diff options
203 files changed, 6657 insertions, 3257 deletions
@@ -152,7 +152,8 @@ Xiaoqiang Zhao <zxq_yx_007@163.com> Xinhua Cao <caoxinhua@huawei.com> Xiong Zhang <xiong.y.zhang@intel.com> Yin Yin <yin.yin@cs2c.com.cn> -yuchenlin <npes87184@gmail.com> +Yu-Chen Lin <npes87184@gmail.com> +Yu-Chen Lin <npes87184@gmail.com> <yuchenlin@synology.com> YunQiang Su <syq@debian.org> YunQiang Su <ysu@wavecomp.com> Yuri Pudgorodskiy <yur@virtuozzo.com> diff --git a/MAINTAINERS b/MAINTAINERS index 1740a4fddc..36d94c17a6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -404,6 +404,14 @@ S: Supported F: target/i386/kvm.c F: scripts/kvm/vmxcap +WHPX CPUs +M: Sunil Muthuswamy <sunilmut@microsoft.com> +S: Supported +F: target/i386/whpx-all.c +F: target/i386/whp-dispatch.h +F: accel/stubs/whpx-stub.c +F: include/sysemu/whpx.h + Guest CPU Cores (Xen) --------------------- X86 Xen CPUs @@ -2031,7 +2039,8 @@ F: include/qemu/main-loop.h F: include/sysemu/runstate.h F: util/main-loop.c F: util/qemu-timer.c -F: vl.c +F: softmmu/vl.c +F: softmmu/main.c F: qapi/run-state.json Human Monitor (HMP) @@ -2183,6 +2192,14 @@ F: qtest.c F: accel/qtest.c F: tests/qtest/ +Device Fuzzing +M: Alexander Bulekov <alxndr@bu.edu> +R: Paolo Bonzini <pbonzini@redhat.com> +R: Bandan Das <bsd@redhat.com> +R: Stefan Hajnoczi <stefanha@redhat.com> +S: Maintained +F: tests/qtest/fuzz/ + Register API M: Alistair Francis <alistair@alistair23.me> S: Maintained @@ -477,7 +477,7 @@ config-host.h-timestamp: config-host.mak qemu-options.def: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool $(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$@") -TARGET_DIRS_RULES := $(foreach t, all clean install, $(addsuffix /$(t), $(TARGET_DIRS))) +TARGET_DIRS_RULES := $(foreach t, all fuzz clean install, $(addsuffix /$(t), $(TARGET_DIRS))) SOFTMMU_ALL_RULES=$(filter %-softmmu/all, $(TARGET_DIRS_RULES)) $(SOFTMMU_ALL_RULES): $(authz-obj-y) @@ -490,6 +490,15 @@ ifdef DECOMPRESS_EDK2_BLOBS $(SOFTMMU_ALL_RULES): $(edk2-decompressed) endif +SOFTMMU_FUZZ_RULES=$(filter %-softmmu/fuzz, $(TARGET_DIRS_RULES)) +$(SOFTMMU_FUZZ_RULES): $(authz-obj-y) +$(SOFTMMU_FUZZ_RULES): $(block-obj-y) +$(SOFTMMU_FUZZ_RULES): $(chardev-obj-y) +$(SOFTMMU_FUZZ_RULES): $(crypto-obj-y) +$(SOFTMMU_FUZZ_RULES): $(io-obj-y) +$(SOFTMMU_FUZZ_RULES): config-all-devices.mak +$(SOFTMMU_FUZZ_RULES): $(edk2-decompressed) + .PHONY: $(TARGET_DIRS_RULES) # The $(TARGET_DIRS_RULES) are of the form SUBDIR/GOAL, so that # $(dir $@) yields the sub-directory, and $(notdir $@) yields the sub-goal @@ -540,6 +549,9 @@ subdir-slirp: slirp/all $(filter %/all, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \ $(qom-obj-y) +$(filter %/fuzz, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \ + $(qom-obj-y) $(crypto-user-obj-$(CONFIG_USER_ONLY)) + ROM_DIRS = $(addprefix pc-bios/, $(ROMS)) ROM_DIRS_RULES=$(foreach t, all clean, $(addsuffix /$(t), $(ROM_DIRS))) # Only keep -O and -g cflags @@ -549,6 +561,7 @@ $(ROM_DIRS_RULES): .PHONY: recurse-all recurse-clean recurse-install recurse-all: $(addsuffix /all, $(TARGET_DIRS) $(ROM_DIRS)) +recurse-fuzz: $(addsuffix /fuzz, $(TARGET_DIRS) $(ROM_DIRS)) recurse-clean: $(addsuffix /clean, $(TARGET_DIRS) $(ROM_DIRS)) recurse-install: $(addsuffix /install, $(TARGET_DIRS)) $(addsuffix /install, $(TARGET_DIRS)): all @@ -865,7 +878,7 @@ ifdef CONFIG_VIRTFS $(INSTALL_DATA) $(MANUAL_BUILDDIR)/interop/virtfs-proxy-helper.1 "$(DESTDIR)$(mandir)/man1" endif ifeq ($(CONFIG_LINUX)$(CONFIG_SECCOMP)$(CONFIG_LIBCAP_NG),yyy) - $(INSTALL_DATA) docs/interop/virtiofsd.1 "$(DESTDIR)$(mandir)/man1" + $(INSTALL_DATA) $(MANUAL_BUILDDIR)/interop/virtiofsd.1 "$(DESTDIR)$(mandir)/man1" endif install-datadir: diff --git a/Makefile.objs b/Makefile.objs index 26b9cff954..8a1cbe8000 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -58,8 +58,6 @@ common-obj-y += ui/ common-obj-m += ui/ common-obj-y += dma-helpers.o -common-obj-y += vl.o -vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS) common-obj-$(CONFIG_TPM) += tpm.o common-obj-y += backends/ diff --git a/Makefile.target b/Makefile.target index 6e61f607b1..2d43dc586a 100644 --- a/Makefile.target +++ b/Makefile.target @@ -160,6 +160,7 @@ obj-y += qapi/ obj-y += memory.o obj-y += memory_mapping.o obj-y += migration/ram.o +obj-y += softmmu/ LIBS := $(libs_softmmu) $(LIBS) # Hardware support @@ -202,7 +203,7 @@ endif COMMON_LDADDS = ../libqemuutil.a # build either PROG or PROGW -$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS) +$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS) $(softmmu-main-y) $(call LINK, $(filter-out %.mak, $^)) ifdef CONFIG_DARWIN $(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"REZ","$(TARGET_DIR)$@") @@ -227,6 +228,22 @@ ifdef CONFIG_TRACE_SYSTEMTAP rm -f *.stp endif +ifdef CONFIG_FUZZ +include $(SRC_PATH)/tests/qtest/fuzz/Makefile.include +include $(SRC_PATH)/tests/qtest/Makefile.include + +fuzz: fuzz-vars +fuzz-vars: QEMU_CFLAGS := $(FUZZ_CFLAGS) $(QEMU_CFLAGS) +fuzz-vars: QEMU_LDFLAGS := $(FUZZ_LDFLAGS) $(QEMU_LDFLAGS) +fuzz-vars: $(QEMU_PROG_FUZZ) +dummy := $(call unnest-vars,, fuzz-obj-y) + + +$(QEMU_PROG_FUZZ): config-devices.mak $(all-obj-y) $(COMMON_LDADDS) $(fuzz-obj-y) + $(call LINK, $(filter-out %.mak, $^)) + +endif + install: all ifneq ($(PROGS),) $(call install-prog,$(PROGS),$(DESTDIR)$(bindir)) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index c111312dfd..6df3a4d030 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -308,13 +308,23 @@ static int kvm_set_user_memory_region(KVMMemoryListener *kml, KVMSlot *slot, boo /* Set the slot size to 0 before setting the slot to the desired * value. This is needed based on KVM commit 75d61fbc. */ mem.memory_size = 0; - kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); + if (ret < 0) { + goto err; + } } mem.memory_size = slot->memory_size; ret = kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, &mem); slot->old_flags = mem.flags; +err: trace_kvm_set_user_memory(mem.slot, mem.flags, mem.guest_phys_addr, mem.memory_size, mem.userspace_addr, ret); + if (ret < 0) { + error_report("%s: KVM_SET_USER_MEMORY_REGION failed, slot=%d," + " start=0x%" PRIx64 ", size=0x%" PRIx64 ": %s", + __func__, mem.slot, slot->start_addr, + (uint64_t)mem.memory_size, strerror(errno)); + } return ret; } diff --git a/audio/alsaaudio.c b/audio/alsaaudio.c index a23a5a0b60..a8e62542f9 100644 --- a/audio/alsaaudio.c +++ b/audio/alsaaudio.c @@ -819,7 +819,7 @@ static size_t alsa_read(HWVoiceIn *hw, void *buf, size_t len) switch (nread) { case 0: trace_alsa_read_zero(len); - return pos;; + return pos; case -EPIPE: if (alsa_recover(alsa->handle)) { @@ -835,7 +835,7 @@ static size_t alsa_read(HWVoiceIn *hw, void *buf, size_t len) default: alsa_logerr(nread, "Failed to read %zu frames to %p\n", len, dst); - return pos;; + return pos; } } @@ -532,20 +532,139 @@ out: return ret; } -int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp) +/** + * Helper function for bdrv_create_file_fallback(): Resize @blk to at + * least the given @minimum_size. + * + * On success, return @blk's actual length. + * Otherwise, return -errno. + */ +static int64_t create_file_fallback_truncate(BlockBackend *blk, + int64_t minimum_size, Error **errp) { - BlockDriver *drv; + Error *local_err = NULL; + int64_t size; + int ret; + + ret = blk_truncate(blk, minimum_size, false, PREALLOC_MODE_OFF, &local_err); + if (ret < 0 && ret != -ENOTSUP) { + error_propagate(errp, local_err); + return ret; + } + + size = blk_getlength(blk); + if (size < 0) { + error_free(local_err); + error_setg_errno(errp, -size, + "Failed to inquire the new image file's length"); + return size; + } + + if (size < minimum_size) { + /* Need to grow the image, but we failed to do that */ + error_propagate(errp, local_err); + return -ENOTSUP; + } + + error_free(local_err); + local_err = NULL; + + return size; +} + +/** + * Helper function for bdrv_create_file_fallback(): Zero the first + * sector to remove any potentially pre-existing image header. + */ +static int create_file_fallback_zero_first_sector(BlockBackend *blk, + int64_t current_size, + Error **errp) +{ + int64_t bytes_to_clear; + int ret; + + bytes_to_clear = MIN(current_size, BDRV_SECTOR_SIZE); + if (bytes_to_clear) { + ret = blk_pwrite_zeroes(blk, 0, bytes_to_clear, BDRV_REQ_MAY_UNMAP); + if (ret < 0) { + error_setg_errno(errp, -ret, + "Failed to clear the new image's first sector"); + return ret; + } + } + + return 0; +} + +static int bdrv_create_file_fallback(const char *filename, BlockDriver *drv, + QemuOpts *opts, Error **errp) +{ + BlockBackend *blk; + QDict *options = qdict_new(); + int64_t size = 0; + char *buf = NULL; + PreallocMode prealloc; Error *local_err = NULL; int ret; + size = qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0); + buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC); + prealloc = qapi_enum_parse(&PreallocMode_lookup, buf, + PREALLOC_MODE_OFF, &local_err); + g_free(buf); + if (local_err) { + error_propagate(errp, local_err); + return -EINVAL; + } + + if (prealloc != PREALLOC_MODE_OFF) { + error_setg(errp, "Unsupported preallocation mode '%s'", + PreallocMode_str(prealloc)); + return -ENOTSUP; + } + + qdict_put_str(options, "driver", drv->format_name); + + blk = blk_new_open(filename, NULL, options, + BDRV_O_RDWR | BDRV_O_RESIZE, errp); + if (!blk) { + error_prepend(errp, "Protocol driver '%s' does not support image " + "creation, and opening the image failed: ", + drv->format_name); + return -EINVAL; + } + + size = create_file_fallback_truncate(blk, size, errp); + if (size < 0) { + ret = size; + goto out; + } + + ret = create_file_fallback_zero_first_sector(blk, size, errp); + if (ret < 0) { + goto out; + } + + ret = 0; +out: + blk_unref(blk); + return ret; +} + +int bdrv_create_file(const char *filename, QemuOpts *opts, Error **errp) +{ + BlockDriver *drv; + drv = bdrv_find_protocol(filename, true, errp); if (drv == NULL) { return -ENOENT; } - ret = bdrv_create(drv, filename, opts, &local_err); - error_propagate(errp, local_err); - return ret; + if (drv->bdrv_co_create_opts) { + return bdrv_create(drv, filename, opts, errp); + } else { + return bdrv_create_file_fallback(filename, drv, opts, errp); + } } /** @@ -1444,6 +1563,24 @@ QemuOptsList bdrv_runtime_opts = { }, }; +static QemuOptsList fallback_create_opts = { + .name = "fallback-create-opts", + .head = QTAILQ_HEAD_INITIALIZER(fallback_create_opts.head), + .desc = { + { + .name = BLOCK_OPT_SIZE, + .type = QEMU_OPT_SIZE, + .help = "Virtual disk size" + }, + { + .name = BLOCK_OPT_PREALLOC, + .type = QEMU_OPT_STRING, + .help = "Preallocation mode (allowed values: off)" + }, + { /* end of list */ } + } +}; + /* * Common part for opening disk images and files * @@ -2435,13 +2572,13 @@ BdrvChild *bdrv_root_attach_child(BlockDriverState *child_bs, if (bdrv_get_aio_context(child_bs) != ctx) { ret = bdrv_try_set_aio_context(child_bs, ctx, &local_err); if (ret < 0 && child_role->can_set_aio_ctx) { - GSList *ignore = g_slist_prepend(NULL, child);; + GSList *ignore = g_slist_prepend(NULL, child); ctx = bdrv_get_aio_context(child_bs); if (child_role->can_set_aio_ctx(child, ctx, &ignore, NULL)) { error_free(local_err); ret = 0; g_slist_free(ignore); - ignore = g_slist_prepend(NULL, child);; + ignore = g_slist_prepend(NULL, child); child_role->set_aio_ctx(child, ctx, &ignore); } g_slist_free(ignore); @@ -2499,10 +2636,7 @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, static void bdrv_detach_child(BdrvChild *child) { - if (child->next.le_prev) { - QLIST_REMOVE(child, next); - child->next.le_prev = NULL; - } + QLIST_SAFE_REMOVE(child, next); bdrv_replace_child(child, NULL); @@ -4807,14 +4941,15 @@ BlockDriverState *bdrv_find_node(const char *node_name) } /* Put this QMP function here so it can access the static graph_bdrv_states. */ -BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp) +BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, + Error **errp) { BlockDeviceInfoList *list, *entry; BlockDriverState *bs; list = NULL; QTAILQ_FOREACH(bs, &graph_bdrv_states, node_list) { - BlockDeviceInfo *info = bdrv_block_device_info(NULL, bs, errp); + BlockDeviceInfo *info = bdrv_block_device_info(NULL, bs, flat, errp); if (!info) { qapi_free_BlockDeviceInfoList(list); return NULL; @@ -5771,15 +5906,13 @@ void bdrv_img_create(const char *filename, const char *fmt, return; } - if (!proto_drv->create_opts) { - error_setg(errp, "Protocol driver '%s' does not support image creation", - proto_drv->format_name); - return; - } - /* Create parameter list */ create_opts = qemu_opts_append(create_opts, drv->create_opts); - create_opts = qemu_opts_append(create_opts, proto_drv->create_opts); + if (proto_drv->create_opts) { + create_opts = qemu_opts_append(create_opts, proto_drv->create_opts); + } else { + create_opts = qemu_opts_append(create_opts, &fallback_create_opts); + } opts = qemu_opts_create(create_opts, NULL, 0, &error_abort); @@ -6201,65 +6334,55 @@ int bdrv_amend_options(BlockDriverState *bs, QemuOpts *opts, return bs->drv->bdrv_amend_options(bs, opts, status_cb, cb_opaque, errp); } -/* This function will be called by the bdrv_recurse_is_first_non_filter method - * of block filter and by bdrv_is_first_non_filter. - * It is used to test if the given bs is the candidate or recurse more in the - * node graph. +/* + * This function checks whether the given @to_replace is allowed to be + * replaced by a node that always shows the same data as @bs. This is + * used for example to verify whether the mirror job can replace + * @to_replace by the target mirrored from @bs. + * To be