRIu64 ", offset: %" PRIu64 " length: %" PRIu64 " end: %" PRIu64 " bits %" PRIu64 " chunks %d" +rdma_registration_handle_compress(int64_t length, int index, int64_t offset) "Zapping zero chunk: %" PRId64 " bytes, index %d, offset %" PRId64 +rdma_registration_handle_finished(void) "" +rdma_registration_handle_ram_blocks(void) "" +rdma_registration_handle_ram_blocks_loop(const char *name, uint64_t offset, uint64_t length, void *local_host_addr, unsigned int src_index) "%s: @0x%" PRIx64 "/%" PRIu64 " host:@%p src_index: %u" +rdma_registration_handle_register(int requests) "%d requests" +rdma_registration_handle_register_loop(int req, int index, uint64_t addr, uint64_t chunks) "Registration request (%d): index %d, current_addr %" PRIu64 " chunks: %" PRIu64 +rdma_registration_handle_register_rkey(int rkey) "0x%x" +rdma_registration_handle_unregister(int requests) "%d requests" +rdma_registration_handle_unregister_loop(int count, int index, uint64_t chunk) "Unregistration request (%d): index %d, chunk %" PRIu64 +rdma_registration_handle_unregister_success(uint64_t chunk) "%" PRIu64 +rdma_registration_handle_wait(void) "" +rdma_registration_start(uint64_t flags) "%" PRIu64 +rdma_registration_stop(uint64_t flags) "%" PRIu64 +rdma_registration_stop_ram(void) "" rdma_start_incoming_migration(void) "" rdma_start_incoming_migration_after_dest_init(void) "" rdma_start_incoming_migration_after_rdma_listen(void) "" diff --git a/python/qemu/machine/console_socket.py b/python/qemu/machine/console_socket.py index 4e28ba9bb2..0a4e09ffc7 100644 --- a/python/qemu/machine/console_socket.py +++ b/python/qemu/machine/console_socket.py @@ -24,19 +24,32 @@ class ConsoleSocket(socket.socket): """ ConsoleSocket represents a socket attached to a char device. - Optionally (if drain==True), drains the socket and places the bytes - into an in memory buffer for later processing. - - Optionally a file path can be passed in and we will also - dump the characters to this file for debugging purposes. + :param address: An AF_UNIX path or address. + :param sock_fd: Optionally, an existing socket file descriptor. + One of address or sock_fd must be specified. + :param file: Optionally, a filename to log to. + :param drain: Optionally, drains the socket and places the bytes + into an in memory buffer for later processing. """ - def __init__(self, address: str, file: Optional[str] = None, + def __init__(self, + address: Optional[str] = None, + sock_fd: Optional[int] = None, + file: Optional[str] = None, drain: bool = False): + if address is None and sock_fd is None: + raise ValueError("one of 'address' or 'sock_fd' must be specified") + if address is not None and sock_fd is not None: + raise ValueError("can't specify both 'address' and 'sock_fd'") + self._recv_timeout_sec = 300.0 self._sleep_time = 0.5 self._buffer: Deque[int] = deque() - socket.socket.__init__(self, socket.AF_UNIX, socket.SOCK_STREAM) - self.connect(address) + if address is not None: + socket.socket.__init__(self, socket.AF_UNIX, socket.SOCK_STREAM) + self.connect(address) + else: + assert sock_fd is not None + socket.socket.__init__(self, fileno=sock_fd) self._logfile = None if file: # pylint: disable=consider-using-with diff --git a/python/qemu/machine/machine.py b/python/qemu/machine/machine.py index 35d5a672db..31cb9d617d 100644 --- a/python/qemu/machine/machine.py +++ b/python/qemu/machine/machine.py @@ -127,7 +127,6 @@ class QEMUMachine: name: Optional[str] = None, base_temp_dir: str = "/var/tmp", monitor_address: Optional[SocketAddrT] = None, - sock_dir: Optional[str] = None, drain_console: bool = False, console_log: Optional[str] = None, log_dir: Optional[str] = None, @@ -141,7 +140,6 @@ class QEMUMachine: @param name: prefix for socket and log file names (default: qemu-PID) @param base_temp_dir: default location where temp files are created @param monitor_address: address for QMP monitor - @param sock_dir: where to create socket (defaults to base_temp_dir) @param drain_console: (optional) True to drain console socket to buffer @param console_log: (optional) path to console log file @param log_dir: where to create and keep log files @@ -159,9 +157,10 @@ class QEMUMachine: self._name = name or f"{id(self):x}" self._sock_pair: Optional[Tuple[socket.socket, socket.socket]] = None + self._cons_sock_pair: Optional[ + Tuple[socket.socket, socket.socket]] = None self._temp_dir: Optional[str] = None self._base_temp_dir = base_temp_dir - self._sock_dir = sock_dir self._log_dir = log_dir self._monitor_address = monitor_address @@ -187,9 +186,6 @@ class QEMUMachine: self._console_index = 0 self._console_set = False self._console_device_type: Optional[str] = None - self._console_address = os.path.join( - self.sock_dir, f"{self._name}.con" - ) self._console_socket: Optional[socket.socket] = None self._console_file: Optional[socket.SocketIO] = None self._remove_files: List[str] = [] @@ -301,9 +297,7 @@ class QEMUMachine: if self._qmp_set: if self._sock_pair: - fd = self._sock_pair[0].fileno() - os.set_inheritable(fd, True) - moncdev = f"socket,id=mon,fd={fd}" + moncdev = f"socket,id=mon,fd={self._sock_pair[0].fileno()}" elif isinstance(self._monitor_address, tuple): moncdev = "socket,id=mon,host={},port={}".format( *self._monitor_address @@ -318,8 +312,9 @@ class QEMUMachine: for _ in range(self._console_index): args.extend(['-serial', 'null']) if self._console_set: - chardev = ('socket,id=console,path=%s,server=on,wait=off' % - self._console_address) + assert self._cons_sock_pair is not None + fd = self._cons_sock_pair[0].fileno() + chardev = f"socket,id=console,fd={fd}" args.extend(['-chardev', chardev]) if self._console_device_type is None: args.extend(['-serial', 'chardev:console']) @@ -334,12 +329,10 @@ class QEMUMachine: return self._args def _pre_launch(self) -> None: - if self._console_set: - self._remove_files.append(self._console_address) - if self._qmp_set: if self._monitor_address is None: self._sock_pair = socket.socketpair() + os.set_inheritable(self._sock_pair[0].fileno(), True) sock = self._sock_pair[1] if isinstance(self._monitor_address, str): self._remove_files.append(self._monitor_address) @@ -353,6 +346,10 @@ class QEMUMachine: nickname=self._name ) + if self._console_set: + self._cons_sock_pair = socket.socketpair() + os.set_inheritable(self._cons_sock_pair[0].fileno(), True) + # NOTE: Make sure any opened resources are *definitely* freed in # _post_shutdown()! # pylint: disable=consider-using-with @@ -370,6 +367,9 @@ class QEMUMachine: def _post_launch(self) -> None: if self._sock_pair: self._sock_pair[0].close() + if self._cons_sock_pair: + self._cons_sock_pair[0].close() + if self._qmp_connection: if self._sock_pair: self._qmp.connect() @@ -397,6 +397,11 @@ class QEMUMachine: finally: assert self._qmp_connection is None + if self._sock_pair: + self._sock_pair[0].close() + self._sock_pair[1].close() + self._sock_pair = None + self._close_qemu_log_file() self._load_io_log() @@ -520,6 +525,11 @@ class QEMUMachine: self._console_socket.close() self._console_socket = None + if self._cons_sock_pair: + self._cons_sock_pair[0].close() + self._cons_sock_pair[1].close() + self._cons_sock_pair = None + def _hard_shutdown(self) -> None: """ Perform early cleanup, kill the VM, and wait for it to terminate. @@ -692,21 +702,31 @@ class QEMUMachine: conv_keys = True qmp_args = self._qmp_args(conv_keys, args) - ret = self._qmp.cmd(cmd, args=qmp_args) + ret = self._qmp.cmd_raw(cmd, args=qmp_args) if cmd == 'quit' and 'error' not in ret and 'return' in ret: self._quit_issued = True return ret - def command(self, cmd: str, - conv_keys: bool = True, - **args: Any) -> QMPReturnValue: + def cmd(self, cmd: str, + args_dict: Optional[Dict[str, object]] = None, + conv_keys: Optional[bool] = None, + **args: Any) -> QMPReturnValue: """ Invoke a QMP command. On success return the response dict. On failure raise an exception. """ + if args_dict is not None: + assert not args + assert conv_keys is None + args = args_dict + conv_keys = False + + if conv_keys is None: + conv_keys = True + qmp_args = self._qmp_args(conv_keys, args) - ret = self._qmp.command(cmd, **qmp_args) + ret = self._qmp.cmd(cmd, **qmp_args) if cmd == 'quit': self._quit_issued = True return ret @@ -881,10 +901,19 @@ class QEMUMachine: """ if self._console_socket is None: LOG.debug("Opening console socket") + if not self._console_set: + raise QEMUMachineError( + "Attempt to access console socket with no connection") + assert self._cons_sock_pair is not None + # os.dup() is used here for sock_fd because otherwise we'd + # have two rich python socket objects that would each try to + # close the same underlying fd when either one gets garbage + # collected. self._console_socket = console_socket.ConsoleSocket( - self._console_address, + sock_fd=os.dup(self._cons_sock_pair[1].fileno()), file=self._console_log_path, drain=self._drain_console) + self._cons_sock_pair[1].close() return self._console_socket @property @@ -910,15 +939,6 @@ class QEMUMachine: return self._temp_dir @property - def sock_dir(self) -> str: - """ - Returns the directory used for sockfiles by this machine. - """ - if self._sock_dir: - return self._sock_dir - return self.temp_dir - - @property def log_dir(self) -> str: """ Returns a directory to be used for writing logs diff --git a/python/qemu/machine/qtest.py b/python/qemu/machine/qtest.py index 1c46138bd0..4f5ede85b2 100644 --- a/python/qemu/machine/qtest.py +++ b/python/qemu/machine/qtest.py @@ -24,6 +24,7 @@ from typing import ( Optional, Sequence, TextIO, + Tuple, ) from qemu.qmp import SocketAddrT @@ -38,23 +39,41 @@ class QEMUQtestProtocol: :param address: QEMU address, can be either a unix socket path (string) or a tuple in the form ( address, port ) for a TCP connection - :param server: server mode, listens on the socket (bool) + :param sock: An existing socket can be provided as an alternative to + an address. One of address or sock must be provided. + :param server: server mode, listens on the socket. Only meaningful + in conjunction with an address and not an existing + socket. + :raise socket.error: on socket connection errors .. note:: No connection is established by __init__(), this is done by the connect() or accept() methods. """ - def __init__(self, address: SocketAddrT, + def __init__(self, + address: Optional[SocketAddrT] = None, + sock: Optional[socket.socket] = None, server: bool = False): + if address is None and sock is None: + raise ValueError("Either 'address' or 'sock' must be specified") + if address is not None and sock is not None: + raise ValueError( + "Either 'address' or 'sock' must be specified, but not both") + if sock is not None and server: + raise ValueError("server=True is meaningless when passing socket") + self._address = address - self._sock = self._get_sock() + self._sock = sock or self._get_sock() self._sockfile: Optional[TextIO] = None + if server: + assert self._address is not None self._sock.bind(self._address) self._sock.listen(1) def _get_sock(self) -> socket.socket: + assert self._address is not None if isinstance(self._address, tuple): family = socket.AF_INET else: @@ -67,7 +86,8 @@ class QEMUQtestProtocol: @raise socket.error on socket connection errors """ - self._sock.connect(self._address) + if self._address is not None: + self._sock.connect(self._address) self._sockfile = self._sock.makefile(mode='r') def accept(self) -> None: @@ -115,41 +135,49 @@ class QEMUQtestMachine(QEMUMachine): wrapper: Sequence[str] = (), name: Optional[str] = None, base_temp_dir: str = "/var/tmp", - sock_dir: Optional[str] = None, qmp_timer: Optional[float] = None): # pylint: disable=too-many-arguments if name is None: name = "qemu-%d" % os.getpid() - if sock_dir is None: - sock_dir = base_temp_dir super().__init__(binary, args, wrapper=wrapper, name=name, base_temp_dir=base_temp_dir, - sock_dir=sock_dir, qmp_timer=qmp_timer) + qmp_timer=qmp_timer) self._qtest: Optional[QEMUQtestProtocol] = None - self._qtest_path = os.path.join(sock_dir, name + "-qtest.sock") + self._qtest_sock_pair: Optional[ + Tuple[socket.socket, socket.socket]] = None @property def _base_args(self) -> List[str]: args = super()._base_args + assert self._qtest_sock_pair is not None + fd = self._qtest_sock_pair[0].fileno() args.extend([ - '-qtest', f"unix:path={self._qtest_path}", + '-chardev', f"socket,id=qtest,fd={fd}", + '-qtest', 'chardev:qtest', '-accel', 'qtest' ]) return args def _pre_launch(self) -> None: + self._qtest_sock_pair = socket.socketpair() + os.set_inheritable(self._qtest_sock_pair[0].fileno(), True) super()._pre_launch() - self._qtest = QEMUQtestProtocol(self._qtest_path, server=True) + self._qtest = QEMUQtestProtocol(sock=self._qtest_sock_pair[1]) def _post_launch(self) -> None: assert self._qtest is not None super()._post_launch() - self._qtest.accept() + if self._qtest_sock_pair: + self._qtest_sock_pair[0].close() + self._qtest.connect() def _post_shutdown(self) -> None: + if self._qtest_sock_pair: + self._qtest_sock_pair[0].close() + self._qtest_sock_pair[1].close() + self._qtest_sock_pair = None super()._post_shutdown() - self._remove_if_exists(self._qtest_path) def qtest(self, cmd: str) -> str: """ diff --git a/python/qemu/qmp/legacy.py b/python/qemu/qmp/legacy.py index e1e9383978..22a2b5616e 100644 --- a/python/qemu/qmp/legacy.py +++ b/python/qemu/qmp/legacy.py @@ -194,24 +194,20 @@ class QEMUMonitorProtocol: ) ) - def cmd(self, name: str, - args: Optional[Dict[str, object]] = None, - cmd_id: Optional[object] = None) -> QMPMessage: + def cmd_raw(self, name: str, + args: Optional[Dict[str, object]] = None) -> QMPMessage: """ Build a QMP command and send it to the QMP Monitor. :param name: command name (string) :param args: command arguments (dict) - :param cmd_id: command id (dict, list, string or int) """ qmp_cmd: QMPMessage = {'execute': name} if args: qmp_cmd['arguments'] = args - if cmd_id: - qmp_cmd['id'] = cmd_id return self.cmd_obj(qmp_cmd) - def command(self, cmd: str, **kwds: object) -> QMPReturnValue: + def cmd(self, cmd: str, **kwds: object) -> QMPReturnValue: """ Build and send a QMP command to the monitor, report errors if any """ diff --git a/python/qemu/qmp/protocol.py b/python/qemu/qmp/protocol.py index 753182131f..a4ffdfad51 100644 --- a/python/qemu/qmp/protocol.py +++ b/python/qemu/qmp/protocol.py @@ -495,7 +495,6 @@ class AsyncProtocol(Generic[T]): try: self.logger.debug("Stopping server.") self._server.close() - await self._server.wait_closed() self.logger.debug("Server stopped.") finally: self._server = None diff --git a/python/qemu/qmp/qmp_shell.py b/python/qemu/qmp/qmp_shell.py index 619ab42ced..98e684e9e8 100644 --- a/python/qemu/qmp/qmp_shell.py +++ b/python/qemu/qmp/qmp_shell.py @@ -91,14 +91,21 @@ from subprocess import Popen import sys from typing import ( IO, + Dict, Iterator, List, NoReturn, Optional, Sequence, + cast, ) -from qemu.qmp import ConnectError, QMPError, SocketAddrT +from qemu.qmp import ( + ConnectError, + ExecuteError, + QMPError, + SocketAddrT, +) from qemu.qmp.legacy import ( QEMUMonitorProtocol, QMPBadPortError, @@ -194,11 +201,12 @@ class QMPShell(QEMUMonitorProtocol): super().close() def _fill_completion(self) -> None: - cmds = self.cmd('query-commands') - if 'error' in cmds: - return - for cmd in cmds['return']: - self._completer.append(cmd['name']) + try: + cmds = cast(List[Dict[str, str]], self.cmd('query-commands')) + for cmd in cmds: + self._completer.append(cmd['name']) + except ExecuteError: + pass def _completer_setup(self) -> None: self._completer = QMPCompleter() diff --git a/python/qemu/utils/qemu_ga_client.py b/python/qemu/utils/qemu_ga_client.py index d8411bb2d0..9a665e6e99 100644 --- a/python/qemu/utils/qemu_ga_client.py +++ b/python/qemu/utils/qemu_ga_client.py @@ -64,7 +64,7 @@ from qemu.qmp.legacy import QEMUMonitorProtocol class QemuGuestAgent(QEMUMonitorProtocol): def __getattr__(self, name: str) -> Callable[..., Any]: def wrapper(**kwds: object) -> object: - return self.command('guest-' + name.replace('_', '-'), **kwds) + return self.cmd('guest-' + name.replace('_', '-'), **kwds) return wrapper diff --git a/python/qemu/utils/qom.py b/python/qemu/utils/qom.py index bcf192f477..426a0f245f 100644 --- a/python/qemu/utils/qom.py +++ b/python/qemu/utils/qom.py @@ -84,7 +84,7 @@ class QOMSet(QOMCommand): self.value = args.value def run(self) -> int: - rsp = self.qmp.command( + rsp = self.qmp.cmd( 'qom-set', path=self.path, property=self.prop, @@ -129,7 +129,7 @@ class QOMGet(QOMCommand): self.prop = tmp[1] def run(self) -> int: - rsp = self.qmp.command( + rsp = self.qmp.cmd( 'qom-get', path=self.path, property=self.prop @@ -231,8 +231,8 @@ class QOMTree(QOMCommand): if item.child: continue try: - rsp = self.qmp.command('qom-get', path=path, - property=item.name) + rsp = self.qmp.cmd('qom-get', path=path, + property=item.name) print(f" {item.name}: {rsp} ({item.type})") except ExecuteError as err: print(f" {item.name}: <EXCEPTION: {err!s}> ({item.type})") diff --git a/python/qemu/utils/qom_common.py b/python/qemu/utils/qom_common.py index 80da1b2304..dd2c8b1908 100644 --- a/python/qemu/utils/qom_common.py +++ b/python/qemu/utils/qom_common.py @@ -140,7 +140,7 @@ class QOMCommand: """ :return: a strongly typed list from the 'qom-list' command. """ - rsp = self.qmp.command('qom-list', path=path) + rsp = self.qmp.cmd('qom-list', path=path) # qom-list returns List[ObjectPropertyInfo] assert isinstance(rsp, list) return [ObjectPropertyInfo.make(x) for x in rsp] diff --git a/python/qemu/utils/qom_fuse.py b/python/qemu/utils/qom_fuse.py index 8dcd59fcde..cf7e344bd5 100644 --- a/python/qemu/utils/qom_fuse.py +++ b/python/qemu/utils/qom_fuse.py @@ -137,7 +137,7 @@ class QOMFuse(QOMCommand, Operations): if path == '': path = '/' try: - data = str(self.qmp.command('qom-get', path=path, property=prop)) + data = str(self.qmp.cmd('qom-get', path=path, property=prop)) data += '\n' # make values shell friendly except ExecuteError as err: raise FuseOSError(EPERM) from err @@ -152,8 +152,8 @@ class QOMFuse(QOMCommand, Operations): return False path, prop = path.rsplit('/', 1) prefix = '/'.join(['..'] * (len(path.split('/')) - 1)) - return prefix + str(self.qmp.command('qom-get', path=path, - property=prop)) + return prefix + str(self.qmp.cmd('qom-get', path=path, + property=prop)) def getattr(self, path: str, fh: Optional[IO[bytes]] = None) -> Mapping[str, object]: diff --git a/python/setup.cfg b/python/setup.cfg index 8c67dce457..48668609d3 100644 --- a/python/setup.cfg +++ b/python/setup.cfg @@ -18,6 +18,7 @@ classifiers = Programming Language :: Python :: 3.9 Programming Language :: Python :: 3.10 Programming Language :: Python :: 3.11 + Programming Language :: Python :: 3.12 Typing :: Typed [options] @@ -182,7 +183,7 @@ multi_line_output=3 # of python available on your system to run this test. [tox:tox] -envlist = py38, py39, py310, py311 +envlist = py38, py39, py310, py311, py312 skip_missing_interpreters = true [testenv] diff --git a/qapi/compat.json b/qapi/compat.json index f4c19837eb..42034d9368 100644 --- a/qapi/compat.json +++ b/qapi/compat.json @@ -43,8 +43,8 @@ # This is intended for testing users of the management interfaces. # # Limitation: covers only syntactic aspects of QMP, i.e. stuff tagged -# with feature 'deprecated'. We may want to extend it to cover -# semantic aspects and CLI. +# with feature 'deprecated' or 'unstable'. We may want to extend it +# to cover semantic aspects and CLI. # # Limitation: deprecated-output policy @hide is not implemented for # enumeration values. They behave the same as with policy @accept. diff --git a/qapi/migration.json b/qapi/migration.json index d7dfaa5db9..db3df12d6c 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -73,7 +73,7 @@ { 'struct': 'MigrationStats', 'data': {'transferred': 'int', 'remaining': 'int', 'total': 'int' , 'duplicate': 'int', - 'skipped': { 'type': 'int', 'features': ['deprecated'] }, + 'skipped': { 'type': 'int', 'features': [ 'deprecated' ] }, 'normal': 'int', 'normal-bytes': 'int', 'dirty-pages-rate': 'int', 'mbps': 'number', 'dirty-sync-count': 'int', @@ -440,10 +440,9 @@ # compress and xbzrle are both on, compress only takes effect in # the ram bulk stage, after that, it will be disabled and only # xbzrle takes effect, this can help to minimize migration -# traffic. The feature is disabled by default. (since 2.4 ) +# traffic. The feature is disabled by default. (since 2.4) # -# @events: generate events for each migration state change (since 2.4 -# ) +# @events: generate events for each migration state change (since 2.4) # # @auto-converge: If enabled, QEMU will automatically throttle down # the guest to speed up convergence of RAM migration. (since 1.6) @@ -758,6 +757,16 @@ # @max-bandwidth: to set maximum speed for migration. maximum speed # in bytes per second. (Since 2.8) # +# @avail-switchover-bandwidth: to set the available bandwidth that +# migration can use during switchover phase. NOTE! This does not +# limit the bandwidth during switchover, but only for calculations when +# making decisions to switchover. By default, this value is zero, +# which means QEMU will estimate the bandwidth automatically. This can +# be set when the estimated value is not accurate, while the user is +# able to guarantee such bandwidth is available when switching over. +# When specified correctly, this can make the switchover decision much +# more accurate. (Since 8.2) +# # @downtime-limit: set maximum tolerated downtime for migration. # maximum downtime in milliseconds (Since 2.8) # @@ -839,7 +848,7 @@ 'cpu-throttle-initial', 'cpu-throttle-increment', 'cpu-throttle-tailslow', 'tls-creds', 'tls-hostname', 'tls-authz', 'max-bandwidth', - 'downtime-limit', + 'avail-switchover-bandwidth', 'downtime-limit', { 'name': 'x-checkpoint-delay', 'features': [ 'unstable' ] }, 'block-incremental', 'multifd-channels', @@ -924,6 +933,16 @@ # @max-bandwidth: to set maximum speed for migration. maximum speed # in bytes per second. (Since 2.8) # +# @avail-switchover-bandwidth: to set the available bandwidth that +# migration can use during switchover phase. NOTE! This does not +# limit the bandwidth during switchover, but only for calculations when +# making decisions to switchover. By default, this value is zero, +# which means QEMU will estimate the bandwidth automatically. This can +# be set when the estimated value is not accurate, while the user is +# able to guarantee such bandwidth is available when switching over. +# When specified correctly, this can make the switchover decision much +# more accurate. (Since 8.2) +# # @downtime-limit: set maximum tolerated downtime for migration. # maximum downtime in milliseconds (Since 2.8) # @@ -1017,6 +1036,7 @@ '*tls-hostname': 'StrOrNull', '*tls-authz': 'StrOrNull', '*max-bandwidth': 'size', + '*avail-switchover-bandwidth': 'size', '*downtime-limit': 'uint64', '*x-checkpoint-delay': { 'type': 'uint32', 'features': [ 'unstable' ] }, @@ -1127,6 +1147,16 @@ # @max-bandwidth: to set maximum speed for migration. maximum speed # in bytes per second. (Since 2.8) # +# @avail-switchover-bandwidth: to set the available bandwidth that +# migration can use during switchover phase. NOTE! This does not +# limit the bandwidth during switchover, but only for calculations when +# making decisions to switchover. By default, this value is zero, +# which means QEMU will estimate the bandwidth automatically. This can +# be set when the estimated value is not accurate, while the user is +# able to guarantee such bandwidth is available when switching over. +# When specified correctly, this can make the switchover decision much +# more accurate. (Since 8.2) +# # @downtime-limit: set maximum tolerated downtime for migration. # maximum downtime in milliseconds (Since 2.8) # @@ -1217,6 +1247,7 @@ '*tls-hostname': 'str', '*tls-authz': 'str', '*max-bandwidth': 'size', + '*avail-switchover-bandwidth': 'size', '*downtime-limit': 'uint64', '*x-checkpoint-delay': { 'type': 'uint32', 'features': [ 'unstable' ] }, diff --git a/qemu-img.c b/qemu-img.c index 6068ab0d27..585b65640f 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -3165,7 +3165,9 @@ static int get_block_status(BlockDriverState *bs, int64_t offset, has_offset = !!(ret & BDRV_BLOCK_OFFSET_VALID); if (file && has_offset) { + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(file); + bdrv_graph_rdunlock_main_loop(); filename = file->filename; } @@ -3470,7 +3472,10 @@ static int img_snapshot(int argc, char **argv) sn.date_sec = rt / G_USEC_PER_SEC; sn.date_nsec = (rt % G_USEC_PER_SEC) * 1000; + bdrv_graph_rdlock_main_loop(); ret = bdrv_snapshot_create(bs, &sn); + bdrv_graph_rdunlock_main_loop(); + if (ret) { error_report("Could not create snapshot '%s': %s", snapshot_name, strerror(-ret)); @@ -3486,6 +3491,7 @@ static int img_snapshot(int argc, char **argv) break; case SNAPSHOT_DELETE: + bdrv_graph_rdlock_main_loop(); ret = bdrv_snapshot_find(bs, &sn, snapshot_name); if (ret < 0) { error_report("Could not delete snapshot '%s': snapshot not " @@ -3499,6 +3505,7 @@ static int img_snapshot(int argc, char **argv) ret = 1; } } + bdrv_graph_rdunlock_main_loop(); break; } @@ -3683,7 +3690,9 @@ static int img_rebase(int argc, char **argv) qdict_put_bool(options, BDRV_OPT_FORCE_SHARE, true); } + bdrv_graph_rdlock_main_loop(); bdrv_refresh_filename(bs); + bdrv_graph_rdunlock_main_loop(); overlay_filename = bs->exact_filename[0] ? bs->exact_filename : bs->filename; out_real_path = @@ -4120,6 +4129,8 @@ static int print_amend_option_help(const char *format) { BlockDriver *drv; + GRAPH_RDLOCK_GUARD_MAINLOOP(); + /* Find driver and parse its options */ drv = bdrv_find_format(format); if (!drv) { @@ -4258,9 +4269,11 @@ static int img_amend(int argc, char **argv) goto out; } + bdrv_graph_rdlock_main_loop(); if (!bs->drv->bdrv_amend_options) { error_report("Format driver '%s' does not support option amendment", fmt); + bdrv_graph_rdunlock_main_loop(); ret = -1; goto out; } @@ -4280,6 +4293,7 @@ static int img_amend(int argc, char **argv) "This option is only supported for image creation\n"); } + bdrv_graph_rdunlock_main_loop(); error_report_err(err); ret = -1; goto out; @@ -4289,6 +4303,8 @@ static int img_amend(int argc, char **argv) qemu_progress_print(0.f, 0); ret = bdrv_amend_options(bs, opts, &amend_status_cb, NULL, force, &err); qemu_progress_print(100.f, 0); + bdrv_graph_rdunlock_main_loop(); + if (ret < 0) { error_report_err(err); goto out; diff --git a/qemu-io-cmds.c b/qemu-io-cmds.c index 3f75d2f5a6..f5d7202a13 100644 --- a/qemu-io-cmds.c +++ b/qemu-io-cmds.c @@ -2037,6 +2037,9 @@ static int info_f(BlockBackend *blk, int argc, char **argv) char s1[64], s2[64]; int ret; + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + if (bs->drv && bs->drv->format_name) { printf("format name: %s\n", bs->drv->format_name); } diff --git a/qga/meson.build b/qga/meson.build index 59cae0cc6e..940a51d55d 100644 --- a/qga/meson.build +++ b/qga/meson.build @@ -145,6 +145,9 @@ if targetos == 'windows' else libpcre = 'libpcre2' endif + qga_msi_version = get_option('qemu_ga_version') == '' \ + ? project.version() \ + : get_option('qemu_ga_version') qga_msi = custom_target('QGA MSI', input: files('installer/qemu-ga.wxs'), output: 'qemu-ga-@0@.msi'.format(host_arch), @@ -155,9 +158,9 @@ if targetos == 'windows' qemu_ga_msi_vss, '-D', 'BUILD_DIR=' + meson.project_build_root(), '-D', 'BIN_DIR=' + glib_pc.get_variable('bindir'), - '-D', 'QEMU_GA_VERSION=' + config_host['QEMU_GA_VERSION'], - '-D', 'QEMU_GA_MANUFACTURER=' + config_host['QEMU_GA_MANUFACTURER'], - '-D', 'QEMU_GA_DISTRO=' + config_host['QEMU_GA_DISTRO'], + '-D', 'QEMU_GA_VERSION=' + qga_msi_version, + '-D', 'QEMU_GA_MANUFACTURER=' + get_option('qemu_ga_manufacturer'), + '-D', 'QEMU_GA_DISTRO=' + get_option('qemu_ga_distro'), '-D', 'LIBPCRE=' + libpcre, ]) all_qga += [qga_msi] diff --git a/scripts/analyze-migration.py b/scripts/analyze-migration.py index 082424558b..de506cb8bf 100755 --- a/scripts/analyze-migration.py +++ b/scripts/analyze-migration.py @@ -38,13 +38,13 @@ class MigrationFile(object): self.file = open(self.filename, "rb") def read64(self): - return int.from_bytes(self.file.read(8), byteorder='big', signed=True) + return int.from_bytes(self.file.read(8), byteorder='big', signed=False) def read32(self): - return int.from_bytes(self.file.read(4), byteorder='big', signed=True) + return int.from_bytes(self.file.read(4), byteorder='big', signed=False) def read16(self): - return int.from_bytes(self.file.read(2), byteorder='big', signed=True) + return int.from_bytes(self.file.read(2), byteorder='big', signed=False) def read8(self): return int.from_bytes(self.file.read(1), byteorder='big', signed=True) @@ -123,6 +123,7 @@ class RamSection(object): self.TARGET_PAGE_SIZE = ramargs['page_size'] self.dump_memory = ramargs['dump_memory'] self.write_memory = ramargs['write_memory'] + self.ignore_shared = ramargs['ignore_shared'] self.sizeinfo = collections.OrderedDict() self.data = collections.OrderedDict() self.data['section sizes'] = self.sizeinfo @@ -169,6 +170,8 @@ class RamSection(object): f.truncate(0) f.truncate(len) self.files[self.name] = f + if self.ignore_shared: + mr_addr = self.file.read64() flags &= ~self.RAM_SAVE_FLAG_MEM_SIZE if flags & self.RAM_SAVE_FLAG_COMPRESS: @@ -261,12 +264,41 @@ class HTABSection(object): class ConfigurationSection(object): - def __init__(self, file): + def __init__(self, file, desc): self.file = file + self.desc = desc + self.caps = [] + + def parse_capabilities(self, vmsd_caps): + if not vmsd_caps: + return + + ncaps = vmsd_caps.data['caps_count'].data + self.caps = vmsd_caps.data['capabilities'] + + if type(self.caps) != list: + self.caps = [self.caps] + + if len(self.caps) != ncaps: + raise Exception("Number of capabilities doesn't match " + "caps_count field") + + def has_capability(self, cap): + return any([str(c) == cap for c in self.caps]) def read(self): - name_len = self.file.read32() - name = self.file.readstr(len = name_len) + if self.desc: + version_id = self.desc['version'] + section = VMSDSection(self.file, version_id, self.desc, + 'configuration') + section.read() + self.parse_capabilities( + section.data.get("configuration/capabilities")) + else: + # backward compatibility for older streams that don't have + # the configuration section in the json + name_len = self.file.read32() + name = self.file.readstr(len = name_len) class VMSDFieldGeneric(object): def __init__(self, desc, file): @@ -288,6 +320,23 @@ class VMSDFieldGeneric(object): self.data = self.file.readvar(size) return self.data +class VMSDFieldCap(object): + def __init__(self, desc, file): + self.file = file + self.desc = desc + self.data = "" + + def __repr__(self): + return self.data + + def __str__(self): + return self.data + + def read(self): + len = self.file.read8() + self.data = self.file.readstr(len) + + class VMSDFieldInt(VMSDFieldGeneric): def __init__(self, desc, file): super(VMSDFieldInt, self).__init__(desc, file) @@ -462,6 +511,7 @@ vmsd_field_readers = { "unused_buffer" : VMSDFieldGeneric, "bitmap" : VMSDFieldGeneric, "struct" : VMSDFieldStruct, + "capability": VMSDFieldCap, "unknown" : VMSDFieldGeneric, } @@ -525,6 +575,7 @@ class MigrationDump(object): ramargs['page_size'] = self.vmsd_desc['page_size'] ramargs['dump_memory'] = dump_memory ramargs['write_memory'] = write_memory + ramargs['ignore_shared'] = False self.section_classes[('ram',0)][1] = ramargs while True: @@ -532,8 +583,10 @@ class MigrationDump(object): if section_type == self.QEMU_VM_EOF: break elif section_type == self.QEMU_VM_CONFIGURATION: - section = ConfigurationSection(file) + config_desc = self.vmsd_desc.get('configuration') + section = ConfigurationSection(file, config_desc) section.read() + ramargs['ignore_shared'] = section.has_capability('x-ignore-shared') elif section_type == self.QEMU_VM_SECTION_START or section_type == self.QEMU_VM_SECTION_FULL: section_id = file.read32() name = file.readstr() diff --git a/scripts/block-coroutine-wrapper.py b/scripts/block-coroutine-wrapper.py index 685d0b4ed4..a601c3c672 100644 --- a/scripts/block-coroutine-wrapper.py +++ b/scripts/block-coroutine-wrapper.py @@ -87,8 +87,9 @@ class FuncDecl: raise ValueError(f"Invalid no_co function name: {self.name}") if not self.create_only_co: raise ValueError(f"no_co function can't be mixed: {self.name}") - if self.graph_rdlock: - raise ValueError(f"no_co function can't be rdlock: {self.name}") + if self.graph_rdlock and self.graph_wrlock: + raise ValueError("function can't be both rdlock and wrlock: " + f"{self.name}") self.target_name = f'{subsystem}_{subname}' self.ctx = self.gen_ctx() @@ -256,7 +257,10 @@ def gen_no_co_wrapper(func: FuncDecl) -> str: graph_lock='' graph_unlock='' - if func.graph_wrlock: + if func.graph_rdlock: + graph_lock=' bdrv_graph_rdlock_main_loop();' + graph_unlock=' bdrv_graph_rdunlock_main_loop();' + elif func.graph_wrlock: graph_lock=' bdrv_graph_wrlock(NULL);' graph_unlock=' bdrv_graph_wrunlock();' diff --git a/scripts/cpu-x86-uarch-abi.py b/scripts/cpu-x86-uarch-abi.py index 82ff07582f..f6baeeff24 100644 --- a/scripts/cpu-x86-uarch-abi.py +++ b/scripts/cpu-x86-uarch-abi.py @@ -85,7 +85,7 @@ skip = [ names = [] -for model in models["return"]: +for model in models: if "alias-of" in model: continue names.append(model["name"]) @@ -94,11 +94,11 @@ models = {} for name in sorted(names): cpu = shell.cmd("query-cpu-model-expansion", - { "type": "static", - "model": { "name": name }}) + { "type": "static", + "model": { "name": name }}) got = {} - for (feature, present) in cpu["return"]["model"]["props"].items(): + for (feature, present) in cpu["model"]["props"].items(): if present and feature not in skip: got[feature] = True diff --git a/scripts/device-crash-test b/scripts/device-crash-test index 353aa575d7..da8b56edd9 100755 --- a/scripts/device-crash-test +++ b/scripts/device-crash-test @@ -269,14 +269,14 @@ def formatTestCase(t): def qomListTypeNames(vm, **kwargs): """Run qom-list-types QMP command, return type names""" - types = vm.command('qom-list-types', **kwargs) + types = vm.cmd('qom-list-types', **kwargs) return [t['name'] for t in types] def infoQDM(vm): """Parse 'info qdm' output""" args = {'command-line': 'info qdm'} - devhelp = vm.command('human-monitor-command', **args) + devhelp = vm.cmd('human-monitor-command', **args) for l in devhelp.split('\n'): l = l.strip() if l == '' or l.endswith(':'): @@ -304,9 +304,9 @@ class QemuBinaryInfo(object): # there's no way to query DeviceClass::user_creatable using QMP, # so use 'info qdm': self.no_user_devs = set([d['name'] for d in infoQDM(vm, ) if d['no-user']]) - self.machines = list(m['name'] for m in vm.command('query-machines')) + self.machines = list(m['name'] for m in vm.cmd('query-machines')) self.user_devs = self.alldevs.difference(self.no_user_devs) - self.kvm_available = vm.command('query-kvm')['enabled'] + self.kvm_available = vm.cmd('query-kvm')['enabled'] finally: vm.shutdown() diff --git a/scripts/feature_to_c.py b/scripts/feature_to_c.py index bcbcb83beb..bcbcb83beb 100755..100644 --- a/scripts/feature_to_c.py +++ b/scripts/feature_to_c.py diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 02fa828100..00a0870b26 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -907,6 +907,7 @@ sub get_subsystem_name { if (length($subsystem) > 20) { $subsystem = substr($subsystem, 0, 17); $subsystem =~ s/\s*$//; + $subsystem =~ s/[()]//g; $subsystem = $subsystem . "..."; } return $subsystem; diff --git a/scripts/meson-buildoptions.py b/scripts/meson-buildoptions.py index 8d2e526132..4814a8ff61 100644 --- a/scripts/meson-buildoptions.py +++ b/scripts/meson-buildoptions.py @@ -25,13 +25,15 @@ import textwrap import shlex import sys +# Options with nonstandard names (e.g. --with/--without) or OS-dependent +# defaults. Try not to add any. SKIP_OPTIONS = { "default_devices", "fuzzing_engine", - "qemu_suffix", - "smbd", } +# Options whose name doesn't match the option for backwards compatibility +# reasons, because Meson gives them a funny name, or both OPTION_NAMES = { "b_coverage": "gcov", "b_lto": "lto", @@ -40,13 +42,25 @@ OPTION_NAMES = { "malloc": "enable-malloc", "pkgversion": "with-pkgversion", "qemu_firmwarepath": "firmwarepath", + "qemu_suffix": "with-suffix", "trace_backends": "enable-trace-backends", "trace_file": "with-trace-file", } +# Options that configure autodetects, even though meson defines them as boolean +AUTO_OPTIONS = { + "plugins", + "werror", +} + +# Builtin options that should be definable via configure. Some of the others +# we really do not want (e.g. c_args is defined via the native file, not +# via -D, because it's a mix of CFLAGS and --extra-cflags); for specific +# cases "../configure -D" can be used as an escape hatch. BUILTIN_OPTIONS = { "b_coverage", "b_lto", + "bindir", "datadir", "debug", "includedir", @@ -55,8 +69,10 @@ BUILTIN_OPTIONS = { "localedir", "localstatedir", "mandir", + "prefix", "strip", "sysconfdir", + "werror", } LINE_WIDTH = 76 @@ -168,6 +184,7 @@ def cli_metavar(opt): def print_help(options): print("meson_options_help() {") + feature_opts = [] for opt in sorted(options, key=cli_help_key): key = cli_help_key(opt) # The first section includes options that have an arguments, @@ -176,7 +193,7 @@ def print_help(options): metavar = cli_metavar(opt) left = f"--{key}={metavar}" help_line(left, opt, 27, True) - elif opt["type"] == "boolean": + elif opt["type"] == "boolean" and opt["name"] not in AUTO_OPTIONS: left = f"--{key}" help_line(left, opt, 27, False) elif allow_arg(opt): @@ -185,16 +202,17 @@ def print_help(options): else: left = f"--{key}=CHOICE" help_line(left, opt, 27, True) + else: + feature_opts.append(opt) sh_print() sh_print("Optional features, enabled with --enable-FEATURE and") sh_print("disabled with --disable-FEATURE, default is enabled if available") sh_print("(unless built with --without-default-features):") sh_print() - for opt in options: - key = opt["name"].replace("_", "-") - if opt["type"] != "boolean" and not allow_arg(opt): - help_line(key, opt, 18, False) + for opt in sorted(feature_opts, key=cli_option): + key = cli_option(opt) + help_line(key, opt, 18, False) print("}") diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index 2a74b0275b..7ca4b77eae 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -3,6 +3,7 @@ meson_options_help() { printf "%s\n" ' --audio-drv-list=CHOICES Set audio driver list [default] (choices: alsa/co' printf "%s\n" ' reaudio/default/dsound/jack/oss/pa/pipewire/sdl/s' printf "%s\n" ' ndio)' + printf "%s\n" ' --bindir=VALUE Executable directory [bin]' printf "%s\n" ' --block-drv-ro-whitelist=VALUE' printf "%s\n" ' set block driver read-only whitelist (by default' printf "%s\n" ' affects only QEMU, not tools like qemu-img)' @@ -17,6 +18,7 @@ meson_options_help() { printf "%s\n" ' code for the Hexagon frontend' printf "%s\n" ' --disable-install-blobs install provided firmware blobs' printf "%s\n" ' --disable-qom-cast-debug cast debugging support' + printf "%s\n" ' --disable-relocatable toggle relocatable install' printf "%s\n" ' --docdir=VALUE Base directory for documentation installation' printf "%s\n" ' (can be empty) [share/doc]' printf "%s\n" ' --enable-block-drv-whitelist-in-tools' @@ -39,7 +41,6 @@ meson_options_help() { printf "%s\n" ' jemalloc/system/tcmalloc)' printf "%s\n" ' --enable-module-upgrades try to load modules from alternate paths for' printf "%s\n" ' upgrades' - printf "%s\n" ' --enable-plugins TCG plugins via shared library loading' printf "%s\n" ' --enable-rng-none dummy RNG, avoid using /dev/(u)random and' printf "%s\n" ' getrandom()' printf "%s\n" ' --enable-safe-stack SafeStack Stack Smash Protection (requires' @@ -62,6 +63,14 @@ meson_options_help() { printf "%s\n" ' --localedir=VALUE Locale data directory [share/locale]' printf "%s\n" ' --localstatedir=VALUE Localstate data directory [/var/local]' printf "%s\n" ' --mandir=VALUE Manual page directory [share/man]' + printf "%s\n" ' --prefix=VALUE Installation prefix [/usr/local]' + printf "%s\n" ' --qemu-ga-distro=VALUE second path element in qemu-ga registry entries' + printf "%s\n" ' [Linux]' + printf "%s\n" ' --qemu-ga-manufacturer=VALUE' + printf "%s\n" ' "manufacturer" name for qemu-ga registry entries' + printf "%s\n" ' [QEMU]' + printf "%s\n" ' --qemu-ga-version=VALUE version number for qemu-ga installer' + printf "%s\n" ' --smbd=VALUE Path to smbd for slirp networking' printf "%s\n" ' --sysconfdir=VALUE Sysconf data directory [etc]' printf "%s\n" ' --tls-priority=VALUE Default TLS protocol/cipher priority string' printf "%s\n" ' [NORMAL]' @@ -69,6 +78,8 @@ meson_options_help() { printf "%s\n" ' auto/sigaltstack/ucontext/windows)' printf "%s\n" ' --with-pkgversion=VALUE use specified string as sub-version of the' printf "%s\n" ' package' + printf "%s\n" ' --with-suffix=VALUE Suffix for QEMU data/modules/config directories' + printf "%s\n" ' (can be empty) [qemu]' printf "%s\n" ' --with-trace-file=VALUE Trace file prefix for simple backend [trace]' printf "%s\n" '' printf "%s\n" 'Optional features, enabled with --enable-FEATURE and' @@ -148,6 +159,7 @@ meson_options_help() { printf "%s\n" ' pa PulseAudio sound support' printf "%s\n" ' parallels parallels image format support' printf "%s\n" ' pipewire PipeWire sound support' + printf "%s\n" ' plugins TCG plugins via shared library loading' printf "%s\n" ' png PNG support with libpng' printf "%s\n" ' pvrdma Enable PVRDMA support' printf "%s\n" ' qcow1 qcow1 image format support' @@ -156,6 +168,7 @@ meson_options_help() { printf "%s\n" ' rbd Ceph block device driver' printf "%s\n" ' rdma Enable RDMA-based migration' printf "%s\n" ' replication replication support' + printf "%s\n" ' rutabaga-gfx rutabaga_gfx support' printf "%s\n" ' sdl SDL user interface' printf "%s\n" ' sdl-image SDL Image support for icons' printf "%s\n" ' seccomp seccomp support' @@ -200,6 +213,7 @@ meson_options_help() { printf "%s\n" ' vpc vpc image format support' printf "%s\n" ' vte vte support for the gtk UI' printf "%s\n" ' vvfat vvfat image format support' + printf "%s\n" ' werror Treat warnings as errors' printf "%s\n" ' whpx WHPX acceleration support' printf "%s\n" ' xen Xen backend support' printf "%s\n" ' xen-pci-passthrough' @@ -228,6 +242,7 @@ _meson_option_parse() { --disable-gcov) printf "%s" -Db_coverage=false ;; --enable-lto) printf "%s" -Db_lto=true ;; --disable-lto) printf "%s" -Db_lto=false ;; + --bindir=*) quote_sh "-Dbindir=$2" ;; --enable-blkio) printf "%s" -Dblkio=enabled ;; --disable-blkio) printf "%s" -Dblkio=disabled ;; --block-drv-ro-whitelist=*) quote_sh "-Dblock_drv_ro_whitelist=$2" ;; @@ -406,6 +421,7 @@ _meson_option_parse() { --disable-plugins) printf "%s" -Dplugins=false ;; --enable-png) printf "%s" -Dpng=enabled ;; --disable-png) printf "%s" -Dpng=disabled ;; + --prefix=*) quote_sh "-Dprefix=$2" ;; --enable-pvrdma) printf "%s" -Dpvrdma=enabled ;; --disable-pvrdma) printf "%s" -Dpvrdma=disabled ;; --enable-qcow1) printf "%s" -Dqcow1=enabled ;; @@ -413,6 +429,10 @@ _meson_option_parse() { --enable-qed) printf "%s" -Dqed=enabled ;; --disable-qed) printf "%s" -Dqed=disabled ;; --firmwarepath=*) quote_sh "-Dqemu_firmwarepath=$(meson_option_build_array $2)" ;; + --qemu-ga-distro=*) quote_sh "-Dqemu_ga_distro=$2" ;; + --qemu-ga-manufacturer=*) quote_sh "-Dqemu_ga_manufacturer=$2" ;; + --qemu-ga-version=*) quote_sh "-Dqemu_ga_version=$2" ;; + --with-suffix=*) quote_sh "-Dqemu_suffix=$2" ;; --enable-qga-vss) printf "%s" -Dqga_vss=enabled ;; --disable-qga-vss) printf "%s" -Dqga_vss=disabled ;; --enable-qom-cast-debug) printf "%s" -Dqom_cast_debug=true ;; @@ -421,10 +441,14 @@ _meson_option_parse() { --disable-rbd) printf "%s" -Drbd=disabled ;; --enable-rdma) printf "%s" -Drdma=enabled ;; --disable-rdma) printf "%s" -Drdma=disabled ;; + --enable-relocatable) printf "%s" -Drelocatable=true ;; + --disable-relocatable) printf "%s" -Drelocatable=false ;; --enable-replication) printf "%s" -Dreplication=enabled ;; --disable-replication) printf "%s" -Dreplication=disabled ;; --enable-rng-none) printf "%s" -Drng_none=true ;; --disable-rng-none) printf "%s" -Drng_none=false ;; + --enable-rutabaga-gfx) printf "%s" -Drutabaga_gfx=enabled ;; + --disable-rutabaga-gfx) printf "%s" -Drutabaga_gfx=disabled ;; --enable-safe-stack) printf "%s" -Dsafe_stack=true ;; --disable-safe-stack) printf "%s" -Dsafe_stack=false ;; --enable-sanitizers) printf "%s" -Dsanitizers=true ;; @@ -443,6 +467,7 @@ _meson_option_parse() { --disable-slirp-smbd) printf "%s" -Dslirp_smbd=disabled ;; --enable-smartcard) printf "%s" -Dsmartcard=enabled ;; --disable-smartcard) printf "%s" -Dsmartcard=disabled ;; + --smbd=*) quote_sh "-Dsmbd=$2" ;; --enable-snappy) printf "%s" -Dsnappy=enabled ;; --disable-snappy) printf "%s" -Dsnappy=disabled ;; --enable-sndio) printf "%s" -Dsndio=enabled ;; @@ -519,6 +544,8 @@ _meson_option_parse() { --disable-vte) printf "%s" -Dvte=disabled ;; --enable-vvfat) printf "%s" -Dvvfat=enabled ;; --disable-vvfat) printf "%s" -Dvvfat=disabled ;; + --enable-werror) printf "%s" -Dwerror=true ;; + --disable-werror) printf "%s" -Dwerror=false ;; --enable-whpx) printf "%s" -Dwhpx=enabled ;; --disable-whpx) printf "%s" -Dwhpx=disabled ;; --enable-xen) printf "%s" -Dxen=enabled ;; diff --git a/scripts/python_qmp_updater.py b/scripts/python_qmp_updater.py new file mode 100755 index 0000000000..494a169812 --- /dev/null +++ b/scripts/python_qmp_updater.py @@ -0,0 +1,136 @@ +#!/usr/bin/env python3 +# +# Intended usage: +# +# git grep -l '\.qmp(' | xargs ./scripts/python_qmp_updater.py +# + +import re +import sys +from typing import Optional + +start_reg = re.compile(r'^(?P<padding> *)(?P<res>\w+) = (?P<vm>.*).qmp\(', + flags=re.MULTILINE) + +success_reg_templ = re.sub('\n *', '', r""" + (\n*{padding}(?P<comment>\#.*$))? + \n*{padding} + ( + self.assert_qmp\({res},\ 'return',\ {{}}\) + | + assert\ {res}\['return'\]\ ==\ {{}} + | + assert\ {res}\ ==\ {{'return':\ {{}}}} + | + self.assertEqual\({res}\['return'\],\ {{}}\) + )""") + +some_check_templ = re.sub('\n *', '', r""" + (\n*{padding}(?P<comment>\#.*$))? + \s*self.assert_qmp\({res},""") + + +def tmatch(template: str, text: str, + padding: str, res: str) -> Optional[re.Match[str]]: + return re.match(template.format(padding=padding, res=res), text, + flags=re.MULTILINE) + + +def find_closing_brace(text: str, start: int) -> int: + """ + Having '(' at text[start] search for pairing ')' and return its index. + """ + assert text[start] == '(' + + height = 1 + + for i in range(start + 1, len(text)): + if text[i] == '(': + height += 1 + elif text[i] == ')': + height -= 1 + if height == 0: + return i + + raise ValueError + + +def update(text: str) -> str: + result = '' + + while True: + m = start_reg.search(text) + if m is None: + result += text + break + + result += text[:m.start()] + + args_ind = m.end() + args_end = find_closing_brace(text, args_ind - 1) + + all_args = text[args_ind:args_end].split(',', 1) + + name = all_args[0] + args = None if len(all_args) == 1 else all_args[1] + + unchanged_call = text[m.start():args_end+1] + text = text[args_end+1:] + + padding, res, vm = m.group('padding', 'res', 'vm') + + m = tmatch(success_reg_templ, text, padding, res) + + if m is None: + result += unchanged_call + + if ('query-' not in name and + 'x-debug-block-dirty-bitmap-sha256' not in name and + not tmatch(some_check_templ, text, padding, res)): + print(unchanged_call + text[:200] + '...\n\n') + + continue + + if m.group('comment'): + result += f'{padding}{m.group("comment")}\n' + + result += f'{padding}{vm}.cmd({name}' + + if args: + result += ',' + + if '\n' in args: + m_args = re.search('(?P<pad> *).*$', args) + assert m_args is not None + + cur_padding = len(m_args.group('pad')) + expected = len(f'{padding}{res} = {vm}.qmp(') + drop = len(f'{res} = ') + if cur_padding == expected - 1: + # tolerate this bad style + drop -= 1 + elif cur_padding < expected - 1: + # assume nothing to do + drop = 0 + + if drop: + args = re.sub('\n' + ' ' * drop, '\n', args) + + result += args + + result += ')' + + text = text[m.end():] + + return result + + +for fname in sys.argv[1:]: + print(fname) + with open(fname) as f: + t = f.read() + + t = update(t) + + with open(fname, 'w') as f: + f.write(t) diff --git a/scripts/qapi/gen.py b/scripts/qapi/gen.py index bf5716b5f3..5412716617 100644 --- a/scripts/qapi/gen.py +++ b/scripts/qapi/gen.py @@ -13,8 +13,8 @@ from contextlib import contextmanager import os -import sys import re +import sys from typing import ( Dict, Iterator, diff --git a/scripts/qapi/parser.py b/scripts/qapi/parser.py index 22e7bcc4b1..bf31018aef 100644 --- a/scripts/qapi/parser.py +++ b/scripts/qapi/parser.py @@ -22,6 +22,7 @@ from typing import ( Dict, List, Mapping, + Match, Optional, Set, Union, @@ -563,11 +564,11 @@ class QAPIDoc: self._switch_section(QAPIDoc.NullSection(self._parser)) @staticmethod - def _match_at_name_colon(string: str): + def _match_at_name_colon(string: str) -> Optional[Match[str]]: return re.match(r'@([^:]*): *', string) @staticmethod - def _match_section_tag(string: str): + def _match_section_tag(string: str) -> Optional[Match[str]]: return re.match(r'(Returns|Since|Notes?|Examples?|TODO): *', string) def _append_body_line(self, line: str) -> None: diff --git a/scripts/qapi/schema.py b/scripts/qapi/schema.py index 231ebf61ba..d739e558e9 100644 --- a/scripts/qapi/schema.py +++ b/scripts/qapi/schema.py @@ -73,6 +73,11 @@ class QAPISchemaEntity: self.features = features or [] self._checked = False + def __repr__(self): + if self.name is None: + return "<%s at 0x%x>" % (type(self).__name__, id(self)) + return "<%s:%s at 0x%x>" % type(self).__name__, self.name, id(self) + def c_name(self): return c_name(self.name) diff --git a/scripts/render_block_graph.py b/scripts/render_block_graph.py index 8f731a5cfe..3e1a2e3fa7 100755 --- a/scripts/render_block_graph.py +++ b/scripts/render_block_graph.py @@ -43,13 +43,13 @@ def render_block_graph(qmp, filename, format='png'): representation in @format into "@filename.@format" ''' - bds_nodes = qmp.command('query-named-block-nodes') + bds_nodes = qmp.cmd('query-named-block-nodes') bds_nodes = {n['node-name']: n for n in bds_nodes} - job_nodes = qmp.command('query-block-jobs') + job_nodes = qmp.cmd('query-block-jobs') job_nodes = {n['device']: n for n in job_nodes} - block_graph = qmp.command('x-debug-query-block-graph') + block_graph = qmp.cmd('x-debug-query-block-graph') graph = Digraph(comment='Block Nodes Graph') graph.format = format @@ -94,7 +94,7 @@ class LibvirtGuest(): def __init__(self, name): self.name = name - def command(self, cmd): + def cmd(self, cmd): # only supports qmp commands without parameters m = {'execute': cmd} ar = ['virsh', 'qemu-monitor-command', self.name, json.dumps(m)] diff --git a/scripts/tracetool/__init__.py b/scripts/tracetool/__init__.py index 33cf85e2b0..b29594d75e 100644 --- a/scripts/tracetool/__init__.py +++ b/scripts/tracetool/__init__.py @@ -210,12 +210,12 @@ class Event(object): """ - _CRE = re.compile("((?P<props>[\w\s]+)\s+)?" - "(?P<name>\w+)" - "\((?P<args>[^)]*)\)" - "\s*" - "(?:(?:(?P<fmt_trans>\".+),)?\s*(?P<fmt>\".+))?" - "\s*") + _CRE = re.compile(r"((?P<props>[\w\s]+)\s+)?" + r"(?P<name>\w+)" + r"\((?P<args>[^)]*)\)" + r"\s*" + r"(?:(?:(?P<fmt_trans>\".+),)?\s*(?P<fmt>\".+))?" + r"\s*") _VALID_PROPS = set(["disable", "vcpu"]) @@ -326,7 +326,7 @@ class Event(object): fmt) # Star matching on PRI is dangerous as one might have multiple # arguments with that format, hence the non-greedy version of it. - _FMT = re.compile("(%[\d\.]*\w+|%.*?PRI\S+)") + _FMT = re.compile(r"(%[\d\.]*\w+|%.*?PRI\S+)") def formats(self): """List conversion specifiers in the argument print format string.""" diff --git a/scripts/tracetool/format/log_stap.py b/scripts/tracetool/format/log_stap.py index 0b6549d534..b49afababd 100644 --- a/scripts/tracetool/format/log_stap.py +++ b/scripts/tracetool/format/log_stap.py @@ -83,7 +83,7 @@ def c_fmt_to_stap(fmt): # and "%ll" is not valid at all. Similarly the size_t # based "%z" size qualifier is not valid. We just # strip all size qualifiers for sanity. - fmt = re.sub("%(\d*)(l+|z)(x|u|d)", "%\\1\\3", "".join(bits)) + fmt = re.sub(r"%(\d*)(l+|z)(x|u|d)", r"%\1\3", "".join(bits)) return fmt def generate(events, backend, group): diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index 35a64bb501..34295c0fe5 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -161,7 +161,8 @@ done rm -rf "$output/linux-headers/linux" mkdir -p "$output/linux-headers/linux" for header in const.h stddef.h kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h \ - psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h vduse.h; do + psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h \ + vduse.h iommufd.h; do cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux" done diff --git a/stubs/qmp_memory_device.c b/stubs/memory_device.c index e75cac62dc..15fd93ff67 100644 --- a/stubs/qmp_memory_device.c +++ b/stubs/memory_device.c @@ -10,3 +10,13 @@ uint64_t get_plugged_memory_size(void) { return (uint64_t)-1; } + +unsigned int memory_devices_get_reserved_memslots(void) +{ + return 0; +} + +bool memory_devices_memslot_auto_decision_active(void) +{ + return false; +} diff --git a/stubs/meson.build b/stubs/meson.build index ef6e39a64d..0bf25e6ca5 100644 --- a/stubs/meson.build +++ b/stubs/meson.build @@ -32,7 +32,7 @@ stub_ss.add(files('monitor.c')) stub_ss.add(files('monitor-core.c')) stub_ss.add(files('physmem.c')) stub_ss.add(files('qemu-timer-notify-cb.c')) -stub_ss.add(files('qmp_memory_device.c')) +stub_ss.add(files('memory_device.c')) stub_ss.add(files('qmp-command-available.c')) stub_ss.add(files('qmp-quit.c')) stub_ss.add(files('qtest.c')) @@ -65,4 +65,3 @@ else stub_ss.add(files('qdev.c')) endif stub_ss.add(files('semihost-all.c')) -stub_ss.add(when: 'CONFIG_VFIO_USER_SERVER', if_false: files('vfio-user-obj.c')) diff --git a/stubs/ramfb.c b/stubs/ramfb.c index 48143f3354..cf64733b10 100644 --- a/stubs/ramfb.c +++ b/stubs/ramfb.c @@ -2,6 +2,8 @@ #include "qapi/error.h" #include "hw/display/ramfb.h" +const VMStateDescription ramfb_vmstate = {}; + void ramfb_display_update(QemuConsole *con, RAMFBState *s) { } diff --git a/subprojects/libvduse/libvduse.c b/subprojects/libvduse/libvduse.c index 377959a0b4..21ffbb5b8d 100644 --- a/subprojects/libvduse/libvduse.c +++ b/subprojects/libvduse/libvduse.c @@ -1031,7 +1031,7 @@ int vduse_dev_handler(VduseDev *dev) /* The iova will be updated by iova_to_va() later, so just remove it */ vduse_iova_remove_region(dev, req.iova.start, req.iova.last); for (i = 0; i < dev->num_queues; i++) { - VduseVirtq *vq = &dev->vqs[i]; + vq = &dev->vqs[i]; if (vq->ready) { if (vduse_queue_update_vring(vq, vq->vring.desc_addr, vq->vring.avail_addr, diff --git a/subprojects/libvhost-user/libvhost-user.c b/subprojects/libvhost-user/libvhost-user.c index ac6d5d01d3..6684057370 100644 --- a/subprojects/libvhost-user/libvhost-user.c +++ b/subprojects/libvhost-user/libvhost-user.c @@ -870,10 +870,10 @@ vu_rem_mem_reg(VuDev *dev, VhostUserMsg *vmsg) { for (i = 0; i < dev->nregions; i++) { if (reg_equal(&dev->regions[i], msg_region)) { VuDevRegion *r = &dev->regions[i]; - void *m = (void *) (uintptr_t) r->mmap_addr; + void *ma = (void *) (uintptr_t) r->mmap_addr; - if (m) { - munmap(m, r->size + r->mmap_offset); + if (ma) { + munmap(ma, r->size + r->mmap_offset); } /* @@ -1005,10 +1005,10 @@ vu_set_mem_table_exec(VuDev *dev, VhostUserMsg *vmsg) for (i = 0; i < dev->nregions; i++) { VuDevRegion *r = &dev->regions[i]; - void *m = (void *) (uintptr_t) r->mmap_addr; + void *ma = (void *) (uintptr_t) r->mmap_addr; - if (m) { - munmap(m, r->size + r->mmap_offset); + if (ma) { + munmap(ma, r->size + r->mmap_offset); } } dev->nregions = memory->nregions; diff --git a/system/memory.c b/system/memory.c index fa1c99f9ba..a800fbc9e5 100644 --- a/system/memory.c +++ b/system/memory.c @@ -224,6 +224,7 @@ struct FlatRange { bool romd_mode; bool readonly; bool nonvolatile; + bool unmergeable; }; #define FOR_EACH_FLAT_RANGE(var, view) \ @@ -240,6 +241,7 @@ section_from_flat_range(FlatRange *fr, FlatView *fv) .offset_within_address_space = int128_get64(fr->addr.start), .readonly = fr->readonly, .nonvolatile = fr->nonvolatile, + .unmergeable = fr->unmergeable, }; } @@ -250,7 +252,8 @@ static bool flatrange_equal(FlatRange *a, FlatRange *b) && a->offset_in_region == b->offset_in_region && a->romd_mode == b->romd_mode && a->readonly == b->readonly - && a->nonvolatile == b->nonvolatile; + && a->nonvolatile == b->nonvolatile + && a->unmergeable == b->unmergeable; } static FlatView *flatview_new(MemoryRegion *mr_root) @@ -323,7 +326,8 @@ static bool can_merge(FlatRange *r1, FlatRange *r2) && r1->dirty_log_mask == r2->dirty_log_mask && r1->romd_mode == r2->romd_mode && r1->readonly == r2->readonly - && r1->nonvolatile == r2->nonvolatile; + && r1->nonvolatile == r2->nonvolatile + && !r1->unmergeable && !r2->unmergeable; } /* Attempt to simplify a view by merging adjacent ranges */ @@ -599,7 +603,8 @@ static void render_memory_region(FlatView *view, Int128 base, AddrRange clip, bool readonly, - bool nonvolatile) + bool nonvolatile, + bool unmergeable) { MemoryRegion *subregion; unsigned i; @@ -616,6 +621,7 @@ static void render_memory_region(FlatView *view, int128_addto(&base, int128_make64(mr->addr)); readonly |= mr->readonly; nonvolatile |= mr->nonvolatile; + unmergeable |= mr->unmergeable; tmp = addrrange_make(base, mr->size); @@ -629,14 +635,14 @@ static void render_memory_region(FlatView *view, int128_subfrom(&base, int128_make64(mr->alias->addr)); int128_subfrom(&base, int128_make64(mr->alias_offset)); render_memory_region(view, mr->alias, base, clip, - readonly, nonvolatile); + readonly, nonvolatile, unmergeable); return; } /* Render subregions in priority order. */ QTAILQ_FOREACH(subregion, &mr->subregions, subregions_link) { render_memory_region(view, subregion, base, clip, - readonly, nonvolatile); + readonly, nonvolatile, unmergeable); } if (!mr->terminates) { @@ -652,6 +658,7 @@ static void render_memory_region(FlatView *view, fr.romd_mode = mr->romd_mode; fr.readonly = readonly; fr.nonvolatile = nonvolatile; + fr.unmergeable = unmergeable; /* Render the region itself into any gaps left by the current view. */ for (i = 0; i < view->nr && int128_nz(remain); ++i) { @@ -753,7 +760,7 @@ static FlatView *generate_memory_topology(MemoryRegion *mr) if (mr) { render_memory_region(view, mr, int128_zero(), addrrange_make(int128_zero(), int128_2_64()), - false, false); + false, false, false); } flatview_simplify(view); @@ -2085,7 +2092,7 @@ int memory_region_iommu_num_indexes(IOMMUMemoryRegion *iommu_mr) RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr) { - if (!memory_region_is_mapped(mr) || !memory_region_is_ram(mr)) { + if (!memory_region_is_ram(mr)) { return NULL; } return mr->rdm; @@ -2094,7 +2101,7 @@ RamDiscardManager *memory_region_get_ram_discard_manager(MemoryRegion *mr) void memory_region_set_ram_discard_manager(MemoryRegion *mr, RamDiscardManager *rdm) { - g_assert(memory_region_is_ram(mr) && !memory_region_is_mapped(mr)); + g_assert(memory_region_is_ram(mr)); g_assert(!rdm || !mr->rdm); mr->rdm = rdm; } @@ -2755,6 +2762,18 @@ void memory_region_set_alias_offset(MemoryRegion *mr, hwaddr offset) memory_region_transaction_commit(); } +void memory_region_set_unmergeable(MemoryRegion *mr, bool unmergeable) +{ + if (unmergeable == mr->unmergeable) { + return; + } + + memory_region_transaction_begin(); + mr->unmergeable = unmergeable; + memory_region_update_pending |= mr->enabled; + memory_region_transaction_commit(); +} + uint64_t memory_region_get_alignment(const MemoryRegion *mr) { return mr->align; diff --git a/system/memory_mapping.c b/system/memory_mapping.c index d7f1d096e0..6f884c5b90 100644 --- a/system/memory_mapping.c +++ b/system/memory_mapping.c @@ -291,7 +291,7 @@ void guest_phys_blocks_append(GuestPhysBlockList *list) memory_listener_unregister(&g.listener); } -static CPUState *find_paging_enabled_cpu(CPUState *start_cpu) +static CPUState *find_paging_enabled_cpu(void) { CPUState *cpu; @@ -304,26 +304,24 @@ static CPUState *find_paging_enabled_cpu(CPUState *start_cpu) return NULL; } -void qemu_get_guest_memory_mapping(MemoryMappingList *list, +bool qemu_get_guest_memory_mapping(MemoryMappingList *list, const GuestPhysBlockList *guest_phys_blocks, Error **errp) { + ERRP_GUARD(); CPUState *cpu, *first_paging_enabled_cpu; GuestPhysBlock *block; ram_addr_t offset, length; - first_paging_enabled_cpu = find_paging_enabled_cpu(first_cpu); + first_paging_enabled_cpu = find_paging_enabled_cpu(); if (first_paging_enabled_cpu) { for (cpu = first_paging_enabled_cpu; cpu != NULL; cpu = CPU_NEXT(cpu)) { - Error *err = NULL; - cpu_get_memory_mapping(cpu, list, &err); - if (err) { - error_propagate(errp, err); - return; + if (!cpu_get_memory_mapping(cpu, list, errp)) { + return false; } } - return; + return true; } /* @@ -335,6 +333,7 @@ void qemu_get_guest_memory_mapping(MemoryMappingList *list, length = block->target_end - block->target_start; create_new_memory_mapping(list, offset, offset, length); } + return true; } void qemu_get_guest_simple_memory_mapping(MemoryMappingList *list, diff --git a/system/physmem.c b/system/physmem.c index edc3ed8ab9..fc2b0fee01 100644 --- a/system/physmem.c +++ b/system/physmem.c @@ -2221,23 +2221,6 @@ ram_addr_t qemu_ram_block_host_offset(RAMBlock *rb, void *host) return res; } -/* - * Translates a host ptr back to a RAMBlock, a ram_addr and an offset - * in that RAMBlock. - * - * ptr: Host pointer to look up - * round_offset: If true round the result offset down to a page boundary - * *ram_addr: set to result ram_addr - * *offset: set to result offset within the RAMBlock - * - * Returns: RAMBlock (or NULL if not found) - * - * By the time this function returns, the returned pointer is not protected - * by RCU anymore. If the caller is not within an RCU critical section and - * does not hold the iothread lock, it must have other means of protecting the - * pointer, such as a reference to the region that includes the incoming - * ram_addr_t. - */ RAMBlock *qemu_ram_block_from_host(void *ptr, bool round_offset, ram_addr_t *offset) { diff --git a/system/qdev-monitor.c b/system/qdev-monitor.c index 74f4e41338..1b8005ae55 100644 --- a/system/qdev-monitor.c +++ b/system/qdev-monitor.c @@ -86,6 +86,9 @@ static const QDevAlias qdev_alias_table[] = { { "virtio-gpu-pci", "virtio-gpu", QEMU_ARCH_VIRTIO_PCI }, { "virtio-gpu-gl-device", "virtio-gpu-gl", QEMU_ARCH_VIRTIO_MMIO }, { "virtio-gpu-gl-pci", "virtio-gpu-gl", QEMU_ARCH_VIRTIO_PCI }, + { "virtio-gpu-rutabaga-device", "virtio-gpu-rutabaga", + QEMU_ARCH_VIRTIO_MMIO }, + { "virtio-gpu-rutabaga-pci", "virtio-gpu-rutabaga", QEMU_ARCH_VIRTIO_PCI }, { "virtio-input-host-device", "virtio-input-host", QEMU_ARCH_VIRTIO_MMIO }, { "virtio-input-host-ccw", "virtio-input-host", QEMU_ARCH_VIRTIO_CCW }, { "virtio-input-host-pci", "virtio-input-host", QEMU_ARCH_VIRTIO_PCI }, diff --git a/system/vl.c b/system/vl.c index ba83040675..3100ac01ed 100644 --- a/system/vl.c +++ b/system/vl.c @@ -216,6 +216,7 @@ static struct { { .driver = "ati-vga", .flag = &default_vga }, { .driver = "vhost-user-vga", .flag = &default_vga }, { .driver = "virtio-vga-gl", .flag = &default_vga }, + { .driver = "virtio-vga-rutabaga", .flag = &default_vga }, }; static QemuOptsList qemu_rtc_opts = { diff --git a/target/arm/arm-powerctl.c b/target/arm/arm-powerctl.c index 326a03153d..c078849403 100644 --- a/target/arm/arm-powerctl.c +++ b/target/arm/arm-powerctl.c @@ -65,60 +65,9 @@ static void arm_set_cpu_on_async_work(CPUState *target_cpu_state, /* Initialize the cpu we are turning on */ cpu_reset(target_cpu_state); + arm_emulate_firmware_reset(target_cpu_state, info->target_el); target_cpu_state->halted = 0; - if (info->target_aa64) { - if ((info->target_el < 3) && arm_feature(&target_cpu->env, - ARM_FEATURE_EL3)) { - /* - * As target mode is AArch64, we need to set lower - * exception level (the requested level 2) to AArch64 - */ - target_cpu->env.cp15.scr_el3 |= SCR_RW; - } - - if ((info->target_el < 2) && arm_feature(&target_cpu->env, - ARM_FEATURE_EL2)) { - /* - * As target mode is AArch64, we need to set lower - * exception level (the requested level 1) to AArch64 - */ - target_cpu->env.cp15.hcr_el2 |= HCR_RW; - } - - target_cpu->env.pstate = aarch64_pstate_mode(info->target_el, true); - } else { - /* We are requested to boot in AArch32 mode */ - static const uint32_t mode_for_el[] = { 0, - ARM_CPU_MODE_SVC, - ARM_CPU_MODE_HYP, - ARM_CPU_MODE_SVC }; - - cpsr_write(&target_cpu->env, mode_for_el[info->target_el], CPSR_M, - CPSRWriteRaw); - } - - if (info->target_el == 3) { - /* Processor is in secure mode */ - target_cpu->env.cp15.scr_el3 &= ~SCR_NS; - } else { - /* Processor is not in secure mode */ - target_cpu->env.cp15.scr_el3 |= SCR_NS; - - /* Set NSACR.{CP11,CP10} so NS can access the FPU */ - target_cpu->env.cp15.nsacr |= 3 << 10; - - /* - * If QEMU is providing the equivalent of EL3 firmware, then we need - * to make sure a CPU targeting EL2 comes out of reset with a - * functional HVC insn. - */ - if (arm_feature(&target_cpu->env, ARM_FEATURE_EL3) - && info->target_el == 2) { - target_cpu->env.cp15.scr_el3 |= SCR_HCE; - } - } - /* We check if the started CPU is now at the correct level */ assert(info->target_el == arm_current_el(&target_cpu->env)); diff --git a/target/arm/common-semi-target.h b/target/arm/common-semi-target.h index 19438ed8cd..da51f2d7f5 100644 --- a/target/arm/common-semi-target.h +++ b/target/arm/common-semi-target.h @@ -10,9 +10,7 @@ #ifndef TARGET_ARM_COMMON_SEMI_TARGET_H #define TARGET_ARM_COMMON_SEMI_TARGET_H -#ifndef CONFIG_USER_ONLY -#include "hw/arm/boot.h" -#endif +#include "target/arm/cpu-qom.h" static inline target_ulong common_semi_arg(CPUState *cs, int argno) { diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h index 514c22ced9..d06c08a734 100644 --- a/target/arm/cpu-qom.h +++ b/target/arm/cpu-qom.h @@ -23,8 +23,6 @@ #include "hw/core/cpu.h" #include "qom/object.h" -struct arm_boot_info; - #define TYPE_ARM_CPU "arm-cpu" OBJECT_DECLARE_CPU_TYPE(ARMCPU, ARMCPUClass, ARM_CPU) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 6c6c551573..aa4e006f21 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -553,6 +553,101 @@ static void arm_cpu_reset_hold(Object *obj) } } +void arm_emulate_firmware_reset(CPUState *cpustate, int target_el) +{ + ARMCPU *cpu = ARM_CPU(cpustate); + CPUARMState *env = &cpu->env; + bool have_el3 = arm_feature(env, ARM_FEATURE_EL3); + bool have_el2 = arm_feature(env, ARM_FEATURE_EL2); + + /* + * Check we have the EL we're aiming for. If that is the + * highest implemented EL, then cpu_reset has already done + * all the work. + */ + switch (target_el) { + case 3: + assert(have_el3); + return; + case 2: + assert(have_el2); + if (!have_el3) { + return; + } + break; + case 1: + if (!have_el3 && !have_el2) { + return; + } + break; + default: + g_assert_not_reached(); + } + + if (have_el3) { + /* + * Set the EL3 state so code can run at EL2. This should match + * the requirements set by Linux in its booting spec. + */ + if (env->aarch64) { + env->cp15.scr_el3 |= SCR_RW; + if (cpu_isar_feature(aa64_pauth, cpu)) { + env->cp15.scr_el3 |= SCR_API | SCR_APK; + } + if (cpu_isar_feature(aa64_mte, cpu)) { + env->cp15.scr_el3 |= SCR_ATA; + } + if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cptr_el[3] |= R_CPTR_EL3_EZ_MASK; + env->vfp.zcr_el[3] = 0xf; + } + if (cpu_isar_feature(aa64_sme, cpu)) { + env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK; + env->cp15.scr_el3 |= SCR_ENTP2; + env->vfp.smcr_el[3] = 0xf; + } + if (cpu_isar_feature(aa64_hcx, cpu)) { + env->cp15.scr_el3 |= SCR_HXEN; + } + if (cpu_isar_feature(aa64_fgt, cpu)) { + env->cp15.scr_el3 |= SCR_FGTEN; + } + } + + if (target_el == 2) { + /* If the guest is at EL2 then Linux expects the HVC insn to work */ + env->cp15.scr_el3 |= SCR_HCE; + } + + /* Put CPU into non-secure state */ + env->cp15.scr_el3 |= SCR_NS; + /* Set NSACR.{CP11,CP10} so NS can access the FPU */ + env->cp15.nsacr |= 3 << 10; + } + + if (have_el2 && target_el < 2) { + /* Set EL2 state so code can run at EL1. */ + if (env->aarch64) { + env->cp15.hcr_el2 |= HCR_RW; + } + } + + /* Set the CPU to the desired state */ + if (env->aarch64) { + env->pstate = aarch64_pstate_mode(target_el, true); + } else { + static const uint32_t mode_for_el[] = { + 0, + ARM_CPU_MODE_SVC, + ARM_CPU_MODE_HYP, + ARM_CPU_MODE_SVC, + }; + + cpsr_write(env, mode_for_el[target_el], CPSR_M, CPSRWriteRaw); + } +} + + #if defined(CONFIG_TCG) && !defined(CONFIG_USER_ONLY) static inline bool arm_excp_unmasked(CPUState *cs, unsigned int excp_idx, diff --git a/target/arm/cpu.h b/target/arm/cpu.h index a9edfb8353..76d4cef9e3 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -1149,6 +1149,28 @@ int arm_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int cpuid, DumpState *s); +/** + * arm_emulate_firmware_reset: Emulate firmware CPU reset handling + * @cpu: CPU (which must have been freshly reset) + * @target_el: exception level to put the CPU into + * @secure: whether to put the CPU in secure state + * + * When QEMU is directly running a guest kernel at a lower level than + * EL3 it implicitly emulates some aspects of the guest firmware. + * This includes that on reset we need to configure the parts of the + * CPU corresponding to EL3 so that the real guest code can run at its + * lower exception level. This function does that post-reset CPU setup, + * for when we do direct boot of a guest kernel, and for when we + * emulate PSCI and similar firmware interfaces starting a CPU at a + * lower exception level. + * + * @target_el must be an EL implemented by the CPU between 1 and 3. + * We do not support dropping into a Secure EL other than 3. + * + * It is the responsibility of the caller to call arm_rebuild_hflags(). + */ +void arm_emulate_firmware_reset(CPUState *cpustate, int target_el); + #ifdef TARGET_AARCH64 int aarch64_cpu_gdb_read_register(CPUState *cpu, GByteArray *buf, int reg); int aarch64_cpu_gdb_write_register(CPUState *cpu, uint8_t *buf, int reg); diff --git a/target/arm/helper.c b/target/arm/helper.c index 74fbb6e1d7..b29edb26af 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -1283,7 +1283,7 @@ static bool pmevcntr_is_64_bit(CPUARMState *env, int counter) bool hlp = env->cp15.mdcr_el2 & MDCR_HLP; int hpmn = env->cp15.mdcr_el2 & MDCR_HPMN; - if (hpmn != 0 && counter >= hpmn) { + if (counter >= hpmn) { return hlp; } } @@ -2475,22 +2475,7 @@ static CPAccessResult gt_counter_access(CPUARMState *env, int timeridx, if (!extract32(env->cp15.c14_cntkctl, timeridx, 1)) { return CP_ACCESS_TRAP; } - - /* If HCR_EL2.<E2H,TGE> == '10': check CNTHCTL_EL2.EL1PCTEN. */ - if (hcr & HCR_E2H) { - if (timeridx == GTIMER_PHYS && - !extract32(env->cp15.cnthctl_el2, 10, 1)) { - return CP_ACCESS_TRAP_EL2; - } - } else { - /* If HCR_EL2.<E2H> == 0: check CNTHCTL_EL2.EL1PCEN. */ - if (has_el2 && timeridx == GTIMER_PHYS && - !extract32(env->cp15.cnthctl_el2, 1, 1)) { - return CP_ACCESS_TRAP_EL2; - } - } - break; - + /* fall through */ case 1: /* Check CNTHCTL_EL2.EL1PCTEN, which changes location based on E2H. */ if (has_el2 && timeridx == GTIMER_PHYS && diff --git a/target/arm/kvm.c b/target/arm/kvm.c index b66b936a95..7903e2ddde 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -553,24 +553,19 @@ bool write_kvmstate_to_list(ARMCPU *cpu) bool ok = true; for (i = 0; i < cpu->cpreg_array_len; i++) { - struct kvm_one_reg r; uint64_t regidx = cpu->cpreg_indexes[i]; uint32_t v32; int ret; - r.id = regidx; - switch (regidx & KVM_REG_SIZE_MASK) { case KVM_REG_SIZE_U32: - r.addr = (uintptr_t)&v32; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); + ret = kvm_get_one_reg(cs, regidx, &v32); if (!ret) { cpu->cpreg_values[i] = v32; } break; case KVM_REG_SIZE_U64: - r.addr = (uintptr_t)(cpu->cpreg_values + i); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, &r); + ret = kvm_get_one_reg(cs, regidx, cpu->cpreg_values + i); break; default: g_assert_not_reached(); @@ -589,7 +584,6 @@ bool write_list_to_kvmstate(ARMCPU *cpu, int level) bool ok = true; for (i = 0; i < cpu->cpreg_array_len; i++) { - struct kvm_one_reg r; uint64_t regidx = cpu->cpreg_indexes[i]; uint32_t v32; int ret; @@ -598,19 +592,17 @@ bool write_list_to_kvmstate(ARMCPU *cpu, int level) continue; } - r.id = regidx; switch (regidx & KVM_REG_SIZE_MASK) { case KVM_REG_SIZE_U32: v32 = cpu->cpreg_values[i]; - r.addr = (uintptr_t)&v32; + ret = kvm_set_one_reg(cs, regidx, &v32); break; case KVM_REG_SIZE_U64: - r.addr = (uintptr_t)(cpu->cpreg_values + i); + ret = kvm_set_one_reg(cs, regidx, cpu->cpreg_values + i); break; default: g_assert_not_reached(); } - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, &r); if (ret) { /* We might fail for "unknown register" and also for * "you tried to set a register which is constant with @@ -709,17 +701,13 @@ int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu) void kvm_arm_get_virtual_time(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); - struct kvm_one_reg reg = { - .id = KVM_REG_ARM_TIMER_CNT, - .addr = (uintptr_t)&cpu->kvm_vtime, - }; int ret; if (cpu->kvm_vtime_dirty) { return; } - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, KVM_REG_ARM_TIMER_CNT, &cpu->kvm_vtime); if (ret) { error_report("Failed to get KVM_REG_ARM_TIMER_CNT"); abort(); @@ -731,17 +719,13 @@ void kvm_arm_get_virtual_time(CPUState *cs) void kvm_arm_put_virtual_time(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); - struct kvm_one_reg reg = { - .id = KVM_REG_ARM_TIMER_CNT, - .addr = (uintptr_t)&cpu->kvm_vtime, - }; int ret; if (!cpu->kvm_vtime_dirty) { return; } - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, KVM_REG_ARM_TIMER_CNT, &cpu->kvm_vtime); if (ret) { error_report("Failed to set KVM_REG_ARM_TIMER_CNT"); abort(); diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index 5e95c496bb..4bb68646e4 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -30,7 +30,6 @@ #include "internals.h" #include "hw/acpi/acpi.h" #include "hw/acpi/ghes.h" -#include "hw/arm/virt.h" static bool have_guest_debug; @@ -540,14 +539,10 @@ static int kvm_arm_sve_set_vls(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); uint64_t vls[KVM_ARM64_SVE_VLS_WORDS] = { cpu->sve_vq.map }; - struct kvm_one_reg reg = { - .id = KVM_REG_ARM64_SVE_VLS, - .addr = (uint64_t)&vls[0], - }; assert(cpu->sve_max_vq <= KVM_ARM64_SVE_VQ_MAX); - return kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + return kvm_set_one_reg(cs, KVM_REG_ARM64_SVE_VLS, &vls[0]); } #define ARM_CPU_ID_MPIDR 3, 0, 0, 0, 5 @@ -726,19 +721,17 @@ static void kvm_inject_arm_sea(CPUState *c) static int kvm_arch_put_fpsimd(CPUState *cs) { CPUARMState *env = &ARM_CPU(cs)->env; - struct kvm_one_reg reg; int i, ret; for (i = 0; i < 32; i++) { uint64_t *q = aa64_vfp_qreg(env, i); #if HOST_BIG_ENDIAN uint64_t fp_val[2] = { q[1], q[0] }; - reg.addr = (uintptr_t)fp_val; + ret = kvm_set_one_reg(cs, AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]), + fp_val); #else - reg.addr = (uintptr_t)q; + ret = kvm_set_one_reg(cs, AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]), q); #endif - reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); if (ret) { return ret; } @@ -759,14 +752,11 @@ static int kvm_arch_put_sve(CPUState *cs) CPUARMState *env = &cpu->env; uint64_t tmp[ARM_MAX_VQ * 2]; uint64_t *r; - struct kvm_one_reg reg; int n, ret; for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) { r = sve_bswap64(tmp, &env->vfp.zregs[n].d[0], cpu->sve_max_vq * 2); - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, KVM_REG_ARM64_SVE_ZREG(n, 0), r); if (ret) { return ret; } @@ -775,9 +765,7 @@ static int kvm_arch_put_sve(CPUState *cs) for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) { r = sve_bswap64(tmp, r = &env->vfp.pregs[n].p[0], DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_PREG(n, 0); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, KVM_REG_ARM64_SVE_PREG(n, 0), r); if (ret) { return ret; } @@ -785,9 +773,7 @@ static int kvm_arch_put_sve(CPUState *cs) r = sve_bswap64(tmp, &env->vfp.pregs[FFR_PRED_NUM].p[0], DIV_ROUND_UP(cpu->sve_max_vq * 2, 8)); - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_FFR(0); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, KVM_REG_ARM64_SVE_FFR(0), r); if (ret) { return ret; } @@ -797,7 +783,6 @@ static int kvm_arch_put_sve(CPUState *cs) int kvm_arch_put_registers(CPUState *cs, int level) { - struct kvm_one_reg reg; uint64_t val; uint32_t fpr; int i, ret; @@ -814,9 +799,8 @@ int kvm_arch_put_registers(CPUState *cs, int level) } for (i = 0; i < 31; i++) { - reg.id = AARCH64_CORE_REG(regs.regs[i]); - reg.addr = (uintptr_t) &env->xregs[i]; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(regs.regs[i]), + &env->xregs[i]); if (ret) { return ret; } @@ -827,16 +811,12 @@ int kvm_arch_put_registers(CPUState *cs, int level) */ aarch64_save_sp(env, 1); - reg.id = AARCH64_CORE_REG(regs.sp); - reg.addr = (uintptr_t) &env->sp_el[0]; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(regs.sp), &env->sp_el[0]); if (ret) { return ret; } - reg.id = AARCH64_CORE_REG(sp_el1); - reg.addr = (uintptr_t) &env->sp_el[1]; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(sp_el1), &env->sp_el[1]); if (ret) { return ret; } @@ -847,23 +827,17 @@ int kvm_arch_put_registers(CPUState *cs, int level) } else { val = cpsr_read(env); } - reg.id = AARCH64_CORE_REG(regs.pstate); - reg.addr = (uintptr_t) &val; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(regs.pstate), &val); if (ret) { return ret; } - reg.id = AARCH64_CORE_REG(regs.pc); - reg.addr = (uintptr_t) &env->pc; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(regs.pc), &env->pc); if (ret) { return ret; } - reg.id = AARCH64_CORE_REG(elr_el1); - reg.addr = (uintptr_t) &env->elr_el[1]; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(elr_el1), &env->elr_el[1]); if (ret) { return ret; } @@ -882,9 +856,8 @@ int kvm_arch_put_registers(CPUState *cs, int level) /* KVM 0-4 map to QEMU banks 1-5 */ for (i = 0; i < KVM_NR_SPSR; i++) { - reg.id = AARCH64_CORE_REG(spsr[i]); - reg.addr = (uintptr_t) &env->banked_spsr[i + 1]; - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_CORE_REG(spsr[i]), + &env->banked_spsr[i + 1]); if (ret) { return ret; } @@ -899,18 +872,14 @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - reg.addr = (uintptr_t)(&fpr); fpr = vfp_get_fpsr(env); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_SIMD_CTRL_REG(fp_regs.fpsr), &fpr); if (ret) { return ret; } - reg.addr = (uintptr_t)(&fpr); fpr = vfp_get_fpcr(env); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); - ret = kvm_vcpu_ioctl(cs, KVM_SET_ONE_REG, ®); + ret = kvm_set_one_reg(cs, AARCH64_SIMD_CTRL_REG(fp_regs.fpcr), &fpr); if (ret) { return ret; } @@ -939,14 +908,11 @@ int kvm_arch_put_registers(CPUState *cs, int level) static int kvm_arch_get_fpsimd(CPUState *cs) { CPUARMState *env = &ARM_CPU(cs)->env; - struct kvm_one_reg reg; int i, ret; for (i = 0; i < 32; i++) { uint64_t *q = aa64_vfp_qreg(env, i); - reg.id = AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]); - reg.addr = (uintptr_t)q; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_SIMD_CORE_REG(fp_regs.vregs[i]), q); if (ret) { return ret; } else { @@ -970,15 +936,12 @@ static int kvm_arch_get_sve(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); CPUARMState *env = &cpu->env; - struct kvm_one_reg reg; uint64_t *r; int n, ret; for (n = 0; n < KVM_ARM64_SVE_NUM_ZREGS; ++n) { r = &env->vfp.zregs[n].d[0]; - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_ZREG(n, 0); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, KVM_REG_ARM64_SVE_ZREG(n, 0), r); if (ret) { return ret; } @@ -987,9 +950,7 @@ static int kvm_arch_get_sve(CPUState *cs) for (n = 0; n < KVM_ARM64_SVE_NUM_PREGS; ++n) { r = &env->vfp.pregs[n].p[0]; - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_PREG(n, 0); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, KVM_REG_ARM64_SVE_PREG(n, 0), r); if (ret) { return ret; } @@ -997,9 +958,7 @@ static int kvm_arch_get_sve(CPUState *cs) } r = &env->vfp.pregs[FFR_PRED_NUM].p[0]; - reg.addr = (uintptr_t)r; - reg.id = KVM_REG_ARM64_SVE_FFR(0); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, KVM_REG_ARM64_SVE_FFR(0), r); if (ret) { return ret; } @@ -1010,7 +969,6 @@ static int kvm_arch_get_sve(CPUState *cs) int kvm_arch_get_registers(CPUState *cs) { - struct kvm_one_reg reg; uint64_t val; unsigned int el; uint32_t fpr; @@ -1020,31 +978,24 @@ int kvm_arch_get_registers(CPUState *cs) CPUARMState *env = &cpu->env; for (i = 0; i < 31; i++) { - reg.id = AARCH64_CORE_REG(regs.regs[i]); - reg.addr = (uintptr_t) &env->xregs[i]; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(regs.regs[i]), + &env->xregs[i]); if (ret) { return ret; } } - reg.id = AARCH64_CORE_REG(regs.sp); - reg.addr = (uintptr_t) &env->sp_el[0]; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(regs.sp), &env->sp_el[0]); if (ret) { return ret; } - reg.id = AARCH64_CORE_REG(sp_el1); - reg.addr = (uintptr_t) &env->sp_el[1]; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(sp_el1), &env->sp_el[1]); if (ret) { return ret; } - reg.id = AARCH64_CORE_REG(regs.pstate); - reg.addr = (uintptr_t) &val; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(regs.pstate), &val); if (ret) { return ret; } @@ -1061,9 +1012,7 @@ int kvm_arch_get_registers(CPUState *cs) */ aarch64_restore_sp(env, 1); - reg.id = AARCH64_CORE_REG(regs.pc); - reg.addr = (uintptr_t) &env->pc; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(regs.pc), &env->pc); if (ret) { return ret; } @@ -1077,9 +1026,7 @@ int kvm_arch_get_registers(CPUState *cs) aarch64_sync_64_to_32(env); } - reg.id = AARCH64_CORE_REG(elr_el1); - reg.addr = (uintptr_t) &env->elr_el[1]; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(elr_el1), &env->elr_el[1]); if (ret) { return ret; } @@ -1089,9 +1036,8 @@ int kvm_arch_get_registers(CPUState *cs) * KVM SPSRs 0-4 map to QEMU banks 1-5 */ for (i = 0; i < KVM_NR_SPSR; i++) { - reg.id = AARCH64_CORE_REG(spsr[i]); - reg.addr = (uintptr_t) &env->banked_spsr[i + 1]; - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_CORE_REG(spsr[i]), + &env->banked_spsr[i + 1]); if (ret) { return ret; } @@ -1112,17 +1058,13 @@ int kvm_arch_get_registers(CPUState *cs) return ret; } - reg.addr = (uintptr_t)(&fpr); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpsr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_SIMD_CTRL_REG(fp_regs.fpsr), &fpr); if (ret) { return ret; } vfp_set_fpsr(env, fpr); - reg.addr = (uintptr_t)(&fpr); - reg.id = AARCH64_SIMD_CTRL_REG(fp_regs.fpcr); - ret = kvm_vcpu_ioctl(cs, KVM_GET_ONE_REG, ®); + ret = kvm_get_one_reg(cs, AARCH64_SIMD_CTRL_REG(fp_regs.fpcr), &fpr); if (ret) { return ret; } diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index 1f918ff537..0d5d8e307d 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -89,6 +89,10 @@ void aa32_max_features(ARMCPU *cpu) t = FIELD_DP32(t, ID_DFR0, COPSDBG, 9); /* FEAT_Debugv8p4 */ t = FIELD_DP32(t, ID_DFR0, PERFMON, 6); /* FEAT_PMUv3p5 */ cpu->isar.id_dfr0 = t; + + t = cpu->isar.id_dfr1; + t = FIELD_DP32(t, ID_DFR1, HPMN0, 1); /* FEAT_HPMN0 */ + cpu->isar.id_dfr1 = t; } /* CPU models. These are not needed for the AArch64 linux-user build. */ diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index 68928e5127..d978aa5f7a 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1109,6 +1109,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64dfr0; t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 9); /* FEAT_Debugv8p4 */ t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 6); /* FEAT_PMUv3p5 */ + t = FIELD_DP64(t, ID_AA64DFR0, HPMN0, 1); /* FEAT_HPMN0 */ cpu->isar.id_aa64dfr0 = t; t = cpu->isar.id_aa64smfr0; diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index 48927fbb8c..b3660173d1 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -7882,7 +7882,7 @@ static void op_addr_block_post(DisasContext *s, arg_ldst_block *a, } } -static bool op_stm(DisasContext *s, arg_ldst_block *a, int min_n) +static bool op_stm(DisasContext *s, arg_ldst_block *a) { int i, j, n, list, mem_idx; bool user = a->u; @@ -7899,7 +7899,14 @@ static bool op_stm(DisasContext *s, arg_ldst_block *a, int min_n) list = a->list; n = ctpop16(list); - if (n < min_n || a->rn == 15) { + /* + * This is UNPREDICTABLE for n < 1 in all encodings, and we choose + * to UNDEF. In the T32 STM encoding n == 1 is also UNPREDICTABLE, + * but hardware treats it like the A32 version and implements the + * single-register-store, and some in-the-wild (buggy) software + * assumes that, so we don't UNDEF on that case. + */ + if (n < 1 || a->rn == 15) { unallocated_encoding(s); return true; } @@ -7935,8 +7942,7 @@ static bool op_stm(DisasContext *s, arg_ldst_block *a, int min_n) static bool trans_STM(DisasContext *s, arg_ldst_block *a) { - /* BitCount(list) < 1 is UNPREDICTABLE */ - return op_stm(s, a, 1); + return op_stm(s, a); } static bool trans_STM_t32(DisasContext *s, arg_ldst_block *a) @@ -7946,11 +7952,10 @@ static bool trans_STM_t32(DisasContext *s, arg_ldst_block *a) unallocated_encoding(s); return true; } - /* BitCount(list) < 2 is UNPREDICTABLE */ - return op_stm(s, a, 2); + return op_stm(s, a); } -static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n) +static bool do_ldm(DisasContext *s, arg_ldst_block *a) { int i, j, n, list, mem_idx; bool loaded_base; @@ -7979,7 +7984,14 @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n) list = a->list; n = ctpop16(list); - if (n < min_n || a->rn == 15) { + /* + * This is UNPREDICTABLE for n < 1 in all encodings, and we choose + * to UNDEF. In the T32 LDM encoding n == 1 is also UNPREDICTABLE, + * but hardware treats it like the A32 version and implements the + * single-register-load, and some in-the-wild (buggy) software + * assumes that, so we don't UNDEF on that case. + */ + if (n < 1 || a->rn == 15) { unallocated_encoding(s); return true; } @@ -8045,8 +8057,7 @@ static bool trans_LDM_a32(DisasContext *s, arg_ldst_block *a) unallocated_encoding(s); return true; } - /* BitCount(list) < 1 is UNPREDICTABLE */ - return do_ldm(s, a, 1); + return do_ldm(s, a); } static bool trans_LDM_t32(DisasContext *s, arg_ldst_block *a) @@ -8056,16 +8067,14 @@ static bool trans_LDM_t32(DisasContext *s, arg_ldst_block *a) unallocated_encoding(s); return true; } - /* BitCount(list) < 2 is UNPREDICTABLE */ - return do_ldm(s, a, 2); + return do_ldm(s, a); } static bool trans_LDM_t16(DisasContext *s, arg_ldst_block *a) { /* Writeback is conditional on the base register not being loaded. */ a->w = !(a->list & (1 << a->rn)); - /* BitCount(list) < 1 is UNPREDICTABLE */ - return do_ldm(s, a, 1); + return do_ldm(s, a); } static bool trans_CLRM(DisasContext *s, arg_CLRM *a) diff --git a/target/hexagon/hex_common.py b/target/hexagon/hex_common.py index dce1b852a7..0da65d6dd6 100755 --- a/target/hexagon/hex_common.py +++ b/target/hexagon/hex_common.py @@ -45,7 +45,7 @@ regre = re.compile(r"((?<!DUP)[MNORCPQXSGVZA])([stuvwxyzdefg]+)([.]?[LlHh]?)(\d+ immre = re.compile(r"[#]([rRsSuUm])(\d+)(?:[:](\d+))?") reg_or_immre = re.compile( r"(((?<!DUP)[MNRCOPQXSGVZA])([stuvwxyzdefg]+)" - + "([.]?[LlHh]?)(\d+S?))|([#]([rRsSuUm])(\d+)[:]?(\d+)?)" + r"([.]?[LlHh]?)(\d+S?))|([#]([rRsSuUm])(\d+)[:]?(\d+)?)" ) relimmre = re.compile(r"[#]([rR])(\d+)(?:[:](\d+))?") absimmre = re.compile(r"[#]([sSuUm])(\d+)(?:[:](\d+))?") @@ -337,7 +337,7 @@ def read_attribs_file(name): def read_overrides_file(name): - overridere = re.compile("#define fGEN_TCG_([A-Za-z0-9_]+)\(.*") + overridere = re.compile(r"#define fGEN_TCG_([A-Za-z0-9_]+)\(.*") for line in open(name, "rt").readlines(): if not overridere.match(line): continue diff --git a/target/i386/arch_memory_mapping.c b/target/i386/arch_memory_mapping.c index 271cb5e41b..d1ff659128 100644 --- a/target/i386/arch_memory_mapping.c +++ b/target/i386/arch_memory_mapping.c @@ -266,7 +266,7 @@ static void walk_pml5e(MemoryMappingList *list, AddressSpace *as, } #endif -void x86_cpu_get_memory_mapping(CPUState *cs, MemoryMappingList *list, +bool x86_cpu_get_memory_mapping(CPUState *cs, MemoryMappingList *list, Error **errp) { X86CPU *cpu = X86_CPU(cs); @@ -275,7 +275,7 @@ void x86_cpu_get_memory_mapping(CPUState *cs, MemoryMappingList *list, if (!cpu_paging_enabled(cs)) { /* paging is disabled */ - return; + return true; } a20_mask = x86_get_a20_mask(env); @@ -310,5 +310,7 @@ void x86_cpu_get_memory_mapping(CPUState *cs, MemoryMappingList *list, pse = !!(env->cr[4] & CR4_PSE_MASK); walk_pde2(list, cs->as, pde_addr, a20_mask, pse); } + + return true; } diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 3aab05ddad..bdca901dfa 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -778,6 +778,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { }, .cpuid = {.eax = 1, .reg = R_EDX, }, .tcg_features = TCG_FEATURES, + .no_autoenable_flags = CPUID_HT, }, [FEAT_1_ECX] = { .type = CPUID_FEATURE_WORD, diff --git a/target/i386/cpu.h b/target/i386/cpu.h index e1875466b9..471e71dbc5 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -2055,7 +2055,7 @@ int x86_cpu_write_elf64_qemunote(WriteCoreDumpFunction f, CPUState *cpu, int x86_cpu_write_elf32_qemunote(WriteCoreDumpFunction f, CPUState *cpu, DumpState *s); -void x86_cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, +bool x86_cpu_get_memory_mapping(CPUState *cpu, MemoryMappingList *list, Error **errp); void x86_cpu_dump_state(CPUState *cs, FILE *f, int flags); diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index f6c7f7e268..ab72bcdfad 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -373,6 +373,8 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function, if (function == 1 && reg == R_EDX) { /* KVM before 2.6.30 misreports the following features */ ret |= CPUID_MTRR | CPUID_PAT | CPUID_MCE | CPUID_MCA; + /* KVM never reports CPUID_HT but QEMU can support when vcpus > 1 */ + ret |= CPUID_HT; } else if (function == 1 && reg == R_ECX) { /* We can set the hypervisor flag, even if KVM does not return it on * GET_SUPPORTED_CPUID diff --git a/target/i386/svm.h b/target/i386/svm.h index f9a785489d..1bd7844730 100644 --- a/target/i386/svm.h +++ b/target/i386/svm.h @@ -132,6 +132,7 @@ /* only included in documentation, maybe wrong */ #define SVM_EXIT_MONITOR 0x08a #define SVM_EXIT_MWAIT 0x08b +#define SVM_EXIT_XSETBV 0x08d #define SVM_EXIT_NPF 0x400 #define SVM_EXIT_ERR -1 diff --git a/target/i386/tcg/seg_helper.c b/target/i386/tcg/seg_helper.c index 2b92aee207..eb29a1fd4e 100644 --- a/target/i386/tcg/seg_helper.c +++ b/target/i386/tcg/seg_helper.c @@ -229,7 +229,7 @@ static void tss_load_seg(CPUX86State *env, X86Seg seg_reg, int selector, static void tss_set_busy(CPUX86State *env, int tss_selector, bool value, uintptr_t retaddr) { - target_ulong ptr = env->gdt.base + (env->tr.selector & ~7); + target_ulong ptr = env->gdt.base + (tss_selector & ~7); uint32_t e2 = cpu_ldl_kernel_ra(env, ptr + 4, retaddr); if (value) { diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index d2061ec44a..4f6f9fa7e5 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -5916,6 +5916,7 @@ static bool disas_insn(DisasContext *s, CPUState *cpu) | PREFIX_REPZ | PREFIX_REPNZ))) { goto illegal_op; } + gen_svm_check_intercept(s, SVM_EXIT_XSETBV); if (!check_cpl0(s)) { break; } diff --git a/target/loongarch/cpu.h b/target/loongarch/cpu.h index 40e70a8119..8b54cf109c 100644 --- a/target/loongarch/cpu.h +++ b/target/loongarch/cpu.h @@ -458,11 +458,11 @@ static inline void set_pc(CPULoongArchState *env, uint64_t value) * LoongArch CPUs hardware flags. */ #define HW_FLAGS_PLV_MASK R_CSR_CRMD_PLV_MASK /* 0x03 */ -#define HW_FLAGS_CRMD_PG R_CSR_CRMD_PG_MASK /* 0x10 */ #define HW_FLAGS_EUEN_FPE 0x04 #define HW_FLAGS_EUEN_SXE 0x08 -#define HW_FLAGS_EUEN_ASXE 0x10 +#define HW_FLAGS_CRMD_PG R_CSR_CRMD_PG_MASK /* 0x10 */ #define HW_FLAGS_VA32 0x20 +#define HW_FLAGS_EUEN_ASXE 0x40 static inline void cpu_get_tb_cpu_state(CPULoongArchState *env, vaddr *pc, uint64_t *cs_base, uint32_t *flags) diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c index c8a29eac2b..2040f3e44d 100644 --- a/target/loongarch/disas.c +++ b/target/loongarch/disas.c @@ -190,6 +190,12 @@ static void output_hint_r_i(DisasContext *ctx, arg_hint_r_i *a, output(ctx, mnemonic, "%d, r%d, %d", a->hint, a->rj, a->imm); } +static void output_hint_rr(DisasContext *ctx, arg_hint_rr *a, + const char *mnemonic) +{ + output(ctx, mnemonic, "%d, r%d, r%d", a->hint, a->rj, a->rk); +} + static void output_i(DisasContext *ctx, arg_i *a, const char *mnemonic) { output(ctx, mnemonic, "%d", a->imm); @@ -549,6 +555,7 @@ INSN(ld_bu, rr_i) INSN(ld_hu, rr_i) INSN(ld_wu, rr_i) INSN(preld, hint_r_i) +INSN(preldx, hint_rr) INSN(fld_s, fr_i) INSN(fst_s, fr_i) INSN(fld_d, fr_i) diff --git a/target/loongarch/insn_trans/trans_memory.c.inc b/target/loongarch/insn_trans/trans_memory.c.inc index c3de1404ea..42f4e74012 100644 --- a/target/loongarch/insn_trans/trans_memory.c.inc +++ b/target/loongarch/insn_trans/trans_memory.c.inc @@ -110,6 +110,11 @@ static bool trans_preld(DisasContext *ctx, arg_preld *a) return true; } +static bool trans_preldx(DisasContext *ctx, arg_preldx * a) +{ + return true; +} + static bool trans_dbar(DisasContext *ctx, arg_dbar * a) { tcg_gen_mb(TCG_BAR_SC | TCG_MO_ALL); diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode index 64b308f9fb..62f58cc541 100644 --- a/target/loongarch/insns.decode +++ b/target/loongarch/insns.decode @@ -24,6 +24,7 @@ &rrr rd rj rk &rr_i rd rj imm &hint_r_i hint rj imm +&hint_rr hint rj rk &rrr_sa rd rj rk sa &rr_ms_ls rd rj ms ls &ff fd fj @@ -69,6 +70,7 @@ @rr_i16 .... .. imm:s16 rj:5 rd:5 &rr_i @rr_i16s2 .... .. ................ rj:5 rd:5 &rr_i imm=%offs16 @hint_r_i12 .... ...... imm:s12 rj:5 hint:5 &hint_r_i +@hint_rr .... ........ ..... rk:5 rj:5 hint:5 &hint_rr @rrr_sa2p1 .... ........ ... .. rk:5 rj:5 rd:5 &rrr_sa sa=%sa2p1 @rrr_sa2 .... ........ ... sa:2 rk:5 rj:5 rd:5 &rrr_sa @rrr_sa3 .... ........ .. sa:3 rk:5 rj:5 rd:5 &rrr_sa @@ -228,6 +230,7 @@ ldx_bu 0011 10000010 00000 ..... ..... ..... @rrr ldx_hu 0011 10000010 01000 ..... ..... ..... @rrr ldx_wu 0011 10000010 10000 ..... ..... ..... @rrr preld 0010 101011 ............ ..... ..... @hint_r_i12 +preldx 0011 10000010 11000 ..... ..... ..... @hint_rr dbar 0011 10000111 00100 ............... @i15 ibar 0011 10000111 00101 ............... @i15 ldptr_w 0010 0100 .............. ..... ..... @rr_i14s2 diff --git a/target/mips/cpu.h b/target/mips/cpu.h index 67f8e8b988..5fddceff3a 100644 --- a/target/mips/cpu.h +++ b/target/mips/cpu.h @@ -1345,11 +1345,10 @@ uint64_t cpu_mips_phys_to_kseg1(void *opaque, uint64_t addr); #if !defined(CONFIG_USER_ONLY) -/* mips_int.c */ +/* HW declaration specific to the MIPS target */ void cpu_mips_soft_irq(CPUMIPSState *env, int irq, int level); - -/* mips_itu.c */ -void itc_reconfigure(struct MIPSITUState *tag); +void cpu_mips_irq_init_cpu(MIPSCPU *cpu); +void cpu_mips_clock_init(MIPSCPU *cpu); #endif /* !CONFIG_USER_ONLY */ diff --git a/target/mips/sysemu/cp0_timer.c b/target/mips/sysemu/cp0_timer.c index 9d2bcb0dea..62de502caa 100644 --- a/target/mips/sysemu/cp0_timer.c +++ b/target/mips/sysemu/cp0_timer.c @@ -22,7 +22,6 @@ #include "qemu/osdep.h" #include "hw/irq.h" -#include "hw/mips/cpudevs.h" #include "qemu/timer.h" #include "sysemu/kvm.h" #include "internal.h" diff --git a/target/mips/tcg/sysemu/cp0_helper.c b/target/mips/tcg/sysemu/cp0_helper.c index 5da1124589..d349548743 100644 --- a/target/mips/tcg/sysemu/cp0_helper.c +++ b/target/mips/tcg/sysemu/cp0_helper.c @@ -28,6 +28,7 @@ #include "qemu/host-utils.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" +#include "hw/misc/mips_itu.h" /* SMP helpers. */ diff --git a/target/mips/tcg/sysemu/tlb_helper.c b/target/mips/tcg/sysemu/tlb_helper.c index 7dbc2e24c4..4ede904800 100644 --- a/target/mips/tcg/sysemu/tlb_helper.c +++ b/target/mips/tcg/sysemu/tlb_helper.c @@ -24,7 +24,6 @@ #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/log.h" -#include "hw/mips/cpudevs.h" #include "exec/helper-proto.h" /* TLB management */ diff --git a/tests/avocado/acpi-bits.py b/tests/avocado/acpi-bits.py index bb3f818689..eca13dc518 100644 --- a/tests/avocado/acpi-bits.py +++ b/tests/avocado/acpi-bits.py @@ -92,17 +92,14 @@ class QEMUBitsMachine(QEMUMachine): # pylint: disable=too-few-public-methods base_temp_dir: str = "/var/tmp", debugcon_log: str = "debugcon-log.txt", debugcon_addr: str = "0x403", - sock_dir: Optional[str] = None, qmp_timer: Optional[float] = None): # pylint: disable=too-many-arguments if name is None: name = "qemu-bits-%d" % os.getpid() - if sock_dir is None: - sock_dir = base_temp_dir super().__init__(binary, args, wrapper=wrapper, name=name, base_temp_dir=base_temp_dir, - sock_dir=sock_dir, qmp_timer=qmp_timer) + qmp_timer=qmp_timer) self.debugcon_log = debugcon_log self.debugcon_addr = debugcon_addr self.base_temp_dir = base_temp_dir diff --git a/tests/avocado/avocado_qemu/__init__.py b/tests/avocado/avocado_qemu/__init__.py index 0172a359b7..d71e989db6 100644 --- a/tests/avocado/avocado_qemu/__init__.py +++ b/tests/avocado/avocado_qemu/__init__.py @@ -322,7 +322,7 @@ class QemuSystemTest(QemuBaseTest): def _new_vm(self, name, *args): self._sd = tempfile.TemporaryDirectory(prefix="qemu_") vm = QEMUMachine(self.qemu_bin, base_temp_dir=self.workdir, - sock_dir=self._sd.name, log_dir=self.logdir) + log_dir=self.logdir) self.log.debug('QEMUMachine "%s" created', name) self.log.debug('QEMUMachine "%s" temp_dir: %s', name, vm.temp_dir) self.log.debug('QEMUMachine "%s" log_dir: %s', name, vm.log_dir) @@ -408,8 +408,8 @@ class LinuxSSHMixIn: def ssh_connect(self, username, credential, credential_is_key=True): self.ssh_logger = logging.getLogger('ssh') - res = self.vm.command('human-monitor-command', - command_line='info usernet') + res = self.vm.cmd('human-monitor-command', + command_line='info usernet') port = get_info_usernet_hostfwd_port(res) self.assertIsNotNone(port) self.assertGreater(port, 0) diff --git a/tests/avocado/cpu_queries.py b/tests/avocado/cpu_queries.py index cf69f69b11..86c2d5c92d 100644 --- a/tests/avocado/cpu_queries.py +++ b/tests/avocado/cpu_queries.py @@ -23,12 +23,13 @@ class QueryCPUModelExpansion(QemuSystemTest): self.vm.add_args('-S') self.vm.launch() - cpus = self.vm.command('query-cpu-definitions') + cpus = self.vm.cmd('query-cpu-definitions') for c in cpus: self.log.info("Checking CPU: %s", c) self.assertNotIn('', c['unavailable-features'], c['name']) for c in cpus: model = {'name': c['name']} - e = self.vm.command('query-cpu-model-expansion', model=model, type='full') + e = self.vm.cmd('query-cpu-model-expansion', model=model, + type='full') self.assertEquals(e['model']['name'], c['name']) diff --git a/tests/avocado/hotplug_cpu.py b/tests/avocado/hotplug_cpu.py index 6374bf1b54..292bb43e4d 100644 --- a/tests/avocado/hotplug_cpu.py +++ b/tests/avocado/hotplug_cpu.py @@ -29,9 +29,9 @@ class HotPlugCPU(LinuxTest): with self.assertRaises(AssertionError): self.ssh_command('test -e /sys/devices/system/cpu/cpu1') - self.vm.command('device_add', - driver='Haswell-x86_64-cpu', - socket_id=0, - core_id=1, - thread_id=0) + self.vm.cmd('device_add', + driver='Haswell-x86_64-cpu', + socket_id=0, + core_id=1, + thread_id=0) self.ssh_command('test -e /sys/devices/system/cpu/cpu1') diff --git a/tests/avocado/info_usernet.py b/tests/avocado/info_usernet.py index fdc4d90c42..e1aa7a6e0a 100644 --- a/tests/avocado/info_usernet.py +++ b/tests/avocado/info_usernet.py @@ -22,8 +22,8 @@ class InfoUsernet(QemuSystemTest): self.require_netdev('user') self.vm.add_args('-netdev', 'user,id=vnet,hostfwd=:127.0.0.1:0-:22') self.vm.launch() - res = self.vm.command('human-monitor-command', - command_line='info usernet') + res = self.vm.cmd('human-monitor-command', + command_line='info usernet') port = get_info_usernet_hostfwd_port(res) self.assertIsNotNone(port, ('"info usernet" output content does not seem to ' diff --git a/tests/avocado/machine_arm_integratorcp.py b/tests/avocado/machine_arm_integratorcp.py index 1ffe1073ef..87f5cf3953 100644 --- a/tests/avocado/machine_arm_integratorcp.py +++ b/tests/avocado/machine_arm_integratorcp.py @@ -81,9 +81,9 @@ class IntegratorMachine(QemuSystemTest): self.boot_integratorcp() framebuffer_ready = 'Console: switching to colour frame buffer device' wait_for_console_pattern(self, framebuffer_ready) - self.vm.command('human-monitor-command', command_line='stop') - self.vm.command('human-monitor-command', - command_line='screendump %s' % screendump_path) + self.vm.cmd('human-monitor-command', command_line='stop') + self.vm.cmd('human-monitor-command', + command_line='screendump %s' % screendump_path) logger = logging.getLogger('framebuffer') cpu_count = 1 diff --git a/tests/avocado/machine_aspeed.py b/tests/avocado/machine_aspeed.py index 90f1b7cb77..df31b2a8a8 100644 --- a/tests/avocado/machine_aspeed.py +++ b/tests/avocado/machine_aspeed.py @@ -181,8 +181,8 @@ class AST2x00Machine(QemuSystemTest): 'i2c i2c-3: new_device: Instantiated device lm75 at 0x4d'); exec_command_and_wait_for_pattern(self, 'cat /sys/class/hwmon/hwmon1/temp1_input', '0') - self.vm.command('qom-set', path='/machine/peripheral/tmp-test', - property='temperature', value=18000); + self.vm.cmd('qom-set', path='/machine/peripheral/tmp-test', + property='temperature', value=18000); exec_command_and_wait_for_pattern(self, 'cat /sys/class/hwmon/hwmon1/temp1_input', '18000') @@ -213,8 +213,8 @@ class AST2x00Machine(QemuSystemTest): 'i2c i2c-3: new_device: Instantiated device lm75 at 0x4d'); exec_command_and_wait_for_pattern(self, 'cat /sys/class/hwmon/hwmon0/temp1_input', '0') - self.vm.command('qom-set', path='/machine/peripheral/tmp-test', - property='temperature', value=18000); + self.vm.cmd('qom-set', path='/machine/peripheral/tmp-test', + property='temperature', value=18000); exec_command_and_wait_for_pattern(self, 'cat /sys/class/hwmon/hwmon0/temp1_input', '18000') @@ -247,7 +247,10 @@ class AST2x00Machine(QemuSystemTest): image_path = self.fetch_asset(image_url, asset_hash=image_hash, algorithm='sha256') - socket = os.path.join(self.vm.sock_dir, 'swtpm-socket') + # force creation of VM object, which also defines self._sd + vm = self.vm + + socket = os.path.join(self._sd.name, 'swtpm-socket') subprocess.run(['swtpm', 'socket', '-d', '--tpm2', '--tpmstate', f'dir={self.vm.temp_dir}', @@ -357,8 +360,8 @@ class AST2x00MachineSDK(QemuSystemTest, LinuxSSHMixIn): 'i2c i2c-5: new_device: Instantiated device lm75 at 0x4d'); self.ssh_command_output_contains( 'cat /sys/class/hwmon/hwmon19/temp1_input', '0') - self.vm.command('qom-set', path='/machine/peripheral/tmp-test', - property='temperature', value=18000); + self.vm.cmd('qom-set', path='/machine/peripheral/tmp-test', + property='temperature', value=18000); self.ssh_command_output_contains( 'cat /sys/class/hwmon/hwmon19/temp1_input', '18000') diff --git a/tests/avocado/machine_m68k_nextcube.py b/tests/avocado/machine_m68k_nextcube.py index 6790e7d9cd..d6da2fbb01 100644 --- a/tests/avocado/machine_m68k_nextcube.py +++ b/tests/avocado/machine_m68k_nextcube.py @@ -43,8 +43,8 @@ class NextCubeMachine(QemuSystemTest): # 'displaysurface_create 1120x832' trace-event. time.sleep(2) - self.vm.command('human-monitor-command', - command_line='screendump %s' % screenshot_path) + self.vm.cmd('human-monitor-command', + command_line='screendump %s' % screenshot_path) @skipUnless(PIL_AVAILABLE, 'Python PIL not installed') def test_bootrom_framebuffer_size(self): diff --git a/tests/avocado/machine_mips_malta.py b/tests/avocado/machine_mips_malta.py index 92233451c5..9bd54518bf 100644 --- a/tests/avocado/machine_mips_malta.py +++ b/tests/avocado/machine_mips_malta.py @@ -71,9 +71,9 @@ class MaltaMachineFramebuffer(QemuSystemTest): framebuffer_ready = 'Console: switching to colour frame buffer device' wait_for_console_pattern(self, framebuffer_ready, failure_message='Kernel panic - not syncing') - self.vm.command('human-monitor-command', command_line='stop') - self.vm.command('human-monitor-command', - command_line='screendump %s' % screendump_path) + self.vm.cmd('human-monitor-command', command_line='stop') + self.vm.cmd('human-monitor-command', + command_line='screendump %s' % screendump_path) logger = logging.getLogger('framebuffer') match_threshold = 0.95 diff --git a/tests/avocado/machine_s390_ccw_virtio.py b/tests/avocado/machine_s390_ccw_virtio.py index e7a2a20ba6..e1f493bc44 100644 --- a/tests/avocado/machine_s390_ccw_virtio.py +++ b/tests/avocado/machine_s390_ccw_virtio.py @@ -107,10 +107,10 @@ class S390CCWVirtioMachine(QemuSystemTest): 'dd if=/dev/hwrng of=/dev/null bs=1k count=10', '10+0 records out') self.clear_guest_dmesg() - self.vm.command('device_del', id='rn1') + self.vm.cmd('device_del', id='rn1') self.wait_for_crw_reports() self.clear_guest_dmesg() - self.vm.command('device_del', id='rn2') + self.vm.cmd('device_del', id='rn2') self.wait_for_crw_reports() exec_command_and_wait_for_pattern(self, 'dd if=/dev/hwrng of=/dev/null bs=1k count=10', @@ -132,8 +132,8 @@ class S390CCWVirtioMachine(QemuSystemTest): '0x0000000c') # add another device self.clear_guest_dmesg() - self.vm.command('device_add', driver='virtio-net-ccw', - devno='fe.0.4711', id='net_4711') + self.vm.cmd('device_add', driver='virtio-net-ccw', + devno='fe.0.4711', id='net_4711') self.wait_for_crw_reports() exec_command_and_wait_for_pattern(self, 'for i in 1 2 3 4 5 6 7 ; do ' 'if [ -e /sys/bus/ccw/devices/*4711 ]; then break; fi ;' @@ -141,7 +141,7 @@ class S390CCWVirtioMachine(QemuSystemTest): '0.0.4711') # and detach it again self.clear_guest_dmesg() - self.vm.command('device_del', id='net_4711') + self.vm.cmd('device_del', id='net_4711') self.vm.event_wait(name='DEVICE_DELETED', match={'data': {'device': 'net_4711'}}) self.wait_for_crw_reports() @@ -151,10 +151,10 @@ class S390CCWVirtioMachine(QemuSystemTest): # test the virtio-balloon device exec_command_and_wait_for_pattern(self, 'head -n 1 /proc/meminfo', 'MemTotal: 115640 kB') - self.vm.command('human-monitor-command', command_line='balloon 96') + self.vm.cmd('human-monitor-command', command_line='balloon 96') exec_command_and_wait_for_pattern(self, 'head -n 1 /proc/meminfo', 'MemTotal: 82872 kB') - self.vm.command('human-monitor-command', command_line='balloon 128') + self.vm.cmd('human-monitor-command', command_line='balloon 128') exec_command_and_wait_for_pattern(self, 'head -n 1 /proc/meminfo', 'MemTotal: 115640 kB') @@ -245,7 +245,7 @@ class S390CCWVirtioMachine(QemuSystemTest): '12+0 records out') with tempfile.NamedTemporaryFile(suffix='.ppm', prefix='qemu-scrdump-') as ppmfile: - self.vm.command('screendump', filename=ppmfile.name) + self.vm.cmd('screendump', filename=ppmfile.name) ppmfile.seek(0) line = ppmfile.readline() self.assertEqual(line, b"P6\n") @@ -261,16 +261,16 @@ class S390CCWVirtioMachine(QemuSystemTest): # Hot-plug a virtio-crypto device and see whether it gets accepted self.log.info("Test hot-plug virtio-crypto device") self.clear_guest_dmesg() - self.vm.command('object-add', qom_type='cryptodev-backend-builtin', - id='cbe0') - self.vm.command('device_add', driver='virtio-crypto-ccw', id='crypdev0', - cryptodev='cbe0', devno='fe.0.2342') + self.vm.cmd('object-add', qom_type='cryptodev-backend-builtin', + id='cbe0') + self.vm.cmd('device_add', driver='virtio-crypto-ccw', id='crypdev0', + cryptodev='cbe0', devno='fe.0.2342') exec_command_and_wait_for_pattern(self, 'while ! (dmesg -c | grep Accelerator.device) ; do' ' sleep 1 ; done', 'Accelerator device is ready') exec_command_and_wait_for_pattern(self, 'lscss', '0.0.2342') - self.vm.command('device_del', id='crypdev0') - self.vm.command('object-del', id='cbe0') + self.vm.cmd('device_del', id='crypdev0') + self.vm.cmd('object-del', id='cbe0') exec_command_and_wait_for_pattern(self, 'while ! (dmesg -c | grep Start.virtcrypto_remove) ; do' ' sleep 1 ; done', 'Start virtcrypto_remove.') diff --git a/tests/avocado/migration.py b/tests/avocado/migration.py index fdc1d234fb..09b62f813e 100644 --- a/tests/avocado/migration.py +++ b/tests/avocado/migration.py @@ -30,7 +30,7 @@ class MigrationTest(QemuSystemTest): @staticmethod def migration_finished(vm): - return vm.command('query-migrate')['status'] in ('completed', 'failed') + return vm.cmd('query-migrate')['status'] in ('completed', 'failed') def assert_migration(self, src_vm, dst_vm): wait.wait_for(self.migration_finished, @@ -41,10 +41,10 @@ class MigrationTest(QemuSystemTest): timeout=self.timeout, step=0.1, args=(dst_vm,)) - self.assertEqual(src_vm.command('query-migrate')['status'], 'completed') - self.assertEqual(dst_vm.command('query-migrate')['status'], 'completed') - self.assertEqual(dst_vm.command('query-status')['status'], 'running') - self.assertEqual(src_vm.command('query-status')['status'],'postmigrate') + self.assertEqual(src_vm.cmd('query-migrate')['status'], 'completed') + self.assertEqual(dst_vm.cmd('query-migrate')['status'], 'completed') + self.assertEqual(dst_vm.cmd('query-status')['status'], 'running') + self.assertEqual(src_vm.cmd('query-status')['status'],'postmigrate') def do_migrate(self, dest_uri, src_uri=None): dest_vm = self.get_vm('-incoming', dest_uri) diff --git a/tests/avocado/pc_cpu_hotplug_props.py b/tests/avocado/pc_cpu_hotplug_props.py index 52b878188e..b56f51d02a 100644 --- a/tests/avocado/pc_cpu_hotplug_props.py +++ b/tests/avocado/pc_cpu_hotplug_props.py @@ -32,4 +32,4 @@ class OmittedCPUProps(QemuSystemTest): self.vm.add_args('-smp', '1,sockets=2,cores=2,threads=2,maxcpus=8') self.vm.add_args('-device', 'qemu64-x86_64-cpu,socket-id=1,core-id=0,thread-id=0') self.vm.launch() - self.assertEquals(len(self.vm.command('query-cpus-fast')), 2) + self.assertEquals(len(self.vm.cmd('query-cpus-fast')), 2) diff --git a/tests/avocado/version.py b/tests/avocado/version.py index dd775955eb..93ffdf3d97 100644 --- a/tests/avocado/version.py +++ b/tests/avocado/version.py @@ -20,6 +20,6 @@ class Version(QemuSystemTest): def test_qmp_human_info_version(self): self.vm.add_args('-nodefaults') self.vm.launch() - res = self.vm.command('human-monitor-command', - command_line='info version') + res = self.vm.cmd('human-monitor-command', + command_line='info version') self.assertRegexpMatches(res, r'^(\d+\.\d+\.\d)') diff --git a/tests/avocado/virtio_check_params.py b/tests/avocado/virtio_check_params.py index 4093da8a67..5fe370a179 100644 --- a/tests/avocado/virtio_check_params.py +++ b/tests/avocado/virtio_check_params.py @@ -43,7 +43,7 @@ VM_DEV_PARAMS = {'virtio-scsi-pci': ['-device', 'virtio-scsi-pci,id=scsi0'], class VirtioMaxSegSettingsCheck(QemuSystemTest): @staticmethod def make_pattern(props): - pattern_items = ['{0} = \w+'.format(prop) for prop in props] + pattern_items = [r'{0} = \w+'.format(prop) for prop in props] return '|'.join(pattern_items) def query_virtqueue(self, vm, dev_type_name): @@ -51,8 +51,8 @@ class VirtioMaxSegSettingsCheck(QemuSystemTest): error = None props = None - output = vm.command('human-monitor-command', - command_line = 'info qtree') + output = vm.cmd('human-monitor-command', + command_line = 'info qtree') props_list = DEV_TYPES[dev_type_name].values(); pattern = self.make_pattern(props_list) res = re.findall(pattern, output) @@ -121,7 +121,7 @@ class VirtioMaxSegSettingsCheck(QemuSystemTest): # collect all machine types except 'none', 'isapc', 'microvm' with QEMUMachine(self.qemu_bin) as vm: vm.launch() - machines = [m['name'] for m in vm.command('query-machines')] + machines = [m['name'] for m in vm.cmd('query-machines')] vm.shutdown() machines.remove('none') machines.remove('isapc') diff --git a/tests/avocado/virtio_version.py b/tests/avocado/virtio_version.py index c84e48813a..afe5e828b5 100644 --- a/tests/avocado/virtio_version.py +++ b/tests/avocado/virtio_version.py @@ -48,7 +48,8 @@ def pci_modern_device_id(virtio_devid): return virtio_devid + 0x1040 def devtype_implements(vm, devtype, implements): - return devtype in [d['name'] for d in vm.command('qom-list-types', implements=implements)] + return devtype in [d['name'] for d in + vm.cmd('qom-list-types', implements=implements)] def get_pci_interfaces(vm, devtype): interfaces = ('pci-express-device', 'conventional-pci-device') @@ -78,7 +79,7 @@ class VirtioVersionCheck(QemuSystemTest): vm.add_args('-S') vm.launch() - pcibuses = vm.command('query-pci') + pcibuses = vm.cmd('query-pci') alldevs = [dev for bus in pcibuses for dev in bus['devices']] devfortest = [dev for dev in alldevs if dev['qdev_id'] == 'devfortest'] diff --git a/tests/avocado/vnc.py b/tests/avocado/vnc.py index aeeefc70be..862c8996a8 100644 --- a/tests/avocado/vnc.py +++ b/tests/avocado/vnc.py @@ -88,9 +88,8 @@ class Vnc(QemuSystemTest): self.vm.add_args('-nodefaults', '-S', '-vnc', ':0,password=on') self.vm.launch() self.assertTrue(self.vm.qmp('query-vnc')['return']['enabled']) - set_password_response = self.vm.qmp('change-vnc-password', - password='new_password') - self.assertEqual(set_password_response['return'], {}) + self.vm.cmd('change-vnc-password', + password='new_password') def test_change_listen(self): a, b, c = find_free_ports(3) @@ -105,12 +104,11 @@ class Vnc(QemuSystemTest): self.assertFalse(check_connect(b)) self.assertFalse(check_connect(c)) - res = self.vm.qmp('display-update', type='vnc', - addresses=[{'type': 'inet', 'host': VNC_ADDR, - 'port': str(b)}, - {'type': 'inet', 'host': VNC_ADDR, - 'port': str(c)}]) - self.assertEqual(res['return'], {}) + self.vm.cmd('display-update', type='vnc', + addresses=[{'type': 'inet', 'host': VNC_ADDR, + 'port': str(b)}, + {'type': 'inet', 'host': VNC_ADDR, + 'port': str(c)}]) self.assertEqual(self.vm.qmp('query-vnc')['return']['service'], str(b)) self.assertFalse(check_connect(a)) self.assertTrue(check_connect(b)) diff --git a/tests/avocado/x86_cpu_model_versions.py b/tests/avocado/x86_cpu_model_versions.py index a6edf74c1c..9e07b8a55d 100644 --- a/tests/avocado/x86_cpu_model_versions.py +++ b/tests/avocado/x86_cpu_model_versions.py @@ -84,7 +84,8 @@ class X86CPUModelAliases(avocado_qemu.QemuSystemTest): # with older QEMU versions that didn't have the versioned CPU model self.vm.add_args('-S') self.vm.launch() - cpus = dict((m['name'], m) for m in self.vm.command('query-cpu-definitions')) + cpus = dict((m['name'], m) for m in + self.vm.cmd('query-cpu-definitions')) self.assertFalse(cpus['Cascadelake-Server']['static'], 'unversioned Cascadelake-Server CPU model must not be static') @@ -115,7 +116,8 @@ class X86CPUModelAliases(avocado_qemu.QemuSystemTest): self.vm.add_args('-S') self.vm.launch() - cpus = dict((m['name'], m) for m in self.vm.command('query-cpu-definitions')) + cpus = dict((m['name'], m) for m in + self.vm.cmd('query-cpu-definitions')) self.assertFalse(cpus['Cascadelake-Server']['static'], 'unversioned Cascadelake-Server CPU model must not be static') @@ -220,7 +222,8 @@ class X86CPUModelAliases(avocado_qemu.QemuSystemTest): self.vm.add_args('-S') self.vm.launch() - cpus = dict((m['name'], m) for m in self.vm.command('query-cpu-definitions')) + cpus = dict((m['name'], m) for m in + self.vm.cmd('query-cpu-definitions')) self.assertFalse(cpus['Cascadelake-Server']['static'], 'unversioned Cascadelake-Server CPU model must not be static') @@ -246,8 +249,8 @@ class CascadelakeArchCapabilities(avocado_qemu.QemuSystemTest): :avocado: tags=arch:x86_64 """ def get_cpu_prop(self, prop): - cpu_path = self.vm.command('query-cpus-fast')[0].get('qom-path') - return self.vm.command('qom-get', path=cpu_path, property=prop) + cpu_path = self.vm.cmd('query-cpus-fast')[0].get('qom-path') + return self.vm.cmd('qom-get', path=cpu_path, property=prop) def test_4_1(self): """ diff --git a/tests/docker/docker.py b/tests/docker/docker.py index 688ef62989..3b8a26704d 100755 --- a/tests/docker/docker.py +++ b/tests/docker/docker.py @@ -186,7 +186,7 @@ def _check_binfmt_misc(executable): (binary)) return None, True - m = re.search("interpreter (\S+)\n", entry) + m = re.search(r"interpreter (\S+)\n", entry) interp = m.group(1) if interp and interp != executable: print("binfmt_misc for %s does not point to %s, using %s" % diff --git a/tests/docker/dockerfiles/python.docker b/tests/docker/dockerfiles/python.docker index 383ccbdc3a..a3c1321190 100644 --- a/tests/docker/dockerfiles/python.docker +++ b/tests/docker/dockerfiles/python.docker @@ -11,7 +11,11 @@ ENV PACKAGES \ python3-pip \ python3-tox \ python3-virtualenv \ - python3.10 + python3.10 \ + python3.11 \ + python3.12 \ + python3.8 \ + python3.9 RUN dnf install -y $PACKAGES RUN rpm -q $PACKAGES | sort > /packages.txt diff --git a/tests/migration/guestperf/engine.py b/tests/migration/guestperf/engine.py index e69d16a62c..da96ca034a 100644 --- a/tests/migration/guestperf/engine.py +++ b/tests/migration/guestperf/engine.py @@ -77,7 +77,7 @@ class Engine(object): return TimingRecord(pid, now, 1000 * (stime + utime) / jiffies_per_sec) def _migrate_progress(self, vm): - info = vm.command("query-migrate") + info = vm.cmd("query-migrate") if "ram" not in info: info["ram"] = {} @@ -109,7 +109,7 @@ class Engine(object): src_vcpu_time = [] src_pid = src.get_pid() - vcpus = src.command("query-cpus-fast") + vcpus = src.cmd("query-cpus-fast") src_threads = [] for vcpu in vcpus: src_threads.append(vcpu["thread-id"]) @@ -128,82 +128,82 @@ class Engine(object): if self._verbose: print("Starting migration") if scenario._auto_converge: - resp = src.command("migrate-set-capabilities", - capabilities = [ - { "capability": "auto-converge", - "state": True } - ]) - resp = src.command("migrate-set-parameters", - cpu_throttle_increment=scenario._auto_converge_step) + resp = src.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "auto-converge", + "state": True } + ]) + resp = src.cmd("migrate-set-parameters", + cpu_throttle_increment=scenario._auto_converge_step) if scenario._post_copy: - resp = src.command("migrate-set-capabilities", - capabilities = [ - { "capability": "postcopy-ram", - "state": True } - ]) - resp = dst.command("migrate-set-capabilities", - capabilities = [ - { "capability": "postcopy-ram", - "state": True } - ]) - - resp = src.command("migrate-set-parameters", - max_bandwidth=scenario._bandwidth * 1024 * 1024) - - resp = src.command("migrate-set-parameters", - downtime_limit=scenario._downtime) + resp = src.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "postcopy-ram", + "state": True } + ]) + resp = dst.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "postcopy-ram", + "state": True } + ]) + + resp = src.cmd("migrate-set-parameters", + max_bandwidth=scenario._bandwidth * 1024 * 1024) + + resp = src.cmd("migrate-set-parameters", + downtime_limit=scenario._downtime) if scenario._compression_mt: - resp = src.command("migrate-set-capabilities", - capabilities = [ - { "capability": "compress", - "state": True } - ]) - resp = src.command("migrate-set-parameters", - compress_threads=scenario._compression_mt_threads) - resp = dst.command("migrate-set-capabilities", - capabilities = [ - { "capability": "compress", - "state": True } - ]) - resp = dst.command("migrate-set-parameters", - decompress_threads=scenario._compression_mt_threads) + resp = src.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "compress", + "state": True } + ]) + resp = src.cmd("migrate-set-parameters", + compress_threads=scenario._compression_mt_threads) + resp = dst.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "compress", + "state": True } + ]) + resp = dst.cmd("migrate-set-parameters", + decompress_threads=scenario._compression_mt_threads) if scenario._compression_xbzrle: - resp = src.command("migrate-set-capabilities", - capabilities = [ - { "capability": "xbzrle", - "state": True } - ]) - resp = dst.command("migrate-set-capabilities", - capabilities = [ - { "capability": "xbzrle", - "state": True } - ]) - resp = src.command("migrate-set-parameters", - xbzrle_cache_size=( - hardware._mem * - 1024 * 1024 * 1024 / 100 * - scenario._compression_xbzrle_cache)) + resp = src.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "xbzrle", + "state": True } + ]) + resp = dst.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "xbzrle", + "state": True } + ]) + resp = src.cmd("migrate-set-parameters", + xbzrle_cache_size=( + hardware._mem * + 1024 * 1024 * 1024 / 100 * + scenario._compression_xbzrle_cache)) if scenario._multifd: - resp = src.command("migrate-set-capabilities", - capabilities = [ - { "capability": "multifd", - "state": True } - ]) - resp = src.command("migrate-set-parameters", - multifd_channels=scenario._multifd_channels) - resp = dst.command("migrate-set-capabilities", - capabilities = [ - { "capability": "multifd", - "state": True } - ]) - resp = dst.command("migrate-set-parameters", - multifd_channels=scenario._multifd_channels) - - resp = src.command("migrate", uri=connect_uri) + resp = src.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "multifd", + "state": True } + ]) + resp = src.cmd("migrate-set-parameters", + multifd_channels=scenario._multifd_channels) + resp = dst.cmd("migrate-set-capabilities", + capabilities = [ + { "capability": "multifd", + "state": True } + ]) + resp = dst.cmd("migrate-set-parameters", + multifd_channels=scenario._multifd_channels) + + resp = src.cmd("migrate", uri=connect_uri) post_copy = False paused = False @@ -228,7 +228,7 @@ class Engine(object): if progress._status in ("completed", "failed", "cancelled"): if progress._status == "completed" and paused: - dst.command("cont") + dst.cmd("cont") if progress_history[-1] != progress: progress_history.append(progress) @@ -256,13 +256,13 @@ class Engine(object): if progress._ram._iterations > scenario._max_iters: if self._verbose: print("No completion after %d iterations over RAM" % scenario._max_iters) - src.command("migrate_cancel") + src.cmd("migrate_cancel") continue if time.time() > (start + scenario._max_time): if self._verbose: print("No completion after %d seconds" % scenario._max_time) - src.command("migrate_cancel") + src.cmd("migrate_cancel") continue if (scenario._post_copy and @@ -270,7 +270,7 @@ class Engine(object): not post_copy): if self._verbose: print("Switching to post-copy after %d iterations" % scenario._post_copy_iters) - resp = src.command("migrate-start-postcopy") + resp = src.cmd("migrate-start-postcopy") post_copy = True if (scenario._pause and @@ -278,7 +278,7 @@ class Engine(object): not paused): if self._verbose: print("Pausing VM after %d iterations" % scenario._pause_iters) - resp = src.command("stop") + resp = src.cmd("stop") paused = True def _is_ppc64le(self): diff --git a/tests/qemu-iotests/030 b/tests/qemu-iotests/030 index 98595d47fe..0e6a39d103 100755 --- a/tests/qemu-iotests/030 +++ b/tests/qemu-iotests/030 @@ -56,8 +56,7 @@ class TestSingleDrive(iotests.QMPTestCase): def test_stream(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') self.wait_until_completed() @@ -77,8 +76,7 @@ class TestSingleDrive(iotests.QMPTestCase): qemu_io('-f', iotests.imgfmt, '-rU', '-c', 'map', mid_img).stdout, 'image file map matches backing file before streaming') - result = self.vm.qmp('block-stream', device='mid', job_id='stream-mid') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='mid', job_id='stream-mid') self.wait_until_completed(drive='stream-mid') @@ -94,8 +92,7 @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') @@ -108,8 +105,7 @@ class TestSingleDrive(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') self.wait_until_completed() @@ -129,8 +125,7 @@ class TestSingleDrive(iotests.QMPTestCase): '-f', iotests.imgfmt, '-rU', '-c', 'map', test_img).stdout # This is a no-op: no data should ever be copied from the base image - result = self.vm.qmp('block-stream', device='drive0', base=mid_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', base=mid_img) self.wait_until_completed() @@ -144,8 +139,7 @@ class TestSingleDrive(iotests.QMPTestCase): def test_stream_partial(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0', base=backing_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', base=backing_img) self.wait_until_completed() @@ -172,24 +166,22 @@ class TestSingleDrive(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, ro_top_path, str(self.image_len)) - result = self.vm.qmp('blockdev-add', - node_name='ro-top', - driver=iotests.imgfmt, - read_only=True, - file={ - 'driver': 'file', - 'filename': ro_top_path, - 'read-only': True - }, - backing='mid') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='ro-top', + driver=iotests.imgfmt, + read_only=True, + file={ + 'driver': 'file', + 'filename': ro_top_path, + 'read-only': True + }, + backing='mid') result = self.vm.qmp('block-stream', job_id='stream', device='ro-top', base_node='base') self.assert_qmp(result, 'error/desc', 'Block node is read-only') - result = self.vm.qmp('blockdev-del', node_name='ro-top') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='ro-top') class TestParallelOps(iotests.QMPTestCase): @@ -254,10 +246,9 @@ class TestParallelOps(iotests.QMPTestCase): node_name = 'node%d' % i job_id = 'stream-%s' % node_name pending_jobs.append(job_id) - result = self.vm.qmp('block-stream', device=node_name, - job_id=job_id, bottom=f'node{i-1}', - speed=1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device=node_name, + job_id=job_id, bottom=f'node{i-1}', + speed=1024) # Do this in reverse: After unthrottling them, some jobs may finish # before we have unthrottled all of them. This will drain their @@ -269,8 +260,7 @@ class TestParallelOps(iotests.QMPTestCase): # Starting from the top (i.e. in reverse) does not have this problem: # When a job finishes, the ones below it are not advanced. for job in reversed(pending_jobs): - result = self.vm.qmp('block-job-set-speed', device=job, speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device=job, speed=0) # Wait for all jobs to be finished. while len(pending_jobs) > 0: @@ -297,10 +287,9 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Set a speed limit to make sure that this job blocks the rest - result = self.vm.qmp('block-stream', device='node4', - job_id='stream-node4', base=self.imgs[1], - filter_node_name='stream-filter', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node4', + job_id='stream-node4', base=self.imgs[1], + filter_node_name='stream-filter', speed=1024*1024) result = self.vm.qmp('block-stream', device='node5', job_id='stream-node5', base=self.imgs[2]) self.assert_qmp(result, 'error/desc', @@ -328,8 +317,7 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_qmp(result, 'error/desc', "Node 'node2' is busy: block device is in use by block job: stream") - result = self.vm.qmp('block-job-set-speed', device='stream-node4', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='stream-node4', speed=0) self.wait_until_completed(drive='stream-node4') self.assert_no_active_block_jobs() @@ -341,8 +329,7 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Set a speed limit to make sure that this job blocks the rest - result = self.vm.qmp('block-commit', device='drive0', top=self.imgs[5], base=self.imgs[3], job_id='commit-node3', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', top=self.imgs[5], base=self.imgs[3], job_id='commit-node3', speed=1024*1024) result = self.vm.qmp('block-stream', device='node3', job_id='stream-node3') self.assert_qmp(result, 'error/desc', @@ -365,8 +352,7 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_qmp(result, 'error/desc', "Node 'drive0' is busy: block device is in use by block job: commit") - result = self.vm.qmp('block-job-set-speed', device='commit-node3', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='commit-node3', speed=0) self.wait_until_completed(drive='commit-node3') @@ -377,23 +363,20 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Set a speed limit to make sure that this job blocks the rest - result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[3], job_id='commit-drive0', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', base=self.imgs[3], job_id='commit-drive0', speed=1024*1024) result = self.vm.qmp('block-stream', device='node5', base=self.imgs[3], job_id='stream-node6') self.assert_qmp(result, 'error/desc', "Node 'node5' is busy: block device is in use by block job: commit") - result = self.vm.qmp('block-job-set-speed', device='commit-drive0', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='commit-drive0', speed=0) event = self.vm.event_wait(name='BLOCK_JOB_READY') self.assert_qmp(event, 'data/device', 'commit-drive0') self.assert_qmp(event, 'data/type', 'commit') self.assert_qmp_absent(event, 'data/error') - result = self.vm.qmp('block-job-complete', device='commit-drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device='commit-drive0') self.wait_until_completed(drive='commit-drive0') @@ -404,18 +387,16 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Commit from node2 into node0 - result = self.vm.qmp('block-commit', device='drive0', - top=self.imgs[2], base=self.imgs[0], - filter_node_name='commit-filter', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', + top=self.imgs[2], base=self.imgs[0], + filter_node_name='commit-filter', speed=1024*1024) # Stream from node2 into node4 result = self.vm.qmp('block-stream', device='node4', base_node='node2', job_id='node4') self.assert_qmp(result, 'error/desc', "Cannot freeze 'backing' link to 'commit-filter'") - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=0) self.wait_until_completed() self.assert_no_active_block_jobs() @@ -428,18 +409,15 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Commit from node2 into node0 - result = self.vm.qmp('block-commit', device='drive0', - top_node='node2', base_node='node0', - filter_node_name='commit-filter', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', + top_node='node2', base_node='node0', + filter_node_name='commit-filter', speed=1024*1024) # Stream from node2 into node4 - result = self.vm.qmp('block-stream', device='node4', - base_node='commit-filter', job_id='node4') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node4', + base_node='commit-filter', job_id='node4') - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=0) self.vm.run_job(job='drive0', auto_dismiss=True) self.vm.run_job(job='node4', auto_dismiss=True) @@ -458,12 +436,10 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Stream from node0 into node2 - result = self.vm.qmp('block-stream', device='node2', base_node='node0', job_id='node2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node2', base_node='node0', job_id='node2') # Commit from the active layer into node3 - result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[3]) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', base=self.imgs[3]) # Wait for all jobs to be finished. pending_jobs = ['node2', 'drive0'] @@ -490,16 +466,13 @@ class TestParallelOps(iotests.QMPTestCase): self.assert_no_active_block_jobs() # Stream from node0 into node4 - result = self.vm.qmp('block-stream', device='node4', base_node='node0', job_id='node4', speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node4', base_node='node0', job_id='node4', speed=1024*1024) # Commit from the active layer into node5 - result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[5], speed=1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', base=self.imgs[5], speed=1024*1024) for job in ['drive0', 'node4']: - result = self.vm.qmp('block-job-set-speed', device=job, speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device=job, speed=0) # Wait for all jobs to be finished. pending_jobs = ['node4', 'drive0'] @@ -549,8 +522,7 @@ class TestParallelOps(iotests.QMPTestCase): "'base' and 'base-node' cannot be specified at the same time") # Success: the base node is a backing file of the top node - result = self.vm.qmp('block-stream', device='node4', base_node='node2', job_id='stream') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node4', base_node='node2', job_id='stream') self.wait_until_completed(drive='stream') @@ -606,8 +578,7 @@ class TestQuorum(iotests.QMPTestCase): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='node0', job_id='stream-node0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='node0', job_id='stream-node0') self.wait_until_completed(drive='stream-node0') @@ -636,8 +607,7 @@ class TestSmallerBackingFile(iotests.QMPTestCase): def test_stream(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') self.wait_until_completed() @@ -694,8 +664,7 @@ class TestEIO(TestErrors): def test_report(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') completed = False error = False @@ -722,8 +691,7 @@ class TestEIO(TestErrors): def test_ignore(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0', on_error='ignore') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', on_error='ignore') error = False completed = False @@ -756,8 +724,7 @@ class TestEIO(TestErrors): def test_stop(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0', on_error='stop') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', on_error='stop') error = False completed = False @@ -779,8 +746,7 @@ class TestEIO(TestErrors): self.assert_qmp(result, 'return[0]/offset', self.STREAM_BUFFER_SIZE) self.assert_qmp(result, 'return[0]/io-status', 'failed') - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') result = self.vm.qmp('query-block-jobs') if result == {'return': []}: @@ -806,8 +772,7 @@ class TestEIO(TestErrors): def test_enospc(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0', on_error='enospc') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', on_error='enospc') completed = False error = False @@ -852,8 +817,7 @@ class TestENOSPC(TestErrors): def test_enospc(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0', on_error='enospc') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', on_error='enospc') error = False completed = False @@ -875,8 +839,7 @@ class TestENOSPC(TestErrors): self.assert_qmp(result, 'return[0]/offset', self.STREAM_BUFFER_SIZE) self.assert_qmp(result, 'return[0]/io-status', 'nospace') - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') result = self.vm.qmp('query-block-jobs') if result == {'return': []}: @@ -921,8 +884,7 @@ class TestStreamStop(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') time.sleep(0.1) events = self.vm.get_qmp_events(wait=False) @@ -955,11 +917,9 @@ class TestSetSpeed(iotests.QMPTestCase): def perf_test_throughput(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) self.wait_until_completed() @@ -969,16 +929,14 @@ class TestSetSpeed(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') # Default speed is 0 result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') self.assert_qmp(result, 'return[0]/speed', 0) - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) # Ensure the speed we set was accepted result = self.vm.qmp('query-block-jobs') @@ -989,8 +947,7 @@ class TestSetSpeed(iotests.QMPTestCase): self.vm.pause_drive('drive0') # Check setting speed in block-stream works - result = self.vm.qmp('block-stream', device='drive0', speed=4 * 1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0', speed=4 * 1024 * 1024) result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') @@ -1007,8 +964,7 @@ class TestSetSpeed(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp('block-stream', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', device='drive0') result = self.vm.qmp('block-job-set-speed', device='drive0', speed=-1) self.assert_qmp(result, 'error/desc', "Parameter 'speed' expects a non-negative value") diff --git a/tests/qemu-iotests/040 b/tests/qemu-iotests/040 index 5601a4873c..5c18e413ec 100755 --- a/tests/qemu-iotests/040 +++ b/tests/qemu-iotests/040 @@ -61,16 +61,14 @@ class ImageCommitTestCase(iotests.QMPTestCase): def run_commit_test(self, top, base, need_ready=False, node_names=False): self.assert_no_active_block_jobs() if node_names: - result = self.vm.qmp('block-commit', device='drive0', top_node=top, base_node=base) + self.vm.cmd('block-commit', device='drive0', top_node=top, base_node=base) else: - result = self.vm.qmp('block-commit', device='drive0', top=top, base=base) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', top=top, base=base) self.wait_for_complete(need_ready) def run_default_commit_test(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('block-commit', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0') self.wait_for_complete() class TestSingleDrive(ImageCommitTestCase): @@ -117,38 +115,30 @@ class TestSingleDrive(ImageCommitTestCase): @iotests.skip_if_unsupported(['throttle']) def test_commit_with_filter_and_quit(self): - result = self.vm.qmp('object-add', qom_type='throttle-group', id='tg') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', qom_type='throttle-group', id='tg') # Add a filter outside of the backing chain - result = self.vm.qmp('blockdev-add', driver='throttle', node_name='filter', throttle_group='tg', file='mid') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', driver='throttle', node_name='filter', throttle_group='tg', file='mid') - result = self.vm.qmp('block-commit', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0') # Quit immediately, thus forcing a simultaneous cancel of the # block job and a bdrv_drain_all() - result = self.vm.qmp('quit') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('quit') # Same as above, but this time we add the filter after starting the job @iotests.skip_if_unsupported(['throttle']) def test_commit_plus_filter_and_quit(self): - result = self.vm.qmp('object-add', qom_type='throttle-group', id='tg') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', qom_type='throttle-group', id='tg') - result = self.vm.qmp('block-commit', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0') # Add a filter outside of the backing chain - result = self.vm.qmp('blockdev-add', driver='throttle', node_name='filter', throttle_group='tg', file='mid') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', driver='throttle', node_name='filter', throttle_group='tg', file='mid') # Quit immediately, thus forcing a simultaneous cancel of the # block job and a bdrv_drain_all() - result = self.vm.qmp('quit') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('quit') def test_device_not_found(self): result = self.vm.qmp('block-commit', device='nonexistent', top='%s' % mid_img) @@ -225,8 +215,7 @@ class TestSingleDrive(ImageCommitTestCase): def test_top_node_in_wrong_chain(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('blockdev-add', driver='null-co', node_name='null') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', driver='null-co', node_name='null') result = self.vm.qmp('block-commit', device='drive0', top_node='null', base_node='base') self.assert_qmp(result, 'error/class', 'GenericError') @@ -239,11 +228,9 @@ class TestSingleDrive(ImageCommitTestCase): return self.assert_no_active_block_jobs() - result = self.vm.qmp('block-commit', device='drive0', top=mid_img, - base=backing_img, speed=(self.image_len // 4)) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('device_del', id='scsi0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', top=mid_img, + base=backing_img, speed=(self.image_len // 4)) + self.vm.cmd('device_del', id='scsi0') cancelled = False deleted = False @@ -269,9 +256,8 @@ class TestSingleDrive(ImageCommitTestCase): return self.assert_no_active_block_jobs() - result = self.vm.qmp('block-commit', device='drive0', top=mid_img, - base=backing_img, speed=(self.image_len // 4)) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', top=mid_img, + base=backing_img, speed=(self.image_len // 4)) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/file', test_img) @@ -406,8 +392,7 @@ class TestSetSpeed(ImageCommitTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp('block-commit', device='drive0', top=mid_img, speed=1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0', top=mid_img, speed=1024 * 1024) # Ensure the speed we set was accepted result = self.vm.qmp('query-block-jobs') @@ -480,8 +465,7 @@ class TestErrorHandling(iotests.QMPTestCase): os.remove(backing_img) def blockdev_add(self, **kwargs): - result = self.vm.qmp('blockdev-add', **kwargs) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', **kwargs) def add_block_nodes(self, base_debug=None, mid_debug=None, top_debug=None): self.blockdev_add(node_name='base-file', driver='file', @@ -527,11 +511,9 @@ class TestErrorHandling(iotests.QMPTestCase): completed = True elif ev['event'] == 'BLOCK_JOB_ERROR': if error_pauses_job: - result = self.vm.qmp('block-job-resume', device='job0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='job0') elif ev['event'] == 'BLOCK_JOB_READY': - result = self.vm.qmp('block-job-complete', device='job0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device='job0') else: self.fail("Unexpected event: %s" % ev) log.append(iotests.filter_qmp_event(ev)) @@ -594,11 +576,10 @@ class TestErrorHandling(iotests.QMPTestCase): self.add_block_nodes(top_debug=top_debug, mid_debug=mid_debug, base_debug=base_debug) - result = self.vm.qmp('block-commit', job_id='job0', device='top-fmt', - top_node='top-fmt' if active else 'mid-fmt', - base_node='mid-fmt' if active else 'base-fmt', - on_error=on_error) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', job_id='job0', device='top-fmt', + top_node='top-fmt' if active else 'mid-fmt', + base_node='mid-fmt' if active else 'base-fmt', + on_error=on_error) def testActiveReadErrorReport(self): self.prepare_and_start_job('report', top_event='read_aio') @@ -770,10 +751,9 @@ class TestCommitWithFilters(iotests.QMPTestCase): self.vm = iotests.VM().add_device('virtio-scsi,id=vio-scsi') self.vm.launch() - result = self.vm.qmp('object-add', qom_type='throttle-group', id='tg') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', qom_type='throttle-group', id='tg') - result = self.vm.qmp('blockdev-add', **{ + self.vm.cmd('blockdev-add', { 'node-name': 'top-filter', 'driver': 'throttle', 'throttle-group': 'tg', @@ -815,7 +795,6 @@ class TestCommitWithFilters(iotests.QMPTestCase): } } }) - self.assert_qmp(result, 'return', {}) def tearDown(self): self.vm.shutdown() @@ -832,13 +811,12 @@ class TestCommitWithFilters(iotests.QMPTestCase): return self.vm.node_info(node)['image']['filename'] def test_filterless_commit(self): - result = self.vm.qmp('block-commit', - job_id='commit', - device='top-filter', - top_node='cow-2', - base_node='cow-1', - backing_file=self.img1) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', + job_id='commit', + device='top-filter', + top_node='cow-2', + base_node='cow-1', + backing_file=self.img1) self.wait_until_completed(drive='commit') self.assertIsNotNone(self.vm.node_info('cow-3')) @@ -849,13 +827,12 @@ class TestCommitWithFilters(iotests.QMPTestCase): self.pattern_files[2] = self.img1 def test_commit_through_filter(self): - result = self.vm.qmp('block-commit', - job_id='commit', - device='top-filter', - top_node='cow-1', - base_node='cow-0', - backing_file=self.img0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', + job_id='commit', + device='top-filter', + top_node='cow-1', + base_node='cow-0', + backing_file=self.img0) self.wait_until_completed(drive='commit') self.assertIsNotNone(self.vm.node_info('cow-2')) @@ -870,9 +847,8 @@ class TestCommitWithFilters(iotests.QMPTestCase): # Add a device, so the commit job finds a parent it can change # to point to the base node (so we can test that top-filter is # dropped from the graph) - result = self.vm.qmp('device_add', id='drv0', driver='scsi-hd', - bus='vio-scsi.0', drive='top-filter') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', id='drv0', driver='scsi-hd', + bus='vio-scsi.0', drive='top-filter') # Try to release our reference to top-filter; that should not # work because drv0 uses it @@ -880,16 +856,14 @@ class TestCommitWithFilters(iotests.QMPTestCase): self.assert_qmp(result, 'error/class', 'GenericError') self.assert_qmp(result, 'error/desc', 'Node top-filter is in use') - result = self.vm.qmp('block-commit', - job_id='commit', - device='top-filter', - base_node='cow-2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', + job_id='commit', + device='top-filter', + base_node='cow-2') self.complete_and_wait(drive='commit') # Try to release our reference to top-filter again - result = self.vm.qmp('blockdev-del', node_name='top-filter') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='top-filter') self.assertIsNone(self.vm.node_info('top-filter')) self.assertIsNone(self.vm.node_info('cow-3')) @@ -904,12 +878,11 @@ class TestCommitWithFilters(iotests.QMPTestCase): self.pattern_files[3] = self.img2 def test_filtered_active_commit_without_filter(self): - result = self.vm.qmp('block-commit', - job_id='commit', - device='top-filter', - top_node='cow-3', - base_node='cow-2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', + job_id='commit', + device='top-filter', + top_node='cow-3', + base_node='cow-2') self.complete_and_wait(drive='commit') self.assertIsNotNone(self.vm.node_info('top-filter')) @@ -934,23 +907,22 @@ class TestCommitWithOverriddenBacking(iotests.QMPTestCase): self.vm.launch() # Use base_b instead of base_a as the backing of top - result = self.vm.qmp('blockdev-add', **{ - 'node-name': 'top', - 'driver': iotests.imgfmt, - 'file': { - 'driver': 'file', - 'filename': self.img_top - }, - 'backing': { - 'node-name': 'base', - 'driver': iotests.imgfmt, - 'file': { - 'driver': 'file', - 'filename': self.img_base_b - } - } - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', { + 'node-name': 'top', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': self.img_top + }, + 'backing': { + 'node-name': 'base', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': self.img_base_b + } + } + }) def tearDown(self): self.vm.shutdown() @@ -970,11 +942,10 @@ class TestCommitWithOverriddenBacking(iotests.QMPTestCase): def test_commit_to_b(self): # Try committing to base_b (which should work, since that is # actually top's backing image) - result = self.vm.qmp('block-commit', - job_id='commit', - device='top', - base=self.img_base_b) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', + job_id='commit', + device='top', + base=self.img_base_b) self.vm.event_wait('BLOCK_JOB_READY') self.vm.qmp('block-job-complete', device='commit') diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index 8429958bf0..98d17b1388 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -65,9 +65,8 @@ class TestSingleDrive(iotests.QMPTestCase): def test_complete(self): self.assert_no_active_block_jobs() - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + target=self.qmp_target) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -79,9 +78,8 @@ class TestSingleDrive(iotests.QMPTestCase): def test_cancel(self): self.assert_no_active_block_jobs() - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + target=self.qmp_target) self.cancel_and_wait(force=True) result = self.vm.qmp('query-block') @@ -90,9 +88,8 @@ class TestSingleDrive(iotests.QMPTestCase): def test_cancel_after_ready(self): self.assert_no_active_block_jobs() - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + target=self.qmp_target) self.wait_ready_and_cancel() result = self.vm.qmp('query-block') @@ -104,9 +101,8 @@ class TestSingleDrive(iotests.QMPTestCase): def test_pause(self): self.assert_no_active_block_jobs() - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + target=self.qmp_target) self.pause_job('drive0') @@ -117,8 +113,7 @@ class TestSingleDrive(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') self.complete_and_wait() self.vm.shutdown() @@ -129,9 +124,8 @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_no_active_block_jobs() # A small buffer is rounded up automatically - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - buf_size=4096, target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + buf_size=4096, target=self.qmp_target) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -145,9 +139,8 @@ class TestSingleDrive(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, '-o', 'cluster_size=%d,size=%d' % (self.image_len, self.image_len), target_img) - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - buf_size=65536, mode='existing', target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + buf_size=65536, mode='existing', target=self.qmp_target) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -162,9 +155,8 @@ class TestSingleDrive(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, '-o', 'cluster_size=%d,backing_file=%s' % (self.image_len, backing_img), '-F', 'raw', target_img) - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - mode='existing', target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + mode='existing', target=self.qmp_target) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -178,9 +170,8 @@ class TestSingleDrive(iotests.QMPTestCase): def test_implicit_node(self): self.assert_no_active_block_jobs() - result = self.vm.qmp(self.qmp_cmd, device='drive0', sync='full', - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, device='drive0', sync='full', + target=self.qmp_target) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/file', test_img) @@ -236,8 +227,7 @@ class TestSingleBlockdev(TestSingleDrive): args = {'driver': iotests.imgfmt, 'node-name': self.qmp_target, 'file': { 'filename': target_img, 'driver': 'file' } } - result = self.vm.qmp("blockdev-add", **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("blockdev-add", args) def test_mirror_to_self(self): result = self.vm.qmp(self.qmp_cmd, job_id='job0', @@ -254,10 +244,9 @@ class TestSingleBlockdev(TestSingleDrive): result = self.vm.qmp('block_resize', node_name=node, size=65536) self.assert_qmp(result, 'error/class', 'GenericError') - result = self.vm.qmp(self.qmp_cmd, job_id='job0', device='drive0', - sync='full', target=self.qmp_target, - auto_finalize=False, auto_dismiss=False) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, job_id='job0', device='drive0', + sync='full', target=self.qmp_target, + auto_finalize=False, auto_dismiss=False) result = self.vm.run_job('job0', auto_finalize=False, pre_finalize=pre_finalize) @@ -270,14 +259,12 @@ class TestSingleBlockdev(TestSingleDrive): self.do_test_resize(None, self.qmp_target) def do_test_target_size(self, size): - result = self.vm.qmp('block_resize', node_name=self.qmp_target, - size=size) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block_resize', node_name=self.qmp_target, + size=size) - result = self.vm.qmp(self.qmp_cmd, job_id='job0', - device='drive0', sync='full', auto_dismiss=False, - target=self.qmp_target) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.qmp_cmd, job_id='job0', + device='drive0', sync='full', auto_dismiss=False, + target=self.qmp_target) result = self.vm.run_job('job0') self.assertEqual(result, 'Source and target image have different sizes') @@ -337,9 +324,8 @@ class TestMirrorNoBacking(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, '-F', 'raw', target_img) - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=target_img) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -353,9 +339,8 @@ class TestMirrorNoBacking(iotests.QMPTestCase): qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, '-F', 'raw', target_img) - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=target_img) self.wait_ready_and_cancel() result = self.vm.qmp('query-block') @@ -374,9 +359,8 @@ class TestMirrorNoBacking(iotests.QMPTestCase): % (TestMirrorNoBacking.image_len, target_backing_img), '-F', iotests.imgfmt, target_img) - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=target_img) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -409,9 +393,8 @@ class TestMirrorResized(iotests.QMPTestCase): def test_complete_top(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='top', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='top', + target=target_img) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -423,9 +406,8 @@ class TestMirrorResized(iotests.QMPTestCase): def test_complete_full(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img) self.complete_and_wait() result = self.vm.qmp('query-block') @@ -488,9 +470,8 @@ new_state = "1" def test_report_read(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img) completed = False error = False @@ -516,9 +497,8 @@ new_state = "1" def test_ignore_read(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img, on_source_error='ignore') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img, on_source_error='ignore') event = self.vm.get_qmp_event(wait=True) while event['event'] == 'JOB_STATUS_CHANGE': @@ -541,10 +521,9 @@ new_state = "1" qemu_img('create', '-f', iotests.imgfmt, '-ocluster_size=131072,backing_file=%s' %(backing_img), '-F', 'raw', target_img) - result = self.vm.qmp('drive-mirror', device='drive0', sync='top', - on_source_error='ignore', - mode='existing', target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='top', + on_source_error='ignore', + mode='existing', target=target_img) event = self.vm.get_qmp_event(wait=True) while event['event'] == 'JOB_STATUS_CHANGE': @@ -568,9 +547,8 @@ new_state = "1" def test_stop_read(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img, on_source_error='stop') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img, on_source_error='stop') error = False ready = False @@ -590,8 +568,7 @@ new_state = "1" self.assert_qmp(result, 'return[0]/status', 'paused') self.assert_qmp(result, 'return[0]/io-status', 'failed') - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') error = True elif event['event'] == 'BLOCK_JOB_READY': self.assertTrue(error, 'job completed unexpectedly') @@ -656,9 +633,8 @@ new_state = "1" def test_report_write(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=self.target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=self.target_img) completed = False error = False @@ -682,10 +658,9 @@ new_state = "1" def test_ignore_write(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=self.target_img, - on_target_error='ignore') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=self.target_img, + on_target_error='ignore') event = self.vm.event_wait(name='BLOCK_JOB_ERROR') self.assertEqual(event['event'], 'BLOCK_JOB_ERROR') @@ -698,10 +673,9 @@ new_state = "1" def test_stop_write(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - mode='existing', target=self.target_img, - on_target_error='stop') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + mode='existing', target=self.target_img, + on_target_error='stop') error = False ready = False @@ -721,8 +695,7 @@ new_state = "1" self.assert_qmp(result, 'return[0]/status', 'paused') self.assert_qmp(result, 'return[0]/io-status', 'failed') - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') result = self.vm.qmp('query-block-jobs') self.assertIn(result['return'][0]['status'], ['running', 'ready']) @@ -755,17 +728,15 @@ class TestSetSpeed(iotests.QMPTestCase): def test_set_speed(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img) # Default speed is 0 result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') self.assert_qmp(result, 'return[0]/speed', 0) - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) # Ensure the speed we set was accepted result = self.vm.qmp('query-block-jobs') @@ -775,9 +746,8 @@ class TestSetSpeed(iotests.QMPTestCase): self.wait_ready_and_cancel() # Check setting speed in drive-mirror works - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img, speed=4*1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img, speed=4*1024*1024) result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') @@ -794,9 +764,8 @@ class TestSetSpeed(iotests.QMPTestCase): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img) result = self.vm.qmp('block-job-set-speed', device='drive0', speed=-1) self.assert_qmp(result, 'error/class', 'GenericError') @@ -811,13 +780,12 @@ class TestUnbackedSource(iotests.QMPTestCase): str(TestUnbackedSource.image_len)) self.vm = iotests.VM() self.vm.launch() - result = self.vm.qmp('blockdev-add', node_name='drive0', - driver=iotests.imgfmt, - file={ - 'driver': 'file', - 'filename': test_img, - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', node_name='drive0', + driver=iotests.imgfmt, + file={ + 'driver': 'file', + 'filename': test_img, + }) def tearDown(self): self.vm.shutdown() @@ -826,28 +794,25 @@ class TestUnbackedSource(iotests.QMPTestCase): def test_absolute_paths_full(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', job_id='drive0', device='drive0', - sync='full', target=target_img, - mode='absolute-paths') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='drive0', device='drive0', + sync='full', target=target_img, + mode='absolute-paths') self.complete_and_wait() self.assert_no_active_block_jobs() def