replaceable, @bs and @to_replace may either be guaranteed to + * always show the same data (because they are only connected through + * filters), or some driver may allow replacing one of its children + * because it can guarantee that this child's data is not visible at + * all (for example, for dissenting quorum children that have no other + * parents). */ -bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) +bool bdrv_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) { - /* return false if basic checks fails */ if (!bs || !bs->drv) { return false; } - /* the code reached a non block filter driver -> check if the bs is - * the same as the candidate. It's the recursion termination condition. - */ - if (!bs->drv->is_filter) { - return bs == candidate; + if (bs == to_replace) { + return true; } - /* Down this path the driver is a block filter driver */ - /* If the block filter recursion method is defined use it to recurse down - * the node graph. - */ - if (bs->drv->bdrv_recurse_is_first_non_filter) { - return bs->drv->bdrv_recurse_is_first_non_filter(bs, candidate); + /* See what the driver can do */ + if (bs->drv->bdrv_recurse_can_replace) { + return bs->drv->bdrv_recurse_can_replace(bs, to_replace); } - /* the driver is a block filter but don't allow to recurse -> return false - */ - return false; -} - -/* This function checks if the candidate is the first non filter bs down it's - * bs chain. Since we don't have pointers to parents it explore all bs chains - * from the top. Some filters can choose not to pass down the recursion. - */ -bool bdrv_is_first_non_filter(BlockDriverState *candidate) -{ - BlockDriverState *bs; - BdrvNextIterator it; - - /* walk down the bs forest recursively */ - for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) { - bool perm; - - /* try to recurse in this top level bs */ - perm = bdrv_recurse_is_first_non_filter(bs, candidate); - - /* candidate is the first non filter */ - if (perm) { - bdrv_next_cleanup(&it); - return true; - } + /* For filters without an own implementation, we can recurse on our own */ + if (bs->drv->is_filter) { + BdrvChild *child = bs->file ?: bs->backing; + return bdrv_recurse_can_replace(child->bs, to_replace); } + /* Safe default */ return false; } +/* + * Check whether the given @node_name can be replaced by a node that + * has the same data as @parent_bs. If so, return @node_name's BDS; + * NULL otherwise. + * + * @node_name must be a (recursive) *child of @parent_bs (or this + * function will return NULL). + * + * The result (whether the node can be replaced or not) is only valid + * for as long as no graph or permission changes occur. + */ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp) { @@ -6284,8 +6407,11 @@ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, * Another benefit is that this tests exclude backing files which are * blocked by the backing blockers. */ - if (!bdrv_recurse_is_first_non_filter(parent_bs, to_replace_bs)) { - error_setg(errp, "Only top most non filter can be replaced"); + if (!bdrv_recurse_can_replace(parent_bs, to_replace_bs)) { + error_setg(errp, "Cannot replace '%s' by a node mirrored from '%s', " + "because it cannot be guaranteed that doing so would not " + "lead to an abrupt change of visible data", + node_name, parent_bs->node_name); to_replace_bs = NULL; goto out; } diff --git a/block/backup-top.c b/block/backup-top.c index fa78f3256d..1bfb360bd3 100644 --- a/block/backup-top.c +++ b/block/backup-top.c @@ -48,11 +48,17 @@ static coroutine_fn int backup_top_co_preadv( } static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, - uint64_t bytes) + uint64_t bytes, BdrvRequestFlags flags) { BDRVBackupTopState *s = bs->opaque; - uint64_t end = QEMU_ALIGN_UP(offset + bytes, s->bcs->cluster_size); - uint64_t off = QEMU_ALIGN_DOWN(offset, s->bcs->cluster_size); + uint64_t off, end; + + if (flags & BDRV_REQ_WRITE_UNCHANGED) { + return 0; + } + + off = QEMU_ALIGN_DOWN(offset, s->bcs->cluster_size); + end = QEMU_ALIGN_UP(offset + bytes, s->bcs->cluster_size); return block_copy(s->bcs, off, end - off, NULL); } @@ -60,7 +66,7 @@ static coroutine_fn int backup_top_cbw(BlockDriverState *bs, uint64_t offset, static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) { - int ret = backup_top_cbw(bs, offset, bytes); + int ret = backup_top_cbw(bs, offset, bytes, 0); if (ret < 0) { return ret; } @@ -71,7 +77,7 @@ static int coroutine_fn backup_top_co_pdiscard(BlockDriverState *bs, static int coroutine_fn backup_top_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags) { - int ret = backup_top_cbw(bs, offset, bytes); + int ret = backup_top_cbw(bs, offset, bytes, flags); if (ret < 0) { return ret; } @@ -84,11 +90,9 @@ static coroutine_fn int backup_top_co_pwritev(BlockDriverState *bs, uint64_t bytes, QEMUIOVector *qiov, int flags) { - if (!(flags & BDRV_REQ_WRITE_UNCHANGED)) { - int ret = backup_top_cbw(bs, offset, bytes); - if (ret < 0) { - return ret; - } + int ret = backup_top_cbw(bs, offset, bytes, flags); + if (ret < 0) { + return ret; } return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags); @@ -196,8 +200,13 @@ BlockDriverState *bdrv_backup_top_append(BlockDriverState *source, return NULL; } - top->total_sectors = source->total_sectors; state = top->opaque; + top->total_sectors = source->total_sectors; + top->supported_write_flags = BDRV_REQ_WRITE_UNCHANGED | + (BDRV_REQ_FUA & source->supported_write_flags); + top->supported_zero_flags = BDRV_REQ_WRITE_UNCHANGED | + ((BDRV_REQ_FUA | BDRV_REQ_MAY_UNMAP | BDRV_REQ_NO_FALLBACK) & + source->supported_zero_flags); bdrv_ref(target); state->target = bdrv_attach_child(top, target, "target", &child_file, errp); diff --git a/block/blkverify.c b/block/blkverify.c index 304b0a1368..ba6b1853ae 100644 --- a/block/blkverify.c +++ b/block/blkverify.c @@ -268,18 +268,18 @@ static int blkverify_co_flush(BlockDriverState *bs) return bdrv_co_flush(s->test_file->bs); } -static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) +static bool blkverify_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) { BDRVBlkverifyState *s = bs->opaque; - bool perm = bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); - - if (perm) { - return true; - } - - return bdrv_recurse_is_first_non_filter(s->test_file->bs, candidate); + /* + * blkverify quits the whole qemu process if there is a mismatch + * between bs->file->bs and s->test_file->bs. Therefore, we know + * know that both must match bs and we can recurse down to either. + */ + return bdrv_recurse_can_replace(bs->file->bs, to_replace) || + bdrv_recurse_can_replace(s->test_file->bs, to_replace); } static void blkverify_refresh_filename(BlockDriverState *bs) @@ -327,7 +327,7 @@ static BlockDriver bdrv_blkverify = { .bdrv_co_flush = blkverify_co_flush, .is_filter = true, - .bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter, + .bdrv_recurse_can_replace = blkverify_recurse_can_replace, }; static void bdrv_blkverify_init(void) diff --git a/block/commit.c b/block/commit.c index 23c90b3b91..8e672799af 100644 --- a/block/commit.c +++ b/block/commit.c @@ -43,27 +43,6 @@ typedef struct CommitBlockJob { char *backing_file_str; } CommitBlockJob; -static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base, - int64_t offset, uint64_t bytes, - void *buf) -{ - int ret = 0; - - assert(bytes < SIZE_MAX); - - ret = blk_co_pread(bs, offset, bytes, buf, 0); - if (ret < 0) { - return ret; - } - - ret = blk_co_pwrite(base, offset, bytes, buf, 0); - if (ret < 0) { - return ret; - } - - return 0; -} - static int commit_prepare(Job *job) { CommitBlockJob *s = container_of(job, CommitBlockJob, common.job); @@ -140,7 +119,6 @@ static int coroutine_fn commit_run(Job *job, Error **errp) int ret = 0; int64_t n = 0; /* bytes */ void *buf = NULL; - int bytes_written = 0; int64_t len, base_len; ret = len = blk_getlength(s->top); @@ -165,6 +143,7 @@ static int coroutine_fn commit_run(Job *job, Error **errp) for (offset = 0; offset < len; offset += n) { bool copy; + bool error_in_source = true; /* Note that even when no rate limit is applied we need to yield * with no pending I/O here so that bdrv_drain_all() returns. @@ -179,12 +158,20 @@ static int coroutine_fn commit_run(Job *job, Error **errp) copy = (ret == 1); trace_commit_one_iteration(s, offset, n, ret); if (copy) { - ret = commit_populate(s->top, s->base, offset, n, buf); - bytes_written += n; + assert(n < SIZE_MAX); + + ret = blk_co_pread(s->top, offset, n, buf, 0); + if (ret >= 0) { + ret = blk_co_pwrite(s->base, offset, n, buf, 0); + if (ret < 0) { + error_in_source = false; + } + } } if (ret < 0) { BlockErrorAction action = - block_job_error_action(&s->common, false, s->on_error, -ret); + block_job_error_action(&s->common, s->on_error, + error_in_source, -ret); if (action == BLOCK_ERROR_ACTION_REPORT) { goto out; } else { diff --git a/block/copy-on-read.c b/block/copy-on-read.c index e95223d3cb..242d3ff055 100644 --- a/block/copy-on-read.c +++ b/block/copy-on-read.c @@ -118,13 +118,6 @@ static void cor_lock_medium(BlockDriverState *bs, bool locked) } -static bool cor_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - - static BlockDriver bdrv_copy_on_read = { .format_name = "copy-on-read", @@ -143,8 +136,6 @@ static BlockDriver bdrv_copy_on_read = { .bdrv_co_block_status = bdrv_co_block_status_from_file, - .bdrv_recurse_is_first_non_filter = cor_recurse_is_first_non_filter, - .has_variable_length = true, .is_filter = true, }; diff --git a/block/file-posix.c b/block/file-posix.c index ab82ee1a67..6345477112 100644 --- a/block/file-posix.c +++ b/block/file-posix.c @@ -3477,67 +3477,6 @@ static coroutine_fn int hdev_co_pwrite_zeroes(BlockDriverState *bs, return raw_do_pwrite_zeroes(bs, offset, bytes, flags, true); } -static int coroutine_fn hdev_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) -{ - int fd; - int ret = 0; - struct stat stat_buf; - int64_t total_size = 0; - bool has_prefix; - - /* This function is used by both protocol block drivers and therefore either - * of these prefixes may be given. - * The return value has to be stored somewhere, otherwise this is an error - * due to -Werror=unused-value. */ - has_prefix = - strstart(filename, "host_device:", &filename) || - strstart(filename, "host_cdrom:" , &filename); - - (void)has_prefix; - - ret = raw_normalize_devicepath(&filename, errp); - if (ret < 0) { - return ret; - } - - /* Read out options */ - total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - - fd = qemu_open(filename, O_WRONLY | O_BINARY); - if (fd < 0) { - ret = -errno; - error_setg_errno(errp, -ret, "Could not open device"); - return ret; - } - - if (fstat(fd, &stat_buf) < 0) { - ret = -errno; - error_setg_errno(errp, -ret, "Could not stat device"); - } else if (!S_ISBLK(stat_buf.st_mode) && !S_ISCHR(stat_buf.st_mode)) { - error_setg(errp, - "The given file is neither a block nor a character device"); - ret = -ENODEV; - } else if (lseek(fd, 0, SEEK_END) < total_size) { - error_setg(errp, "Device is too small"); - ret = -ENOSPC; - } - - if (!ret && total_size) { - uint8_t buf[BDRV_SECTOR_SIZE] = { 0 }; - int64_t zero_size = MIN(BDRV_SECTOR_SIZE, total_size); - if (lseek(fd, 0, SEEK_SET) == -1) { - ret = -errno; - } else { - ret = qemu_write_full(fd, buf, zero_size); - ret = ret == zero_size ? 0 : -errno; - } - } - qemu_close(fd); - return ret; -} - static BlockDriver bdrv_host_device = { .format_name = "host_device", .protocol_name = "host_device", @@ -3550,8 +3489,6 @@ static BlockDriver bdrv_host_device = { .bdrv_reopen_prepare = raw_reopen_prepare, .bdrv_reopen_commit = raw_reopen_commit, .bdrv_reopen_abort = raw_reopen_abort, - .bdrv_co_create_opts = hdev_co_create_opts, - .create_opts = &raw_create_opts, .mutable_opts = mutable_opts, .bdrv_co_invalidate_cache = raw_co_invalidate_cache, .bdrv_co_pwrite_zeroes = hdev_co_pwrite_zeroes, @@ -3678,8 +3615,6 @@ static BlockDriver bdrv_host_cdrom = { .bdrv_reopen_prepare = raw_reopen_prepare, .bdrv_reopen_commit = raw_reopen_commit, .bdrv_reopen_abort = raw_reopen_abort, - .bdrv_co_create_opts = hdev_co_create_opts, - .create_opts = &raw_create_opts, .mutable_opts = mutable_opts, .bdrv_co_invalidate_cache = raw_co_invalidate_cache, @@ -3812,8 +3747,6 @@ static BlockDriver bdrv_host_cdrom = { .bdrv_reopen_prepare = raw_reopen_prepare, .bdrv_reopen_commit = raw_reopen_commit, .bdrv_reopen_abort = raw_reopen_abort, - .bdrv_co_create_opts = hdev_co_create_opts, - .create_opts = &raw_create_opts, .mutable_opts = mutable_opts, .bdrv_co_preadv = raw_co_preadv, diff --git a/block/filter-compress.c b/block/filter-compress.c index 60137fb680..82c315b298 100644 --- a/block/filter-compress.c +++ b/block/filter-compress.c @@ -128,13 +128,6 @@ static void compress_lock_medium(BlockDriverState *bs, bool locked) } -static bool compress_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - - static BlockDriver bdrv_compress = { .format_name = "compress", @@ -154,8 +147,6 @@ static BlockDriver bdrv_compress = { .bdrv_co_block_status = bdrv_co_block_status_from_file, - .bdrv_recurse_is_first_non_filter = compress_recurse_is_first_non_filter, - .has_variable_length = true, .is_filter = true, }; diff --git a/block/io_uring.c b/block/io_uring.c index 56892fd1ab..a3142ca989 100644 --- a/block/io_uring.c +++ b/block/io_uring.c @@ -187,7 +187,7 @@ static void luring_process_completions(LuringState *s) ret = 0; } } else { - ret = -ENOSPC;; + ret = -ENOSPC; } } end: diff --git a/block/iscsi.c b/block/iscsi.c index c8feaa2f0e..682abd8e09 100644 --- a/block/iscsi.c +++ b/block/iscsi.c @@ -2164,58 +2164,6 @@ static int coroutine_fn