test_absolute_paths_top(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', job_id='drive0', device='drive0', - sync='top', target=target_img, - mode='absolute-paths') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='drive0', device='drive0', + sync='top', target=target_img, + mode='absolute-paths') self.complete_and_wait() self.assert_no_active_block_jobs() def test_absolute_paths_none(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', job_id='drive0', device='drive0', - sync='none', target=target_img, - mode='absolute-paths') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='drive0', device='drive0', + sync='none', target=target_img, + mode='absolute-paths') self.complete_and_wait() self.assert_no_active_block_jobs() @@ -857,14 +822,12 @@ class TestUnbackedSource(iotests.QMPTestCase): qemu_io('-c', 'write -P 42 0 64k', target_img) self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', job_id='drive0', device='drive0', - sync='full', target=target_img, mode='existing') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='drive0', device='drive0', + sync='full', target=target_img, mode='existing') self.complete_and_wait() self.assert_no_active_block_jobs() - result = self.vm.qmp('blockdev-del', node_name='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='drive0') self.assertTrue(iotests.compare_images(test_img, target_img), 'target image does not match source after mirroring') @@ -874,26 +837,22 @@ class TestUnbackedSource(iotests.QMPTestCase): str(self.image_len)) qemu_io('-c', 'write -P 42 0 64k', target_img) - result = self.vm.qmp('blockdev-add', node_name='target', - driver=iotests.imgfmt, - file={ - 'driver': 'file', - 'filename': target_img, - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', node_name='target', + driver=iotests.imgfmt, + file={ + 'driver': 'file', + 'filename': target_img, + }) self.assert_no_active_block_jobs() - result = self.vm.qmp('blockdev-mirror', job_id='drive0', device='drive0', - sync='full', target='target') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', job_id='drive0', device='drive0', + sync='full', target='target') self.complete_and_wait() self.assert_no_active_block_jobs() - result = self.vm.qmp('blockdev-del', node_name='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='drive0') - result = self.vm.qmp('blockdev-del', node_name='target') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='target') self.assertTrue(iotests.compare_images(test_img, target_img), 'target image does not match source after mirroring') @@ -918,10 +877,9 @@ class TestGranularity(iotests.QMPTestCase): def test_granularity(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-mirror', device='drive0', - sync='full', target=target_img, - mode='absolute-paths', granularity=8192) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', + sync='full', target=target_img, + mode='absolute-paths', granularity=8192) event = self.vm.get_qmp_event(wait=60.0) while event['event'] == 'JOB_STATUS_CHANGE': @@ -963,8 +921,7 @@ class TestRepairQuorum(iotests.QMPTestCase): #assemble the quorum block device from the individual files args = { "driver": "quorum", "node-name": "quorum0", "vote-threshold": 2, "children": [ "img0", "img1", "img2" ] } - result = self.vm.qmp("blockdev-add", **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("blockdev-add", args) def tearDown(self): @@ -978,10 +935,9 @@ class TestRepairQuorum(iotests.QMPTestCase): pass def test_complete(self): - result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', - sync='full', node_name="repair0", replaces="img1", - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='job0', device='quorum0', + sync='full', node_name="repair0", replaces="img1", + target=quorum_repair_img, format=iotests.imgfmt) self.complete_and_wait(drive="job0") self.assert_has_block_node("repair0", quorum_repair_img) @@ -991,10 +947,9 @@ class TestRepairQuorum(iotests.QMPTestCase): 'target image does not match source after mirroring') def test_cancel(self): - result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', - sync='full', node_name="repair0", replaces="img1", - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='job0', device='quorum0', + sync='full', node_name="repair0", replaces="img1", + target=quorum_repair_img, format=iotests.imgfmt) self.cancel_and_wait(drive="job0", force=True) # here we check that the last registered quorum file has not been @@ -1002,10 +957,9 @@ class TestRepairQuorum(iotests.QMPTestCase): self.assert_has_block_node(None, quorum_img3) def test_cancel_after_ready(self): - result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', - sync='full', node_name="repair0", replaces="img1", - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='job0', device='quorum0', + sync='full', node_name="repair0", replaces="img1", + target=quorum_repair_img, format=iotests.imgfmt) self.wait_ready_and_cancel(drive="job0") # here we check that the last registered quorum file has not been @@ -1016,10 +970,9 @@ class TestRepairQuorum(iotests.QMPTestCase): 'target image does not match source after mirroring') def test_pause(self): - result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', - sync='full', node_name="repair0", replaces="img1", - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='job0', device='quorum0', + sync='full', node_name="repair0", replaces="img1", + target=quorum_repair_img, format=iotests.imgfmt) self.pause_job('job0') @@ -1030,8 +983,7 @@ class TestRepairQuorum(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='job0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='job0') self.complete_and_wait(drive="job0") self.vm.shutdown() @@ -1084,19 +1036,18 @@ class TestRepairQuorum(iotests.QMPTestCase): self.assert_qmp(result, 'error/class', 'GenericError') def test_after_a_quorum_snapshot(self): - result = self.vm.qmp('blockdev-snapshot-sync', node_name='img1', - snapshot_file=quorum_snapshot_file, - snapshot_node_name="snap1"); + self.vm.cmd('blockdev-snapshot-sync', node_name='img1', + snapshot_file=quorum_snapshot_file, + snapshot_node_name="snap1") result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', sync='full', node_name='repair0', replaces="img1", target=quorum_repair_img, format=iotests.imgfmt) self.assert_qmp(result, 'error/class', 'GenericError') - result = self.vm.qmp('drive-mirror', job_id='job0', device='quorum0', - sync='full', node_name='repair0', replaces="snap1", - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='job0', device='quorum0', + sync='full', node_name='repair0', replaces="snap1", + target=quorum_repair_img, format=iotests.imgfmt) self.complete_and_wait('job0') self.assert_has_block_node("repair0", quorum_repair_img) @@ -1107,15 +1058,13 @@ class TestRepairQuorum(iotests.QMPTestCase): Check that we cannot replace a Quorum child when it has other parents. """ - result = self.vm.qmp('nbd-server-start', - addr={ - 'type': 'unix', - 'data': {'path': nbd_sock_path} - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-start', + addr={ + 'type': 'unix', + 'data': {'path': nbd_sock_path} + }) - result = self.vm.qmp('nbd-server-add', device='img1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-add', device='img1') result = self.vm.qmp('drive-mirror', job_id='mirror', device='quorum0', sync='full', node_name='repair0', replaces='img1', @@ -1130,20 +1079,17 @@ class TestRepairQuorum(iotests.QMPTestCase): The same as test_with_other_parent(), but add the NBD server only when the mirror job is already running. """ - result = self.vm.qmp('nbd-server-start', - addr={ - 'type': 'unix', - 'data': {'path': nbd_sock_path} - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-start', + addr={ + 'type': 'unix', + 'data': {'path': nbd_sock_path} + }) - result = self.vm.qmp('drive-mirror', job_id='mirror', device='quorum0', - sync='full', node_name='repair0', replaces='img1', - target=quorum_repair_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', job_id='mirror', device='quorum0', + sync='full', node_name='repair0', replaces='img1', + target=quorum_repair_img, format=iotests.imgfmt) - result = self.vm.qmp('nbd-server-add', device='img1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-add', device='img1') # The full error message goes to stderr, we will check it later self.complete_and_wait('mirror', @@ -1199,9 +1145,8 @@ class TestOrphanedSource(iotests.QMPTestCase): def test_success(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('blockdev-mirror', job_id='job', device='src', - sync='full', target='dest') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', job_id='job', device='src', + sync='full', target='dest') self.complete_and_wait('job') @@ -1217,27 +1162,24 @@ class TestOrphanedSource(iotests.QMPTestCase): # Unshare consistent-read on the target # (The mirror job does not care) - result = self.vm.qmp('blockdev-add', - driver='blkdebug', - node_name='dest-perm', - image='dest', - unshare_child_perms=['consistent-read']) - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-mirror', job_id='job', device='src', - sync='full', target='dest', - filter_node_name='mirror-filter') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + driver='blkdebug', + node_name='dest-perm', + image='dest', + unshare_child_perms=['consistent-read']) + + self.vm.cmd('blockdev-mirror', job_id='job', device='src', + sync='full', target='dest', + filter_node_name='mirror-filter') # Require consistent-read on the source # (We can only add this node once the job has started, or it # will complain that it does not want to run on non-root nodes) - result = self.vm.qmp('blockdev-add', - driver='blkdebug', - node_name='src-perm', - image='src', - take_child_perms=['consistent-read']) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + driver='blkdebug', + node_name='src-perm', + image='src', + take_child_perms=['consistent-read']) # While completing, mirror will attempt to replace src by # dest, which must fail because src-perm requires @@ -1277,26 +1219,23 @@ class TestReplaces(iotests.QMPTestCase): """ Check that we can replace filter nodes. """ - result = self.vm.qmp('blockdev-add', **{ - 'driver': 'copy-on-read', - 'node-name': 'filter0', - 'file': { - 'driver': 'copy-on-read', - 'node-name': 'filter1', - 'file': { - 'driver': 'null-co' - } - } - }) - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-add', - node_name='target', driver='null-co') - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-mirror', job_id='mirror', device='filter0', - target='target', sync='full', replaces='filter1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', { + 'driver': 'copy-on-read', + 'node-name': 'filter0', + 'file': { + 'driver': 'copy-on-read', + 'node-name': 'filter1', + 'file': { + 'driver': 'null-co' + } + } + }) + + self.vm.cmd('blockdev-add', + node_name='target', driver='null-co') + + self.vm.cmd('blockdev-mirror', job_id='mirror', device='filter0', + target='target', sync='full', replaces='filter1') self.complete_and_wait('mirror') @@ -1318,16 +1257,15 @@ class TestFilters(iotests.QMPTestCase): self.vm = iotests.VM().add_device('virtio-scsi,id=vio-scsi') self.vm.launch() - result = self.vm.qmp('blockdev-add', **{ - 'node-name': 'target', - 'driver': iotests.imgfmt, - 'file': { - 'driver': 'file', - 'filename': target_img - }, - 'backing': None - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', { + 'node-name': 'target', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': target_img + }, + 'backing': None + }) self.filterless_chain = { 'node-name': 'source', @@ -1354,19 +1292,17 @@ class TestFilters(iotests.QMPTestCase): os.remove(backing_img) def test_cor(self): - result = self.vm.qmp('blockdev-add', **{ - 'node-name': 'filter', - 'driver': 'copy-on-read', - 'file': self.filterless_chain - }) - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='filter', - target='target', - sync='top') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', { + 'node-name': 'filter', + 'driver': 'copy-on-read', + 'file': self.filterless_chain + }) + + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='filter', + target='target', + sync='top') self.complete_and_wait('mirror') @@ -1383,23 +1319,20 @@ class TestFilters(iotests.QMPTestCase): assert target_map[1]['depth'] == 0 def test_implicit_mirror_filter(self): - result = self.vm.qmp('blockdev-add', **self.filterless_chain) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', self.filterless_chain) # We need this so we can query from above the mirror node - result = self.vm.qmp('device_add', - driver='scsi-hd', - id='virtio', - bus='vio-scsi.0', - drive='source') - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='source', - target='target', - sync='top') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', + driver='scsi-hd', + id='virtio', + bus='vio-scsi.0', + drive='source') + + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='source', + target='target', + sync='top') # The mirror filter is now an implicit node, so it should be # invisible when querying the backing chain @@ -1417,24 +1350,21 @@ class TestFilters(iotests.QMPTestCase): def test_explicit_mirror_filter(self): # Same test as above, but this time we give the mirror filter # a node-name so it will not be invisible - result = self.vm.qmp('blockdev-add', **self.filterless_chain) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', self.filterless_chain) # We need this so we can query from above the mirror node - result = self.vm.qmp('device_add', - driver='scsi-hd', - id='virtio', - bus='vio-scsi.0', - drive='source') - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='source', - target='target', - sync='top', - filter_node_name='mirror-filter') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', + driver='scsi-hd', + id='virtio', + bus='vio-scsi.0', + drive='source') + + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='source', + target='target', + sync='top', + filter_node_name='mirror-filter') # With a node-name given to it, the mirror filter should now # be visible diff --git a/tests/qemu-iotests/045 b/tests/qemu-iotests/045 index 45eb239baa..a341f21cd7 100755 --- a/tests/qemu-iotests/045 +++ b/tests/qemu-iotests/045 @@ -77,8 +77,7 @@ class TestFdSets(iotests.QMPTestCase): self.vm.shutdown() def test_remove_fdset(self): - result = self.vm.qmp('remove-fd', fdset_id=2) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('remove-fd', fdset_id=2) result = self.vm.qmp('query-fdsets') self.assert_qmp(result, 'return[0]/fdset-id', 1) self.assert_qmp(result, 'return[1]/fdset-id', 0) @@ -90,8 +89,7 @@ class TestFdSets(iotests.QMPTestCase): def test_remove_fd(self): result = self.vm.qmp('query-fdsets') fd_image3 = result['return'][0]['fds'][0]['fd'] - result = self.vm.qmp('remove-fd', fdset_id=2, fd=fd_image3) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('remove-fd', fdset_id=2, fd=fd_image3) result = self.vm.qmp('query-fdsets') self.assert_qmp(result, 'return[0]/fdset-id', 2) self.assert_qmp(result, 'return[1]/fdset-id', 1) @@ -151,8 +149,7 @@ class TestSCMFd(iotests.QMPTestCase): def test_getfd(self): self._send_fd_by_SCM() - result = self.vm.qmp('getfd', fdname='image0:r') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('getfd', fdname='image0:r') def test_getfd_invalid_fdname(self): self._send_fd_by_SCM() @@ -163,10 +160,8 @@ class TestSCMFd(iotests.QMPTestCase): def test_closefd(self): self._send_fd_by_SCM() - result = self.vm.qmp('getfd', fdname='image0:r') - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('closefd', fdname='image0:r') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('getfd', fdname='image0:r') + self.vm.cmd('closefd', fdname='image0:r') def test_closefd_fd_not_found(self): fdname = 'image0:r' diff --git a/tests/qemu-iotests/055 b/tests/qemu-iotests/055 index 5d6b607051..d8372b5598 100755 --- a/tests/qemu-iotests/055 +++ b/tests/qemu-iotests/055 @@ -69,8 +69,7 @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', target=target, sync='full') - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', target=target, sync='full') event = self.cancel_and_wait(resume=True) self.assert_qmp(event, 'data/type', 'backup') @@ -85,9 +84,8 @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', - target=target, sync='full') - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', + target=target, sync='full') self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') @@ -100,8 +98,7 @@ class TestSingleDrive(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') self.wait_until_completed() @@ -123,10 +120,9 @@ class TestSingleDrive(iotests.QMPTestCase): result = self.vm.qmp('block_resize', node_name=node, size=65536) self.assert_qmp(result, 'error/class', 'GenericError') - result = self.vm.qmp('blockdev-backup', job_id='job0', device='drive0', - target='drive1', sync='full', auto_finalize=False, - auto_dismiss=False) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-backup', job_id='job0', device='drive0', + target='drive1', sync='full', auto_finalize=False, + auto_dismiss=False) self.vm.run_job('job0', auto_finalize=False, pre_finalize=pre_finalize) @@ -137,8 +133,7 @@ class TestSingleDrive(iotests.QMPTestCase): self.do_test_resize_blockdev_backup('drive1', 'target') def do_test_target_size(self, size): - result = self.vm.qmp('block_resize', device='drive1', size=size) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block_resize', device='drive1', size=size) result = self.vm.qmp('blockdev-backup', job_id='job0', device='drive0', target='drive1', sync='full') @@ -219,16 +214,14 @@ class TestSetSpeed(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', target=target, sync='full') - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', target=target, sync='full') # Default speed is 0 result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') self.assert_qmp(result, 'return[0]/speed', 0) - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=8 * 1024 * 1024) # Ensure the speed we set was accepted result = self.vm.qmp('query-block-jobs') @@ -240,9 +233,8 @@ class TestSetSpeed(iotests.QMPTestCase): # Check setting speed option works self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', - target=target, sync='full', speed=4*1024*1024) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', + target=target, sync='full', speed=4*1024*1024) result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') @@ -267,9 +259,8 @@ class TestSetSpeed(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', - target=target, sync='full') - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', + target=target, sync='full') result = self.vm.qmp('block-job-set-speed', device='drive0', speed=-1) self.assert_qmp(result, 'error/class', 'GenericError') @@ -306,7 +297,7 @@ class TestSingleTransaction(iotests.QMPTestCase): def do_test_cancel(self, cmd, target): self.assert_no_active_block_jobs() - result = self.vm.qmp('transaction', actions=[{ + self.vm.cmd('transaction', actions=[{ 'type': cmd, 'data': { 'device': 'drive0', 'target': target, @@ -315,8 +306,6 @@ class TestSingleTransaction(iotests.QMPTestCase): } ]) - self.assert_qmp(result, 'return', {}) - event = self.cancel_and_wait() self.assert_qmp(event, 'data/type', 'backup') @@ -329,7 +318,7 @@ class TestSingleTransaction(iotests.QMPTestCase): def do_test_pause(self, cmd, target, image): self.assert_no_active_block_jobs() - result = self.vm.qmp('transaction', actions=[{ + self.vm.cmd('transaction', actions=[{ 'type': cmd, 'data': { 'device': 'drive0', 'target': target, @@ -337,12 +326,10 @@ class TestSingleTransaction(iotests.QMPTestCase): 'speed': 64 * 1024 }, } ]) - self.assert_qmp(result, 'return', {}) self.pause_job('drive0', wait=False) - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=0) self.pause_wait('drive0') @@ -353,8 +340,7 @@ class TestSingleTransaction(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') self.wait_until_completed() @@ -519,8 +505,7 @@ class TestCompressedToQcow2(iotests.QMPTestCase): self.assert_no_active_block_jobs() - result = self.vm.qmp(cmd, device='drive0', sync='full', compress=True, **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', sync='full', compress=True, **args) self.wait_until_completed() @@ -545,8 +530,7 @@ class TestCompressedToQcow2(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', sync='full', compress=True, **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', sync='full', compress=True, **args) event = self.cancel_and_wait(resume=True) self.assert_qmp(event, 'data/type', 'backup') @@ -568,8 +552,7 @@ class TestCompressedToQcow2(iotests.QMPTestCase): self.assert_no_active_block_jobs() self.vm.pause_drive('drive0') - result = self.vm.qmp(cmd, device='drive0', sync='full', compress=True, **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, device='drive0', sync='full', compress=True, **args) self.pause_job('drive0', wait=False) self.vm.resume_drive('drive0') @@ -582,8 +565,7 @@ class TestCompressedToQcow2(iotests.QMPTestCase): result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/offset', offset) - result = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') self.wait_until_completed() diff --git a/tests/qemu-iotests/056 b/tests/qemu-iotests/056 index bef865eec4..808ea6b48a 100755 --- a/tests/qemu-iotests/056 +++ b/tests/qemu-iotests/056 @@ -75,9 +75,8 @@ class TestSyncModesNoneAndTop(iotests.QMPTestCase): def test_complete_top(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-backup', device='drive0', sync='top', - format=iotests.imgfmt, target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-backup', device='drive0', sync='top', + format=iotests.imgfmt, target=target_img) self.wait_until_completed(check_offset=False) @@ -89,9 +88,8 @@ class TestSyncModesNoneAndTop(iotests.QMPTestCase): def test_cancel_sync_none(self): self.assert_no_active_block_jobs() - result = self.vm.qmp('drive-backup', device='drive0', - sync='none', target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-backup', device='drive0', + sync='none', target=target_img) time.sleep(1) self.vm.hmp_qemu_io('drive0', 'write -P0x5e 0 512') self.vm.hmp_qemu_io('drive0', 'aio_flush') @@ -115,18 +113,15 @@ class TestBeforeWriteNotifier(iotests.QMPTestCase): def test_before_write_notifier(self): self.vm.pause_drive("drive0") - result = self.vm.qmp('drive-backup', device='drive0', - sync='full', target=target_img, - format="file", speed=1) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-job-pause', device="drive0") - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-backup', device='drive0', + sync='full', target=target_img, + format="file", speed=1) + self.vm.cmd('block-job-pause', device="drive0") # Speed is low enough that this must be an uncopied range, which will # trigger the before write notifier self.vm.hmp_qemu_io('drive0', 'aio_write -P 1 512512 512') self.vm.resume_drive("drive0") - result = self.vm.qmp('block-job-resume', device="drive0") - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-resume', device="drive0") event = self.cancel_and_wait() self.assert_qmp(event, 'data/type', 'backup') @@ -191,8 +186,7 @@ class BackupTest(iotests.QMPTestCase): self.qmp_backup_and_wait(device='drive0', format=iotests.imgfmt, sync='full', target=self.ref_img, auto_dismiss=False) - res = self.vm.qmp('block-job-dismiss', id='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-dismiss', id='drive0') # Now to the test backup: We simulate the following guest # writes: @@ -211,11 +205,9 @@ class BackupTest(iotests.QMPTestCase): ('66', '1M', '1M')]) # Let the job complete - res = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=0) self.qmp_backup_wait('drive0') - res = self.vm.qmp('block-job-dismiss', id='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-dismiss', id='drive0') self.assertTrue(iotests.compare_images(self.ref_img, self.dest_img), 'target image does not match reference image') @@ -237,8 +229,7 @@ class BackupTest(iotests.QMPTestCase): auto_dismiss=False) res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return[0]/status', 'concluded') - res = self.vm.qmp('block-job-dismiss', id='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-dismiss', id='drive0') res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return', []) @@ -263,8 +254,7 @@ class BackupTest(iotests.QMPTestCase): auto_dismiss=False) self.assertEqual(res, False) # OK, dismiss the zombie. - res = self.vm.qmp('block-job-dismiss', id='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-dismiss', id='drive0') res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return', []) # Ensure it's really gone. @@ -281,23 +271,22 @@ class BackupTest(iotests.QMPTestCase): ('0x55', '8M', '352k'), ('0x78', '15872k', '1M'))) # Add destination node via blkdebug - res = self.vm.qmp('blockdev-add', - node_name='target0', - driver=iotests.imgfmt, - file={ - 'driver': 'blkdebug', - 'image': { - 'driver': 'file', - 'filename': self.dest_img - }, - 'inject-error': [{ - 'event': 'write_aio', - 'errno': 5, - 'immediately': False, - 'once': True - }], - }) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='target0', + driver=iotests.imgfmt, + file={ + 'driver': 'blkdebug', + 'image': { + 'driver': 'file', + 'filename': self.dest_img + }, + 'inject-error': [{ + 'event': 'write_aio', + 'errno': 5, + 'immediately': False, + 'once': True + }], + }) res = self.qmp_backup(cmd='blockdev-backup', device='drive0', target='target0', @@ -323,8 +312,7 @@ class BackupTest(iotests.QMPTestCase): res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return[0]/status', 'paused') # OK, unstick job and move forward. - res = self.vm.qmp('block-job-resume', device='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-resume', device='drive0') # And now we need to wait for it to conclude; res = self.qmp_backup_wait(device='drive0') self.assertTrue(res) @@ -332,8 +320,7 @@ class BackupTest(iotests.QMPTestCase): # Job should now be languishing: res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return[0]/status', 'concluded') - res = self.vm.qmp('block-job-dismiss', id='drive0') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-dismiss', id='drive0') res = self.vm.qmp('query-block-jobs') self.assert_qmp(res, 'return', []) diff --git a/tests/qemu-iotests/093 b/tests/qemu-iotests/093 index 93274dc8cb..4f9e224e8a 100755 --- a/tests/qemu-iotests/093 +++ b/tests/qemu-iotests/093 @@ -55,8 +55,7 @@ class ThrottleTestCase(iotests.QMPTestCase): # Set the I/O throttling parameters to all drives for i in range(0, ndrives): params['device'] = 'drive%d' % i - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("block_set_io_throttle", conv_keys=False, **params) def do_test_throttle(self, ndrives, seconds, params, first_drive = 0): def check_limit(limit, num): @@ -253,8 +252,7 @@ class ThrottleTestCase(iotests.QMPTestCase): # drive1 remains in the group with a throttled request. params['bps_rd'] = 0 params['device'] = 'drive0' - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("block_set_io_throttle", conv_keys=False, **params) # Removing the I/O limits from drive0 drains its two pending requests. # The read request in drive1 is still throttled. @@ -286,8 +284,7 @@ class ThrottleTestGroupNames(iotests.QMPTestCase): def set_io_throttle(self, device, params): params["device"] = device - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **params) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("block_set_io_throttle", conv_keys=False, **params) def verify_name(self, device, name): result = self.vm.qmp("query-block") @@ -379,23 +376,19 @@ class ThrottleTestRemovableMedia(iotests.QMPTestCase): def test_removable_media(self): # Add a couple of dummy nodes named cd0 and cd1 - result = self.vm.qmp("blockdev-add", driver="null-co", - read_zeroes=True, node_name="cd0") - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp("blockdev-add", driver="null-co", - read_zeroes=True, node_name="cd1") - self.assert_qmp(result, 'return', {}) + self.vm.cmd("blockdev-add", driver="null-co", + read_zeroes=True, node_name="cd0") + self.vm.cmd("blockdev-add", driver="null-co", + read_zeroes=True, node_name="cd1") # Attach a CD drive with cd0 inserted - result = self.vm.qmp("device_add", driver="scsi-cd", - id="dev0", drive="cd0") - self.assert_qmp(result, 'return', {}) + self.vm.cmd("device_add", driver="scsi-cd", + id="dev0", drive="cd0") # Set I/O limits args = { "id": "dev0", "iops": 100, "iops_rd": 0, "iops_wr": 0, "bps": 50, "bps_rd": 0, "bps_wr": 0 } - result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("block_set_io_throttle", conv_keys=False, **args) # Check that the I/O limits have been set result = self.vm.qmp("query-block") @@ -403,12 +396,9 @@ class ThrottleTestRemovableMedia(iotests.QMPTestCase): self.assert_qmp(result, 'return[0]/inserted/bps', 50) # Now eject cd0 and insert cd1 - result = self.vm.qmp("blockdev-open-tray", id='dev0') - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp("blockdev-remove-medium", id='dev0') - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp("blockdev-insert-medium", id='dev0', node_name='cd1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd("blockdev-open-tray", id='dev0') + self.vm.cmd("blockdev-remove-medium", id='dev0') + self.vm.cmd("blockdev-insert-medium", id='dev0', node_name='cd1') # Check that the I/O limits are still the same result = self.vm.qmp("query-block") @@ -416,16 +406,14 @@ class ThrottleTestRemovableMedia(iotests.QMPTestCase): self.assert_qmp(result, 'return[0]/inserted/bps', 50) # Eject cd1 - result = self.vm.qmp("blockdev-remove-medium", id='dev0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd("blockdev-remove-medium", id='dev0') # Check that we can't set limits if the device has no medium result = self.vm.qmp("block_set_io_throttle", conv_keys=False, **args) self.assert_qmp(result, 'error/class', 'GenericError') # Remove the CD drive - result = self.vm.qmp("device_del", id='dev0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd("device_del", id='dev0') if __name__ == '__main__': diff --git a/tests/qemu-iotests/118 b/tests/qemu-iotests/118 index cae52ffa5e..10dc47459f 100755 --- a/tests/qemu-iotests/118 +++ b/tests/qemu-iotests/118 @@ -74,11 +74,9 @@ class ChangeBaseClass(iotests.QMPTestCase): class GeneralChangeTestsBaseClass(ChangeBaseClass): def test_blockdev_change_medium(self): - result = self.vm.qmp('blockdev-change-medium', - id=self.device_name, filename=new_img, - format=iotests.imgfmt) - - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', + id=self.device_name, filename=new_img, + format=iotests.imgfmt) self.wait_for_open() self.wait_for_close() @@ -89,8 +87,7 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) def test_eject(self): - result = self.vm.qmp('eject', id=self.device_name, force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('eject', id=self.device_name, force=True) self.wait_for_open() @@ -100,8 +97,7 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp_absent(result, 'return[0]/inserted') def test_tray_eject_change(self): - result = self.vm.qmp('eject', id=self.device_name, force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('eject', id=self.device_name, force=True) self.wait_for_open() @@ -110,9 +106,8 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/tray_open', True) self.assert_qmp_absent(result, 'return[0]/inserted') - result = self.vm.qmp('blockdev-change-medium', id=self.device_name, - filename=new_img, format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', id=self.device_name, + filename=new_img, format=iotests.imgfmt) self.wait_for_close() @@ -122,9 +117,8 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) def test_tray_open_close(self): - result = self.vm.qmp('blockdev-open-tray', - id=self.device_name, force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-open-tray', + id=self.device_name, force=True) self.wait_for_open() @@ -136,8 +130,7 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): else: self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-close-tray', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-close-tray', id=self.device_name) if self.has_real_tray or not self.was_empty: self.wait_for_close() @@ -151,8 +144,7 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) def test_tray_eject_close(self): - result = self.vm.qmp('eject', id=self.device_name, force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('eject', id=self.device_name, force=True) self.wait_for_open() @@ -161,8 +153,7 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/tray_open', True) self.assert_qmp_absent(result, 'return[0]/inserted') - result = self.vm.qmp('blockdev-close-tray', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-close-tray', id=self.device_name) self.wait_for_close() @@ -172,9 +163,8 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp_absent(result, 'return[0]/inserted') def test_tray_open_change(self): - result = self.vm.qmp('blockdev-open-tray', id=self.device_name, - force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-open-tray', id=self.device_name, + force=True) self.wait_for_open() @@ -186,10 +176,9 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): else: self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', id=self.device_name, - filename=new_img, - format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', id=self.device_name, + filename=new_img, + format=iotests.imgfmt) self.wait_for_close() @@ -199,17 +188,15 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) def test_cycle(self, read_only_node=False): - result = self.vm.qmp('blockdev-add', - node_name='new', - driver=iotests.imgfmt, - read_only=read_only_node, - file={'filename': new_img, - 'driver': 'file'}) - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('blockdev-open-tray', - id=self.device_name, force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='new', + driver=iotests.imgfmt, + read_only=read_only_node, + file={'filename': new_img, + 'driver': 'file'}) + + self.vm.cmd('blockdev-open-tray', + id=self.device_name, force=True) self.wait_for_open() @@ -221,26 +208,23 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): else: self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-remove-medium', - id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-remove-medium', + id=self.device_name) result = self.vm.qmp('query-block') if self.has_real_tray: self.assert_qmp(result, 'return[0]/tray_open', True) self.assert_qmp_absent(result, 'return[0]/inserted') - result = self.vm.qmp('blockdev-insert-medium', - id=self.device_name, node_name='new') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-insert-medium', + id=self.device_name, node_name='new') result = self.vm.qmp('query-block') if self.has_real_tray: self.assert_qmp(result, 'return[0]/tray_open', True) self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) - result = self.vm.qmp('blockdev-close-tray', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-close-tray', id=self.device_name) self.wait_for_close() @@ -253,9 +237,8 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): self.test_cycle(True) def test_close_on_closed(self): - result = self.vm.qmp('blockdev-close-tray', id=self.device_name) # Should be a no-op - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-close-tray', id=self.device_name) self.assertEqual(self.vm.get_qmp_events(wait=False), []) def test_remove_on_closed(self): @@ -269,12 +252,11 @@ class GeneralChangeTestsBaseClass(ChangeBaseClass): if not self.has_real_tray: return - result = self.vm.qmp('blockdev-add', - node_name='new', - driver=iotests.imgfmt, - file={'filename': new_img, - 'driver': 'file'}) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='new', + driver=iotests.imgfmt, + file={'filename': new_img, + 'driver': 'file'}) result = self.vm.qmp('blockdev-insert-medium', id=self.device_name, node_name='new') @@ -307,15 +289,13 @@ class TestInitiallyFilled(GeneralChangeTestsBaseClass): os.remove(new_img) def test_insert_on_filled(self): - result = self.vm.qmp('blockdev-add', - node_name='new', - driver=iotests.imgfmt, - file={'filename': new_img, - 'driver': 'file'}) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='new', + driver=iotests.imgfmt, + file={'filename': new_img, + 'driver': 'file'}) - result = self.vm.qmp('blockdev-open-tray', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-open-tray', id=self.device_name) self.wait_for_open() @@ -344,14 +324,12 @@ class TestInitiallyEmpty(GeneralChangeTestsBaseClass): os.remove(new_img) def test_remove_on_empty(self): - result = self.vm.qmp('blockdev-open-tray', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-open-tray', id=self.device_name) self.wait_for_open() - result = self.vm.qmp('blockdev-remove-medium', id=self.device_name) # Should be a no-op - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-remove-medium', id=self.device_name) # Do this in a function to avoid leaking variables like case into the global # name space (otherwise tests would be run for the abstract base classes) @@ -399,11 +377,10 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', True) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='retain') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='retain') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -419,11 +396,10 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', True) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='retain') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='retain') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -462,12 +438,11 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', True) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', - id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='read-write') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', + id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='read-write') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', False) @@ -483,12 +458,11 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', False) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', - id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='read-only') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', + id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='read-only') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -503,12 +477,11 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', False) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', - id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='read-only') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', + id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='read-only') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -546,11 +519,10 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', True) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-change-medium', id=self.device_name, - filename=new_img, - format=iotests.imgfmt, - read_only_mode='retain') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-change-medium', id=self.device_name, + filename=new_img, + format=iotests.imgfmt, + read_only_mode='retain') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -587,27 +559,24 @@ class TestChangeReadOnly(ChangeBaseClass): self.assert_qmp(result, 'return[0]/inserted/ro', False) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-add', - node_name='new', - driver=iotests.imgfmt, - read_only=True, - file={'filename': new_img, - 'driver': 'file'}) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='new', + driver=iotests.imgfmt, + read_only=True, + file={'filename': new_img, + 'driver': 'file'}) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', False) self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) - result = self.vm.qmp('blockdev-remove-medium', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-remove-medium', id=self.device_name) result = self.vm.qmp('query-block') self.assert_qmp_absent(result, 'return[0]/inserted') - result = self.vm.qmp('blockdev-insert-medium', id=self.device_name, - node_name='new') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-insert-medium', id=self.device_name, + node_name='new') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/ro', True) @@ -638,22 +607,19 @@ class TestBlockJobsAfterCycle(ChangeBaseClass): # For device-less BBs, calling blockdev-open-tray or blockdev-close-tray # is not necessary - result = self.vm.qmp('blockdev-remove-medium', id=self.device_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-remove-medium', id=self.device_name) result = self.vm.qmp('query-block') self.assert_qmp_absent(result, 'return[0]/inserted') - result = self.vm.qmp('blockdev-add', - node_name='node0', - driver=iotests.imgfmt, - file={'filename': old_img, - 'driver': 'file'}) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name='node0', + driver=iotests.imgfmt, + file={'filename': old_img, + 'driver': 'file'}) - result = self.vm.qmp('blockdev-insert-medium', id=self.device_name, - node_name='node0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-insert-medium', id=self.device_name, + node_name='node0') result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/image/filename', old_img) @@ -670,10 +636,9 @@ class TestBlockJobsAfterCycle(ChangeBaseClass): @iotests.skip_for_formats(('vpc', 'parallels', 'qcow', 'vdi', 'vmdk', 'raw', 'vhdx')) def test_snapshot_and_commit(self): - result = self.vm.qmp('blockdev-snapshot-sync', device='drive0', - snapshot_file=new_img, - format=iotests.imgfmt) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-snapshot-sync', device='drive0', + snapshot_file=new_img, + format=iotests.imgfmt) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/image/filename', new_img) @@ -681,16 +646,14 @@ class TestBlockJobsAfterCycle(ChangeBaseClass): 'return[0]/inserted/image/backing-image/filename', old_img) - result = self.vm.qmp('block-commit', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='drive0') self.vm.event_wait(name='BLOCK_JOB_READY') result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/device', 'drive0') - result = self.vm.qmp('block-job-complete', device='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device='drive0') self.vm.event_wait(name='BLOCK_JOB_COMPLETED') diff --git a/tests/qemu-iotests/124 b/tests/qemu-iotests/124 index 845ab5303c..b2f4328e34 100755 --- a/tests/qemu-iotests/124 +++ b/tests/qemu-iotests/124 @@ -24,6 +24,7 @@ import os import iotests from iotests import try_remove +from qemu.qmp.qmp_client import ExecuteError def io_write_patterns(img, patterns): @@ -141,8 +142,7 @@ class TestIncrementalBackupBase(iotests.QMPTestCase): def do_qmp_backup(self, error='Input/output error', **kwargs): - res = self.vm.qmp('drive-backup', **kwargs) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('drive-backup', **kwargs) return self.wait_qmp_backup(kwargs['device'], error) @@ -201,9 +201,8 @@ class TestIncrementalBackupBase(iotests.QMPTestCase): def add_bitmap(self, name, drive, **kwargs): bitmap = Bitmap(name, drive) self.bitmaps.append(bitmap) - result = self.vm.qmp('block-dirty-bitmap-add', node=drive['id'], - name=bitmap.name, **kwargs) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-dirty-bitmap-add', node=drive['id'], + name=bitmap.name, **kwargs) return bitmap @@ -388,13 +387,12 @@ class TestIncrementalBackup(TestIncrementalBackupBase): ('0x64', '32736k', '64k'))) bitmap1 = self.add_bitmap('bitmap1', drive0) - result = self.vm.qmp('transaction', actions=[ + self.vm.cmd('transaction', actions=[ transaction_bitmap_clear(bitmap0.drive['id'], bitmap0.name), transaction_bitmap_clear(bitmap1.drive['id'], bitmap1.name), transaction_drive_backup(drive0['id'], drive0['backup'], sync='full', format=drive0['fmt']) ]) - self.assert_qmp(result, 'return', {}) self.wait_until_completed(drive0['id']) self.files.append(drive0['backup']) @@ -417,7 +415,7 @@ class TestIncrementalBackup(TestIncrementalBackupBase): ('0xcd', '32M', '124k'))) # Create a blkdebug interface to this img as 'drive1' - result = self.vm.qmp('blockdev-add', + self.vm.cmd('blockdev-add', node_name=drive1['id'], driver=drive1['fmt'], file={ @@ -440,7 +438,6 @@ class TestIncrementalBackup(TestIncrementalBackupBase): }], } ) - self.assert_qmp(result, 'return', {}) # Create bitmaps and full backups for both drives drive0 = self.drives[0] @@ -475,9 +472,8 @@ class TestIncrementalBackup(TestIncrementalBackupBase): format=drive1['fmt'], mode='existing', bitmap=dr1bm0.name) ] - result = self.vm.qmp('transaction', actions=transaction, - properties={'completion-mode': 'grouped'} ) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('transaction', actions=transaction, + properties={'completion-mode': 'grouped'} ) # Observe that drive0's backup is cancelled and drive1 completes with # an error. @@ -504,9 +500,8 @@ class TestIncrementalBackup(TestIncrementalBackupBase): target1 = self.prepare_backup(dr1bm0) # Re-run the exact same transaction. - result = self.vm.qmp('transaction', actions=transaction, - properties={'completion-mode':'grouped'}) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('transaction', actions=transaction, + properties={'completion-mode':'grouped'}) # Both should complete successfully this time. self.assertTrue(self.wait_qmp_backup(drive0['id'])) @@ -567,7 +562,7 @@ class TestIncrementalBackup(TestIncrementalBackupBase): The granularity must always be a power of 2. ''' self.assert_no_active_block_jobs() - self.assertRaises(AssertionError, self.add_bitmap, + self.assertRaises(ExecuteError, self.add_bitmap, 'bitmap0', self.drives[0], granularity=64000) @@ -585,9 +580,8 @@ class TestIncrementalBackup(TestIncrementalBackupBase): self.add_bitmap('bitmap0', self.drives[0]) - res = self.vm.qmp('block_resize', device=self.drives[0]['id'], - size=(65 * 1048576)) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block_resize', device=self.drives[0]['id'], + size=(65 * 1048576)) # Dirty the image past the old end self.vm.hmp_qemu_io(self.drives[0]['id'], 'write 64M 64k') @@ -617,7 +611,7 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase): ''' drive0 = self.drives[0] - result = self.vm.qmp('blockdev-add', + self.vm.cmd('blockdev-add', node_name=drive0['id'], driver=drive0['fmt'], file={ @@ -640,7 +634,6 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase): }], } ) - self.assert_qmp(result, 'return', {}) self.create_anchor_backup(drive0) self.add_bitmap('bitmap0', drive0) @@ -668,29 +661,28 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase): drive0 = self.drives[0] # NB: The blkdebug script here looks for a "flush, read" pattern. # The flush occurs in hmp_io_writes, and the read during the block job. - result = self.vm.qmp('blockdev-add', - node_name=drive0['id'], - driver=drive0['fmt'], - file={ - 'driver': 'blkdebug', - 'image': { - 'driver': 'file', - 'filename': drive0['file'] - }, - 'set-state': [{ - 'event': 'flush_to_disk', - 'state': 1, - 'new_state': 2 - }], - 'inject-error': [{ - 'event': 'read_aio', - 'errno': 5, - 'state': 2, - 'immediately': False, - 'once': True - }], - }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + node_name=drive0['id'], + driver=drive0['fmt'], + file={ + 'driver': 'blkdebug', + 'image': { + 'driver': 'file', + 'filename': drive0['file'] + }, + 'set-state': [{ + 'event': 'flush_to_disk', + 'state': 1, + 'new_state': 2 + }], + 'inject-error': [{ + 'event': 'read_aio', + 'errno': 5, + 'state': 2, + 'immediately': False, + 'once': True + }], + }) self.create_anchor_backup(drive0) bitmap = self.add_bitmap('bitmap0', drive0) @@ -711,16 +703,15 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase): # Start backup parent, _ = bitmap.last_target() target = self.prepare_backup(bitmap, parent) - res = self.vm.qmp('drive-backup', - job_id=bitmap.drive['id'], - device=bitmap.drive['id'], - sync='incremental', - bitmap=bitmap.name, - format=bitmap.drive['fmt'], - target=target, - mode='existing', - on_source_error='stop') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('drive-backup', + job_id=bitmap.drive['id'], + device=bitmap.drive['id'], + sync='incremental', + bitmap=bitmap.name, + format=bitmap.drive['fmt'], + target=target, + mode='existing', + on_source_error='stop') # Wait for the error event = self.vm.event_wait(name="BLOCK_JOB_ERROR", @@ -739,8 +730,7 @@ class TestIncrementalBackupBlkdebug(TestIncrementalBackupBase): })) # Resume and check incremental backup for consistency - res = self.vm.qmp('block-job-resume', device=bitmap.drive['id']) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-resume', device=bitmap.drive['id']) self.wait_qmp_backup(bitmap.drive['id']) # Bitmap Status Check diff --git a/tests/qemu-iotests/129 b/tests/qemu-iotests/129 index c75ec62ecf..97773cd96d 100755 --- a/tests/qemu-iotests/129 +++ b/tests/qemu-iotests/129 @@ -55,11 +55,9 @@ class TestStopWithBlockJob(iotests.QMPTestCase): def do_test_stop(self, cmd, **args): """Test 'stop' while block job is running on a throttled drive. The 'stop' command shouldn't drain the job""" - result = self.vm.qmp(cmd, **args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd(cmd, **args) - result = self.vm.qmp("stop") - self.assert_qmp(result, 'return', {}) + self.vm.cmd("stop") result = self.vm.qmp("query-block-jobs") self.assert_qmp(result, 'return[0]/status', 'running') @@ -87,7 +85,7 @@ class TestStopWithBlockJob(iotests.QMPTestCase): iotests.qemu_img('create', '-f', iotests.imgfmt, self.overlay_img, '1G') - result = self.vm.qmp('blockdev-add', **{ + self.vm.cmd('blockdev-add', { 'node-name': 'overlay', 'driver': iotests.imgfmt, 'file': { @@ -95,11 +93,9 @@ class TestStopWithBlockJob(iotests.QMPTestCase): 'filename': self.overlay_img } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-snapshot', - node='source', overlay='overlay') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-snapshot', + node='source', overlay='overlay') self.do_test_stop('block-commit', device='drive0', top_node='source') diff --git a/tests/qemu-iotests/132 b/tests/qemu-iotests/132 index 367ea08036..12a64b3d95 100755 --- a/tests/qemu-iotests/132 +++ b/tests/qemu-iotests/132 @@ -47,9 +47,8 @@ class TestSingleDrive(iotests.QMPTestCase): pass def test_mirror_discard(self): - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - target=target_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + target=target_img) self.vm.hmp_qemu_io('drive0', 'discard 0 64k') self.complete_and_wait('drive0') self.vm.shutdown() diff --git a/tests/qemu-iotests/139 b/tests/qemu-iotests/139 index 178b1ee230..ebb4cd62b6 100755 --- a/tests/qemu-iotests/139 +++ b/tests/qemu-iotests/139 @@ -58,8 +58,7 @@ class TestBlockdevDel(iotests.QMPTestCase): 'file': {'driver': 'file', 'node-name': file_node, 'filename': base_img}} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) self.checkBlockDriverState(node) self.checkBlockDriverState(file_node) @@ -73,8 +72,7 @@ class TestBlockdevDel(iotests.QMPTestCase): 'backing': None, 'file': {'driver': 'file', 'filename': new_img}} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) self.checkBlockDriverState(node) # Delete a BlockDriverState @@ -89,17 +87,14 @@ class TestBlockdevDel(iotests.QMPTestCase): # Add a device model def addDeviceModel(self, device, backend, driver = 'virtio-blk'): - result = self.vm.qmp('device_add', id = device, - driver = driver, drive = backend) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', id = device, + driver = driver, drive = backend) # Delete a device model def delDeviceModel(self, device, is_virtio_blk = True): - result = self.vm.qmp('device_del', id = device) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_del', id = device) - result = self.vm.qmp('system_reset') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('system_reset') if is_virtio_blk: device_path = '/machine/peripheral/%s/virtio-backend' % device @@ -126,9 +121,8 @@ class TestBlockdevDel(iotests.QMPTestCase): # Insert a BlockDriverState def insertDrive(self, device, node): self.checkBlockDriverState(node) - result = self.vm.qmp('blockdev-insert-medium', - id = device, node_name = node) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-insert-medium', + id = device, node_name = node) self.checkBlockDriverState(node) # Create a snapshot using 'blockdev-snapshot-sync' @@ -139,8 +133,7 @@ class TestBlockdevDel(iotests.QMPTestCase): 'snapshot-file': new_img, 'snapshot-node-name': overlay, 'format': iotests.imgfmt} - result = self.vm.qmp('blockdev-snapshot-sync', conv_keys=False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-snapshot-sync', conv_keys=False, **opts) self.checkBlockDriverState(node) self.checkBlockDriverState(overlay) @@ -148,9 +141,8 @@ class TestBlockdevDel(iotests.QMPTestCase): def createSnapshot(self, node, overlay): self.checkBlockDriverState(node) self.checkBlockDriverState(overlay) - result = self.vm.qmp('blockdev-snapshot', - node = node, overlay = overlay) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-snapshot', + node = node, overlay = overlay) self.checkBlockDriverState(node) self.checkBlockDriverState(overlay) @@ -163,14 +155,12 @@ class TestBlockdevDel(iotests.QMPTestCase): 'node-name': new_node, 'sync': 'top', 'format': iotests.imgfmt} - result = self.vm.qmp('drive-mirror', conv_keys=False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('drive-mirror', conv_keys=False, **opts) self.checkBlockDriverState(new_node) # Complete an existing block job def completeBlockJob(self, id, node_before, node_after): - result = self.vm.qmp('block-job-complete', device=id) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device=id) self.wait_until_completed(id) # Add a BlkDebug node @@ -186,8 +176,7 @@ class TestBlockdevDel(iotests.QMPTestCase): opts = {'driver': 'blkdebug', 'node-name': debug, 'image': image} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) self.checkBlockDriverState(node) self.checkBlockDriverState(debug) @@ -211,8 +200,7 @@ class TestBlockdevDel(iotests.QMPTestCase): 'node-name': blkverify, 'test': node_0, 'raw': node_1} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) self.checkBlockDriverState(test) self.checkBlockDriverState(raw) self.checkBlockDriverState(blkverify) @@ -235,8 +223,7 @@ class TestBlockdevDel(iotests.QMPTestCase): 'node-name': quorum, 'vote-threshold': 1, 'children': [ child_0, child_1 ]} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) self.checkBlockDriverState(child0) self.checkBlockDriverState(child1) self.checkBlockDriverState(quorum) diff --git a/tests/qemu-iotests/147 b/tests/qemu-iotests/147 index 47dfa62e6b..6d6f077a14 100755 --- a/tests/qemu-iotests/147 +++ b/tests/qemu-iotests/147 @@ -58,8 +58,7 @@ class NBDBlockdevAddBase(iotests.QMPTestCase): def client_test(self, filename, address, export=None, node_name='nbd-blockdev', delete=True): bao = self.blockdev_add_options(address, export, node_name) - result = self.vm.qmp('blockdev-add', **bao) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', bao) found = False result = self.vm.qmp('query-named-block-nodes') @@ -75,8 +74,7 @@ class NBDBlockdevAddBase(iotests.QMPTestCase): self.assertTrue(found) if delete: - result = self.vm.qmp('blockdev-del', node_name=node_name) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name=node_name) class QemuNBD(NBDBlockdevAddBase): @@ -158,16 +156,14 @@ class BuiltinNBD(NBDBlockdevAddBase): self.assert_qmp(result, 'return', {}) if export_name is None: - result = self.server.qmp('nbd-server-add', device='nbd-export') + self.server.cmd('nbd-server-add', device='nbd-export') else: - result = self.server.qmp('nbd-server-add', device='nbd-export', - name=export_name) - self.assert_qmp(result, 'return', {}) + self.server.cmd('nbd-server-add', device='nbd-export', + name=export_name) if export_name2 is not None: - result = self.server.qmp('nbd-server-add', device='nbd-export', - name=export_name2) - self.assert_qmp(result, 'return', {}) + self.server.cmd('nbd-server-add', device='nbd-export', + name=export_name2) return True @@ -175,8 +171,7 @@ class BuiltinNBD(NBDBlockdevAddBase): self.assertTrue(self._try_server_up(address, export_name, export_name2)) def _server_down(self): - result = self.server.qmp('nbd-server-stop') - self.assert_qmp(result, 'return', {}) + self.server.cmd('nbd-server-stop') def do_test_inet(self, export_name=None): while True: @@ -218,10 +213,8 @@ class BuiltinNBD(NBDBlockdevAddBase): flatten_sock_addr(address), 'exp1', 'node1', False) self.client_test('nbd://localhost:%i/%s' % (nbd_port, 'exp2'), flatten_sock_addr(address), 'exp2', 'node2', False) - result = self.vm.qmp('blockdev-del', node_name='node1') - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-del', node_name='node2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='node1') + self.vm.cmd('blockdev-del', node_name='node2') self._server_down() def test_inet6(self): @@ -272,8 +265,7 @@ class BuiltinNBD(NBDBlockdevAddBase): result = self.vm.send_fd_scm(fd=sockfd.fileno()) self.assertEqual(result, 0, 'Failed to send socket FD') - result = self.vm.qmp('getfd', fdname='nbd-fifo') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('getfd', fdname='nbd-fifo') address = { 'type': 'fd', 'data': { 'str': 'nbd-fifo' } } diff --git a/tests/qemu-iotests/151 b/tests/qemu-iotests/151 index b4d1bc2553..f2ff9c5dac 100755 --- a/tests/qemu-iotests/151 +++ b/tests/qemu-iotests/151 @@ -79,14 +79,13 @@ class TestActiveMirror(iotests.QMPTestCase): self.vm.hmp_qemu_io('source', 'aio_write -z %i 1M' % offset) # Start the block job - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - filter_node_name='mirror-node', - device='source-node', - target='target-node', - sync='full', - copy_mode='write-blocking') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + filter_node_name='mirror-node', + device='source-node', + target='target-node', + sync='full', + copy_mode='write-blocking') # Start some more requests for offset in range(3 * self.image_len // 8, 5 * self.image_len // 8, 1024 * 1024): @@ -125,23 +124,21 @@ class TestActiveMirror(iotests.QMPTestCase): result = self.vm.hmp_qemu_io('source', 'write -P 1 0 2M') # Start the block job (very slowly) - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - filter_node_name='mirror-node', - device='source-node', - target='target-node', - sync='full', - copy_mode='write-blocking', - buf_size=(1048576 // 4), - speed=1) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + filter_node_name='mirror-node', + device='source-node', + target='target-node', + sync='full', + copy_mode='write-blocking', + buf_size=(1048576 // 4), + speed=1) # Start an unaligned request to a dirty area result = self.vm.hmp_qemu_io('source', 'write -P 2 %i 1' % (1048576 + 42)) # Let the job finish - result = self.vm.qmp('block-job-set-speed', device='mirror', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='mirror', speed=0) self.complete_and_wait(drive='mirror') self.potential_writes_in_flight = False @@ -151,14 +148,14 @@ class TestActiveMirror(iotests.QMPTestCase): result = self.vm.hmp_qemu_io('source', 'write -P 1 0 2M') # Start the block job (very slowly) - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - filter_node_name='mirror-node', - device='source-node', - target='target-node', - sync='full', - copy_mode='write-blocking', - speed=1) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + filter_node_name='mirror-node', + device='source-node', + target='target-node', + sync='full', + copy_mode='write-blocking', + speed=1) self.vm.hmp_qemu_io('source', 'break write_aio A') self.vm.hmp_qemu_io('source', 'aio_write 0 1M') # 1 @@ -189,8 +186,7 @@ class TestActiveMirror(iotests.QMPTestCase): # After resuming 4, one of 2 and 3 goes first and set in_flight_bitmap, # so the other will wait for it. - result = self.vm.qmp('block-job-set-speed', device='mirror', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='mirror', speed=0) self.complete_and_wait(drive='mirror') self.potential_writes_in_flight = False @@ -211,7 +207,7 @@ class TestThrottledWithNbdExportBase(iotests.QMPTestCase): self.vm = iotests.VM() self.vm.launch() - result = self.vm.qmp('object-add', **{ + self.vm.cmd('object-add', **{ 'qom-type': 'throttle-group', 'id': 'thrgr', 'limits': { @@ -219,9 +215,8 @@ class TestThrottledWithNbdExportBase(iotests.QMPTestCase): 'iops-total-max': self.iops } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', **{ + self.vm.cmd('blockdev-add', **{ 'node-name': 'source-node', 'driver': 'throttle', 'throttle-group': 'thrgr', @@ -233,9 +228,8 @@ class TestThrottledWithNbdExportBase(iotests.QMPTestCase): } } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', **{ + self.vm.cmd('blockdev-add', **{ 'node-name': 'target-node', 'driver': iotests.imgfmt, 'file': { @@ -243,23 +237,20 @@ class TestThrottledWithNbdExportBase(iotests.QMPTestCase): 'filename': target_img } }) - self.assert_qmp(result, 'return', {}) self.nbd_sock = iotests.file_path('nbd.sock', base_dir=iotests.sock_dir) self.nbd_url = f'nbd+unix:///source-node?socket={self.nbd_sock}' - result = self.vm.qmp('nbd-server-start', addr={ + self.vm.cmd('nbd-server-start', addr={ 'type': 'unix', 'data': { 'path': self.nbd_sock } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('block-export-add', id='exp0', type='nbd', - node_name='source-node', writable=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-export-add', id='exp0', type='nbd', + node_name='source-node', writable=True) def tearDown(self): # Wait for background requests to settle @@ -312,15 +303,14 @@ class TestLowThrottledWithNbdExport(TestThrottledWithNbdExportBase): # Launch the mirror job mirror_buf_size = 65536 - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - filter_node_name='mirror-node', - device='source-node', - target='target-node', - sync='full', - copy_mode='write-blocking', - buf_size=mirror_buf_size) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + filter_node_name='mirror-node', + device='source-node', + target='target-node', + sync='full', + copy_mode='write-blocking', + buf_size=mirror_buf_size) # We create the external requests via qemu-io processes on the NBD # server. Have their offset start in the middle of the image so they @@ -408,13 +398,12 @@ class TestHighThrottledWithNbdExport(TestThrottledWithNbdExportBase): # start blockdev-mirror self.vm.qtest(f'clock_step {1 * 1000 * 1000 * 1000}') - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='source-node', - target='target-node', - sync='full', - copy_mode='write-blocking') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='source-node', + target='target-node', + sync='full', + copy_mode='write-blocking') if __name__ == '__main__': diff --git a/tests/qemu-iotests/152 b/tests/qemu-iotests/152 index 4e179c340f..197bea9e77 100755 --- a/tests/qemu-iotests/152 +++ b/tests/qemu-iotests/152 @@ -41,16 +41,16 @@ class TestUnaligned(iotests.QMPTestCase): pass def test_unaligned(self): - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - granularity=65536, target=target_img) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + granularity=65536, target=target_img) self.complete_and_wait() self.vm.shutdown() self.assertEqual(iotests.image_size(test_img), iotests.image_size(target_img), "Target size doesn't match source when granularity when unaligend") def test_unaligned_with_update(self): - result = self.vm.qmp('drive-mirror', device='drive0', sync='full', - granularity=65536, target=target_img) + self.vm.cmd('drive-mirror', device='drive0', sync='full', + granularity=65536, target=target_img) self.wait_ready() self.vm.hmp_qemu_io('drive0', 'write 0 512') self.complete_and_wait(wait_ready=False) diff --git a/tests/qemu-iotests/155 b/tests/qemu-iotests/155 index eadda52615..38eacb4127 100755 --- a/tests/qemu-iotests/155 +++ b/tests/qemu-iotests/155 @@ -110,8 +110,7 @@ class BaseClass(iotests.QMPTestCase): elif self.target_blockdev_backing: options['backing'] = self.target_blockdev_backing - result = self.vm.qmp('blockdev-add', **options) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', options) def tearDown(self): self.vm.shutdown() @@ -178,20 +177,18 @@ class MirrorBaseClass(BaseClass): def runMirror(self, sync): if self.cmd == 'blockdev-mirror': - result = self.vm.qmp(self.cmd, job_id='mirror-job', device='source', - sync=sync, target='target', - auto_finalize=False) + self.vm.cmd(self.cmd, job_id='mirror-job', device='source', + sync=sync, target='target', + auto_finalize=False) else: if self.existing: mode = 'existing' else: mode = 'absolute-paths' - result = self.vm.qmp(self.cmd, job_id='mirror-job', device='source', - sync=sync, target=target_img, - format=iotests.imgfmt, mode=mode, - node_name='target', auto_finalize=False) - - self.assert_qmp(result, 'return', {}) + self.vm.cmd(self.cmd, job_id='mirror-job', device='source', + sync=sync, target=target_img, + format=iotests.imgfmt, mode=mode, + node_name='target', auto_finalize=False) self.vm.run_job('mirror-job', auto_finalize=False, pre_finalize=self.openBacking, auto_dismiss=True) @@ -258,16 +255,14 @@ class TestBlockdevMirrorReopen(MirrorBaseClass): def openBacking(self): if not self.target_open_with_backing: - result = self.vm.qmp('blockdev-add', node_name="backing", - driver="null-co") - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-reopen', options=[{ - 'node-name': "target", - 'driver': iotests.imgfmt, - 'file': "target-file", - 'backing': "backing" - }]) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', node_name="backing", + driver="null-co") + self.vm.cmd('blockdev-reopen', options=[{ + 'node-name': "target", + 'driver': iotests.imgfmt, + 'file': "target-file", + 'backing': "backing" + }]) class TestBlockdevMirrorReopenIothread(TestBlockdevMirrorReopen): use_iothread = True @@ -281,12 +276,10 @@ class TestBlockdevMirrorSnapshot(MirrorBaseClass): def openBacking(self): if not self.target_open_with_backing: - result = self.vm.qmp('blockdev-add', node_name="backing", - driver="null-co") - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-snapshot', node="backing", - overlay="target") - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', node_name="backing", + driver="null-co") + self.vm.cmd('blockdev-snapshot', node="backing", + overlay="target") class TestBlockdevMirrorSnapshotIothread(TestBlockdevMirrorSnapshot): use_iothread = True @@ -295,14 +288,12 @@ class TestCommit(BaseClass): existing = False def testCommit(self): - result = self.vm.qmp('block-commit', job_id='commit-job', - device='source', base=back1_img) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', job_id='commit-job', + device='source', base=back1_img) self.vm.event_wait('BLOCK_JOB_READY') - result = self.vm.qmp('block-job-complete', device='commit-job') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device='commit-job') self.vm.event_wait('BLOCK_JOB_COMPLETED') diff --git a/tests/qemu-iotests/165 b/tests/qemu-iotests/165 index e3ef28e2ee..b24907a62f 100755 --- a/tests/qemu-iotests/165 +++ b/tests/qemu-iotests/165 @@ -116,9 +116,8 @@ class TestPersistentDirtyBitmap(iotests.QMPTestCase): sha256_2 = self.getSha256() assert sha256_1 != sha256_2 # Otherwise, it's not very interesting. - result = self.vm.qmp('block-dirty-bitmap-clear', node='drive0', - name='bitmap0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-dirty-bitmap-clear', node='drive0', + name='bitmap0') # Start with regions1 @@ -137,7 +136,7 @@ class TestPersistentDirtyBitmap(iotests.QMPTestCase): assert sha256_1 == self.getSha256() # Reopen to RW - result = self.vm.qmp('blockdev-reopen', options=[{ + self.vm.cmd('blockdev-reopen', options=[{ 'node-name': 'node0', 'driver': iotests.imgfmt, 'file': { @@ -146,7 +145,6 @@ class TestPersistentDirtyBitmap(iotests.QMPTestCase): }, 'read-only': False }]) - self.assert_qmp(result, 'return', {}) # Check that bitmap is reopened to RW and we can write to it. self.writeRegions(regions2) diff --git a/tests/qemu-iotests/196 b/tests/qemu-iotests/196 index 76509a5ad1..e5105b1354 100755 --- a/tests/qemu-iotests/196 +++ b/tests/qemu-iotests/196 @@ -45,8 +45,7 @@ class TestInvalidateAutoclear(iotests.QMPTestCase): self.vm_b.add_incoming("exec: cat '" + migfile + "'") def test_migration(self): - result = self.vm_a.qmp('migrate', uri='exec:cat>' + migfile) - self.assert_qmp(result, 'return', {}); + self.vm_a.cmd('migrate', uri='exec:cat>' + migfile) self.assertNotEqual(self.vm_a.event_wait("STOP"), None) with open(disk, 'r+b') as f: diff --git a/tests/qemu-iotests/205 b/tests/qemu-iotests/205 index 15f798288a..2370e1a138 100755 --- a/tests/qemu-iotests/205 +++ b/tests/qemu-iotests/205 @@ -44,10 +44,8 @@ class TestNbdServerRemove(iotests.QMPTestCase): } } - result = self.vm.qmp('nbd-server-start', addr=address) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('nbd-server-add', device='drive0', name='exp') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-start', addr=address) + self.vm.cmd('nbd-server-add', device='drive0', name='exp') def tearDown(self): self.vm.shutdown() diff --git a/tests/qemu-iotests/218 b/tests/qemu-iotests/218 index 6320c4cb56..81aa68806f 100755 --- a/tests/qemu-iotests/218 +++ b/tests/qemu-iotests/218 @@ -41,34 +41,30 @@ iotests.script_initialize(supported_fmts=['qcow2', 'raw']) def start_mirror(vm, speed=None, buf_size=None): vm.launch() - ret = vm.qmp('blockdev-add', - node_name='source', - driver='null-co', - size=1048576) - assert ret['return'] == {} - - ret = vm.qmp('blockdev-add', - node_name='target', - driver='null-co', - size=1048576) - assert ret['return'] == {} + vm.cmd('blockdev-add', + node_name='source', + driver='null-co', + size=1048576) + + vm.cmd('blockdev-add', + node_name='target', + driver='null-co', + size=1048576) if speed is not None: - ret = vm.qmp('blockdev-mirror', - job_id='mirror', - device='source', - target='target', - sync='full', - speed=speed, - buf_size=buf_size) + vm.cmd('blockdev-mirror', + job_id='mirror', + device='source', + target='target', + sync='full', + speed=speed, + buf_size=buf_size) else: - ret = vm.qmp('blockdev-mirror', - job_id='mirror', - device='source', - target='target', - sync='full') - - assert ret['return'] == {} + vm.cmd('blockdev-mirror', + job_id='mirror', + device='source', + target='target', + sync='full') log('') @@ -150,38 +146,33 @@ with iotests.VM() as vm, \ vm.launch() - ret = vm.qmp('object-add', qom_type='throttle-group', id='tg', - limits={'bps-read': 4096}) - assert ret['return'] == {} - - ret = vm.qmp('blockdev-add', - node_name='source', - driver=iotests.imgfmt, - file={ - 'driver': 'file', - 'filename': src_img_path - }) - assert ret['return'] == {} - - ret = vm.qmp('blockdev-add', - node_name='throttled-source', - driver='throttle', - throttle_group='tg', - file='source') - assert ret['return'] == {} - - ret = vm.qmp('blockdev-add', - node_name='target', - driver='null-co', - size=(64 * 1048576)) - assert ret['return'] == {} - - ret = vm.qmp('blockdev-mirror', - job_id='mirror', - device='throttled-source', - target='target', - sync='full') - assert ret['return'] == {} + vm.cmd('object-add', qom_type='throttle-group', id='tg', + limits={'bps-read': 4096}) + + vm.cmd('blockdev-add', + node_name='source', + driver=iotests.imgfmt, + file={ + 'driver': 'file', + 'filename': src_img_path + }) + + vm.cmd('blockdev-add', + node_name='throttled-source', + driver='throttle', + throttle_group='tg', + file='source') + + vm.cmd('blockdev-add', + node_name='target', + driver='null-co', + size=(64 * 1048576)) + + vm.cmd('blockdev-mirror', + job_id='mirror', + device='throttled-source', + target='target', + sync='full') log(vm.qmp('quit')) diff --git a/tests/qemu-iotests/245 b/tests/qemu-iotests/245 index 92b28c79be..a934c9d1e6 100755 --- a/tests/qemu-iotests/245 +++ b/tests/qemu-iotests/245 @@ -136,8 +136,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): def test_incorrect_parameters_single_file(self): # Open 'hd0' only (no backing files) opts = hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) original_graph = self.vm.qmp('query-named-block-nodes') # We can reopen the image passing the same options @@ -171,8 +170,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.check_node_graph(original_graph) # Remove the node - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') # This test opens an image with a backing file and tries to reopen # it with illegal / incorrect parameters. @@ -180,8 +178,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # Open hd1 omitting the backing options (hd0 will be opened # with the default options) opts = hd_opts(1) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) original_graph = self.vm.qmp('query-named-block-nodes') # We can't reopen the image passing the same options, 'backing' is mandatory @@ -213,8 +210,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.check_node_graph(original_graph) # Remove the node - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd1') # Reopen an image several times changing some of its options def test_reopen(self): @@ -230,8 +226,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # Open the hd1 image passing all backing options opts = hd_opts(1) opts['backing'] = hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) original_graph = self.vm.qmp('query-named-block-nodes') # We can reopen the image passing the same options @@ -306,8 +301,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.assert_qmp_absent(self.get_node('hd1'), 'image/backing-image') # Open the 'hd0' image - result = self.vm.qmp('blockdev-add', conv_keys = False, **hd_opts(0)) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **hd_opts(0)) # Reopen the hd1 image setting 'hd0' as its backing image self.reopen(opts, {'backing': 'hd0'}) @@ -326,10 +320,8 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.assert_qmp(result, 'error/desc', "Node 'hd0' is busy: node is used as backing hd of 'hd1'") # But we can remove both nodes if done in the proper order - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd1') - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd1') + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') # Reopen a raw image and see the effect of changing the 'offset' option def test_reopen_raw(self): @@ -345,8 +337,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): qemu_io('-f', 'raw', '-c', 'write -P 0xa1 1M 1M', hd_path[0]) # Open the raw file with QEMU - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Read 1MB from offset 0 self.run_qemu_io("hd0", "read -P 0xa0 0 1M") @@ -362,8 +353,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.run_qemu_io("hd0", "read -P 0xa0 0 1M") # Remove the block device - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') # Omitting an option should reset it to the default value, but if # an option cannot be changed it shouldn't be possible to reset it @@ -377,8 +367,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): 'node-name': 'hd0-file' } } # Open the file with QEMU - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # file.x-check-cache-dropped can be changed... self.reopen(opts, { 'file.x-check-cache-dropped': False }) @@ -394,8 +383,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.reopen(opts, { 'file.locking': 'off' }) # Remove the block device - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') # This test modifies the node graph a few times by changing the # 'backing' option on reopen and verifies that the guest data that @@ -407,8 +395,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): for i in range(3): opts.append(hd_opts(i)) opts[i]['backing'] = None - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts[i]) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts[i]) # hd0 self.run_qemu_io("hd0", "read -P 0xa0 0 1M") @@ -499,8 +486,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): for i in range(3): opts.append(hd_opts(i)) opts[i]['backing'] = None - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts[i]) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts[i]) # hd1 <- hd0, hd1 <- hd2 self.reopen(opts[0], {'backing': 'hd1'}) @@ -532,8 +518,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): 'node-name': 'bv', 'test': 'hd0', 'raw': 'hd1'} - result = self.vm.qmp('blockdev-add', conv_keys = False, **bvopts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **bvopts) # blkverify doesn't currently allow reopening. TODO: implement this self.reopen(bvopts, {}, "Block format 'blkverify' used by node 'bv'" + @@ -544,8 +529,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): "Making 'bv' a backing child of 'hd0' would create a cycle") # Delete the blkverify node - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'bv') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'bv') # Replace the protocol layer ('file' parameter) of a disk image def test_replace_file(self): @@ -556,16 +540,13 @@ class TestBlockdevReopen(iotests.QMPTestCase): hd0_opts = {'driver': 'file', 'node-name': 'hd0-file', 'filename': hd_path[0] } hd1_opts = {'driver': 'file', 'node-name': 'hd1-file', 'filename': hd_path[1] } - result = self.vm.qmp('blockdev-add', conv_keys = False, **hd0_opts) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', conv_keys = False, **hd1_opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **hd0_opts) + self.vm.cmd('blockdev-add', conv_keys = False, **hd1_opts) # Add a raw format layer that uses hd0-file as its protocol layer opts = {'driver': 'raw', 'node-name': 'hd', 'file': 'hd0-file'} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Fill the image with data self.run_qemu_io("hd", "read -P 0 0 10k") @@ -588,21 +569,18 @@ class TestBlockdevReopen(iotests.QMPTestCase): def test_insert_throttle_filter(self): # Add an image to the VM hd0_opts = hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **hd0_opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **hd0_opts) # Create a throttle-group object opts = { 'qom-type': 'throttle-group', 'id': 'group0', 'limits': { 'iops-total': 1000 } } - result = self.vm.qmp('object-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', conv_keys = False, **opts) # Add a throttle filter with the group that we just created. # The filter is not used by anyone yet opts = { 'driver': 'throttle', 'node-name': 'throttle0', 'throttle-group': 'group0', 'file': 'hd0-file' } - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Insert the throttle filter between hd0 and hd0-file self.reopen(hd0_opts, {'file': 'throttle0'}) @@ -615,15 +593,13 @@ class TestBlockdevReopen(iotests.QMPTestCase): def