iscsi_co_truncate(BlockDriverState *bs, int64_t offset, return 0; } -static int coroutine_fn iscsi_co_create_opts(const char *filename, QemuOpts *opts, - Error **errp) -{ - int ret = 0; - int64_t total_size = 0; - BlockDriverState *bs; - IscsiLun *iscsilun = NULL; - QDict *bs_options; - Error *local_err = NULL; - - bs = bdrv_new(); - - /* Read out options */ - total_size = DIV_ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0), - BDRV_SECTOR_SIZE); - bs->opaque = g_new0(struct IscsiLun, 1); - iscsilun = bs->opaque; - - bs_options = qdict_new(); - iscsi_parse_filename(filename, bs_options, &local_err); - if (local_err) { - error_propagate(errp, local_err); - ret = -EINVAL; - } else { - ret = iscsi_open(bs, bs_options, 0, NULL); - } - qobject_unref(bs_options); - - if (ret != 0) { - goto out; - } - iscsi_detach_aio_context(bs); - if (iscsilun->type != TYPE_DISK) { - ret = -ENODEV; - goto out; - } - if (bs->total_sectors < total_size) { - ret = -ENOSPC; - goto out; - } - - ret = 0; -out: - if (iscsilun->iscsi != NULL) { - iscsi_destroy_context(iscsilun->iscsi); - } - g_free(bs->opaque); - bs->opaque = NULL; - bdrv_unref(bs); - return ret; -} - static int iscsi_get_info(BlockDriverState *bs, BlockDriverInfo *bdi) { IscsiLun *iscsilun = bs->opaque; @@ -2486,8 +2434,6 @@ static BlockDriver bdrv_iscsi = { .bdrv_parse_filename = iscsi_parse_filename, .bdrv_file_open = iscsi_open, .bdrv_close = iscsi_close, - .bdrv_co_create_opts = iscsi_co_create_opts, - .create_opts = &iscsi_create_opts, .bdrv_reopen_prepare = iscsi_reopen_prepare, .bdrv_reopen_commit = iscsi_reopen_commit, .bdrv_co_invalidate_cache = iscsi_co_invalidate_cache, @@ -2525,8 +2471,6 @@ static BlockDriver bdrv_iser = { .bdrv_parse_filename = iscsi_parse_filename, .bdrv_file_open = iscsi_open, .bdrv_close = iscsi_close, - .bdrv_co_create_opts = iscsi_co_create_opts, - .create_opts = &iscsi_create_opts, .bdrv_reopen_prepare = iscsi_reopen_prepare, .bdrv_reopen_commit = iscsi_reopen_commit, .bdrv_co_invalidate_cache = iscsi_co_invalidate_cache, diff --git a/block/mirror.c b/block/mirror.c index f0f2d9dff1..447051dbc6 100644 --- a/block/mirror.c +++ b/block/mirror.c @@ -103,6 +103,7 @@ struct MirrorOp { bool is_pseudo_op; bool is_active_write; CoQueue waiting_requests; + Coroutine *co; QTAILQ_ENTRY(MirrorOp) next; }; @@ -282,11 +283,14 @@ static int mirror_cow_align(MirrorBlockJob *s, int64_t *offset, } static inline void coroutine_fn -mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) +mirror_wait_for_any_operation(MirrorBlockJob *s, MirrorOp *self, bool active) { MirrorOp *op; QTAILQ_FOREACH(op, &s->ops_in_flight, next) { + if (self == op) { + continue; + } /* Do not wait on pseudo ops, because it may in turn wait on * some other operation to start, which may in fact be the * caller of this function. Since there is only one pseudo op @@ -301,10 +305,10 @@ mirror_wait_for_any_operation(MirrorBlockJob *s, bool active) } static inline void coroutine_fn -mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s) +mirror_wait_for_free_in_flight_slot(MirrorBlockJob *s, MirrorOp *self) { /* Only non-active operations use up in-flight slots */ - mirror_wait_for_any_operation(s, false); + mirror_wait_for_any_operation(s, self, false); } /* Perform a mirror copy operation. @@ -347,7 +351,7 @@ static void coroutine_fn mirror_co_read(void *opaque) while (s->buf_free_count < nb_chunks) { trace_mirror_yield_in_flight(s, op->offset, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, op); } /* Now make a QEMUIOVector taking enough granularity-sized chunks @@ -429,6 +433,7 @@ static unsigned mirror_perform(MirrorBlockJob *s, int64_t offset, default: abort(); } + op->co = co; QTAILQ_INSERT_TAIL(&s->ops_in_flight, op, next); qemu_coroutine_enter(co); @@ -553,7 +558,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s) while (s->in_flight >= MAX_IN_FLIGHT) { trace_mirror_yield_in_flight(s, offset, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, pseudo_op); } if (s->ret < 0) { @@ -607,7 +612,7 @@ static void mirror_free_init(MirrorBlockJob *s) static void coroutine_fn mirror_wait_for_all_io(MirrorBlockJob *s) { while (s->in_flight > 0) { - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); } } @@ -695,7 +700,19 @@ static int mirror_exit_common(Job *job) * drain potential other users of the BDS before changing the graph. */ assert(s->in_drain); bdrv_drained_begin(target_bs); - bdrv_replace_node(to_replace, target_bs, &local_err); + /* + * Cannot use check_to_replace_node() here, because that would + * check for an op blocker on @to_replace, and we have our own + * there. + */ + if (bdrv_recurse_can_replace(src, to_replace)) { + bdrv_replace_node(to_replace, target_bs, &local_err); + } else { + error_setg(&local_err, "Can no longer replace '%s' by '%s', " + "because it can no longer be guaranteed that doing so " + "would not lead to an abrupt change of visible data", + to_replace->node_name, target_bs->node_name); + } bdrv_drained_end(target_bs); if (local_err) { error_report_err(local_err); @@ -792,7 +809,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s) if (s->in_flight >= MAX_IN_FLIGHT) { trace_mirror_yield(s, UINT64_MAX, s->buf_free_count, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); continue; } @@ -945,7 +962,7 @@ static int coroutine_fn mirror_run(Job *job, Error **errp) /* Do not start passive operations while there are active * writes in progress */ while (s->in_active_write_counter) { - mirror_wait_for_any_operation(s, true); + mirror_wait_for_any_operation(s, NULL, true); } if (s->ret < 0) { @@ -971,7 +988,7 @@ static int coroutine_fn mirror_run(Job *job, Error **errp) if (s->in_flight >= MAX_IN_FLIGHT || s->buf_free_count == 0 || (cnt == 0 && s->in_flight > 0)) { trace_mirror_yield(s, cnt, s->buf_free_count, s->in_flight); - mirror_wait_for_free_in_flight_slot(s); + mirror_wait_for_free_in_flight_slot(s, NULL); continue; } else if (cnt != 0) { delay_ns = mirror_iteration(s); diff --git a/block/nbd.c b/block/nbd.c index d085554f21..6d3b22f844 100644 --- a/block/nbd.c +++ b/block/nbd.c @@ -70,6 +70,7 @@ typedef struct BDRVNBDState { CoMutex send_mutex; CoQueue free_sema; Coroutine *connection_co; + Coroutine *teardown_co; QemuCoSleepState *connection_co_sleep_ns_state; bool drained; bool wait_drained_end; @@ -203,7 +204,15 @@ static void nbd_teardown_connection(BlockDriverState *bs) qemu_co_sleep_wake(s->connection_co_sleep_ns_state); } } - BDRV_POLL_WHILE(bs, s->connection_co); + if (qemu_in_coroutine()) { + s->teardown_co = qemu_coroutine_self(); + /* connection_co resumes us when it terminates */ + qemu_coroutine_yield(); + s->teardown_co = NULL; + } else { + BDRV_POLL_WHILE(bs, s->connection_co); + } + assert(!s->connection_co); } static bool nbd_client_connecting(BDRVNBDState *s) @@ -395,6 +404,9 @@ static coroutine_fn void nbd_connection_entry(void *opaque) s->ioc = NULL; } + if (s->teardown_co) { + aio_co_wake(s->teardown_co); + } aio_wait_kick(); } diff --git a/block/qapi.c b/block/qapi.c index 9a5d0c9b27..afd9f3b4a7 100644 --- a/block/qapi.c +++ b/block/qapi.c @@ -42,7 +42,9 @@ #include "qemu/cutils.h" BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, - BlockDriverState *bs, Error **errp) + BlockDriverState *bs, + bool flat, + Error **errp) { ImageInfo **p_image_info; BlockDriverState *bs0; @@ -156,6 +158,11 @@ BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, return NULL; } + /* stop gathering data for flat output */ + if (flat) { + break; + } + if (bs0->drv && bs0->backing) { info->backing_file_depth++; bs0 = bs0->backing->bs; @@ -389,7 +396,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info, if (bs && bs->drv) { info->has_inserted = true; - info->inserted = bdrv_block_device_info(blk, bs, errp); + info->inserted = bdrv_block_device_info(blk, bs, false, errp); if (info->inserted == NULL) { goto err; } @@ -657,7 +664,7 @@ void bdrv_snapshot_dump(QEMUSnapshotInfo *sn) char *sizing = NULL; if (!sn) { - qemu_printf("%-10s%-20s%7s%20s%15s", + qemu_printf("%-10s%-20s%11s%20s%15s", "ID", "TAG", "VM SIZE", "DATE", "VM CLOCK"); } else { ti = sn->date_sec; @@ -672,7 +679,7 @@ void bdrv_snapshot_dump(QEMUSnapshotInfo *sn) (int)(secs % 60), (int)((sn->vm_clock_nsec / 1000000) % 1000)); sizing = size_to_str(sn->vm_state_size); - qemu_printf("%-10s%-20s%7s%20s%15s", + qemu_printf("%-10s%-20s%11s%20s%15s", sn->id_str, sn->name, sizing, date_buf, diff --git a/block/qcow2-bitmap.c b/block/qcow2-bitmap.c index d41f5d049b..8cccc2c9f3 100644 --- a/block/qcow2-bitmap.c +++ b/block/qcow2-bitmap.c @@ -647,7 +647,6 @@ static Qcow2BitmapList *bitmap_list_load(BlockDriverState *bs, uint64_t offset, return bm_list; broken_dir: - ret = -EINVAL; error_setg(errp, "Broken bitmap directory"); fail: diff --git a/block/qcow2-cluster.c b/block/qcow2-cluster.c index 1947f13a2d..78c95dfa16 100644 --- a/block/qcow2-cluster.c +++ b/block/qcow2-cluster.c @@ -1026,8 +1026,11 @@ err: void qcow2_alloc_cluster_abort(BlockDriverState *bs, QCowL2Meta *m) { BDRVQcow2State *s = bs->opaque; - qcow2_free_clusters(bs, m->alloc_offset, m->nb_clusters << s->cluster_bits, - QCOW2_DISCARD_NEVER); + if (!has_data_file(bs)) { + qcow2_free_clusters(bs, m->alloc_offset, + m->nb_clusters << s->cluster_bits, + QCOW2_DISCARD_NEVER); + } } /* diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c index c963bc8de1..7ef1c0e42a 100644 --- a/block/qcow2-refcount.c +++ b/block/qcow2-refcount.c @@ -889,6 +889,7 @@ static int QEMU_WARN_UNUSED_RESULT update_refcount(BlockDriverState *bs, offset); if (table != NULL) { qcow2_cache_put(s->refcount_block_cache, &refcount_block); + old_table_index = -1; qcow2_cache_discard(s->refcount_block_cache, table); } diff --git a/block/qcow2-threads.c b/block/qcow2-threads.c index 8f5a0d1ebe..77bb578cdf 100644 --- a/block/qcow2-threads.c +++ b/block/qcow2-threads.c @@ -246,12 +246,15 @@ qcow2_co_encdec(BlockDriverState *bs, uint64_t host_offset, .len = len, .func = func, }; + uint64_t sector_size; - assert(QEMU_IS_ALIGNED(guest_offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(host_offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(len, BDRV_SECTOR_SIZE)); assert(s->crypto); + sector_size = qcrypto_block_get_sector_size(s->crypto); + assert(QEMU_IS_ALIGNED(guest_offset, sector_size)); + assert(QEMU_IS_ALIGNED(host_offset, sector_size)); + assert(QEMU_IS_ALIGNED(len, sector_size)); + return len == 0 ? 0 : qcow2_co_process(bs, qcow2_encdec_pool_func, &arg); } @@ -270,7 +273,8 @@ qcow2_co_encdec(BlockDriverState *bs, uint64_t host_offset, * will be written to the underlying storage device at * @host_offset * - * @len - length of the buffer (must be a BDRV_SECTOR_SIZE multiple) + * @len - length of the buffer (must be a multiple of the encryption + * sector size) * * Depending on the encryption method, @host_offset and/or @guest_offset * may be used for generating the initialization vector for diff --git a/block/qcow2.c b/block/qcow2.c index ef96606f8d..3c754f616b 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -135,13 +135,16 @@ static ssize_t qcow2_crypto_hdr_init_func(QCryptoBlock *block, size_t headerlen, s->crypto_header.length = headerlen; s->crypto_header.offset = ret; - /* Zero fill remaining space in cluster so it has predictable - * content in case of future spec changes */ + /* + * Zero fill all space in cluster so it has predictable + * content, as we may not initialize some regions of the + * header (eg only 1 out of 8 key slots will be initialized) + */ clusterlen = size_to_clusters(s, headerlen) * s->cluster_size; assert(qcow2_pre_write_overlap_check(bs, 0, ret, clusterlen, false) == 0); ret = bdrv_pwrite_zeroes(bs->file, - ret + headerlen, - clusterlen - headerlen, 0); + ret, + clusterlen, 0); if (ret < 0) { error_setg_errno(errp, -ret, "Could not zero fill encryption header"); return -1; @@ -2068,8 +2071,6 @@ qcow2_co_preadv_encrypted(BlockDriverState *bs, goto fail; } - assert(QEMU_IS_ALIGNED(offset, BDRV_SECTOR_SIZE)); - assert(QEMU_IS_ALIGNED(bytes, BDRV_SECTOR_SIZE)); if (qcow2_co_decrypt(bs, file_cluster_offset + offset_into_cluster(s, offset), offset, buf, bytes) < 0) diff --git a/block/quorum.c b/block/quorum.c index df68adcfaa..6d7a56bd93 100644 --- a/block/quorum.c +++ b/block/quorum.c @@ -796,17 +796,53 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs) return result; } -static bool quorum_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) +static bool quorum_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace) { BDRVQuorumState *s = bs->opaque; int i; for (i = 0; i < s->num_children; i++) { - bool perm = bdrv_recurse_is_first_non_filter(s->children[i]->bs, - candidate); - if (perm) { - return true; + /* + * We have no idea whether our children show the same data as + * this node (@bs). It is actually highly likely that + * @to_replace does not, because replacing a broken child is + * one of the main use cases here. + * + * We do know that the new BDS will match @bs, so replacing + * any of our children by it will be safe. It cannot change + * the data this quorum node presents to its parents. + * + * However, replacing @to_replace by @bs in any of our + * children's chains may change visible data somewhere in + * there. We therefore cannot recurse down those chains with + * bdrv_recurse_can_replace(). + * (More formally, bdrv_recurse_can_replace() requires that + * @to_replace will be replaced by something matching the @bs + * passed to it. We cannot guarantee that.) + * + * Thus, we can only check whether any of our immediate + * children matches @to_replace. + * + * (In the future, we