test_insert_compress_filter(self): # Add an image to the VM: hd (raw) -> hd0 (qcow2) -> hd0-file (file) opts = {'driver': 'raw', 'node-name': 'hd', 'file': hd_opts(0)} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Add a 'compress' filter filter_opts = {'driver': 'compress', 'node-name': 'compress0', 'file': 'hd0'} - result = self.vm.qmp('blockdev-add', conv_keys = False, **filter_opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **filter_opts) # Unmap the beginning of the image (we cannot write compressed # data to an allocated cluster) @@ -659,12 +635,10 @@ class TestBlockdevReopen(iotests.QMPTestCase): def test_swap_files(self): # Add hd0 and hd2 (none of them with backing files) opts0 = hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts0) opts2 = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts2) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts2) # Write different data to both block devices self.run_qemu_io("hd0", "write -P 0xa0 0 1k") @@ -712,15 +686,13 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(i) # Open all three images without backing file opts['backing'] = None - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) opts = {'driver': 'quorum', 'node-name': 'quorum0', 'children': ['hd0', 'hd1', 'hd2'], 'vote-threshold': 2} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Quorum doesn't currently allow reopening. TODO: implement this self.reopen(opts, {}, "Block format 'quorum' used by node 'quorum0'" + @@ -732,14 +704,12 @@ class TestBlockdevReopen(iotests.QMPTestCase): "Making 'quorum0' a backing child of 'hd0' would create a cycle") # Delete quorum0 - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'quorum0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'quorum0') # Delete hd0, hd1 and hd2 for i in range(3): - result = self.vm.qmp('blockdev-del', conv_keys = True, - node_name = 'hd%d' % i) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, + node_name = 'hd%d' % i) ###################### ###### blkdebug ###### @@ -748,8 +718,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): 'node-name': 'bd', 'config': '/dev/null', 'image': hd_opts(0)} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # blkdebug allows reopening if we keep the same options self.reopen(opts) @@ -762,16 +731,14 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.reopen(opts, {}, "Option 'config' cannot be reset to its default value") # Delete the blkdebug node - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'bd') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'bd') ################## ###### null ###### ################## opts = {'driver': 'null-co', 'node-name': 'root', 'size': 1024} - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # 1 << 30 is the default value, but we cannot change it explicitly self.reopen(opts, {'size': (1 << 30)}, "Cannot change the option 'size'") @@ -780,16 +747,14 @@ class TestBlockdevReopen(iotests.QMPTestCase): del opts['size'] self.reopen(opts, {}, "Option 'size' cannot be reset to its default value") - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'root') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'root') ################## ###### file ###### ################## opts = hd_opts(0) opts['file']['locking'] = 'on' - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # 'locking' cannot be changed del opts['file']['locking'] @@ -803,27 +768,23 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.reopen(opts, {'locking': 'off'}, "Cannot change the option 'locking'") self.reopen(opts, {}, "Option 'locking' cannot be reset to its default value") - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') ###################### ###### throttle ###### ###################### opts = { 'qom-type': 'throttle-group', 'id': 'group0', 'limits': { 'iops-total': 1000 } } - result = self.vm.qmp('object-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', conv_keys = False, **opts) opts = { 'qom-type': 'throttle-group', 'id': 'group1', 'limits': { 'iops-total': 2000 } } - result = self.vm.qmp('object-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', conv_keys = False, **opts) # Add a throttle filter with group = group0 opts = { 'driver': 'throttle', 'node-name': 'throttle0', 'throttle-group': 'group0', 'file': hd_opts(0) } - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # We can reopen it if we keep the same options self.reopen(opts) @@ -851,16 +812,13 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.assert_qmp(result, 'error/desc', "object 'group0' is in use, can not be deleted") # But group1 is free this time, and it can be deleted - result = self.vm.qmp('object-del', id = 'group1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-del', id = 'group1') # Let's delete the filter node - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'throttle0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'throttle0') # And we can finally get rid of group0 - result = self.vm.qmp('object-del', id = 'group0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-del', id = 'group0') # If an image has a backing file then the 'backing' option must be # passed on reopen. We don't allow leaving the option out in this @@ -868,13 +826,11 @@ class TestBlockdevReopen(iotests.QMPTestCase): def test_missing_backing_options_1(self): # hd2 opts = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # hd0 opts = hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # hd0 has no backing file: we can omit the 'backing' option self.reopen(opts) @@ -897,11 +853,9 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.reopen(opts) # Remove both hd0 and hd2 - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd2') # If an image has default backing file (as part of its metadata) # then the 'backing' option must be passed on reopen. We don't @@ -911,8 +865,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # hd0 <- hd1 # (hd0 is hd1's default backing file) opts = hd_opts(1) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # hd1 has a backing file: we can't omit the 'backing' option self.reopen(opts, {}, "backing is missing for 'hd1'") @@ -923,8 +876,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # No backing file attached to hd1 now, but we still can't omit the 'backing' option self.reopen(opts, {}, "backing is missing for 'hd1'") - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd1') # Test that making 'backing' a reference to an existing child # keeps its current options @@ -937,8 +889,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts['detect-zeroes'] = 'on' opts['backing']['detect-zeroes'] = 'on' opts['backing']['backing']['detect-zeroes'] = 'on' - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Reopen the chain passing the minimum amount of required options. # By making 'backing' a reference to hd1 (instead of a sub-dict) @@ -961,12 +912,10 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = None - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Stream hd1 into hd0 and wait until it's done - result = self.vm.qmp('block-stream', conv_keys = True, job_id = 'stream0', device = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', conv_keys = True, job_id = 'stream0', device = 'hd0') self.wait_until_completed(drive = 'stream0') # Now we have only hd0 @@ -982,8 +931,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # We can also reopen hd0 if we set 'backing' to null self.reopen(opts, {'backing': None}) - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') # Another block_stream test def test_block_stream_2(self): @@ -991,13 +939,11 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # Stream hd1 into hd0 and wait until it's done - result = self.vm.qmp('block-stream', conv_keys = True, job_id = 'stream0', - device = 'hd0', base_node = 'hd2') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', conv_keys = True, job_id = 'stream0', + device = 'hd0', base_node = 'hd2') self.wait_until_completed(drive = 'stream0') # The chain is hd2 <- hd0 now. hd1 is missing @@ -1019,8 +965,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.reopen(opts, {}, "backing is missing for 'hd0'") # Now we can delete hd0 (and hd2) - result = self.vm.qmp('blockdev-del', conv_keys = True, node_name = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', conv_keys = True, node_name = 'hd0') self.assertEqual(self.get_node('hd2'), None) # Reopen the chain during a block-stream job (from hd1 to hd0) @@ -1029,14 +974,12 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # hd2 <- hd0 - result = self.vm.qmp('block-stream', conv_keys = True, job_id = 'stream0', - device = 'hd0', base_node = 'hd2', - auto_finalize = False) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', conv_keys = True, job_id = 'stream0', + device = 'hd0', base_node = 'hd2', + auto_finalize = False) # We can remove hd2 while the stream job is ongoing opts['backing']['backing'] = None @@ -1054,14 +997,12 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) # hd1 <- hd0 - result = self.vm.qmp('block-stream', conv_keys = True, job_id = 'stream0', - device = 'hd1', filter_node_name='cor', - auto_finalize = False) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', conv_keys = True, job_id = 'stream0', + device = 'hd1', filter_node_name='cor', + auto_finalize = False) # We can't reopen with the original options because there is a filter # inserted by stream job above hd1. @@ -1090,12 +1031,10 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) - result = self.vm.qmp('block-commit', conv_keys = True, job_id = 'commit0', - device = 'hd0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', conv_keys = True, job_id = 'commit0', + device = 'hd0') # We can't remove hd2 while the commit job is ongoing opts['backing']['backing'] = None @@ -1110,8 +1049,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): self.assert_qmp(event, 'data/type', 'commit') self.assert_qmp_absent(event, 'data/error') - result = self.vm.qmp('block-job-complete', device='commit0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device='commit0') self.wait_until_completed(drive = 'commit0') @@ -1121,13 +1059,11 @@ class TestBlockdevReopen(iotests.QMPTestCase): opts = hd_opts(0) opts['backing'] = hd_opts(1) opts['backing']['backing'] = hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) - result = self.vm.qmp('block-commit', conv_keys = True, job_id = 'commit0', - device = 'hd0', top_node = 'hd1', - auto_finalize = False) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', conv_keys = True, job_id = 'commit0', + device = 'hd0', top_node = 'hd1', + auto_finalize = False) # We can't remove hd2 while the commit job is ongoing opts['backing']['backing'] = None @@ -1147,36 +1083,28 @@ class TestBlockdevReopen(iotests.QMPTestCase): def run_test_iothreads(self, iothread_a, iothread_b, errmsg = None, opts_a = None, opts_b = None): opts = opts_a or hd_opts(0) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts) opts2 = opts_b or hd_opts(2) - result = self.vm.qmp('blockdev-add', conv_keys = False, **opts2) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', conv_keys = False, **opts2) - result = self.vm.qmp('object-add', qom_type='iothread', id='iothread0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', qom_type='iothread', id='iothread0') - result = self.vm.qmp('object-add', qom_type='iothread', id='iothread1') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', qom_type='iothread', id='iothread1') - result = self.vm.qmp('device_add', driver='virtio-scsi', id='scsi0', - iothread=iothread_a) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', driver='virtio-scsi', id='scsi0', + iothread=iothread_a) - result = self.vm.qmp('device_add', driver='virtio-scsi', id='scsi1', - iothread=iothread_b) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', driver='virtio-scsi', id='scsi1', + iothread=iothread_b) if iothread_a: - result = self.vm.qmp('device_add', driver='scsi-hd', drive='hd0', - share_rw=True, bus="scsi0.0") - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', driver='scsi-hd', drive='hd0', + share_rw=True, bus="scsi0.0") if iothread_b: - result = self.vm.qmp('device_add', driver='scsi-hd', drive='hd2', - share_rw=True, bus="scsi1.0") - self.assert_qmp(result, 'return', {}) + self.vm.cmd('device_add', driver='scsi-hd', drive='hd2', + share_rw=True, bus="scsi1.0") # Attaching the backing file may or may not work self.reopen(opts, {'backing': 'hd2'}, errmsg) @@ -1205,8 +1133,7 @@ class TestBlockdevReopen(iotests.QMPTestCase): # Create a throttle-group object opts = { 'qom-type': 'throttle-group', 'id': 'group0', 'limits': { 'iops-total': 1000 } } - result = self.vm.qmp('object-add', conv_keys = False, **opts) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('object-add', conv_keys = False, **opts) # Options with a throttle filter between format and protocol opts = [ diff --git a/tests/qemu-iotests/256 b/tests/qemu-iotests/256 index d7e67f4a05..f34af6cef7 100755 --- a/tests/qemu-iotests/256 +++ b/tests/qemu-iotests/256 @@ -40,25 +40,25 @@ with iotests.FilePath('img0') as img0_path, \ def create_target(filepath, name, size): basename = os.path.basename(filepath) nodename = "file_{}".format(basename) - log(vm.command('blockdev-create', job_id='job1', - options={ - 'driver': 'file', - 'filename': filepath, - 'size': 0, - })) + log(vm.cmd('blockdev-create', job_id='job1', + options={ + 'driver': 'file', + 'filename': filepath, + 'size': 0, + })) vm.run_job('job1') - log(vm.command('blockdev-add', driver='file', - node_name=nodename, filename=filepath)) - log(vm.command('blockdev-create', job_id='job2', - options={ - 'driver': iotests.imgfmt, - 'file': nodename, - 'size': size, - })) + log(vm.cmd('blockdev-add', driver='file', + node_name=nodename, filename=filepath)) + log(vm.cmd('blockdev-create', job_id='job2', + options={ + 'driver': iotests.imgfmt, + 'file': nodename, + 'size': size, + })) vm.run_job('job2') - log(vm.command('blockdev-add', driver=iotests.imgfmt, - node_name=name, - file=nodename)) + log(vm.cmd('blockdev-add', driver=iotests.imgfmt, + node_name=name, + file=nodename)) log('--- Preparing images & VM ---\n') vm.add_object('iothread,id=iothread0') diff --git a/tests/qemu-iotests/257 b/tests/qemu-iotests/257 index e7e7a2317e..7d3720b8e5 100755 --- a/tests/qemu-iotests/257 +++ b/tests/qemu-iotests/257 @@ -160,26 +160,26 @@ class Drive: file_node_name = "file_{}".format(basename) vm = self.vm - log(vm.command('blockdev-create', job_id='bdc-file-job', - options={ - 'driver': 'file', - 'filename': self.path, - 'size': 0, - })) + log(vm.cmd('blockdev-create', job_id='bdc-file-job', + options={ + 'driver': 'file', + 'filename': self.path, + 'size': 0, + })) vm.run_job('bdc-file-job') - log(vm.command('blockdev-add', driver='file', - node_name=file_node_name, filename=self.path)) - - log(vm.command('blockdev-create', job_id='bdc-fmt-job', - options={ - 'driver': fmt, - 'file': file_node_name, - 'size': size, - })) + log(vm.cmd('blockdev-add', driver='file', + node_name=file_node_name, filename=self.path)) + + log(vm.cmd('blockdev-create', job_id='bdc-fmt-job', + options={ + 'driver': fmt, + 'file': file_node_name, + 'size': size, + })) vm.run_job('bdc-fmt-job') - log(vm.command('blockdev-add', driver=fmt, - node_name=name, - file=file_node_name)) + log(vm.cmd('blockdev-add', driver=fmt, + node_name=name, + file=file_node_name)) self.fmt = fmt self.size = size self.node = name diff --git a/tests/qemu-iotests/264 b/tests/qemu-iotests/264 index 289381e315..c532ccd809 100755 --- a/tests/qemu-iotests/264 +++ b/tests/qemu-iotests/264 @@ -48,18 +48,16 @@ class TestNbdReconnect(iotests.QMPTestCase): """Stat job with nbd target and kill the server""" assert job in ('blockdev-backup', 'blockdev-mirror') with qemu_nbd_popen('-k', nbd_sock, '-f', iotests.imgfmt, disk_b): - result = self.vm.qmp('blockdev-add', - **{'node_name': 'backup0', - 'driver': 'raw', - 'file': {'driver': 'nbd', - 'server': {'type': 'unix', - 'path': nbd_sock}, - 'reconnect-delay': 10}}) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp(job, device='drive0', - sync='full', target='backup0', - speed=(1 * 1024 * 1024)) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', + {'node-name': 'backup0', + 'driver': 'raw', + 'file': {'driver': 'nbd', + 'server': {'type': 'unix', + 'path': nbd_sock}, + 'reconnect-delay': 10}}) + self.vm.cmd(job, device='drive0', + sync='full', target='backup0', + speed=(1 * 1024 * 1024)) # Wait for some progress t = 0.0 @@ -77,8 +75,7 @@ class TestNbdReconnect(iotests.QMPTestCase): self.assertTrue(jobs) self.assertTrue(jobs[0]['offset'] < jobs[0]['len']) - result = self.vm.qmp('block-job-set-speed', device='drive0', speed=0) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', speed=0) # Emulate server down time for 1 second time.sleep(1) @@ -91,12 +88,10 @@ class TestNbdReconnect(iotests.QMPTestCase): with qemu_nbd_popen('-k', nbd_sock, '-f', iotests.imgfmt, disk_b): e = self.vm.event_wait('BLOCK_JOB_COMPLETED') self.assertEqual(e['data']['offset'], size) - result = self.vm.qmp('blockdev-del', node_name='backup0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='backup0') def cancel_job(self): - result = self.vm.qmp('block-job-cancel', device='drive0', force=True) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-cancel', device='drive0', force=True) start_t = time.time() self.vm.event_wait('BLOCK_JOB_CANCELLED') diff --git a/tests/qemu-iotests/281 b/tests/qemu-iotests/281 index 5e1339bd75..f6746a12e8 100755 --- a/tests/qemu-iotests/281 +++ b/tests/qemu-iotests/281 @@ -56,15 +56,13 @@ class TestDirtyBitmapIOThread(iotests.QMPTestCase): os.remove(self.images[name]) def test_add_dirty_bitmap(self): - result = self.vm.qmp( + self.vm.cmd( 'block-dirty-bitmap-add', node='drive0', name='bitmap1', persistent=True, ) - self.assert_qmp(result, 'return', {}) - # Test for RHBZ#1746217 & RHBZ#1773517 class TestNBDMirrorIOThread(iotests.QMPTestCase): @@ -105,23 +103,21 @@ class TestNBDMirrorIOThread(iotests.QMPTestCase): os.remove(self.images[name]) def test_nbd_mirror(self): - result = self.vm_tgt.qmp( + self.vm_tgt.cmd( 'nbd-server-start', addr={ 'type': 'unix', 'data': { 'path': self.nbd_sock } } ) - self.assert_qmp(result, 'return', {}) - result = self.vm_tgt.qmp( + self.vm_tgt.cmd( 'nbd-server-add', device='drive0', writable=True ) - self.assert_qmp(result, 'return', {}) - result = self.vm_src.qmp( + self.vm_src.cmd( 'drive-mirror', device='drive0', target='nbd+unix:///drive0?socket=' + self.nbd_sock, @@ -130,7 +126,6 @@ class TestNBDMirrorIOThread(iotests.QMPTestCase): speed=64*1024*1024, job_id='j1' ) - self.assert_qmp(result, 'return', {}) self.vm_src.event_wait(name="BLOCK_JOB_READY") @@ -290,8 +285,7 @@ class TestYieldingAndTimers(iotests.QMPTestCase): # they will remain active, fire later, and then access freed data. # (Or, with "block/nbd: Assert there are no timers when closed" # applied, the assertions added in that patch will fail.) - result = self.vm.qmp('blockdev-del', node_name='nbd') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', node_name='nbd') # Give the timers some time to fire (both have a timeout of 1 s). # (Sleeping in an iotest may ring some alarm bells, but note that if @@ -303,9 +297,8 @@ class TestYieldingAndTimers(iotests.QMPTestCase): def test_yield_in_iothread(self): # Move the NBD node to the I/O thread; the NBD block driver should # attach the connection's QIOChannel to that thread's AioContext, too - result = self.vm.qmp('x-blockdev-set-iothread', - node_name='nbd', iothread='iothr') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('x-blockdev-set-iothread', + node_name='nbd', iothread='iothr') # Do some I/O that will be throttled by the QSD, so that the network # connection hopefully will yield here. When it is resumed, it must diff --git a/tests/qemu-iotests/295 b/tests/qemu-iotests/295 index 270ad3999f..04818af264 100755 --- a/tests/qemu-iotests/295 +++ b/tests/qemu-iotests/295 @@ -57,8 +57,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): # create the secrets and load 'em into the VM self.secrets = [ Secret(i) for i in range(0, 6) ] for secret in self.secrets: - result = self.vm.qmp("object-add", **secret.to_qmp_object()) - self.assert_qmp(result, 'return', {}) + self.vm.cmd("object-add", **secret.to_qmp_object()) if iotests.imgfmt == "qcow2": self.pfx = "encrypt." @@ -102,8 +101,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): } } - result = self.vm.qmp('blockdev-add', ** - { + self.vm.cmd('blockdev-add', { 'driver': iotests.imgfmt, 'node-name': id, 'read-only': read_only, @@ -116,12 +114,10 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): } } ) - self.assert_qmp(result, 'return', {}) # close the encrypted block device def closeImageQmp(self, id): - result = self.vm.qmp('blockdev-del', **{ 'node-name': id }) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-del', {'node-name': id}) ########################################################################### # add a key to an encrypted block device @@ -160,8 +156,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): args['force'] = True #TODO: check what jobs return - result = self.vm.qmp('x-blockdev-amend', **args) - assert result['return'] == {} + self.vm.cmd('x-blockdev-amend', **args) self.vm.run_job('job_add_key') # erase a key from an encrypted block device @@ -194,8 +189,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): if force == True: args['force'] = True - result = self.vm.qmp('x-blockdev-amend', **args) - assert result['return'] == {} + self.vm.cmd('x-blockdev-amend', **args) self.vm.run_job('job_erase_key') ########################################################################### diff --git a/tests/qemu-iotests/296 b/tests/qemu-iotests/296 index 0d21b740a7..2b63cefff0 100755 --- a/tests/qemu-iotests/296 +++ b/tests/qemu-iotests/296 @@ -42,7 +42,7 @@ class Secret: return [ "secret,id=" + self._id + ",data=" + self._secret] def to_qmp_object(self): - return { "qom_type" : "secret", "id": self.id(), + return { "qom-type" : "secret", "id": self.id(), "data": self.secret() } ################################################################################ @@ -61,10 +61,8 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): # create the secrets and load 'em into the VMs self.secrets = [ Secret(i) for i in range(0, 4) ] for secret in self.secrets: - result = self.vm1.qmp("object-add", **secret.to_qmp_object()) - self.assert_qmp(result, 'return', {}) - result = self.vm2.qmp("object-add", **secret.to_qmp_object()) - self.assert_qmp(result, 'return', {}) + self.vm1.cmd("object-add", secret.to_qmp_object()) + self.vm2.cmd("object-add", secret.to_qmp_object()) # test case shutdown def tearDown(self): @@ -132,17 +130,15 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): } if reOpen: - result = vm.qmp(command, options=[opts]) + vm.cmd(command, options=[opts]) else: - result = vm.qmp(command, **opts) - self.assert_qmp(result, 'return', {}) + vm.cmd(command, opts) ########################################################################### # add virtio-blk consumer for a block device def addImageUser(self, vm, id, disk_id, share_rw=False): - result = vm.qmp('device_add', ** - { + result = vm.qmp('device_add', { 'driver': 'virtio-blk', 'id': id, 'drive': disk_id, @@ -154,8 +150,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): # close the encrypted block device def closeImageQmp(self, vm, id): - result = vm.qmp('blockdev-del', **{ 'node-name': id }) - self.assert_qmp(result, 'return', {}) + vm.cmd('blockdev-del', {'node-name': id}) ########################################################################### @@ -173,7 +168,7 @@ class EncryptionSetupTestCase(iotests.QMPTestCase): }, } - result = vm.qmp('x-blockdev-amend', **args) + result = vm.qmp('x-blockdev-amend', args) iotests.log(result) # Run the job only if it was created event = ('JOB_STATUS_CHANGE', diff --git a/tests/qemu-iotests/298 b/tests/qemu-iotests/298 index 9e75ac6975..09c9290711 100755 --- a/tests/qemu-iotests/298 +++ b/tests/qemu-iotests/298 @@ -80,25 +80,23 @@ class TestPreallocateFilter(TestPreallocateBase): def test_external_snapshot(self): self.test_prealloc() - result = self.vm.qmp('blockdev-snapshot-sync', node_name='disk', - snapshot_file=overlay, - snapshot_node_name='overlay') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-snapshot-sync', node_name='disk', + snapshot_file=overlay, + snapshot_node_name='overlay') # on reopen to r-o base preallocation should be dropped self.check_small() self.vm.hmp_qemu_io('drive0', 'write 1M 1M') - result = self.vm.qmp('block-commit', device='overlay') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-commit', device='overlay') self.complete_and_wait() # commit of new megabyte should trigger preallocation self.check_big() def test_reopen_opts(self): - result = self.vm.qmp('blockdev-reopen', options=[{ + self.vm.cmd('blockdev-reopen', options=[{ 'node-name': 'disk', 'driver': iotests.imgfmt, 'file': { @@ -113,7 +111,6 @@ class TestPreallocateFilter(TestPreallocateBase): } } }]) - self.assert_qmp(result, 'return', {}) self.vm.hmp_qemu_io('drive0', 'write 0 1M') self.assertTrue(os.path.getsize(disk) == 25 * MiB) diff --git a/tests/qemu-iotests/300 b/tests/qemu-iotests/300 index dbd28384ec..e46616d7b1 100755 --- a/tests/qemu-iotests/300 +++ b/tests/qemu-iotests/300 @@ -50,10 +50,9 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): self.vm_b.add_incoming(f'unix:{mig_sock}') self.vm_b.launch() - result = self.vm_a.qmp('block-dirty-bitmap-add', - node=self.src_node_name, - name=self.src_bmap_name) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-add', + node=self.src_node_name, + name=self.src_bmap_name) # Dirty some random megabytes for _ in range(9): @@ -69,8 +68,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): for name in ('dirty-bitmaps', 'events')] for vm in (self.vm_a, self.vm_b): - result = vm.qmp('migrate-set-capabilities', capabilities=caps) - self.assert_qmp(result, 'return', {}) + vm.cmd('migrate-set-capabilities', capabilities=caps) def tearDown(self) -> None: self.vm_a.shutdown() @@ -93,8 +91,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): def migrate(self, bitmap_name_valid: bool = True, migration_success: bool = True) -> None: - result = self.vm_a.qmp('migrate', uri=f'unix:{mig_sock}') - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate', uri=f'unix:{mig_sock}') with iotests.Timeout(5, 'Timeout waiting for migration to complete'): self.assertEqual(self.vm_a.wait_migration('postmigrate'), @@ -442,10 +439,9 @@ class TestBlockBitmapMappingErrors(TestDirtyBitmapMigration): def test_bitmap_name_too_long(self) -> None: name = 'a' * 256 - result = self.vm_a.qmp('block-dirty-bitmap-add', - node=self.src_node_name, - name=name) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-add', + node=self.src_node_name, + name=name) self.migrate(False, False) @@ -517,22 +513,19 @@ class TestCrossAliasMigration(TestDirtyBitmapMigration): TestDirtyBitmapMigration.setUp(self) # Now create another block device and let both have two bitmaps each - result = self.vm_a.qmp('blockdev-add', - node_name='node-b', driver='null-co') - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('blockdev-add', + node_name='node-b', driver='null-co') - result = self.vm_b.qmp('blockdev-add', - node_name='node-a', driver='null-co') - self.assert_qmp(result, 'return', {}) + self.vm_b.cmd('blockdev-add', + node_name='node-a', driver='null-co') bmaps_to_add = (('node-a', 'bmap-b'), ('node-b', 'bmap-a'), ('node-b', 'bmap-b')) for (node, bmap) in bmaps_to_add: - result = self.vm_a.qmp('block-dirty-bitmap-add', - node=node, name=bmap) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-add', + node=node, name=bmap) @staticmethod def cross_mapping() -> BlockBitmapMapping: @@ -611,24 +604,21 @@ class TestAliasTransformMigration(TestDirtyBitmapMigration): TestDirtyBitmapMigration.setUp(self) # Now create another block device and let both have two bitmaps each - result = self.vm_a.qmp('blockdev-add', - node_name='node-b', driver='null-co', - read_zeroes=False) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('blockdev-add', + node_name='node-b', driver='null-co', + read_zeroes=False) - result = self.vm_b.qmp('blockdev-add', - node_name='node-a', driver='null-co', - read_zeroes=False) - self.assert_qmp(result, 'return', {}) + self.vm_b.cmd('blockdev-add', + node_name='node-a', driver='null-co', + read_zeroes=False) bmaps_to_add = (('node-a', 'bmap-b'), ('node-b', 'bmap-a'), ('node-b', 'bmap-b')) for (node, bmap) in bmaps_to_add: - result = self.vm_a.qmp('block-dirty-bitmap-add', - node=node, name=bmap) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-add', + node=node, name=bmap) @staticmethod def transform_mapping() -> BlockBitmapMapping: diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index ef66fbd62b..e5c5798c71 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -38,7 +38,7 @@ import unittest from contextlib import contextmanager from qemu.machine import qtest -from qemu.qmp.legacy import QMPMessage, QEMUMonitorProtocol +from qemu.qmp.legacy import QMPMessage, QMPReturnValue, QEMUMonitorProtocol from qemu.utils import VerboseProcessError # Use this logger for logging messages directly from the iotests module @@ -460,12 +460,17 @@ class QemuStorageDaemon: def qmp(self, cmd: str, args: Optional[Dict[str, object]] = None) \ -> QMPMessage: assert self._qmp is not None - return self._qmp.cmd(cmd, args) + return self._qmp.cmd_raw(cmd, args) def get_qmp(self) -> QEMUMonitorProtocol: assert self._qmp is not None return self._qmp + def cmd(self, cmd: str, args: Optional[Dict[str, object]] = None) \ + -> QMPReturnValue: + assert self._qmp is not None + return self._qmp.cmd(cmd, **(args or {})) + def stop(self, kill_signal=15): self._p.send_signal(kill_signal) self._p.wait() @@ -823,7 +828,7 @@ class VM(qtest.QEMUQtestMachine): super().__init__(qemu_prog, qemu_opts, wrapper=wrapper, name=name, base_temp_dir=test_dir, - sock_dir=sock_dir, qmp_timer=timer) + qmp_timer=timer) self._num_drives = 0 def _post_shutdown(self) -> None: @@ -1247,8 +1252,7 @@ class QMPTestCase(unittest.TestCase): def cancel_and_wait(self, drive='drive0', force=False, resume=False, wait=60.0): '''Cancel a block job and wait for it to finish, returning the event''' - result = self.vm.qmp('block-job-cancel', device=drive, force=force) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-cancel', device=drive, force=force) if resume: self.vm.resume_drive(drive) @@ -1310,8 +1314,7 @@ class QMPTestCase(unittest.TestCase): if wait_ready: self.wait_ready(drive=drive) - result = self.vm.qmp('block-job-complete', device=drive) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-complete', device=drive) event = self.wait_until_completed(drive=drive, error=completion_error) self.assertTrue(event['data']['type'] in ['mirror', 'commit']) @@ -1330,11 +1333,9 @@ class QMPTestCase(unittest.TestCase): assert found def pause_job(self, job_id='job0', wait=True): - result = self.vm.qmp('block-job-pause', device=job_id) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-pause', device=job_id) if wait: - return self.pause_wait(job_id) - return result + self.pause_wait(job_id) def case_skip(self, reason): '''Skip this test case''' diff --git a/tests/qemu-iotests/linters.py b/tests/qemu-iotests/linters.py index 65c4c4e827..9fb3fd1449 100644 --- a/tests/qemu-iotests/linters.py +++ b/tests/qemu-iotests/linters.py @@ -68,7 +68,7 @@ def run_linter( :raise CalledProcessError: If the linter process exits with failure. """ subprocess.run( - ('python3', '-m', tool, *args), + (sys.executable, '-m', tool, *args), env=env, check=True, stdout=subprocess.PIPE if suppress_output else None, diff --git a/tests/qemu-iotests/testenv.py b/tests/qemu-iotests/testenv.py index 9a37ad9152..e67ebd254b 100644 --- a/tests/qemu-iotests/testenv.py +++ b/tests/qemu-iotests/testenv.py @@ -216,7 +216,7 @@ class TestEnv(ContextManager['TestEnv']): self.source_iotests = source_dir self.build_iotests = build_dir - self.build_root = os.path.join(self.build_iotests, '..', '..') + self.build_root = Path(self.build_iotests).parent.parent self.init_directories() diff --git a/tests/qemu-iotests/tests/backing-file-invalidation b/tests/qemu-iotests/tests/backing-file-invalidation index 4eccc80153..b0e19839db 100755 --- a/tests/qemu-iotests/tests/backing-file-invalidation +++ b/tests/qemu-iotests/tests/backing-file-invalidation @@ -129,12 +129,11 @@ class TestPostMigrateFilename(iotests.QMPTestCase): # For good measure, try creating an overlay and check its backing # chain below. This is how the issue was originally found. - result = self.vm_d.qmp('blockdev-snapshot-sync', - format=iotests.imgfmt, - snapshot_file=imgs[3], - node_name='node0', - snapshot_node_name='node0-overlay') - self.assert_qmp(result, 'return', {}) + self.vm_d.cmd('blockdev-snapshot-sync', + format=iotests.imgfmt, + snapshot_file=imgs[3], + node_name='node0', + snapshot_node_name='node0-overlay') self.vm_d.shutdown() self.vm_d = None diff --git a/tests/qemu-iotests/tests/copy-before-write b/tests/qemu-iotests/tests/copy-before-write index 2ffe092b31..d33bea577d 100755 --- a/tests/qemu-iotests/tests/copy-before-write +++ b/tests/qemu-iotests/tests/copy-before-write @@ -44,12 +44,11 @@ class TestCbwError(iotests.QMPTestCase): opts = ['-nodefaults', '-display', 'none', '-machine', 'none'] self.vm = QEMUMachine(iotests.qemu_prog, opts, - base_temp_dir=iotests.test_dir, - sock_dir=iotests.sock_dir) + base_temp_dir=iotests.test_dir) self.vm.launch() def do_cbw_error(self, on_cbw_error): - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'node-name': 'cbw', 'driver': 'copy-before-write', 'on-cbw-error': on_cbw_error, @@ -79,14 +78,12 @@ class TestCbwError(iotests.QMPTestCase): } } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'node-name': 'access', 'driver': 'snapshot-access', 'file': 'cbw' }) - self.assert_qmp(result, 'return', {}) result = self.vm.qmp('human-monitor-command', command_line='qemu-io cbw "write 0 1M"') @@ -130,14 +127,13 @@ read 1048576/1048576 bytes at offset 0 """) def do_cbw_timeout(self, on_cbw_error): - result = self.vm.qmp('object-add', { + self.vm.cmd('object-add', { 'qom-type': 'throttle-group', 'id': 'group0', 'limits': {'bps-write': 300 * 1024} }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'node-name': 'cbw', 'driver': 'copy-before-write', 'on-cbw-error': on_cbw_error, @@ -161,14 +157,12 @@ read 1048576/1048576 bytes at offset 0 } } }) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'node-name': 'access', 'driver': 'snapshot-access', 'file': 'cbw' }) - self.assert_qmp(result, 'return', {}) result = self.vm.qmp('human-monitor-command', command_line='qemu-io cbw "write 0 512K"') diff --git a/tests/qemu-iotests/tests/export-incoming-iothread b/tests/qemu-iotests/tests/export-incoming-iothread index 7679e49103..d36d6194e0 100755 --- a/tests/qemu-iotests/tests/export-incoming-iothread +++ b/tests/qemu-iotests/tests/export-incoming-iothread @@ -55,7 +55,7 @@ class TestExportIncomingIothread(iotests.QMPTestCase): os.remove(test_img) def test_export_add(self): - result = self.vm.qmp('nbd-server-start', { + self.vm.cmd('nbd-server-start', { 'addr': { 'type': 'unix', 'data': { @@ -63,16 +63,14 @@ class TestExportIncomingIothread(iotests.QMPTestCase): } } }) - self.assert_qmp(result, 'return', {}) # Regression test for issue 945: This should not fail an assertion - result = self.vm.qmp('block-export-add', { + self.vm.cmd('block-export-add', { 'type': 'nbd', 'id': 'exp0', 'node-name': node_name, 'iothread': iothread_id }) - self.assert_qmp(result, 'return', {}) if __name__ == '__main__': diff --git a/tests/qemu-iotests/tests/graph-changes-while-io b/tests/qemu-iotests/tests/graph-changes-while-io index 750e7d4d38..194fda500e 100755 --- a/tests/qemu-iotests/tests/graph-changes-while-io +++ b/tests/qemu-iotests/tests/graph-changes-while-io @@ -66,7 +66,7 @@ class TestGraphChangesWhileIO(QMPTestCase): # While qemu-img bench is running, repeatedly add and remove an # overlay to/from node0 while bench_thr.is_alive(): - result = self.qsd.qmp('blockdev-add', { + self.qsd.cmd('blockdev-add', { 'driver': imgfmt, 'node-name': 'overlay', 'backing': 'node0', @@ -75,12 +75,10 @@ class TestGraphChangesWhileIO(QMPTestCase): 'filename': top } }) - self.assert_qmp(result, 'return', {}) - result = self.qsd.qmp('blockdev-del', { + self.qsd.cmd('blockdev-del', { 'node-name': 'overlay' }) - self.assert_qmp(result, 'return', {}) bench_thr.join() @@ -92,7 +90,7 @@ class TestGraphChangesWhileIO(QMPTestCase): qemu_io('-c', 'write 0 64k', top) qemu_io('-c', 'write 128k 64k', top) - result = self.qsd.qmp('blockdev-add', { + self.qsd.cmd('blockdev-add', { 'driver': imgfmt, 'node-name': 'overlay', 'backing': None, @@ -101,26 +99,22 @@ class TestGraphChangesWhileIO(QMPTestCase): 'filename': top } }) - self.assert_qmp(result, 'return', {}) - result = self.qsd.qmp('blockdev-snapshot', { + self.qsd.cmd('blockdev-snapshot', { 'node': 'node0', 'overlay': 'overlay', }) - self.assert_qmp(result, 'return', {}) # While qemu-img bench is running, repeatedly commit overlay to node0 while bench_thr.is_alive(): - result = self.qsd.qmp('block-commit', { + self.qsd.cmd('block-commit', { 'job-id': 'job0', 'device': 'overlay', }) - self.assert_qmp(result, 'return', {}) - result = self.qsd.qmp('block-job-cancel', { + self.qsd.cmd('block-job-cancel', { 'device': 'job0', }) - self.assert_qmp(result, 'return', {}) cancelled = False while not cancelled: diff --git a/tests/qemu-iotests/tests/image-fleecing b/tests/qemu-iotests/tests/image-fleecing index f6e449d071..5e3b2c7e46 100755 --- a/tests/qemu-iotests/tests/image-fleecing +++ b/tests/qemu-iotests/tests/image-fleecing @@ -213,8 +213,7 @@ def do_test(vm, use_cbw, use_snapshot_access_filter, base_img_path, result = vm.qmp('query-block-jobs') assert len(result['return']) == 1 - result = vm.qmp('block-job-set-speed', device='push-backup', speed=0) - assert result == {'return': {}} + vm.cmd('block-job-set-speed', device='push-backup', speed=0) log(vm.event_wait(name='BLOCK_JOB_COMPLETED', match={'data': {'device': 'push-backup'}}), diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test index dda55fad28..c519e6db8c 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-postcopy-test @@ -118,11 +118,10 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): def start_postcopy(self): """ Run migration until RESUME event on target. Return this event. """ for i in range(nb_bitmaps): - result = self.vm_a.qmp('block-dirty-bitmap-add', node='drive0', - name='bitmap{}'.format(i), - granularity=granularity, - persistent=True) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-add', node='drive0', + name='bitmap{}'.format(i), + granularity=granularity, + persistent=True) result = self.vm_a.qmp('x-debug-block-dirty-bitmap-sha256', node='drive0', name='bitmap0') @@ -140,9 +139,8 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): # We want to calculate resulting sha256. Do it in bitmap0, so, disable # other bitmaps for i in range(1, nb_bitmaps): - result = self.vm_a.qmp('block-dirty-bitmap-disable', node='drive0', - name='bitmap{}'.format(i)) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-disable', node='drive0', + name='bitmap{}'.format(i)) apply_discards(self.vm_a, discards2) @@ -152,24 +150,19 @@ class TestDirtyBitmapPostcopyMigration(iotests.QMPTestCase): # Now, enable some bitmaps, to be updated during migration for i in range(2, nb_bitmaps, 2): - result = self.vm_a.qmp('block-dirty-bitmap-enable', node='drive0', - name='bitmap{}'.format(i)) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('block-dirty-bitmap-enable', node='drive0', + name='bitmap{}'.format(i)) caps = [{'capability': 'dirty-bitmaps', 'state': True}, {'capability': 'events', 'state': True}] - result = self.vm_a.qmp('migrate-set-capabilities', capabilities=caps) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate-set-capabilities', capabilities=caps) - result = self.vm_b.qmp('migrate-set-capabilities', capabilities=caps) - self.assert_qmp(result, 'return', {}) + self.vm_b.cmd('migrate-set-capabilities', capabilities=caps) - result = self.vm_a.qmp('migrate', uri='exec:cat>' + fifo) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate', uri='exec:cat>' + fifo) - result = self.vm_a.qmp('migrate-start-postcopy') - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate-start-postcopy') event_resume = self.vm_b.event_wait('RESUME') self.vm_b_events.append(event_resume) diff --git a/tests/qemu-iotests/tests/migrate-bitmaps-test b/tests/qemu-iotests/tests/migrate-bitmaps-test index 59f3357580..f98e721e97 100755 --- a/tests/qemu-iotests/tests/migrate-bitmaps-test +++ b/tests/qemu-iotests/tests/migrate-bitmaps-test @@ -67,8 +67,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): if persistent: params['persistent'] = True - result = vm.qmp('block-dirty-bitmap-add', **params) - self.assert_qmp(result, 'return', {}) + vm.cmd('block-dirty-bitmap-add', params) def check_bitmap(self, vm, sha256): result = vm.qmp('x-debug-block-dirty-bitmap-sha256', @@ -91,16 +90,15 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): if migrate_bitmaps: mig_caps.append({'capability': 'dirty-bitmaps', 'state': True}) - result = self.vm_a.qmp('migrate-set-capabilities', - capabilities=mig_caps) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate-set-capabilities', + capabilities=mig_caps) self.add_bitmap(self.vm_a, granularity, persistent) for r in regions: self.vm_a.hmp_qemu_io('drive0', 'write %d %d' % r) sha256 = get_bitmap_hash(self.vm_a) - result = self.vm_a.qmp('migrate', uri=mig_cmd) + self.vm_a.cmd('migrate', uri=mig_cmd) while True: event = self.vm_a.event_wait('MIGRATION') if event['data']['status'] == 'completed': @@ -114,8 +112,7 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): removed = (not migrate_bitmaps) and persistent self.check_bitmap(self.vm_a, False if removed else sha256) - result = self.vm_a.qmp('cont') - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('cont') # test that bitmap is still here after invalidation self.check_bitmap(self.vm_a, sha256) @@ -158,9 +155,8 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): if online: os.mkfifo(mig_file) self.vm_b.launch() - result = self.vm_b.qmp('migrate-set-capabilities', - capabilities=mig_caps) - self.assert_qmp(result, 'return', {}) + self.vm_b.cmd('migrate-set-capabilities', + capabilities=mig_caps) self.add_bitmap(self.vm_a, granularity, persistent) for r in regions: @@ -171,11 +167,10 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): self.vm_a.shutdown() self.vm_a.launch() - result = self.vm_a.qmp('migrate-set-capabilities', - capabilities=mig_caps) - self.assert_qmp(result, 'return', {}) + self.vm_a.cmd('migrate-set-capabilities', + capabilities=mig_caps) - result = self.vm_a.qmp('migrate', uri=mig_cmd) + self.vm_a.cmd('migrate', uri=mig_cmd) while True: event = self.vm_a.event_wait('MIGRATION') if event['data']['status'] == 'completed': @@ -184,11 +179,9 @@ class TestDirtyBitmapMigration(iotests.QMPTestCase): if not online: self.vm_a.shutdown() self.vm_b.launch() - result = self.vm_b.qmp('migrate-set-capabilities', - capabilities=mig_caps) - self.assert_qmp(result, 'return', {}) - result = self.vm_b.qmp('migrate-incoming', uri=incoming_cmd) - self.assert_qmp(result, 'return', {}) + self.vm_b.cmd('migrate-set-capabilities', + capabilities=mig_caps) + self.vm_b.cmd('migrate-incoming', uri=incoming_cmd) while True: event = self.vm_b.event_wait('MIGRATION') @@ -254,8 +247,7 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): self.vm = iotests.VM() self.vm.launch() - result = self.vm.qmp('blockdev-add', **blockdev) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-add', blockdev) # Check that the bitmaps are there nodes = self.vm.qmp('query-named-block-nodes', flat=True)['return'] @@ -264,8 +256,7 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): self.assert_qmp(node, 'dirty-bitmaps[0]/name', 'bmap0') caps = [{'capability': 'events', 'state': True}] - result = self.vm.qmp('migrate-set-capabilities', capabilities=caps) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('migrate-set-capabilities', capabilities=caps) def tearDown(self): self.vm.shutdown() @@ -276,14 +267,12 @@ class TestDirtyBitmapBackingMigration(iotests.QMPTestCase): """ Continue the source after migration. """ - result = self.vm.qmp('migrate', uri='exec: cat > /dev/null') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('migrate', uri='exec: cat > /dev/null') with Timeout(10, 'Migration timeout'): self.vm.wait_migration('postmigrate') - result = self.vm.qmp('cont') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('cont') def main() -> None: diff --git a/tests/qemu-iotests/tests/migrate-during-backup b/tests/qemu-iotests/tests/migrate-during-backup index 34103229ee..afb2277896 100755 --- a/tests/qemu-iotests/tests/migrate-during-backup +++ b/tests/qemu-iotests/tests/migrate-during-backup @@ -43,7 +43,7 @@ class TestMigrateDuringBackup(iotests.QMPTestCase): self.vm = iotests.VM().add_drive(disk_a) self.vm.launch() - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'node-name': 'target', 'driver': iotests.imgfmt, 'file': { @@ -51,26 +51,21 @@ class TestMigrateDuringBackup(iotests.QMPTestCase): 'filename': disk_b } }) - self.assert_qmp(result, 'return', {}) def test_migrate(self): - result = self.vm.qmp('blockdev-backup', device='drive0', - target='target', sync='full', - speed=1, x_perf={ - 'max-workers': 1, - 'max-chunk': 64 * 1024 - }) - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('job-pause', id='drive0') - self.assert_qmp(result, 'return', {}) - - result = self.vm.qmp('migrate-set-capabilities', - capabilities=[{'capability': 'events', - 'state': True}]) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('migrate', uri=mig_cmd) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-backup', device='drive0', + target='target', sync='full', + speed=1, x_perf={ + 'max-workers': 1, + 'max-chunk': 64 * 1024 + }) + + self.vm.cmd('job-pause', id='drive0') + + self.vm.cmd('migrate-set-capabilities', + capabilities=[{'capability': 'events', + 'state': True}]) + self.vm.cmd('migrate', uri=mig_cmd) e = self.vm.events_wait((('MIGRATION', {'data': {'status': 'completed'}}), @@ -80,11 +75,9 @@ class TestMigrateDuringBackup(iotests.QMPTestCase): # Don't assert that e is 'failed' now: this way we'll miss # possible crash when backup continues :) - result = self.vm.qmp('block-job-set-speed', device='drive0', - speed=0) - self.assert_qmp(result, 'return', {}) - result = self.vm.qmp('job-resume', id='drive0') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-set-speed', device='drive0', + speed=0) + self.vm.cmd('job-resume', id='drive0') # For future: if something changes so that both migration # and backup pass, let's not miss that moment, as it may diff --git a/tests/qemu-iotests/tests/migration-permissions b/tests/qemu-iotests/tests/migration-permissions index 4e1da369c9..0deaad2d3a 100755 --- a/tests/qemu-iotests/tests/migration-permissions +++ b/tests/qemu-iotests/tests/migration-permissions @@ -47,11 +47,10 @@ class TestMigrationPermissions(iotests.QMPTestCase): vms[i].launch() - result = vms[i].qmp('migrate-set-capabilities', - capabilities=[ - {'capability': 'events', 'state': True} - ]) - self.assert_qmp(result, 'return', {}) + vms[i].cmd('migrate-set-capabilities', + capabilities=[ + {'capability': 'events', 'state': True} + ]) self.vm_s = vms[0] self.vm_d = vms[1] diff --git a/tests/qemu-iotests/tests/mirror-ready-cancel-error b/tests/qemu-iotests/tests/mirror-ready-cancel-error index 01217459b9..ed2e46447e 100755 --- a/tests/qemu-iotests/tests/mirror-ready-cancel-error +++ b/tests/qemu-iotests/tests/mirror-ready-cancel-error @@ -48,51 +48,48 @@ class TestMirrorReadyCancelError(iotests.QMPTestCase): os.remove(target) def add_blockdevs(self, once: bool) -> None: - res = self.vm.qmp('blockdev-add', - **{'node-name': 'source', - 'driver': iotests.imgfmt, - 'file': { - 'driver': 'file', - 'filename': source - }}) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('blockdev-add', + {'node-name': 'source', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'file', + 'filename': source + }}) # blkdebug notes: # Enter state 2 on the first flush, which happens before the # job enters the READY state. The second flush will happen # when the job is about to complete, and we want that one to # fail. - res = self.vm.qmp('blockdev-add', - **{'node-name': 'target', - 'driver': iotests.imgfmt, - 'file': { - 'driver': 'blkdebug', - 'image': { - 'driver': 'file', - 'filename': target - }, - 'set-state': [{ - 'event': 'flush_to_disk', - 'state': 1, - 'new_state': 2 - }], - 'inject-error': [{ - 'event': 'flush_to_disk', - 'once': once, - 'immediately': True, - 'state': 2 - }]}}) - self.assert_qmp(res, 'return', {}) + self.vm.cmd('blockdev-add', + {'node-name': 'target', + 'driver': iotests.imgfmt, + 'file': { + 'driver': 'blkdebug', + 'image': { + 'driver': 'file', + 'filename': target + }, + 'set-state': [{ + 'event': 'flush_to_disk', + 'state': 1, + 'new_state': 2 + }], + 'inject-error': [{ + 'event': 'flush_to_disk', + 'once': once, + 'immediately': True, + 'state': 2 + }]}}) def start_mirror(self) -> None: - res = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='source', - target='target', - filter_node_name='mirror-top', - sync='full', - on_target_error='stop') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='source', + target='target', + filter_node_name='mirror-top', + sync='full', + on_target_error='stop') def cancel_mirror_with_error(self) -> None: self.vm.event_wait('BLOCK_JOB_READY') @@ -107,8 +104,7 @@ class TestMirrorReadyCancelError(iotests.QMPTestCase): while self.vm.event_wait('JOB_STATUS_CHANGE', timeout=0.0) is not None: pass - res = self.vm.qmp('block-job-cancel', device='mirror') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-job-cancel', device='mirror') self.vm.event_wait('BLOCK_JOB_ERROR') diff --git a/tests/qemu-iotests/tests/mirror-top-perms b/tests/qemu-iotests/tests/mirror-top-perms index 8bca592708..fab9907e92 100755 --- a/tests/qemu-iotests/tests/mirror-top-perms +++ b/tests/qemu-iotests/tests/mirror-top-perms @@ -78,12 +78,11 @@ class TestMirrorTopPerms(iotests.QMPTestCase): difficult to let some other qemu process open the image.) """ - result = self.vm.qmp('blockdev-mirror', - job_id='mirror', - device='drive0', - target='null', - sync='full') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('blockdev-mirror', + job_id='mirror', + device='drive0', + target='null', + sync='full') self.vm.event_wait('BLOCK_JOB_READY') @@ -105,9 +104,8 @@ class TestMirrorTopPerms(iotests.QMPTestCase): except machine.VMLaunchFailure as exc: assert 'Is another process using the image' in exc.output - result = self.vm.qmp('block-job-cancel', - device='mirror') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-job-cancel', + device='mirror') self.vm.event_wait('BLOCK_JOB_COMPLETED') diff --git a/tests/qemu-iotests/tests/nbd-multiconn b/tests/qemu-iotests/tests/nbd-multiconn index 478a1eaba2..479e872f2a 100755 --- a/tests/qemu-iotests/tests/nbd-multiconn +++ b/tests/qemu-iotests/tests/nbd-multiconn @@ -20,6 +20,8 @@ import os from contextlib import contextmanager +from types import ModuleType + import iotests from iotests import qemu_img_create, qemu_io @@ -28,7 +30,7 @@ disk = os.path.join(iotests.test_dir, 'disk') size = '4M' nbd_sock = os.path.join(iotests.sock_dir, 'nbd_sock') nbd_uri = 'nbd+unix:///{}?socket=' + nbd_sock - +nbd: ModuleType @contextmanager def open_nbd(export_name): @@ -46,12 +48,11 @@ class TestNbdMulticonn(iotests.QMPTestCase): self.vm = iotests.VM() self.vm.launch() - result = self.vm.qmp('blockdev-add', { + self.vm.cmd('blockdev-add', { 'driver': 'qcow2', 'node-name': 'n', 'file': {'driver': 'file', 'filename': disk} }) - self.assert_qmp(result, 'return', {}) def tearDown(self): self.vm.shutdown() @@ -72,12 +73,10 @@ class TestNbdMulticonn(iotests.QMPTestCase): if max_connections is not None: args['max-connections'] = max_connections - result = self.vm.qmp('nbd-server-start', args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-start', args) yield - result = self.vm.qmp('nbd-server-stop') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('nbd-server-stop') def add_export(self, name, writable=None): args = { @@ -89,8 +88,7 @@ class TestNbdMulticonn(iotests.QMPTestCase): if writable is not None: args['writable'] = writable - result = self.vm.qmp('block-export-add', args) - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-export-add', args) def test_default_settings(self): with self.run_server(): diff --git a/tests/qemu-iotests/tests/reopen-file b/tests/qemu-iotests/tests/reopen-file index 8590a94d53..5a50794ffc 100755 --- a/tests/qemu-iotests/tests/reopen-file +++ b/tests/qemu-iotests/tests/reopen-file @@ -64,12 +64,11 @@ class TestReopenFile(QMPTestCase): self.fail('qemu-io pattern verification failed') def test_reopen_file(self) -> None: - result = self.vm.qmp('blockdev-reopen', options=[{ + self.vm.cmd('blockdev-reopen', options=[{ 'driver': imgfmt, 'node-name': 'format', 'file': 'raw' }]) - self.assert_qmp(result, 'return', {}) # Do some I/O to the image to see whether it still works # (Pattern verification will be checked by tearDown()) diff --git a/tests/qemu-iotests/tests/stream-error-on-reset b/tests/qemu-iotests/tests/stream-error-on-reset index 5a8c3a9e8d..b60aabb68e 100755 --- a/tests/qemu-iotests/tests/stream-error-on-reset +++ b/tests/qemu-iotests/tests/stream-error-on-reset @@ -115,8 +115,7 @@ class TestStreamErrorOnReset(QMPTestCase): # Launch a stream job, which will take at least a second to # complete, because the base image is throttled (so we can # get in between it having started and it having completed) - res = self.vm.qmp('block-stream', job_id='stream', device='top') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('block-stream', job_id='stream', device='top') while True: ev = self.vm.event_wait('JOB_STATUS_CHANGE') @@ -125,8 +124,7 @@ class TestStreamErrorOnReset(QMPTestCase): # forces the virtio-scsi device to be reset, thus draining # the stream job, and making it complete. Completing # inside of that drain should not result in a segfault. - res = self.vm.qmp('system_reset') - self.assert_qmp(res, 'return', {}) + self.vm.cmd('system_reset') elif ev['data']['status'] == 'null': # The test is done once the job is gone break diff --git a/tests/qemu-iotests/tests/stream-under-throttle b/tests/qemu-iotests/tests/stream-under-throttle index c24dfbcaa2..1a50b682fc 100755 --- a/tests/qemu-iotests/tests/stream-under-throttle +++ b/tests/qemu-iotests/tests/stream-under-throttle @@ -102,10 +102,9 @@ class TestStreamWithThrottle(iotests.QMPTestCase): Do a simple stream beneath the two throttle nodes. Should complete with no problems. ''' - result = self.vm.qmp('block-stream', - job_id='stream', - device='unthrottled-node') - self.assert_qmp(result, 'return', {}) + self.vm.cmd('block-stream', + job_id='stream', + device='unthrottled-node') # Should succeed and not time out try: diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index 66795cfcd2..d6022ebd64 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -357,6 +357,8 @@ foreach dir : target_dirs test_deps += [qsd] endif + qtest_env.set('PYTHON', python.full_path()) + foreach test : target_qtests # Executables are shared across targets, declare them only the first time we # encounter them diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index 8eb2053dbb..e1c110537b 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -66,6 +66,12 @@ static bool got_dst_resume; */ #define DIRTYLIMIT_TOLERANCE_RANGE 25 /* MB/s */ +#define ANALYZE_SCRIPT "scripts/analyze-migration.py" + +#define QEMU_VM_FILE_MAGIC 0x5145564d +#define FILE_TEST_FILENAME "migfile" +#define FILE_TEST_OFFSET 0x1000 + #if defined(__linux__) #include <sys/syscall.h> #include <sys/vfs.h> @@ -882,6 +888,7 @@ static void test_migrate_end(QTestState *from, QTestState *to, bool test_dest) cleanup("migsocket"); cleanup("src_serial"); cleanup("dest_serial"); + cleanup(FILE_TEST_FILENAME); } #ifdef CONFIG_GNUTLS @@ -1501,6 +1508,61 @@ static void test_baddest(void) test_migrate_end(from, to, false); } +#ifndef _WIN32 +static void test_analyze_script(void) +{ + MigrateStart args = { + .opts_source = "-uuid 11111111-1111-1111-1111-111111111111", + }; + QTestState *from, *to; + g_autofree char *uri = NULL; + g_autofree char *file = NULL; + int pid, wstatus; + const char *python = g_getenv("PYTHON"); + + if (!python) { + g_test_skip("PYTHON variable not set"); + return; + } + + /* dummy url */ + if (test_migrate_start(&from, &to, "tcp:127.0.0.1:0", &args)) { + return; + } + + /* + * Setting these two capabilities causes the "configuration" + * vmstate to include subsections for them. The script needs to + * parse those subsections properly. + */ + migrate_set_capability(from, "validate-uuid", true); + migrate_set_capability(from, "x-ignore-shared", true); + + file = g_strdup_printf("%s/migfile", tmpfs); + uri = g_strdup_printf("exec:cat > %s", file); + + migrate_ensure_converge(from); + migrate_qmp(from, uri, "{}"); + wait_for_migration_complete(from); + + pid = fork(); + if (!pid) { + close(1); + open("/dev/null", O_WRONLY); + execl(python, python, ANALYZE_SCRIPT, "-f", file, NULL); + g_assert_not_reached(); + } + + g_assert(waitpid(pid, &wstatus, 0) == pid); + if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) != 0) { + g_test_message("Failed to analyze the migration stream"); + g_test_fail(); + } + test_migrate_end(from, to, false); + cleanup("migfile"); +} +#endif + static void test_precopy_common(MigrateCommon *args) { QTestState *from, *to; @@ -1610,6 +1672,70 @@ finish: test_migrate_end(from, to, args->result == MIG_TEST_SUCCEED); } +static void test_file_common(MigrateCommon *args, bool stop_src) +{ + QTestState *from, *to; + void *data_hook = NULL; + g_autofree char *connect_uri = g_strdup(args->connect_uri); + + if (test_migrate_start(&from, &to, args->listen_uri, &args->start)) { + return; + } + + /* + * File migration is never live. We can keep the source VM running + * during migration, but the destination will not be running + * concurrently. + */ + g_assert_false(args->live); + + if (args->start_hook) { + data_hook = args->start_hook(from, to); + } + + migrate_ensure_converge(from); + wait_for_serial("src_serial"); + + if (stop_src) { + qtest_qmp_assert_success(from, "{ 'execute' : 'stop'}"); + if (!got_src_stop) { + qtest_qmp_eventwait(from, "STOP"); + } + } + + if (args->result == MIG_TEST_QMP_ERROR) { + migrate_qmp_fail(from, connect_uri, "{}"); + goto finish; + } + + migrate_qmp(from, connect_uri, "{}"); + wait_for_migration_complete(from); + + /* + * We need to wait for the source to finish before starting the + * destination. + */ + migrate_incoming_qmp(to, connect_uri, "{}"); + wait_for_migration_complete(to); + + if (stop_src) { + qtest_qmp_assert_success(to, "{ 'execute' : 'cont'}"); + } + + if (!got_dst_resume) { + qtest_qmp_eventwait(to, "RESUME"); + } + + wait_for_serial("dest_serial"); + +finish: + if (args->finish_hook) { + args->finish_hook(from, to, data_hook); + } + + test_migrate_end(from, to, args->result == MIG_TEST_SUCCEED); +} + static void test_precopy_unix_plain(void) { g_autofree char *uri = g_strdup_printf("unix:%s/migsocket", tmpfs); @@ -1805,6 +1931,76 @@ static void test_precopy_unix_compress_nowait(void) test_precopy_common(&args); } +static void test_precopy_file(void) +{ + g_autofree char *uri = g_strdup_printf("file:%s/%s", tmpfs, + FILE_TEST_FILENAME); + MigrateCommon args = { + .connect_uri = uri, + .listen_uri = "defer", + }; + + test_file_common(&args, true); +} + +static void file_offset_finish_hook(QTestState *from, QTestState *to, + void *opaque) +{ +#if defined(__linux__) + g_autofree char *path = g_strdup_printf("%s/%s", tmpfs, FILE_TEST_FILENAME); + size_t size = FILE_TEST_OFFSET + sizeof(QEMU_VM_FILE_MAGIC); + uintptr_t *addr, *p; + int fd; + + fd = open(path, O_RDONLY); + g_assert(fd != -1); + addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, 0); + g_assert(addr != MAP_FAILED); + + /* + * Ensure the skipped offset contains zeros and the migration + * stream starts at the right place. + */ + p = addr; + while (p < addr + FILE_TEST_OFFSET / sizeof(uintptr_t)) { + g_assert(*p == 0); + p++; + } + g_assert_cmpint(cpu_to_be64(*p) >> 32, ==, QEMU_VM_FILE_MAGIC); + + munmap(addr, size); + close(fd); +#endif +} + +static void test_precopy_file_offset(void) +{ + g_autofree char *uri = g_strdup_printf("file:%s/%s,offset=%d", tmpfs, + FILE_TEST_FILENAME, + FILE_TEST_OFFSET); + MigrateCommon args = { + .connect_uri = uri, + .listen_uri = "defer", + .finish_hook = file_offset_finish_hook, + }; + + test_file_common(&args, false); +} + +static void test_precopy_file_offset_bad(void) +{ + /* using a value not supported by qemu_strtosz() */ + g_autofree char *uri = g_strdup_printf("file:%s/%s,offset=0x20M", + tmpfs, FILE_TEST_FILENAME); + MigrateCommon args = { + .connect_uri = uri, + .listen_uri = "defer", + .result = MIG_TEST_QMP_ERROR, + }; + + test_file_common(&args, false); +} + static void test_precopy_tcp_plain(void) { MigrateCommon args = { @@ -2837,6 +3033,9 @@ int main(int argc, char **argv) } qtest_add_func("/migration/bad_dest", test_baddest); +#ifndef _WIN32 + qtest_add_func("/migration/analyze-script", test_analyze_script); +#endif qtest_add_func("/migration/precopy/unix/plain", test_precopy_unix_plain); qtest_add_func("/migration/precopy/unix/xbzrle", test_precopy_unix_xbzrle); /* @@ -2849,6 +3048,14 @@ int main(int argc, char **argv) qtest_add_func("/migration/precopy/unix/compress/nowait", test_precopy_unix_compress_nowait); } + + qtest_add_func("/migration/precopy/file", + test_precopy_file); + qtest_add_func("/migration/precopy/file/offset", + test_precopy_file_offset); + qtest_add_func("/migration/precopy/file/offset/bad", + test_precopy_file_offset_bad); + #ifdef CONFIG_GNUTLS qtest_add_func("/migration/precopy/unix/tls/psk", test_precopy_unix_tls_psk); diff --git a/tests/qtest/npcm7xx_timer-test.c b/tests/qtest/npcm7xx_timer-test.c index 43711049ca..58f58c2f71 100644 --- a/tests/qtest/npcm7xx_timer-test.c +++ b/tests/qtest/npcm7xx_timer-test.c @@ -465,6 +465,7 @@ static void test_periodic_interrupt(gconstpointer test_data) int i; tim_reset(td); + clock_step_next(); tim_write_ticr(td, count); tim_write_tcsr(td, CEN | IE | MODE_PERIODIC | PRESCALE(ps)); diff --git a/tests/qtest/ufs-test.c b/tests/qtest/ufs-test.c index ed3dbca154..15d467630c 100644 --- a/tests/qtest/ufs-test.c +++ b/tests/qtest/ufs-test.c @@ -497,7 +497,7 @@ static void ufstest_read_write(void *obj, void *data, QGuestAllocator *alloc) g_assert_cmpuint(block_size, ==, 4096); /* Write data */ - memset(write_buf, rand() % 255 + 1, block_size); + memset(write_buf, 0xab, block_size); ufs_send_scsi_command(ufs, 0, 1, write_cdb, write_buf, block_size, NULL, 0, &utrd, &rsp_upiu); g_assert_cmpuint(le32_to_cpu(utrd.header.dword_2), ==, UFS_OCS_SUCCESS); diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index 2efacf9a5a..62b38c792f 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -73,11 +73,6 @@ endif # System Registers Tests AARCH64_TESTS += sysregs -ifneq ($(CROSS_CC_HAS_SVE),) -# SVE ioctl test -AARCH64_TESTS += sve-ioctls -sve-ioctls: CFLAGS+=-march=armv8.1-a+sve - AARCH64_TESTS += test-aes test-aes: CFLAGS += -O -march=armv8-a+aes test-aes: test-aes-main.c.inc @@ -100,26 +95,29 @@ sha512-vector: sha512.c TESTS += sha512-vector ifneq ($(CROSS_CC_HAS_SVE),) +# SVE ioctl test +AARCH64_TESTS += sve-ioctls +sve-ioctls: CFLAGS+=-march=armv8.1-a+sve + sha512-sve: CFLAGS=-O3 -march=armv8.1-a+sve sha512-sve: sha512.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $< -o $@ $(LDFLAGS) TESTS += sha512-sve -endif -ifeq ($(HOST_GDB_SUPPORTS_ARCH),y) +ifneq ($(GDB),) GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py run-gdbstub-sysregs: sysregs $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(AARCH64_SRC)/gdbstub/test-sve.py, \ basic gdbstub SVE support) run-gdbstub-sve-ioctls: sve-ioctls $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(AARCH64_SRC)/gdbstub/test-sve-ioctl.py, \ basic gdbstub SVE ZLEN support) diff --git a/tests/tcg/loongarch64/system/boot.S b/tests/tcg/loongarch64/system/boot.S index 67eb1c04ce..37a81bafe7 100644 --- a/tests/tcg/loongarch64/system/boot.S +++ b/tests/tcg/loongarch64/system/boot.S @@ -21,9 +21,10 @@ _start: .align 16 _exit: 2: /* QEMU ACPI poweroff */ - li.w t0, 0xff - li.w t1, 0x10080010 - st.w t0, t1, 0 + li.w t0, 0x34 + li.w t1, 0x100e001c + st.b t0, t1, 0 + idle 0 bl 2b diff --git a/tests/tcg/multiarch/Makefile.target b/tests/tcg/multiarch/Makefile.target index 43bddeaf21..f3bfaf1a22 100644 --- a/tests/tcg/multiarch/Makefile.target +++ b/tests/tcg/multiarch/Makefile.target @@ -63,45 +63,39 @@ run-test-mmap: test-mmap run-test-mmap-%: test-mmap $(call run-test, test-mmap-$*, $(QEMU) -p $* $<, $< ($* byte pages)) -ifneq ($(HAVE_GDB_BIN),) -ifeq ($(HOST_GDB_SUPPORTS_ARCH),y) +ifneq ($(GDB),) GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py run-gdbstub-sha1: sha1 $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(MULTIARCH_SRC)/gdbstub/sha1.py, \ basic gdbstub support) run-gdbstub-qxfer-auxv-read: sha1 $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(MULTIARCH_SRC)/gdbstub/test-qxfer-auxv-read.py, \ basic gdbstub qXfer:auxv:read support) run-gdbstub-proc-mappings: sha1 $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(MULTIARCH_SRC)/gdbstub/test-proc-mappings.py, \ proc mappings support) run-gdbstub-thread-breakpoint: testthread $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(MULTIARCH_SRC)/gdbstub/test-thread-breakpoint.py, \ hitting a breakpoint on non-main thread) - -else -run-gdbstub-%: - $(call skip-test, "gdbstub test $*", "no guest arch support") -endif else run-gdbstub-%: - $(call skip-test, "gdbstub test $*", "need working gdb") + $(call skip-test, "gdbstub test $*", "need working gdb with $(patsubst -%,,$(TARGET_NAME)) support") endif EXTRA_RUNS += run-gdbstub-sha1 run-gdbstub-qxfer-auxv-read \ run-gdbstub-proc-mappings run-gdbstub-thread-breakpoint diff --git a/tests/tcg/multiarch/system/Makefile.softmmu-target b/tests/tcg/multiarch/system/Makefile.softmmu-target index 90810a32b2..dee4f58dea 100644 --- a/tests/tcg/multiarch/system/Makefile.softmmu-target +++ b/tests/tcg/multiarch/system/Makefile.softmmu-target @@ -14,13 +14,12 @@ VPATH+=$(MULTIARCH_SYSTEM_SRC) MULTIARCH_TEST_SRCS=$(wildcard $(MULTIARCH_SYSTEM_SRC)/*.c) MULTIARCH_TESTS = $(patsubst $(MULTIARCH_SYSTEM_SRC)/%.c, %, $(MULTIARCH_TEST_SRCS)) -ifneq ($(HAVE_GDB_BIN),) -ifeq ($(HOST_GDB_SUPPORTS_ARCH),y) +ifneq ($(GDB),) GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py run-gdbstub-memory: memory $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) \ --output $<.gdb.out \ --qargs \ @@ -29,7 +28,7 @@ run-gdbstub-memory: memory softmmu gdbstub support) run-gdbstub-interrupt: interrupt $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) \ --output $<.gdb.out \ --qargs \ @@ -38,7 +37,7 @@ run-gdbstub-interrupt: interrupt softmmu gdbstub support) run-gdbstub-untimely-packet: hello $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --gdb-args "-ex 'set debug remote 1'" \ --output untimely-packet.gdb.out \ --stderr untimely-packet.gdb.err \ @@ -51,11 +50,7 @@ run-gdbstub-untimely-packet: hello "GREP", file untimely-packet.gdb.err) else run-gdbstub-%: - $(call skip-test, "gdbstub test $*", "no guest arch support") -endif -else -run-gdbstub-%: - $(call skip-test, "gdbstub test $*", "need working gdb") + $(call skip-test, "gdbstub test $*", "need working gdb with $(patsubst -%,,$(TARGET_NAME)) support") endif MULTIARCH_RUNS += run-gdbstub-memory run-gdbstub-interrupt run-gdbstub-untimely-packet diff --git a/tests/tcg/s390x/Makefile.target b/tests/tcg/s390x/Makefile.target index c650aefe5c..826f0a18e4 100644 --- a/tests/tcg/s390x/Makefile.target +++ b/tests/tcg/s390x/Makefile.target @@ -81,12 +81,12 @@ $(Z15_TESTS): CFLAGS+=-march=z15 -O2 TESTS+=$(Z15_TESTS) endif -ifeq ($(HOST_GDB_SUPPORTS_ARCH),y) +ifneq ($(GDB),) GDB_SCRIPT=$(SRC_PATH)/tests/guest-debug/run-test.py run-gdbstub-signals-s390x: signals-s390x $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(S390X_SRC)/gdbstub/test-signals-s390x.py, \ mixing signals and debugging) @@ -95,7 +95,7 @@ hello-s390x-asm: CFLAGS+=-nostdlib run-gdbstub-svc: hello-s390x-asm $(call run-test, $@, $(GDB_SCRIPT) \ - --gdb $(HAVE_GDB_BIN) \ + --gdb $(GDB) \ --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ --bin $< --test $(S390X_SRC)/gdbstub/test-svc.py, \ single-stepping svc) diff --git a/tests/unit/test-bdrv-drain.c b/tests/unit/test-bdrv-drain.c index 0b603e7c57..f67e9df01c 100644 --- a/tests/unit/test-bdrv-drain.c +++ b/tests/unit/test-bdrv-drain.c @@ -1034,9 +1034,13 @@ static void coroutine_fn test_co_delete_by_drain(void *opaque) blk_co_unref(blk); } else { BdrvChild *c, *next_c; + bdrv_graph_co_rdlock(); QLIST_FOREACH_SAFE(c, &bs->children, next, next_c) { + bdrv_graph_co_rdunlock(); bdrv_co_unref_child(bs, c); + bdrv_graph_co_rdlock(); } + bdrv_graph_co_rdunlock(); } dbdd->done = true; @@ -1168,7 +1172,7 @@ struct detach_by_parent_data { }; static struct detach_by_parent_data detach_by_parent_data; -static void detach_indirect_bh(void *opaque) +static void no_coroutine_fn detach_indirect_bh(void *opaque) { struct detach_by_parent_data *data = opaque; @@ -1184,18 +1188,19 @@ static void detach_indirect_bh(void *opaque) bdrv_graph_wrunlock(); } -static void detach_by_parent_aio_cb(void *opaque, int ret) +static void coroutine_mixed_fn detach_by_parent_aio_cb(void *opaque, int ret) { struct detach_by_parent_data *data = &detach_by_parent_data; g_assert_cmpint(ret, ==, 0); if (data->by_parent_cb) { bdrv_inc_in_flight(data->child_b->bs); - detach_indirect_bh(data); + aio_bh_schedule_oneshot(qemu_get_current_aio_context(), + detach_indirect_bh, &detach_by_parent_data); } } -static void detach_by_driver_cb_drained_begin(BdrvChild *child) +static void GRAPH_RDLOCK detach_by_driver_cb_drained_begin(BdrvChild *child) { struct detach_by_parent_data *data = &detach_by_parent_data; @@ -1232,7 +1237,7 @@ static BdrvChildClass detach_by_driver_cb_class; * state is messed up, but if it is only polled in the single * BDRV_POLL_WHILE() at the end of the drain, this should work fine. */ -static void test_detach_indirect(bool by_parent_cb) +static void TSA_NO_TSA test_detach_indirect(bool by_parent_cb) { BlockBackend *blk; BlockDriverState *parent_a, *parent_b, *a, *b, *c; diff --git a/tests/unit/test-block-iothread.c b/tests/unit/test-block-iothread.c index 9155547313..9b15d2768c 100644 --- a/tests/unit/test-block-iothread.c +++ b/tests/unit/test-block-iothread.c @@ -383,6 +383,9 @@ static void test_sync_op_check(BdrvChild *c) static void test_sync_op_activate(BdrvChild *c) { + GLOBAL_STATE_CODE(); + GRAPH_RDLOCK_GUARD_MAINLOOP(); + /* Early success: Image is not inactive */ bdrv_activate(c->bs, NULL); } @@ -468,11 +471,16 @@ static void test_sync_op(const void *opaque) BlockDriverState *bs; BdrvChild *c; + GLOBAL_STATE_CODE(); + blk = blk_new(qemu_get_aio_context(), BLK_PERM_ALL, BLK_PERM_ALL); bs = bdrv_new_open_driver(&bdrv_test, "base", BDRV_O_RDWR, &error_abort); bs->total_sectors = 65536 / BDRV_SECTOR_SIZE; blk_insert_bs(blk, bs, &error_abort); + + bdrv_graph_rdlock_main_loop(); c = QLIST_FIRST(&bs->parents); + bdrv_graph_rdunlock_main_loop(); blk_set_aio_context(blk, ctx, &error_abort); aio_context_acquire(ctx); diff --git a/tests/unit/test-coroutine.c b/tests/unit/test-coroutine.c index b0d21d673a..a2563647e7 100644 --- a/tests/unit/test-coroutine.c +++ b/tests/unit/test-coroutine.c @@ -645,7 +645,7 @@ int main(int argc, char **argv) * with a sentinel value. If there is no freelist this would legitimately * crash, so skip it. */ - if (CONFIG_COROUTINE_POOL) { + if (IS_ENABLED(CONFIG_COROUTINE_POOL)) { g_test_add_func("/basic/no-dangling-access", test_no_dangling_access); } diff --git a/tests/vm/basevm.py b/tests/vm/basevm.py index a97e23b0ce..61725b8325 100644 --- a/tests/vm/basevm.py +++ b/tests/vm/basevm.py @@ -312,8 +312,8 @@ class BaseVM(object): self._guest = guest # Init console so we can start consuming the chars. self.console_init() - usernet_info = guest.qmp("human-monitor-command", - command_line="info usernet").get("return") + usernet_info = guest.cmd("human-monitor-command", + command_line="info usernet") self.ssh_port = get_info_usernet_hostfwd_port(usernet_info) if not self.ssh_port: raise Exception("Cannot find ssh port from 'info usernet':\n%s" % \ @@ -331,8 +331,8 @@ class BaseVM(object): def console_log(self, text): for line in re.split("[\r\n]", text): # filter out terminal escape sequences - line = re.sub("\x1b\[[0-9;?]*[a-zA-Z]", "", line) - line = re.sub("\x1b\([0-9;?]*[a-zA-Z]", "", line) + line = re.sub("\x1b\\[[0-9;?]*[a-zA-Z]", "", line) + line = re.sub("\x1b\\([0-9;?]*[a-zA-Z]", "", line) # replace unprintable chars line = re.sub("\x1b", "<esc>", line) line = re.sub("[\x00-\x1f]", ".", line) @@ -530,7 +530,7 @@ def get_qemu_version(qemu_path): and return the major number.""" output = subprocess.check_output([qemu_path, '--version']) version_line = output.decode("utf-8") - version_num = re.split(' |\(', version_line)[3].split('.')[0] + version_num = re.split(r' |\(', version_line)[3].split('.')[0] return int(version_num) def parse_config(config, args): diff --git a/tests/vm/netbsd b/tests/vm/netbsd index c7e3f1e735..40b27a3469 100755 --- a/tests/vm/netbsd +++ b/tests/vm/netbsd @@ -40,6 +40,9 @@ class NetBSDVM(basevm.BaseVM): "gsed", "gettext-tools", + # libs: basic + "dtc", + # libs: crypto "gnutls", @@ -67,7 +70,8 @@ class NetBSDVM(basevm.BaseVM): mkdir src build; cd src; tar -xf /dev/rld1a; cd ../build - ../src/configure --disable-opengl {configure_opts}; + ../src/configure --disable-opengl --extra-ldflags=-L/usr/pkg/lib \ + --extra-cflags=-I/usr/pkg/include {configure_opts}; gmake --output-sync -j{jobs} {target} {verbose}; """ poweroff = "/sbin/poweroff" diff --git a/ui/input-legacy.c b/ui/input-legacy.c index 46ea74e44d..210ae5eaca 100644 --- a/ui/input-legacy.c +++ b/ui/input-legacy.c @@ -127,7 +127,7 @@ static void legacy_kbd_event(DeviceState *dev, QemuConsole *src, } } -static QemuInputHandler legacy_kbd_handler = { +static const QemuInputHandler legacy_kbd_handler = { .name = "legacy-kbd", .mask = INPUT_EVENT_MASK_KEY, .event = legacy_kbd_event, diff --git a/ui/input.c b/ui/input.c index cbe8573c5c..dc745860f4 100644 --- a/ui/input.c +++ b/ui/input.c @@ -10,7 +10,7 @@ struct QemuInputHandlerState { DeviceState *dev; - QemuInputHandler *handler; + const QemuInputHandler *handler; int id; int events; QemuConsole *con; @@ -46,7 +46,7 @@ static uint32_t queue_count; static uint32_t queue_limit = 1024; QemuInputHandlerState *qemu_input_handler_register(DeviceState *dev, - QemuInputHandler *handler) + const QemuInputHandler *handler) { QemuInputHandlerState *s = g_new0(QemuInputHandlerState, 1); static int id = 1; diff --git a/ui/shader/meson.build b/ui/shader/meson.build index 592bf596b9..3137e65578 100644 --- a/ui/shader/meson.build +++ b/ui/shader/meson.build @@ -10,5 +10,6 @@ foreach e : shaders output: output, capture: true, input: files('@0@.@1@'.format(e[0], e[1])), + build_by_default: false, command: [shaderinclude, '@INPUT0@']) endforeach diff --git a/ui/vdagent.c b/ui/vdagent.c index 00d36a8677..706d6d97bd 100644 --- a/ui/vdagent.c +++ b/ui/vdagent.c @@ -297,7 +297,7 @@ static void vdagent_pointer_sync(DeviceState *dev) } } -static QemuInputHandler vdagent_mouse_handler = { +static const QemuInputHandler vdagent_mouse_handler = { .name = "vdagent mouse", .mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS, .event = vdagent_pointer_event, diff --git a/util/cutils.c b/util/cutils.c index c99d26c5e2..42364039a5 100644 --- a/util/cutils.c +++ b/util/cutils.c @@ -1163,24 +1163,30 @@ char *get_relocated_path(const char *dir) g_string_append(result, "/qemu-bundle"); if (access(result->str, R_OK) == 0) { #ifdef G_OS_WIN32 - size_t size = mbsrtowcs(NULL, &dir, 0, &(mbstate_t){0}) + 1; + const char *src = dir; + size_t size = mbsrtowcs(NULL, &src, 0, &(mbstate_t){0}) + 1; PWSTR wdir = g_new(WCHAR, size); - mbsrtowcs(wdir, &dir, size, &(mbstate_t){0}); + mbsrtowcs(wdir, &src, size, &(mbstate_t){0}); PCWSTR wdir_skipped_root; - PathCchSkipRoot(wdir, &wdir_skipped_root); + if (PathCchSkipRoot(wdir, &wdir_skipped_root) == S_OK) { + size = wcsrtombs(NULL, &wdir_skipped_root, 0, &(mbstate_t){0}); + char *cursor = result->str + result->len; + g_string_set_size(result, result->len + size); + wcsrtombs(cursor, &wdir_skipped_root, size + 1, &(mbstate_t){0}); + } else { + g_string_append(result, dir); + } - size = wcsrtombs(NULL, &wdir_skipped_root, 0, &(mbstate_t){0}); - char *cursor = result->str + result->len; - g_string_set_size(result, result->len + size); - wcsrtombs(cursor, &wdir_skipped_root, size + 1, &(mbstate_t){0}); g_free(wdir); #else g_string_append(result, dir); #endif - } else if (!starts_with_prefix(dir) || !starts_with_prefix(bindir)) { - g_string_assign(result, dir); - } else { + goto out; + } + + if (IS_ENABLED(CONFIG_RELOCATABLE) && + starts_with_prefix(dir) && starts_with_prefix(bindir)) { g_string_assign(result, exec_dir); /* Advance over common components. */ @@ -1203,7 +1209,10 @@ char *get_relocated_path(const char *dir) assert(G_IS_DIR_SEPARATOR(dir[-1])); g_string_append(result, dir - 1); } + goto out; } + g_string_assign(result, dir); +out: return g_string_free(result, false); } diff --git a/util/qemu-coroutine.c b/util/qemu-coroutine.c index 17a88f6505..5fd2dbaf8b 100644 --- a/util/qemu-coroutine.c +++ b/util/qemu-coroutine.c @@ -57,7 +57,7 @@ Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque) { Coroutine *co = NULL; - if (CONFIG_COROUTINE_POOL) { + if (IS_ENABLED(CONFIG_COROUTINE_POOL)) { CoroutineQSList *alloc_pool = get_ptr_alloc_pool(); co = QSLIST_FIRST(alloc_pool); @@ -99,7 +99,7 @@ static void coroutine_delete(Coroutine *co) { co->caller = NULL; - if (CONFIG_COROUTINE_POOL) { + if (IS_ENABLED(CONFIG_COROUTINE_POOL)) { if (release_pool_size < qatomic_read(&pool_max_size) * 2) { QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next); qatomic_inc(&release_pool_size); |