might add a function to recurse down a + * chain that checks that nothing there cares about a change + * in data from the respective child in question. For + * example, most filters do not care when their child's data + * suddenly changes, as long as their parents do not care.) + */ + if (s->children[i]->bs == to_replace) { + /* + * We now have to ensure that there is no other parent + * that cares about replacing this child by a node with + * potentially different data. + * We do so by checking whether there are any other parents + * at all, which is stricter than necessary, but also very + * simple. (We may decide to implement something more + * complex and permissive when there is an actual need for + * it.) + */ + return QLIST_FIRST(&to_replace->parents) == s->children[i] && + QLIST_NEXT(s->children[i], next_parent) == NULL; } } @@ -1114,6 +1150,23 @@ static char *quorum_dirname(BlockDriverState *bs, Error **errp) return NULL; } +static void quorum_child_perm(BlockDriverState *bs, BdrvChild *c, + const BdrvChildRole *role, + BlockReopenQueue *reopen_queue, + uint64_t perm, uint64_t shared, + uint64_t *nperm, uint64_t *nshared) +{ + *nperm = perm & DEFAULT_PERM_PASSTHROUGH; + + /* + * We cannot share RESIZE or WRITE, as this would make the + * children differ from each other. + */ + *nshared = (shared & (BLK_PERM_CONSISTENT_READ | + BLK_PERM_WRITE_UNCHANGED)) + | DEFAULT_PERM_UNCHANGED; +} + static const char *const quorum_strong_runtime_opts[] = { QUORUM_OPT_VOTE_THRESHOLD, QUORUM_OPT_BLKVERIFY, @@ -1143,10 +1196,9 @@ static BlockDriver bdrv_quorum = { .bdrv_add_child = quorum_add_child, .bdrv_del_child = quorum_del_child, - .bdrv_child_perm = bdrv_filter_default_perms, + .bdrv_child_perm = quorum_child_perm, - .is_filter = true, - .bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter, + .bdrv_recurse_can_replace = quorum_recurse_can_replace, .strong_runtime_opts = quorum_strong_runtime_opts, }; diff --git a/block/replication.c b/block/replication.c index 99532ce521..d6681b6c84 100644 --- a/block/replication.c +++ b/block/replication.c @@ -306,12 +306,6 @@ out: return ret; } -static bool replication_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - static void secondary_do_checkpoint(BDRVReplicationState *s, Error **errp) { Error *local_err = NULL; @@ -699,7 +693,6 @@ static BlockDriver bdrv_replication = { .bdrv_co_writev = replication_co_writev, .is_filter = true, - .bdrv_recurse_is_first_non_filter = replication_recurse_is_first_non_filter, .has_variable_length = true, .strong_runtime_opts = replication_strong_runtime_opts, diff --git a/block/throttle.c b/block/throttle.c index 0349f42257..71f4bb0ad1 100644 --- a/block/throttle.c +++ b/block/throttle.c @@ -207,12 +207,6 @@ static void throttle_reopen_abort(BDRVReopenState *reopen_state) reopen_state->opaque = NULL; } -static bool throttle_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate) -{ - return bdrv_recurse_is_first_non_filter(bs->file->bs, candidate); -} - static void coroutine_fn throttle_co_drain_begin(BlockDriverState *bs) { ThrottleGroupMember *tgm = bs->opaque; @@ -252,8 +246,6 @@ static BlockDriver bdrv_throttle = { .bdrv_co_pwrite_zeroes = throttle_co_pwrite_zeroes, .bdrv_co_pdiscard = throttle_co_pdiscard, - .bdrv_recurse_is_first_non_filter = throttle_recurse_is_first_non_filter, - .bdrv_attach_aio_context = throttle_attach_aio_context, .bdrv_detach_aio_context = throttle_detach_aio_context, diff --git a/block/vvfat.c b/block/vvfat.c index 019b8f1341..ab800c4887 100644 --- a/block/vvfat.c +++ b/block/vvfat.c @@ -3124,17 +3124,10 @@ write_target_commit(BlockDriverState *bs, uint64_t offset, uint64_t bytes, return ret; } -static void write_target_close(BlockDriverState *bs) { - BDRVVVFATState* s = *((BDRVVVFATState**) bs->opaque); - bdrv_unref_child(s->bs, s->qcow); - g_free(s->qcow_filename); -} - static BlockDriver vvfat_write_target = { .format_name = "vvfat_write_target", .instance_size = sizeof(void*), .bdrv_co_pwritev = write_target_commit, - .bdrv_close = write_target_close, }; static void vvfat_qcow_options(int *child_flags, QDict *child_options, diff --git a/blockdev.c b/blockdev.c index c6a727cca9..011dcfec27 100644 --- a/blockdev.c +++ b/blockdev.c @@ -1592,11 +1592,6 @@ static void external_snapshot_prepare(BlkActionState *common, } } - if (!bdrv_is_first_non_filter(state->old_bs)) { - error_setg(errp, QERR_FEATURE_DISABLED, "snapshot"); - goto out; - } - if (action->type == TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC) { BlockdevSnapshotSync *s = action->u.blockdev_snapshot_sync.data; const char *format = s->has_format ? s->format : "qcow2"; @@ -3336,11 +3331,6 @@ void qmp_block_resize(bool has_device, const char *device, aio_context = bdrv_get_aio_context(bs); aio_context_acquire(aio_context); - if (!bdrv_is_first_non_filter(bs)) { - error_setg(errp, QERR_FEATURE_DISABLED, "resize"); - goto out; - } - if (size < 0) { error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "size", "a >0 size"); goto out; @@ -3471,6 +3461,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device, bool has_top, const char *top, bool has_backing_file, const char *backing_file, bool has_speed, int64_t speed, + bool has_on_error, BlockdevOnError on_error, bool has_filter_node_name, const char *filter_node_name, bool has_auto_finalize, bool auto_finalize, bool has_auto_dismiss, bool auto_dismiss, @@ -3481,15 +3472,14 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device, BlockDriverState *base_bs, *top_bs; AioContext *aio_context; Error *local_err = NULL; - /* This will be part of the QMP command, if/when the - * BlockdevOnError change for blkmirror makes it in - */ - BlockdevOnError on_error = BLOCKDEV_ON_ERROR_REPORT; int job_flags = JOB_DEFAULT; if (!has_speed) { speed = 0; } + if (!has_on_error) { + on_error = BLOCKDEV_ON_ERROR_REPORT; + } if (!has_filter_node_name) { filter_node_name = NULL; } @@ -3744,9 +3734,13 @@ void qmp_drive_backup(DriveBackup *backup, Error **errp) blockdev_do_action(&action, errp); } -BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp) +BlockDeviceInfoList *qmp_query_named_block_nodes(bool has_flat, + bool flat, + Error **errp) { - return bdrv_named_nodes_list(errp); + bool return_flat = has_flat && flat; + + return bdrv_named_nodes_list(return_flat, errp); } XDbgBlockGraph *qmp_x_debug_query_block_graph(Error **errp) diff --git a/chardev/spice.c b/chardev/spice.c index 241e2b7770..bf7ea1e294 100644 --- a/chardev/spice.c +++ b/chardev/spice.c @@ -216,9 +216,7 @@ static void char_spice_finalize(Object *obj) vmc_unregister_interface(s); - if (s->next.le_prev) { - QLIST_REMOVE(s, next); - } + QLIST_SAFE_REMOVE(s, next); g_free((char *)s->sin.subtype); g_free((char *)s->sin.portname); @@ -455,7 +455,7 @@ guest_agent_ntddscsi="no" guest_agent_msi="" vss_win32_sdk="" win_sdk="no" -want_tools="yes" +want_tools="" libiscsi="" libnfs="" coroutine="" @@ -505,6 +505,7 @@ debug_mutex="no" libpmem="" default_devices="yes" plugins="no" +fuzzing="no" supported_cpu="no" supported_os="no" @@ -635,6 +636,15 @@ int main(void) { return 0; } EOF } +write_c_fuzzer_skeleton() { + cat > $TMPC <<EOF +#include <stdint.h> +#include <sys/types.h> +int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size); +int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size) { return 0; } +EOF +} + if check_define __linux__ ; then targetos="Linux" elif check_define _WIN32 ; then @@ -1558,6 +1568,10 @@ for opt do ;; --disable-containers) use_containers="no" ;; + --enable-fuzzing) fuzzing=yes + ;; + --disable-fuzzing) fuzzing=no + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -2214,6 +2228,16 @@ else fi ########################################## +# system tools +if test -z "$want_tools"; then + if test "$softmmu" = "no"; then + want_tools=no + else + want_tools=yes + fi +fi + +########################################## # cocoa implies not SDL or GTK # (the cocoa UI code currently assumes it is always the active UI # and doesn't interact well with other UI frontend code) @@ -4135,6 +4159,11 @@ elif test "$fdt" != "yes" ; then fdt=no fi +# fdt is only required when building softmmu targets +if test -z "$fdt" -a "$softmmu" != "yes" ; then + fdt="no" +fi + if test "$fdt" != "no" ; then fdt_libs="-lfdt" # explicitly check for libfdt_env.h as it is missing in some stable installs @@ -6058,6 +6087,15 @@ EOF fi ########################################## +# checks for fuzzer +if test "$fuzzing" = "yes" ; then + write_c_fuzzer_skeleton + if compile_prog "$CPU_CFLAGS -Werror -fsanitize=address,fuzzer" ""; then + have_fuzzer=yes + fi +fi + +########################################## # check for libpmem if test "$libpmem" != "no"; then @@ -6078,6 +6116,11 @@ fi ########################################## # check for slirp +# slirp is only required when building softmmu targets +if test -z "$slirp" -a "$softmmu" != "yes" ; then + slirp="no" +fi + case "$slirp" in "" | yes) if $pkg_config slirp; then @@ -6646,6 +6689,7 @@ echo "libpmem support $libpmem" echo "libudev $libudev" echo "default devices $default_devices" echo "plugin support $plugins" +echo "fuzzing support $fuzzing" if test "$supported_cpu" = "no"; then echo @@ -7484,6 +7528,16 @@ fi if test "$sheepdog" = "yes" ; then echo "CONFIG_SHEEPDOG=y" >> $config_host_mak fi +if test "$fuzzing" = "yes" ; then + if test "$have_fuzzer" = "yes"; then + FUZZ_LDFLAGS=" -fsanitize=address,fuzzer" + FUZZ_CFLAGS=" -fsanitize=address,fuzzer" + CFLAGS=" -fsanitize=address,fuzzer-no-link" + else + error_exit "Your compiler doesn't support -fsanitize=address,fuzzer" + exit 1 + fi +fi if test "$plugins" = "yes" ; then echo "CONFIG_PLUGIN=y" >> $config_host_mak @@ -7585,6 +7639,11 @@ if test "$libudev" != "no"; then echo "CONFIG_LIBUDEV=y" >> $config_host_mak echo "LIBUDEV_LIBS=$libudev_libs" >> $config_host_mak fi +if test "$fuzzing" != "no"; then + echo "CONFIG_FUZZ=y" >> $config_host_mak + echo "FUZZ_CFLAGS=$FUZZ_CFLAGS" >> $config_host_mak + echo "FUZZ_LDFLAGS=$FUZZ_LDFLAGS" >> $config_host_mak +fi if test "$edk2_blobs" = "yes" ; then echo "DECOMPRESS_EDK2_BLOBS=y" >> $config_host_mak diff --git a/contrib/rdmacm-mux/main.c b/contrib/rdmacm-mux/main.c index de53048f06..bd82abbad3 100644 --- a/contrib/rdmacm-mux/main.c +++ b/contrib/rdmacm-mux/main.c @@ -490,7 +490,7 @@ static int read_and_process(int fd) static int accept_all(void) { - int fd, rc = 0;; + int fd, rc = 0; pthread_rwlock_wrlock(&server.lock); diff --git a/default-configs/ppc64-softmmu.mak b/default-configs/ppc64-softmmu.mak index cca52665d9..ae0841fa3a 100644 --- a/default-configs/ppc64-softmmu.mak +++ b/default-configs/ppc64-softmmu.mak @@ -8,3 +8,4 @@ CONFIG_POWERNV=y # For pSeries CONFIG_PSERIES=y +CONFIG_NVDIMM=y diff --git a/docs/devel/fuzzing.txt b/docs/devel/fuzzing.txt new file mode 100644 index 0000000000..324d2cd92b --- /dev/null +++ b/docs/devel/fuzzing.txt @@ -0,0 +1,116 @@ += Fuzzing = + +== Introduction == + +This document describes the virtual-device fuzzing infrastructure in QEMU and +how to use it to implement additional fuzzers. + +== Basics == + +Fuzzing operates by passing inputs to an entry point/target function. The +fuzzer tracks the code coverage triggered by the input. Based on these +findings, the fuzzer mutates the input and repeats the fuzzing. + +To fuzz QEMU, we rely on libfuzzer. Unlike other fuzzers such as AFL, libfuzzer +is an _in-process_ fuzzer. For the developer, this means that it is their +responsibility to ensure that state is reset between fuzzing-runs. + +== Building the fuzzers == + +NOTE: If possible, build a 32-bit binary. When forking, the 32-bit fuzzer is +much faster, since the page-map has a smaller size. This is due to the fact that +AddressSanitizer mmaps ~20TB of memory, as part of its detection. This results +in a large page-map, and a much slower fork(). + +To build the fuzzers, install a recent version of clang: +Configure with (substitute the clang binaries with the version you installed): + + CC=clang-8 CXX=clang++-8 /path/to/configure --enable-fuzzing + +Fuzz targets are built similarly to system/softmmu: + + make i386-softmmu/fuzz + +This builds ./i386-softmmu/qemu-fuzz-i386 + +The first option to this command is: --fuzz_taget=FUZZ_NAME +To list all of the available fuzzers run qemu-fuzz-i386 with no arguments. + +eg: + ./i386-softmmu/qemu-fuzz-i386 --fuzz-target=virtio-net-fork-fuzz + +Internally, libfuzzer parses all arguments that do not begin with "--". +Information about these is available by passing -help=1 + +Now the only thing left to do is wait for the fuzzer to trigger potential +crashes. + +== Adding a new fuzzer == +Coverage over virtual devices can be improved by adding additional fuzzers. +Fuzzers are kept in tests/qtest/fuzz/ and should be added to +tests/qtest/fuzz/Makefile.include + +Fuzzers can rely on both qtest and libqos to communicate with virtual devices. + +1. Create a new source file. For example ``tests/qtest/fuzz/foo-device-fuzz.c``. + +2. Write the fuzzing code using the libqtest/libqos API. See existing fuzzers +for reference. + +3. Register the fuzzer in ``tests/fuzz/Makefile.include`` by appending the +corresponding object to fuzz-obj-y + +Fuzzers can be more-or-less thought of as special qtest programs which can +modify the qtest commands and/or qtest command arguments based on inputs +provided by libfuzzer. Libfuzzer passes a byte array and length. Commonly the +fuzzer loops over the byte-array interpreting it as a list of qtest commands, +addresses, or values. + += Implementation Details = + +== The Fuzzer's Lifecycle == + +The fuzzer has two entrypoints that libfuzzer calls. libfuzzer provides it's +own main(), which performs some setup, and calls the entrypoints: + +LLVMFuzzerInitialize: called prior to fuzzing. Used to initialize all of the +necessary state + +LLVMFuzzerTestOneInput: called for each fuzzing run. Processes the input and +resets the state at the end of each run. + +In more detail: + +LLVMFuzzerInitialize parses the arguments to the fuzzer (must start with two +dashes, so they are ignored by libfuzzer main()). Currently, the arguments +select the fuzz target. Then, the qtest client is initialized. If the target +requires qos, qgraph is set up and the QOM/LIBQOS modules are initialized. +Then the QGraph is walked and the QEMU cmd_line is determined and saved. + +After this, the vl.c:qemu__main is called to set up the guest. There are +target-specific hooks that can be called before and after qemu_main, for +additional setup(e.g. PCI setup, or VM snapshotting). + +LLVMFuzzerTestOneInput: Uses qtest/qos functions to act based on the fuzz +input. It is also responsible for manually calling the main loop/main_loop_wait +to ensure that bottom halves are executed and any cleanup required before the +next input. + +Since the same process is reused for many fuzzing runs, QEMU state needs to +be reset at the end of each run. There are currently two implemented +options for resetting state: +1. Reboot the guest between runs. + Pros: Straightforward and fast for simple fuzz targets. + Cons: Depending on the device, does not reset all device state. If the + device requires some initialization prior to being ready for fuzzing + (common for QOS-based targets), this initialization needs to be done after + each reboot. + Example target: i440fx-qtest-reboot-fuzz +2. Run each test case in a separate forked process and copy the coverage + information back to the parent. This is fairly similar to AFL's "deferred" + fork-server mode [3] + Pros: Relatively fast. Devices only need to be initialized once. No need + to do slow reboots or vmloads. + Cons: Not officially supported by libfuzzer. Does not work well for devices + that rely on dedicated threads. + Example target: virtio-net-fork-fuzz diff --git a/docs/interop/qcow2.txt b/docs/interop/qcow2.txt index af5711e533..5597e24474 100644 --- a/docs/interop/qcow2.txt +++ b/docs/interop/qcow2.txt @@ -79,9 +79,9 @@ The first cluster of a qcow2 image contains the file header: Offset into the image file at which the snapshot table starts. Must be aligned to a cluster boundary. -If the version is 3 or higher, the header has the following additional fields. -For version 2, the values are assumed to be zero, unless specified otherwise -in the description of a field. +For version 2, the header is exactly 72 bytes in length, and finishes here. +For version 3 or higher, the header length is at least 104 bytes, including +the next fields through header_length. 72 - 79: incompatible_features Bitmask of incompatible features. An implementation must @@ -109,7 +109,12 @@ in the description of a field. An External Data File Name header extension may be present if this bit is set. - Bits 3-63: Reserved (set to 0) + Bit 3: Compression type bit. If this bit is set, + a non-default compression is used for compressed + clusters. The compression_type field must be + present and not zero. + + Bits 4-63: Reserved (set to 0) 80 - 87: compatible_features Bitmask of compatible features. An implementation can @@ -164,6 +169,57 @@ in the description of a field. 100 - 103: header_length Length of the header structure in bytes. For version 2 images, the length is always assumed to be 72 bytes. + For version 3 it's at least 104 bytes and must be a multiple + of 8. + + +=== Additional fields (version 3 and higher) === + +In general, these fields are optional and may be safely ignored by the software, +as well as filled by zeros (which is equal to field absence), if software needs +to set field B, but does not care about field A which precedes B. More +formally, additional fields have the following compatibility rules: + +1. If the value of the additional field must not be ignored for correct +handling of the file, it will be accompanied by a corresponding incompatible +feature bit. + +2. If there are no unrecognized incompatible feature bits set, an unknown +additional field may be safely ignored other than preserving its value when +rewriting the image header. + +3. An explicit value of 0 will have the same behavior as when the field is not +present*, if not altered by a specific incompatible bit. + +*. A field is considered not present when header_length is less than or equal +to the field's offset. Also, all additional fields are not present for +version 2. + + 104: compression_type + + Defines the compression method used for compressed clusters. + All compressed clusters in an image use the same compression + type. + + If the incompatible bit "Compression type" is set: the field + must be present and non-zero (which means non-zlib + compression type). Otherwise, this field must not be present + or must be zero (which means zlib). + + Available compression type values: + 0: zlib <https://www.zlib.net/> + + +=== Header padding === + +@header_length must be a multiple of 8, which means that if the end of the last +additional field is not aligned, some padding is needed. This padding must be +zeroed, so that if some existing (or future) additional field will fall into +the padding, it will be interpreted accordingly to point [3.] of the previous +paragraph, i.e. in the same manner as when this field is not present. + + +=== Header extensions === Directly after the image header, optional sections called header extensions can be stored. Each extension has a structure like the following: diff --git a/docs/interop/qemu-img.rst b/docs/interop/qemu-img.rst index 42e4451db4..5f40137c10 100644 --- a/docs/interop/qemu-img.rst +++ b/docs/interop/qemu-img.rst @@ -214,6 +214,13 @@ Parameters to convert subcommand: will still be printed. Areas that cannot be read from the source will be treated as containing only zeroes. +.. option:: --target-is-zero + + Assume that reading the destination image will always return + zeros. This parameter is mutually exclusive with a destination image + that has a backing file. It is required to also use the ``-n`` + parameter to skip image creation. + Parameters to dd subcommand: .. program:: qemu-img-dd @@ -366,7 +373,7 @@ Command description: 4 Error on reading data -.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME +.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-m NUM_COROUTINES] [-W] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME Convert the disk image *FILENAME* or a snapshot *SNAPSHOT_PARAM* to disk image *OUTPUT_FILENAME* using format *OUTPUT_FMT*. It can @@ -35,6 +35,7 @@ #include "sysemu/kvm.h" #include "sysemu/sysemu.h" #include "sysemu/tcg.h" +#include "sysemu/qtest.h" #include "qemu/timer.h" #include "qemu/config-file.h" #include "qemu/error-report.h" @@ -2253,8 +2254,15 @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) if (new_block->host) { qemu_ram_setup_dump(new_block->host, new_block->max_length); qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE); - /* MADV_DONTFORK is also needed by KVM in absence of synchronous MMU */ - qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_DONTFORK); + /* + * MADV_DONTFORK is also needed by KVM in absence of synchronous MMU + * Configure it unless the machine is a qtest server, in which case + * KVM is not used and it may be forked (eg for fuzzing purposes). + */ + if (!qtest_enabled()) { + qemu_madvise(new_block->host, new_block->max_length, + QEMU_MADV_DONTFORK); + } ram_block_notify_add(new_block->host, new_block->max_length); } } diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index 9fdad6dc3f..5219dd0e2e 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -32,33 +32,7 @@ #include "hw/acpi/bios-linker-loader.h" #include "hw/nvram/fw_cfg.h" #include "hw/mem/nvdimm.h" - -static int nvdimm_device_list(Object *obj, void *opaque) -{ - GSList **list = opaque; - - if (object_dynamic_cast(obj, TYPE_NVDIMM)) { - *list = g_slist_append(*list, DEVICE(obj)); - } - - object_child_foreach(obj, nvdimm_device_list, opaque); - return 0; -} - -/* - * inquire NVDIMM devices and link them into the list which is - * returned to the caller. - * - * Note: it is the caller's responsibility to free the list to avoid - * memory leak. - */ -static GSList *nvdimm_get_device_list(void) -{ - GSList *list = NULL; - - object_child_foreach(qdev_get_machine(), nvdimm_device_list, &list); - return list; -} +#include "qemu/nvdimm-utils.h" #define NVDIMM_UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ { (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index 1cde165611..2ae9c15311 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -24,11 +24,15 @@ #include "hw/arm/allwinner-a10.h" #include "hw/misc/unimp.h" #include "sysemu/sysemu.h" +#include "hw/boards.h" +#include "hw/usb/hcd-ohci.h" #define AW_A10_PIC_REG_BASE 0x01c20400 #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 #define AW_A10_EMAC_BASE 0x01c0b000 +#define AW_A10_EHCI_BASE 0x01c14000 +#define AW_A10_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 static void aw_a10_init(Object *obj) @@ -49,6 +53,17 @@ static void aw_a10_init(Object *obj) sysbus_init_child_obj(obj, "sata", &s->sata, sizeof(s->sata), TYPE_ALLWINNER_AHCI); + + if (machine_usb(current_machine)) { + int i; + + for (i = 0; i < AW_A10_NUM_USB; i++) { + sysbus_init_child_obj(obj, "ehci[*]", OBJECT(&s->ehci[i]), + sizeof(s->ehci[i]), TYPE_PLATFORM_EHCI); + sysbus_init_child_obj(obj, "ohci[*]", OBJECT(&s->ohci[i]), + sizeof(s->ohci[i]), TYPE_SYSBUS_OHCI); + } + } } static void aw_a10_realize(DeviceState *dev, Error **errp) @@ -121,6 +136,34 @@ static void aw_a10_realize(DeviceState *dev, Error **errp) serial_mm_init(get_system_memory(), AW_A10_UART0_REG_BASE, 2, qdev_get_gpio_in(dev, 1), 115200, serial_hd(0), DEVICE_NATIVE_ENDIAN); + + if (machine_usb(current_machine)) { + int i; + + for (i = 0; i < AW_A10_NUM_USB; i++) { + char bus[16]; + + sprintf(bus, "usb-bus.%d", i); + + object_property_set_bool(OBJECT(&s->ehci[i]), true, + "companion-enable", &error_fatal); + object_property_set_bool(OBJECT(&s->ehci[i]), true, "realized", + &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ehci[i]), 0, + AW_A10_EHCI_BASE + i * 0x8000); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->ehci[i]), 0, + qdev_get_gpio_in(dev, 39 + i)); + + object_property_set_str(OBJECT(&s->ohci[i]), bus, "masterbus", + &error_fatal); + object_property_set_bool(OBJECT(&s->ohci[i]), true, "realized", + &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ohci[i]), 0, + AW_A10_OHCI_BASE + i * 0x8000); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->ohci[i]), 0, + qdev_get_gpio_in(dev, 64 + i)); + } + } } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index b01ce3ce08..6e64dfab50 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -138,19 +138,10 @@ static void mainstone_common_init(MemoryRegion *address_space_mem, /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { dinfo = drive_get(IF_PFLASH, 0, i); - if (!dinfo) { - if (qtest_enabled()) { - break; - } - error_report("Two flash images must be given with the " - "'pflash' parameter"); - exit(1); - } - if (!pflash_cfi01_register(mainstone_flash_base[i], i ? "mainstone.flash1" : "mainstone.flash0", MAINSTONE_FLASH, - blk_by_legacy_dinfo(dinfo), + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 4, 0, 0, 0, 0, be)) { error_report("Error registering flash memory"); exit(1); diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index c137ff4def..e7f4ca8bf9 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -349,7 +349,7 @@ static void create_virtio_regions(VersalVirt *s) int i; for (i = 0; i < NUM_VIRTIO_TRANSPORT; i++) { - char *name = g_strdup_printf("virtio%d", i);; + char *name = g_strdup_printf("virtio%d", i); hwaddr base = MM_TOP_RSVD + i * virtio_mmio_size; int irq = VERSAL_RSVD_IRQ_FIRST + i; MemoryRegion *mr; diff --git a/hw/arm/z2.c b/hw/arm/z2.c index 34794fe3ae..4bb237f22d 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -314,12 +314,6 @@ static void z2_init(MachineState *machine) be = 0; #endif dinfo = drive_get(IF_PFLASH, 0, 0); - if (!dinfo && !qtest_enabled()) { - error_report("Flash image must be given with the " - "'pflash' parameter"); - exit(1); - } - if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 4, 0, 0, 0, 0, be)) { diff --git a/hw/block/pflash_cfi02.c b/hw/block/pflash_cfi02.c index 7c4744c020..12f18d401a 100644 --- a/hw/block/pflash_cfi02.c +++ b/hw/block/pflash_cfi02.c @@ -308,7 +308,6 @@ static uint64_t pflash_read(void *opaque, hwaddr offset, unsigned int width) hwaddr boff; uint64_t ret; - ret = -1; /* Lazy reset to ROMD mode after a certain amount of read accesses */ if (!pfl->rom_mode && pfl->wcycle == 0 && ++pfl->read_counter > PFLASH_LAZY_ROMD_THRESHOLD) { diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index 09f46ed85f..142863a3b2 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -1272,7 +1272,7 @@ static Property virtio_blk_properties[] = { DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0, true), DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues, 1), - DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 128), + DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 256), DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true), DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD, IOThread *), diff --git a/hw/core/machine.c b/hw/core/machine.c index c8d361b710..9e8c06036f 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -29,6 +29,8 @@ #include "migration/vmstate.h" GlobalProperty hw_compat_4_2[] = { + { "virtio-blk-device", "queue-size", "128"}, + { "virtio-scsi-device", "virtqueue_size", "128"}, { "virtio-blk-device", "x-enable-wce-if-config-wce", "off" }, { "virtio-blk-device", "seg-max-adjust", "off"}, { "virtio-scsi-device", "seg_max_adjust", "off"}, diff --git a/hw/display/artist.c b/hw/display/artist.c index 65be9e3554..753dbb9a77 100644 --- a/hw/display/artist.c +++ b/hw/display/artist.c @@ -558,21 +558,17 @@ static void draw_line(ARTISTState *s, int x1, int y1, int x2, int y2, bool update_start, int skip_pix, int max_pix) { struct vram_buffer *buf; - uint8_t color = artist_get_color(s); + uint8_t color; int dx, dy, t, e, x, y, incy, diago, horiz; bool c1; uint8_t *p; + trace_artist_draw_line(x1, y1, x2, y2); if (update_start) { s->vram_start = (x2 << 16) | y2; } - buf = &s->vram_buffer[ARTIST_BUFFER_AP]; - - c1 = false; - incy = 1; - if (x2 > x1) { dx = x2 - x1; } else { @@ -583,6 +579,11 @@ static void draw_line(ARTISTState *s, int x1, int y1, int x2, int y2, } else { dy = y1 - y2; } + if (!dx || !dy) { + return; + } + + c1 = false; if (dy > dx) { t = y2; y2 = x2; @@ -620,6 +621,8 @@ static void draw_line(ARTISTState *s, int x1, int y1, int x2, int y2, } x = x1; y = y1; + color = artist_get_color(s); + buf = &s->vram_buffer[ARTIST_BUFFER_AP]; do { if (c1) { @@ -654,7 +657,6 @@ static void draw_line_pattern_start(ARTISTState *s) int endy = artist_get_y(s->blockmove_size); int pstart = s->line_pattern_start >> 16; - trace_artist_draw_line(startx, starty, endx, endy); draw_line(s, startx, starty, endx, endy, false, -1, pstart); s->line_pattern_skip = pstart; } @@ -668,7 +670,6 @@ static void draw_line_pattern_next(ARTISTState *s) int endy = artist_get_y(s->blockmove_size); int line_xy = s->line_xy >> 16; - trace_artist_draw_line(startx, starty, endx, endy); draw_line(s, startx, starty, endx, endy, false, s->line_pattern_skip, s->line_pattern_skip + line_xy); s->line_pattern_skip += line_xy; @@ -683,7 +684,6 @@ static void draw_line_size(ARTISTState *s, bool update_start) int endx = artist_get_x(s->line_size); int endy = artist_get_y(s->line_size); - trace_artist_draw_line(startx, starty, endx, endy); draw_line(s, startx, starty, endx, endy, update_start, -1, -1); } @@ -734,16 +734,6 @@ static void draw_line_xy(ARTISTState *s, bool update_start) endy = 0; } - - if (endx < 0) { - return; - } - - if (endy < 0) { - return; - } - - trace_artist_draw_line(startx, starty, endx, endy); draw_line(s, startx, starty, endx, endy, false, -1, -1); } @@ -755,7 +745,6 @@ static void draw_line_end(ARTISTState *s, bool update_start) int endx = artist_get_x(s->line_end); int endy = artist_get_y(s->line_end); - trace_artist_draw_line(startx, starty, endx, endy); draw_line(s, startx, starty, endx, endy, update_start, -1, -1); } diff --git a/hw/display/qxl.c b/hw/display/qxl.c index 64884da708..21a43a1d5e 100644 --- a/hw/display/qxl.c +++ b/hw/display/qxl.c @@ -1631,7 +1631,7 @@ static void ioport_write(void *opaque, hwaddr addr, PCIQXLDevice *d = opaque; uint32_t io_port = addr; qxl_async_io async = QXL_SYNC; - uint32_t orig_io_port = io_port; + uint32_t orig_io_port; if (d->guest_bug && io_port != QXL_IO_RESET) { return; diff --git a/hw/hppa/dino.c b/hw/hppa/dino.c index 9797a7f0d9..2b1b38c58a 100644 --- a/hw/hppa/dino.c +++ b/hw/hppa/dino.c @@ -83,20 +83,21 @@ #define DINO_PCI_HOST_BRIDGE(obj) \ OBJECT_CHECK(DinoState, (obj), TYPE_DINO_PCI_HOST_BRIDGE) -#define DINO800_REGS ((DINO_TLTIM - DINO_GMASK) / 4) +#define DINO800_REGS (1 + (DINO_TLTIM - DINO_GMASK) / 4) static const uint32_t reg800_keep_bits[DINO800_REGS] = { - MAKE_64BIT_MASK(0, 1), - MAKE_64BIT_MASK(0, 7), - MAKE_64BIT_MASK(0, 7), - MAKE_64BIT_MASK(0, 8), - MAKE_64BIT_MASK(0, 7), - MAKE_64BIT_MASK(0, 9), - MAKE_64BIT_MASK(0, 32), - MAKE_64BIT_MASK(0, 8), - MAKE_64BIT_MASK(0, 30), - MAKE_64BIT_MASK(0, 25), - MAKE_64BIT_MASK(0, 22), - MAKE_64BIT_MASK(0, 9), + MAKE_64BIT_MASK(0, 1), /* GMASK */ + MAKE_64BIT_MASK(0, 7), /* PAMR */ + MAKE_64BIT_MASK(0, 7), /* PAPR */ + MAKE_64BIT_MASK(0, 8), /* DAMODE */ + MAKE_64BIT_MASK(0, 7), /* PCICMD */ + MAKE_64BIT_MASK(0, 9), /* PCISTS */ + MAKE_64BIT_MASK(0, 32), /* Undefined */ + MAKE_64BIT_MASK(0, 8), /* MLTIM */ + MAKE_64BIT_MASK(0, 30), /* BRDG_FEAT */ + MAKE_64BIT_MASK(0, 24), /* PCIROR */ + MAKE_64BIT_MASK(0, 22), /* PCIWOR */ + MAKE_64BIT_MASK(0, 32), /* Undocumented */ + MAKE_64BIT_MASK(0, 9), /* TLTIM */ }; typedef struct DinoState { @@ -180,7 +181,9 @@ static bool dino_chip_mem_valid(void *opaque, hwaddr addr, case DINO_IO_ADDR_EN: case DINO_PCI_IO_DATA: case DINO_TOC_ADDR: - case DINO_GMASK ... DINO_TLTIM: + case DINO_GMASK ... DINO_PCISTS: + case DINO_MLTIM ... DINO_PCIWOR: + case DINO_TLTIM: ret = true; break; case DINO_PCI_IO_DATA + 2: diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index f9e0eeaace..22a43e4984 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -1227,17 +1227,17 @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) case 0xd44: /* PFR1. */ return cpu->id_pfr1; case 0xd48: /* DFR0. */ - return cpu->id_dfr0; + return cpu->isar.id_dfr0; case 0xd4c: /* AFR0. */ return cpu->id_afr0; case 0xd50: /* MMFR0. */ - return cpu->id_mmfr0; + return cpu->isar.id_mmfr0; case 0xd54: /* MMFR1. */ - return cpu->id_mmfr1; + return cpu->isar.id_mmfr1; case 0xd58: /* MMFR2. */ - return cpu->id_mmfr2; + return cpu->isar.id_mmfr2; case 0xd5c: /* MMFR3. */ - return cpu->id_mmfr3; + return cpu->isar.id_mmfr3; case 0xd60: /* ISAR0. */ return cpu->isar.id_isar0; case 0xd64: /* ISAR1. */ diff --git a/hw/m68k/next-cube.c b/hw/m68k/next-cube.c index cd93d9e367..14b99ed25d 100644 --- a/hw/m68k/next-cube.c +++ b/hw/m68k/next-cube.c @@ -734,7 +734,7 @@ void next_irq(void *opaque, int number, int level) switch (number) { /* level 3 - floppy, kbd/mouse, power, ether rx/tx, scsi, clock */ case NEXT_FD_I: - shift = 7;; + shift = 7; break; case NEXT_KBD_I: shift = 3; diff --git a/hw/mem/Kconfig b/hw/mem/Kconfig index 620fd4cb59..2ad052a536 100644 --- a/hw/mem/Kconfig +++ b/hw/mem/Kconfig @@ -8,4 +8,4 @@ config MEM_DEVICE config NVDIMM bool default y - depends on PC + depends on (PC || PSERIES) diff --git a/hw/mem/nvdimm.c b/hw/mem/nvdimm.c index 39f1426d1f..8e426d24bb 100644 --- a/hw/mem/nvdimm.c +++ b/hw/mem/nvdimm.c @@ -69,11 +69,51 @@ out: error_propagate(errp, local_err); } +static void nvdimm_get_uuid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + NVDIMMDevice *nvdimm = NVDIMM(obj); + char *value = NULL; + + value = qemu_uuid_unparse_strdup(&nvdimm->uuid); + + visit_type_str(v, name, &value, errp); + g_free(value); +} + + +static void nvdimm_set_uuid(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + NVDIMMDevice *nvdimm = NVDIMM(obj); + Error *local_err = NULL; + char *value; + + visit_type_str(v, name, &value, &local_err); + if (local_err) { + goto out; + } + + if (qemu_uuid_parse(value, &nvdimm->uuid) != 0) { + error_setg(errp, "Property '%s.%s' has invalid value", + object_get_typename(obj), name); + goto out; + } + g_free(value); + +out: + error_propagate(errp, local_err); +} + + static void nvdimm_init(Object *obj) { object_property_add(obj, NVDIMM_LABEL_SIZE_PROP, "int", nvdimm_get_label_size, nvdimm_set_label_size, NULL, NULL, NULL); + + object_property_add(obj, NVDIMM_UUID_PROP, "QemuUUID", nvdimm_get_uuid, + nvdimm_set_uuid, NULL, NULL, NULL); } static void nvdimm_finalize(Object *obj) diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c index ce2f9562d4..9d7482a9df 100644 --- a/hw/misc/aspeed_scu.c +++ b/hw/misc/aspeed_scu.c @@ -77,6 +77,8 @@ #define CPU2_BASE_SEG4 TO_REG(0x110) #define CPU2_BASE_SEG5 TO_REG(0x114) #define CPU2_CACHE_CTRL TO_REG(0x118) +#define CHIP_ID0 TO_REG(0x150) +#define CHIP_ID1 TO_REG(0x154) #define UART_HPLL_CLK TO_REG(0x160) #define PCIE_CTRL TO_REG(0x180) #define BMC_MMIO_CTRL TO_REG(0x184) @@ -115,6 +117,8 @@ #define AST2600_HW_STRAP2_PROT TO_REG(0x518) #define AST2600_RNG_CTRL TO_REG(0x524) #define AST2600_RNG_DATA TO_REG(0x540) +#define AST2600_CHIP_ID0 TO_REG(0x5B0) +#define AST2600_CHIP_ID1 TO_REG(0x5B4) #define AST2600_CLK TO_REG(0x40) @@ -182,6 +186,8 @@ static const uint32_t ast2500_a1_resets[ASPEED_SCU_NR_REGS] = { [CPU2_BASE_SEG1] = 0x80000000U, [CPU2_BASE_SEG4] = 0x1E600000U, [CPU2_BASE_SEG5] = 0xC0000000U, + [CHIP_ID0] = 0x1234ABCDU, + [CHIP_ID1] = 0x88884444U, [UART_HPLL_CLK] = 0x00001903U, [PCIE_CTRL] = 0x0000007BU, [BMC_DEV_ID] = 0x00002402U @@ -232,8 +238,47 @@ static uint64_t aspeed_scu_read(void *opaque, hwaddr offset, unsigned size) return s->regs[reg]; } -static void aspeed_scu_write(void *opaque, hwaddr offset, uint64_t data, - unsigned size) +static void aspeed_ast2400_scu_write(void *opaque, hwaddr offset, + uint64_t data, unsigned size) +{ + AspeedSCUState *s = ASPEED_SCU(opaque); + int reg = TO_REG(offset); + + if (reg >= ASPEED_SCU_NR_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Out-of-bounds write at offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + return; + } + + if (reg > PROT_KEY && reg < CPU2_BASE_SEG1 && + !s->regs[PROT_KEY]) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: SCU is locked!\n", __func__); + } + + trace_aspeed_scu_write(offset, size, data); + + switch (reg) { + case PROT_KEY: + s->regs[reg] = (data == ASPEED_SCU_PROT_KEY) ? 1 : 0; + return; + case SILICON_REV: + case FREQ_CNTR_EVAL: + case VGA_SCRATCH1 ... VGA_SCRATCH8: + case RNG_DATA: + case FREE_CNTR4: + case FREE_CNTR4_EXT: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Write to read-only offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + return; + } + + s->regs[reg] = data; +} + +static void aspeed_ast2500_scu_write(void *opaque, hwaddr offset, + uint64_t data, unsigned size) { AspeedSCUState *s = ASPEED_SCU(opaque); int reg = TO_REG(offset); @@ -257,31 +302,19 @@ static void aspeed_scu_write(void *opaque, hwaddr offset, uint64_t data, case PROT_KEY: s->regs[reg] = (data == ASPEED_SCU_PROT_KEY) ? 1 : 0; return; - case CLK_SEL: - s->regs[reg] = data; - break; case HW_STRAP1: - if (ASPEED_IS_AST2500(s->regs[SILICON_REV])) { - s->regs[HW_STRAP1] |= data; - return; - } - /* Jump to assignment below */ - break; + s->regs[HW_STRAP1] |= data; + return; case SILICON_REV: - if (ASPEED_IS_AST2500(s->regs[SILICON_REV])) { - s->regs[HW_STRAP1] &= ~data; - } else { - qemu_log_mask(LOG_GUEST_ERROR, - "%s: Write to read-only offset 0x%" HWADDR_PRIx "\n", - __func__, offset); - } - /* Avoid assignment below, we've handled everything */ + s->regs[HW_STRAP1] &= ~data; return; case FREQ_CNTR_EVAL: case VGA_SCRATCH1 ... VGA_SCRATCH8: case RNG_DATA: case FREE_CNTR4: case FREE_CNTR4_EXT: + case CHIP_ID0: + case CHIP_ID1: qemu_log_mask(LOG_GUEST_ERROR, "%s: Write to read-only offset 0x%" HWADDR_PRIx "\n", __func__, offset); @@ -291,9 +324,18 @@ static void aspeed_scu_write(void *opaque, hwaddr offset, uint64_t data, s->regs[reg] = data; } -static const MemoryRegionOps aspeed_scu_ops = { +static const MemoryRegionOps aspeed_ast2400_scu_ops = { + .read = aspeed_scu_read, + .write = aspeed_ast2400_scu_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, + .valid.unaligned = false, +}; + +static const MemoryRegionOps aspeed_ast2500_scu_ops = { .read = aspeed_scu_read, - .write = aspeed_scu_write, + .write = aspeed_ast2500_scu_write, .endianness = DEVICE_LITTLE_ENDIAN, .valid.min_access_size = 4, .valid.max_access_size = 4, @@ -469,7 +511,7 @@ static void aspeed_2400_scu_class_init(ObjectClass *klass, void *data) asc->calc_hpll = aspeed_2400_scu_calc_hpll; asc->apb_divider = 2; asc->nr_regs = ASPEED_SCU_NR_REGS; - asc->ops = &aspeed_scu_ops; + asc->ops = &aspeed_ast2400_scu_ops; } static const TypeInfo aspeed_2400_scu_info = { @@ -489,7 +531,7 @@ static void aspeed_2500_scu_class_init(ObjectClass *klass, void *data) asc->calc_hpll = aspeed_2500_scu_calc_hpll; asc->apb_divider = 4; asc->nr_regs = ASPEED_SCU_NR_REGS; - asc->ops = &aspeed_scu_ops; + asc->ops = &aspeed_ast2500_scu_ops; } static const TypeInfo aspeed_2500_scu_info = { @@ -586,6 +628,8 @@ static void aspeed_ast2600_scu_write(void *opaque, hwaddr offset, case AST2600_RNG_DATA: case AST2600_SILICON_REV: case AST2600_SILICON_REV2: + case AST2600_CHIP_ID0: + case AST2600_CHIP_ID1: /* Add read only registers here */ qemu_log_mask(LOG_GUEST_ERROR, "%s: Write to read-only offset 0x%" HWADDR_PRIx "\n", @@ -614,6 +658,9 @@ static const uint32_t ast2600_a0_resets[ASPEED_AST2600_SCU_NR_REGS] = { [AST2600_CLK_STOP_CTRL2] = 0xFFF0FFF0, [AST2600_SDRAM_HANDSHAKE] = 0x00000040, /* SoC completed DRAM init */ [AST2600_HPLL_PARAM] = 0x1000405F, + [AST2600_CHIP_ID0] = 0x1234ABCD, + [AST2600_CHIP_ID1] = 0x88884444, + }; static void aspeed_ast2600_scu_reset(DeviceState *dev) diff --git a/hw/misc/iotkit-secctl.c b/hw/misc/iotkit-secctl.c index 609869821a..9fdb82056a 100644 --- a/hw/misc/iotkit-secctl.c +++ b/hw/misc/iotkit-secctl.c @@ -340,7 +340,7 @@ static MemTxResult iotkit_secctl_s_write(void *opaque, hwaddr addr, qemu_set_irq(s->sec_resp_cfg, s->secrespcfg); break; case A_SECPPCINTCLR: - value &= 0x00f000f3; + s->secppcintstat &= ~(value & 0x00f000f3); foreach_ppc(s, iotkit_secctl_ppc_update_irq_clear); break; case A_SECPPCINTEN: diff --git a/hw/net/rocker/rocker.c b/hw/net/rocker/rocker.c index 81dd3b5f14..15d66f6cbc 100644 --- a/hw/net/rocker/rocker.c +++ b/hw/net/rocker/rocker.c @@ -27,6 +27,7 @@ #include "qemu/iov.h" #include "qemu/module.h" #include "qemu/bitops.h" +#include "qemu/log.h" #include "rocker.h" #include "rocker_hw.h" @@ -207,14 +208,22 @@ static int tx_consume(Rocker *r, DescInfo *info) if (tlvs[ROCKER_TLV_TX_L3_CSUM_OFF]) { tx_l3_csum_off = rocker_tlv_get_le16(tlvs[ROCKER_TLV_TX_L3_CSUM_OFF]); + qemu_log_mask(LOG_UNIMP, "rocker %s: L3 not implemented" + " (cksum off: %u)\n", + __func__, tx_l3_csum_off); } if (tlvs[ROCKER_TLV_TX_TSO_MSS]) { tx_tso_mss = rocker_tlv_get_le16(tlvs[ROCKER_TLV_TX_TSO_MSS]); + qemu_log_mask(LOG_UNIMP, "rocker %s: TSO not implemented (MSS: %u)\n", + __func__, tx_tso_mss); } if (tlvs[ROCKER_TLV_TX_TSO_HDR_LEN]) { tx_tso_hdr_len = rocker_tlv_get_le16(tlvs[ROCKER_TLV_TX_TSO_HDR_LEN]); + qemu_log_mask(LOG_UNIMP, "rocker %s: TSO not implemented" + " (hdr length: %u)\n", + __func__, tx_tso_hdr_len); } rocker_tlv_for_each_nested(tlv_frag, tlvs[ROCKER_TLV_TX_FRAGS], rem) { @@ -249,12 +258,6 @@ static int tx_consume(Rocker *r, DescInfo *info) iovcnt++; } - if (iovcnt) { - /* XXX perform Tx offloads */ - /* XXX silence compiler for now */ - tx_l3_csum_off += tx_tso_mss = tx_tso_hdr_len = 0; - } - err = fp_port_eg(r->fp_port[port], iov, iovcnt); err_too_many_frags: diff --git a/hw/nios2/boot.c b/hw/nios2/boot.c index 46b8349876..88224aa84c 100644 --- a/hw/nios2/boot.c +++ b/hw/nios2/boot.c @@ -109,6 +109,7 @@ static int nios2_load_dtb(struct nios2_boot_info bi, const uint32_t ramsize, } cpu_physical_memory_write(bi.fdt, fdt, fdt_size); + g_free(fdt); return fdt_size; } diff --git a/hw/pci-host/pnv_phb3_msi.c b/hw/pci-host/pnv_phb3_msi.c index ecfc1b2c4e..d645468f4a 100644 --- a/hw/pci-host/pnv_phb3_msi.c +++ b/hw/pci-host/pnv_phb3_msi.c @@ -220,7 +220,7 @@ static void phb3_msi_resend(ICSState *ics) if ((msi->rba[i] & (1ull << j)) == 0) { continue; } - msi->rba[i] &= ~(1u << j); + msi->rba[i] &= ~(1ull << j); phb3_msi_try_send(msi, i * 64 + j, true); } } diff --git a/hw/pci-host/pnv_phb3_pbcq.c b/hw/pci-host/pnv_phb3_pbcq.c index f232228b0e..7b9a121246 100644 --- a/hw/pci-host/pnv_phb3_pbcq.c +++ b/hw/pci-host/pnv_phb3_pbcq.c @@ -173,6 +173,7 @@ static void pnv_pbcq_pci_xscom_write(void *opaque, hwaddr addr, case PBCQ_PCI_BAR2: pbcq->pci_regs[reg] = val & 0xfffffffffc000000ull; pnv_pbcq_update_map(pbcq); + break; default: phb3_pbcq_error(pbcq, "%s @0x%"HWADDR_PRIx"=%"PRIx64, __func__, addr, val); diff --git a/hw/pci-host/pnv_phb4_pec.c b/hw/pci-host/pnv_phb4_pec.c index 68e1db3eac..911d147ffd 100644 --- a/hw/pci-host/pnv_phb4_pec.c +++ b/hw/pci-host/pnv_phb4_pec.c @@ -391,7 +391,7 @@ static void pnv_pec_realize(DeviceState *dev, Error **errp) object_property_set_int(stk_obj, i, "stack-no", &error_abort); object_property_set_link(stk_obj, OBJECT(pec), "pec", &error_abort); - object_property_set_bool(stk_obj, true, "realized", errp); + object_property_set_bool(stk_obj, true, "realized", &local_err); if (local_err) { error_propagate(errp, local_err); return; diff --git a/hw/ppc/Kconfig b/hw/ppc/Kconfig index 354828bf13..dd86e664d2 100644 --- a/hw/ppc/Kconfig +++ b/hw/ppc/Kconfig @@ -29,6 +29,8 @@ config POWERNV select XICS select XIVE select FDT_PPC + select PCI_EXPRESS + select MSI_NONBROKEN config PPC405 bool @@ -135,8 +137,6 @@ config XIVE_SPAPR default y depends on PSERIES select XIVE - select PCI - select PCIE_PORT config XIVE_KVM bool diff --git a/hw/ppc/Makefile.objs b/hw/ppc/Makefile.objs index a4bac57be6..c3d3cc56eb 100644 --- a/hw/ppc/Makefile.objs +++ b/hw/ppc/Makefile.objs @@ -7,7 +7,7 @@ obj-$(CONFIG_PSERIES) += spapr.o spapr_caps.o spapr_vio.o spapr_events.o obj-$(CONFIG_PSERIES) += spapr_hcall.o spapr_iommu.o spapr_rtas.o obj-$(CONFIG_PSERIES) += spapr_pci.o spapr_rtc.o spapr_drc.o obj-$(CONFIG_PSERIES) += spapr_cpu_core.o spapr_ovec.o spapr_irq.o -obj-$(CONFIG_PSERIES) += spapr_tpm_proxy.o +obj-$(CONFIG_PSERIES) += spapr_tpm_proxy.o spapr_nvdimm.o obj-$(CONFIG_SPAPR_RNG) += spapr_rng.o obj-$(call land,$(CONFIG_PSERIES),$(CONFIG_LINUX)) += spapr_pci_vfio.o spapr_pci_nvlink2.o # IBM PowerNV diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index d5dfe9fb84..854cd3ac46 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -594,6 +594,7 @@ done: cpu_physical_memory_write(addr, fdt, fdt_size); } ret = fdt_size; + g_free(fdt); out: g_free(pci_map); diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index ea20a1dc3e..b75ad06390 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -582,6 +582,8 @@ static void pnv_reset(MachineState *machine) qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt)); cpu_physical_memory_write(PNV_FDT_ADDR, fdt, fdt_totalsize(fdt)); + + g_free(fdt); } static ISABus *pnv_chip_power8_isa_create(PnvChip *chip, Error **errp) diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 4d90f99195..c03ce6afb9 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -80,6 +80,7 @@ #include "hw/ppc/spapr_cpu_core.h" #include "hw/mem/memory-device.h" #include "hw/ppc/spapr_tpm_proxy.h" +#include "hw/ppc/spapr_nvdimm.h" #include "monitor/monitor.h" @@ -675,6 +676,14 @@ static int spapr_populate_drmem_v2(SpaprMachineState *spapr, void *fdt, size = di->size; node = di->node; + /* + * The NVDIMM area is hotpluggable after the NVDIMM is unplugged. The + * area is marked hotpluggable in the next iteration for the bigger + * chunk including the NVDIMM occupied area. + */ + if (info->value->type == MEMORY_DEVICE_INFO_KIND_NVDIMM) + continue; + /* Entry for hot-pluggable area */ if (cur_addr < addr) { drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, cur_addr / lmb_size); @@ -1055,7 +1064,7 @@ static void spapr_dt_chosen(SpaprMachineState *spapr, void *fdt) } if (spapr->kernel_size) { - uint64_t kprop[2] = { cpu_to_be64(KERNEL_LOAD_ADDR), + uint64_t kprop[2] = { cpu_to_be64(spapr->kernel_addr), cpu_to_be64(spapr->kernel_size) }; _FDT(fdt_setprop(fdt, chosen, "qemu,boot-kernel", @@ -1243,7 +1252,8 @@ void *spapr_build_fdt(SpaprMachineState *spapr, bool reset, size_t space) /* Build memory reserve map */ if (reset) { if (spapr->kernel_size) { - _FDT((fdt_add_mem_rsv(fdt, KERNEL_LOAD_ADDR, spapr->kernel_size))); + _FDT((fdt_add_mem_rsv(fdt, spapr->kernel_addr, + spapr->kernel_size))); } if (spapr->initrd_size) { _FDT((fdt_add_mem_rsv(fdt, spapr->initrd_base, @@ -1266,12 +1276,19 @@ void *spapr_build_fdt(SpaprMachineState *spapr, bool reset, size_t space) } } + /* NVDIMM devices */ + if (mc->nvdimm_supported) { + spapr_dt_persistent_memory(fdt); + } + return fdt; } static uint64_t translate_kernel_address(void *opaque, uint64_t addr) { - return (addr & 0x0fffffff) + KERNEL_LOAD_ADDR; + SpaprMachineState *spapr = opaque; + + return (addr & 0x0fffffff) + spapr->kernel_addr; } static void emulate_spapr_hypercall(PPCVirtualHypervisor *vhyp, @@ -2629,6 +2646,7 @@ static void spapr_machine_init(MachineState *machine) { SpaprMachineState *spapr = SPAPR_MACHINE(machine); SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine); + MachineClass *mc = MACHINE_GET_CLASS(machine); const char *kernel_filename = machine->kernel_filename; const char *initrd_filename = machine->initrd_filename; PCIHostState *phb; @@ -2858,6 +2876,10 @@ static void spapr_machine_init(MachineState *machine) "may run and log hardware error on the destination"); } + if (mc->nvdimm_supported) { + spapr_create_nvdimm_dr_connectors(spapr); + } + /* Set up RTAS event infrastructure */ spapr_events_init(spapr); @@ -2945,14 +2967,15 @@ static void spapr_machine_init(MachineState *machine) uint64_t lowaddr = 0; spapr->kernel_size = load_elf(kernel_filename, NULL, - translate_kernel_address, NULL, + translate_kernel_address, spapr, NULL, &lowaddr, NULL, NULL, 1, PPC_ELF_MACHINE, 0, 0); if (spapr->kernel_size == ELF_LOAD_WRONG_ENDIAN) { spapr->kernel_size = load_elf(kernel_filename, NULL, - translate_kernel_address, NULL, NULL, + translate_kernel_address, spapr, NULL, &lowaddr, NULL, NULL, 0, - PPC_ELF_MACHINE, 0, 0); + PPC_ELF_MACHINE, + 0, 0); spapr->kernel_le = spapr->kernel_size > 0; } if (spapr->kernel_size < 0) { @@ -2966,7 +2989,7 @@ static void spapr_machine_init(MachineState *machine) /* Try to locate the initrd in the gap between the kernel * and the firmware. Add a bit of space just in case */ - spapr->initrd_base = (KERNEL_LOAD_ADDR + spapr->kernel_size + spapr->initrd_base = (spapr->kernel_addr + spapr->kernel_size + 0x1ffff) & ~0xffff; spapr->initrd_size = load_image_targphys(initrd_filename, spapr->initrd_base, @@ -3212,6 +3235,18 @@ static void spapr_set_vsmt(Object *obj, Visitor *v, const char *name, visit_type_uint32(v, name, (uint32_t *)opaque, errp); } +static void spapr_get_kernel_addr(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint64(v, name, (uint64_t *)opaque, errp); +} + +static void spapr_set_kernel_addr(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint64(v, name, (uint64_t *)opaque, errp); +} + static char *spapr_get_ic_mode(Object *obj, Error **errp) { SpaprMachineState *spapr = SPAPR_MACHINE(obj); @@ -3317,6 +3352,14 @@ static void spapr_instance_init(Object *obj) object_property_add_bool(obj, "vfio-no-msix-emulation", spapr_get_msix_emulation, NULL, NULL); + object_property_add(obj, "kernel-addr", "uint64", spapr_get_kernel_addr, + spapr_set_kernel_addr, NULL, &spapr->kernel_addr, + &error_abort); + object_property_set_description(obj, "kernel-addr", + stringify(KERNEL_LOAD_ADDR) + " for -kernel is the default", + NULL); + spapr->kernel_addr = KERNEL_LOAD_ADDR; /* The machine class defines the default interrupt controller mode */ spapr->irq = smc->irq; object_property_add_str(obj, "ic-mode", spapr_get_ic_mode, @@ -3427,7 +3470,8 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error *local_err = NULL; SpaprMachineState *ms = SPAPR_MACHINE(hotplug_dev); PCDIMMDevice *dimm = PC_DIMM(dev); - uint64_t size, addr; + uint64_t size, addr, slot; + bool is_nvdimm = object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM); size = memory_device_get_region_size(MEMORY_DEVICE(dev), &error_abort); @@ -3436,14 +3480,24 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev, goto out; } - addr = object_property_get_uint(OBJECT(dimm), - PC_DIMM_ADDR_PROP, &local_err); - if (local_err) { - goto out_unplug; + if (!is_nvdimm) { + addr = object_property_get_uint(OBJECT(dimm), + PC_DIMM_ADDR_PROP, &local_err); + if (local_err) { + goto out_unplug; + } + spapr_add_lmbs(dev, addr, size, + spapr_ovec_test(ms->ov5_cas, OV5_HP_EVT), + &local_err); + } else { + slot = object_property_get_uint(OBJECT(dimm), + PC_DIMM_SLOT_PROP, &local_err); + if (local_err) { + goto out_unplug; + } + spapr_add_nvdimm(dev, slot, &local_err); } - spapr_add_lmbs(dev, addr, size, spapr_ovec_test(ms->ov5_cas, OV5_HP_EVT), - &local_err); if (local_err) { goto out_unplug; } @@ -3461,6 +3515,8 @@ static void spapr_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, { const SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(hotplug_dev); SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_dev); + const MachineClass *mc = MACHINE_CLASS(smc); + bool is_nvdimm = object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM); PCDIMMDevice *dimm = PC_DIMM(dev); Error *local_err = NULL; uint64_t size; @@ -3472,16 +3528,27 @@ static void spapr_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, return; } + if (is_nvdimm && !mc->nvdimm_supported) { + error_setg(errp, "NVDIMM hotplug not supported for this machine"); + return; + } + size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &local_err); if (local_err) { error_propagate(errp, local_err); return; } - if (size % SPAPR_MEMORY_BLOCK_SIZE) { + if (!is_nvdimm && size % SPAPR_MEMORY_BLOCK_SIZE) { error_setg(errp, "Hotplugged memory size must be a multiple of " - "%" PRIu64 " MB", SPAPR_MEMORY_BLOCK_SIZE / MiB); + "%" PRIu64 " MB", SPAPR_MEMORY_BLOCK_SIZE / MiB); return; + } else if (is_nvdimm) { + spapr_nvdimm_validate_opts(NVDIMM(dev), size, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } } memdev = object_property_get_link(OBJECT(dimm), PC_DIMM_MEMDEV_PROP, @@ -3621,6 +3688,12 @@ static void spapr_memory_unplug_request(HotplugHandler *hotplug_dev, int i; SpaprDrc *drc; + if (object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)) { + error_setg(&local_err, + "nvdimm device hot unplug is not supported yet."); + goto out; + } + size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &error_abort); nr_lmbs = size / SPAPR_MEMORY_BLOCK_SIZE; @@ -4416,6 +4489,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->update_dt_enabled = true; mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power9_v2.0"); mc->has_hotpluggable_cpus = true; + mc->nvdimm_supported = true; smc->resize_hpt_default = SPAPR_RESIZE_HPT_ENABLED; fwc->get_dev_path = spapr_get_fw_dev_path; nc->nmi_monitor_handler = spapr_nmi; @@ -4483,6 +4557,12 @@ static const TypeInfo spapr_machine_info = { }, }; +static void spapr_machine_latest_class_options(MachineClass *mc) +{ + mc->alias = "pseries"; + mc->is_default = 1; +} + #define DEFINE_SPAPR_MACHINE(suffix, verstr, latest) \ static void spapr_machine_##suffix##_class_init(ObjectClass *oc, \ void *data) \ @@ -4490,8 +4570,7 @@ static const TypeInfo spapr_machine_info = { MachineClass *mc = MACHINE_CLASS(oc); \ spapr_machine_##suffix##_class_options(mc); \ if (latest) { \ - mc->alias = "pseries"; \ - mc->is_default = 1; \ + spapr_machine_latest_class_options(mc); \ } \ } \ static const TypeInfo spapr_machine_##suffix##_info = { \ @@ -4526,6 +4605,7 @@ static void spapr_machine_4_2_class_options(MachineClass *mc) compat_props_add(mc->compat_props, hw_compat_4_2, hw_compat_4_2_len); smc->default_caps.caps[SPAPR_CAP_CCF_ASSIST] = SPAPR_CAP_OFF; smc->default_caps.caps[SPAPR_CAP_FWNMI_MCE] = SPAPR_CAP_OFF; + mc->nvdimm_supported = false; } DEFINE_SPAPR_MACHINE(4_2, "4.2", false); diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index 17aeac3801..e373d342eb 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -22,6 +22,7 @@ #include "qemu/error-report.h" #include "hw/ppc/spapr.h" /* for RTAS return codes */ #include "hw/pci-host/spapr.h" /* spapr_phb_remove_pci_device_cb callback */ +#include "hw/ppc/spapr_nvdimm.h" #include "sysemu/device_tree.h" #include "sysemu/reset.h" #include "trace.h" @@ -455,21 +456,46 @@ void spapr_drc_reset(SpaprDrc *drc) } } -bool spapr_drc_needed(void *opaque) +static bool spapr_drc_unplug_requested_needed(void *opaque) +{ + return spapr_drc_unplug_requested(opaque); +} + +static const VMStateDescription vmstate_spapr_drc_unplug_requested = { + .name = "spapr_drc/unplug_requested", + .version_id = 1, + .minimum_version_id = 1, + .needed = spapr_drc_unplug_requested_needed, + .fields = (VMStateField []) { + VMSTATE_BOOL(unplug_requested, SpaprDrc), + VMSTATE_END_OF_LIST() + } +}; + +bool spapr_drc_transient(SpaprDrc *drc) { - SpaprDrc *drc = (SpaprDrc *)opaque; SpaprDrcClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - /* If no dev is plugged in there is no need to migrate the DRC state */ + /* + * If no dev is plugged in there is no need to migrate the DRC state + * nor to reset the DRC at CAS. + */ if (!drc->dev) { return false; } /* - * We need to migrate the state if it's not equal to the expected - * long-term state, which is the same as the coldplugged initial - * state */ - return (drc->state != drck->ready_state); + * We need to reset the DRC at CAS or to migrate the DRC state if it's + * not equal to the expected long-term state, which is the same as the + * coldplugged initial state, or if an unplug request is pending. + */ + return drc->state != drck->ready_state || + spapr_drc_unplug_requested(drc); +} + +static bool spapr_drc_needed(void *opaque) +{ + return spapr_drc_transient(opaque); } static const VMStateDescription vmstate_spapr_drc = { @@ -480,6 +506,10 @@ static const VMStateDescription vmstate_spapr_drc = { .fields = (VMStateField []) { VMSTATE_UINT32(state, SpaprDrc), VMSTATE_END_OF_LIST() + }, + .subsections = (const VMStateDescription * []) { + &vmstate_spapr_drc_unplug_requested, + NULL } }; @@ -709,6 +739,17 @@ static void spapr_drc_phb_class_init(ObjectClass *k, void *data) drck->dt_populate = spapr_phb_dt_populate; } +static void spapr_drc_pmem_class_init(ObjectClass *k, void *data) +{ + SpaprDrcClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PMEM; + drck->typename = "PMEM"; + drck->drc_name_prefix = "PMEM "; + drck->release = NULL; + drck->dt_populate = spapr_pmem_dt_populate; +} + static const TypeInfo spapr_dr_connector_info = { .name = TYPE_SPAPR_DR_CONNECTOR, .parent = TYPE_DEVICE, @@ -759,6 +800,12 @@ static const TypeInfo spapr_drc_phb_info = { .class_init = spapr_drc_phb_class_init, }; +static const TypeInfo spapr_drc_pmem_info = { + .name = TYPE_SPAPR_DRC_PMEM, + .parent = TYPE_SPAPR_DRC_LOGICAL, + .class_init = spapr_drc_pmem_class_init, +}; + /* helper functions for external users */ SpaprDrc *spapr_drc_by_index(uint32_t index) @@ -1230,6 +1277,7 @@ static void spapr_drc_register_types(void) type_register_static(&spapr_drc_pci_info); type_register_static(&spapr_drc_lmb_info); type_register_static(&spapr_drc_phb_info); + type_register_static(&spapr_drc_pmem_info); spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator", rtas_set_indicator); diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index 884e455f02..8b32b7eea5 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -196,6 +196,7 @@ struct rtas_event_log_v6_hp { #define RTAS_LOG_V6_HP_TYPE_SLOT 3 #define RTAS_LOG_V6_HP_TYPE_PHB 4 #define RTAS_LOG_V6_HP_TYPE_PCI 5 +#define RTAS_LOG_V6_HP_TYPE_PMEM 6 uint8_t hotplug_action; #define RTAS_LOG_V6_HP_ACTION_ADD 1 #define RTAS_LOG_V6_HP_ACTION_REMOVE 2 @@ -631,6 +632,9 @@ static void spapr_hotplug_req_event(uint8_t hp_id, uint8_t hp_action, case SPAPR_DR_CONNECTOR_TYPE_PHB: hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_PHB; break; + case SPAPR_DR_CONNECTOR_TYPE_PMEM: + hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_PMEM; + break; default: /* we shouldn't be signaling hotplug events for resources * that don't support them diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index b8bb66b5c0..6db3dbde9c 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -1640,20 +1640,24 @@ static uint32_t cas_check_pvr(SpaprMachineState *spapr, PowerPCCPU *cpu, return best_compat; } -static bool spapr_hotplugged_dev_before_cas(void) +static bool spapr_transient_dev_before_cas(void) { - Object *drc_container, *obj; + Object *drc_container; ObjectProperty *prop; ObjectPropertyIterator iter; drc_container = container_get(object_get_root(), "/dr-connector"); object_property_iter_init(&iter, drc_container); while ((prop = object_property_iter_next(&iter))) { + SpaprDrc *drc; + if (!strstart(prop->type, "link<", NULL)) { continue; } - obj = object_property_get_link(drc_container, prop->name, NULL); - if (spapr_drc_needed(obj)) { + drc = SPAPR_DR_CONNECTOR(object_property_get_link(drc_container, + prop->name, NULL)); + + if (spapr_drc_transient(drc)) { return true; } } @@ -1830,7 +1834,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu, spapr_irq_update_active_intc(spapr); - if (spapr_hotplugged_dev_before_cas()) { + if (spapr_transient_dev_before_cas()) { spapr->cas_reboot = true; } diff --git a/hw/ppc/spapr_nvdimm.c b/hw/ppc/spapr_nvdimm.c new file mode 100644 index 0000000000..74eeb8bb74 --- /dev/null +++ b/hw/ppc/spapr_nvdimm.c @@ -0,0 +1,475 @@ +/* + * QEMU PAPR Storage Class Memory Interfaces + * + * Copyright (c) 2019-2020, IBM Corporation. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/ppc/spapr_drc.h" +#include "hw/ppc/spapr_nvdimm.h" +#include "hw/mem/nvdimm.h" +#include "qemu/nvdimm-utils.h" +#include "hw/ppc/fdt.h" +#include "qemu/range.h" + +void spapr_nvdimm_validate_opts(NVDIMMDevice *nvdimm, uint64_t size, + Error **errp) +{ + char *uuidstr = NULL; + QemuUUID uuid; + + if (size % SPAPR_MINIMUM_SCM_BLOCK_SIZE) { + error_setg(errp, "NVDIMM memory size excluding the label area" + " must be a multiple of %" PRIu64 "MB", + SPAPR_MINIMUM_SCM_BLOCK_SIZE / MiB); + return; + } + + uuidstr = object_property_get_str(OBJECT(nvdimm), NVDIMM_UUID_PROP, NULL); + qemu_uuid_parse(uuidstr, &uuid); + g_free(uuidstr); + + if (qemu_uuid_is_null(&uuid)) { + error_setg(errp, "NVDIMM device requires the uuid to be set"); + return; + } +} + + +void spapr_add_nvdimm(DeviceState *dev, uint64_t slot, Error **errp) +{ + SpaprDrc *drc; + bool hotplugged = spapr_drc_hotplugged(dev); + Error *local_err = NULL; + + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PMEM, slot); + g_assert(drc); + + spapr_drc_attach(drc, dev, &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + if (hotplugged) { + spapr_hotplug_req_add_by_index(drc); + } +} + +int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp) +{ + NVDIMMDevice *nvdimm = NVDIMM(drc->dev); + + *fdt_start_offset = spapr_dt_nvdimm(fdt, 0, nvdimm); + + return 0; +} + +void spapr_create_nvdimm_dr_connectors(SpaprMachineState *spapr) +{ + MachineState *machine = MACHINE(spapr); + int i; + + for (i = 0; i < machine->ram_slots; i++) { + spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_PMEM, i); + } +} + + +int spapr_dt_nvdimm(void *fdt, int parent_offset, + NVDIMMDevice *nvdimm) +{ + int child_offset; + char *buf; + SpaprDrc *drc; + uint32_t drc_idx; + uint32_t node = object_property_get_uint(OBJECT(nvdimm), PC_DIMM_NODE_PROP, + &error_abort); + uint64_t slot = object_property_get_uint(OBJECT(nvdimm), PC_DIMM_SLOT_PROP, + &error_abort); + uint32_t associativity[] = { + cpu_to_be32(0x4), /* length */ + cpu_to_be32(0x0), cpu_to_be32(0x0), + cpu_to_be32(0x0), cpu_to_be32(node) + }; + uint64_t lsize = nvdimm->label_size; + uint64_t size = object_property_get_int(OBJECT(nvdimm), PC_DIMM_SIZE_PROP, + NULL); + + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PMEM, slot); + g_assert(drc); + + drc_idx = spapr_drc_index(drc); + + buf = g_strdup_printf("ibm,pmemory@%x", drc_idx); + child_offset = fdt_add_subnode(fdt, parent_offset, buf); + g_free(buf); + + _FDT(child_offset); + + _FDT((fdt_setprop_cell(fdt, child_offset, "reg", drc_idx))); + _FDT((fdt_setprop_string(fdt, child_offset, "compatible", "ibm,pmemory"))); + _FDT((fdt_setprop_string(fdt, child_offset, "device_type", "ibm,pmemory"))); + + _FDT((fdt_setprop(fdt, child_offset, "ibm,associativity", associativity, + sizeof(associativity)))); + + buf = qemu_uuid_unparse_strdup(&nvdimm->uuid); + _FDT((fdt_setprop_string(fdt, child_offset, "ibm,unit-guid", buf))); + g_free(buf); + + _FDT((fdt_setprop_cell(fdt, child_offset, "ibm,my-drc-index", drc_idx))); + + _FDT((fdt_setprop_u64(fdt, child_offset, "ibm,block-size", + SPAPR_MINIMUM_SCM_BLOCK_SIZE))); + _FDT((fdt_setprop_u64(fdt, child_offset, "ibm,number-of-blocks", + size / SPAPR_MINIMUM_SCM_BLOCK_SIZE))); + _FDT((fdt_setprop_cell(fdt, child_offset, "ibm,metadata-size", lsize))); + + _FDT((fdt_setprop_string(fdt, child_offset, "ibm,pmem-application", + "operating-system"))); + _FDT(fdt_setprop(fdt, child_offset, "ibm,cache-flush-required", NULL, 0)); + + return child_offset; +} + +void spapr_dt_persistent_memory(void *fdt) +{ + int offset = fdt_subnode_offset(fdt, 0, "persistent-memory"); + GSList *iter, *nvdimms = nvdimm_get_device_list(); + + if (offset < 0) { + offset = fdt_add_subnode(fdt, 0, "persistent-memory"); + _FDT(offset); + _FDT((fdt_setprop_cell(fdt, offset, "#address-cells", 0x1))); + _FDT((fdt_setprop_cell(fdt, offset, "#size-cells", 0x0))); + _FDT((fdt_setprop_string(fdt, offset, "device_type", + "ibm,persistent-memory"))); + } + + /* Create DT entries for cold plugged NVDIMM devices */ + for (iter = nvdimms; iter; iter = iter->next) { + NVDIMMDevice *nvdimm = iter->data; + + spapr_dt_nvdimm(fdt, offset, nvdimm); + } + g_slist_free(nvdimms); + + return; +} + +static target_ulong h_scm_read_metadata(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong opcode, + target_ulong *args) +{ + uint32_t drc_index = args[0]; + uint64_t offset = args[1]; + uint64_t len = args[2]; + SpaprDrc *drc = spapr_drc_by_index(drc_index); + NVDIMMDevice *nvdimm; + NVDIMMClass *ddc; + uint64_t data = 0; + uint8_t buf[8] = { 0 }; + + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_PARAMETER; + } + + if (len != 1 && len != 2 && + len != 4 && len != 8) { + return H_P3; + } + + nvdimm = NVDIMM(drc->dev); + if ((offset + len < offset) || + (nvdimm->label_size < len + offset)) { + return H_P2; + } + + ddc = NVDIMM_GET_CLASS(nvdimm); + ddc->read_label_data(nvdimm, buf, len, offset); + + switch (len) { + case 1: + data = ldub_p(buf); + break; + case 2: + data = lduw_be_p(buf); + break; + case 4: + data = ldl_be_p(buf); + break; + case 8: + data = ldq_be_p(buf); + break; + default: + g_assert_not_reached(); + } + + args[0] = data; + + return H_SUCCESS; +} + +static target_ulong h_scm_write_metadata(PowerPCCPU *cpu, + SpaprMachineState *spapr, + target_ulong opcode, + target_ulong *args) +{ + uint32_t drc_index = args[0]; + uint64_t offset = args[1]; + uint64_t data = args[2]; + uint64_t len = args[3]; + SpaprDrc *drc = spapr_drc_by_index(drc_index); + NVDIMMDevice *nvdimm; + NVDIMMClass *ddc; + uint8_t buf[8] = { 0 }; + + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_PARAMETER; + } + + if (len != 1 && len != 2 && + len != 4 && len != 8) { + return H_P4; + } + + nvdimm = NVDIMM(drc->dev); + if ((offset + len < offset) || + (nvdimm->label_size < len + offset)) { + return H_P2; + } + + switch (len) { + case 1: + if (data & 0xffffffffffffff00) { + return H_P2; + } + stb_p(buf, data); + break; + case 2: + if (data & 0xffffffffffff0000) { + return H_P2; + } + stw_be_p(buf, data); + break; + case 4: + if (data & 0xffffffff00000000) { + return H_P2; + } + stl_be_p(buf, data); + break; + case 8: + stq_be_p(buf, data); + break; + default: + g_assert_not_reached(); + } + + ddc = NVDIMM_GET_CLASS(nvdimm); + ddc->write_label_data(nvdimm, buf, len, offset); + + return H_SUCCESS; +} + +static target_ulong h_scm_bind_mem(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + uint32_t drc_index = args[0]; + uint64_t starting_idx = args[1]; + uint64_t no_of_scm_blocks_to_bind = args[2]; + uint64_t target_logical_mem_addr = args[3]; + uint64_t continue_token = args[4]; + uint64_t size; + uint64_t total_no_of_scm_blocks; + SpaprDrc *drc = spapr_drc_by_index(drc_index); + hwaddr addr; + NVDIMMDevice *nvdimm; + + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_PARAMETER; + } + + /* + * Currently continue token should be zero qemu has already bound + * everything and this hcall doesnt return H_BUSY. + */ + if (continue_token > 0) { + return H_P5; + } + + /* Currently qemu assigns the address. */ + if (target_logical_mem_addr != 0xffffffffffffffff) { + return H_OVERLAP; + } + + nvdimm = NVDIMM(drc->dev); + + size = object_property_get_uint(OBJECT(nvdimm), + PC_DIMM_SIZE_PROP, &error_abort); + + total_no_of_scm_blocks = size / SPAPR_MINIMUM_SCM_BLOCK_SIZE; + + if (starting_idx > total_no_of_scm_blocks) { + return H_P2; + } + + if (((starting_idx + no_of_scm_blocks_to_bind) < starting_idx) || + ((starting_idx + no_of_scm_blocks_to_bind) > total_no_of_scm_blocks)) { + return H_P3; + } + + addr = object_property_get_uint(OBJECT(nvdimm), + PC_DIMM_ADDR_PROP, &error_abort); + + addr += starting_idx * SPAPR_MINIMUM_SCM_BLOCK_SIZE; + + /* Already bound, Return target logical address in R5 */ + args[1] = addr; + args[2] = no_of_scm_blocks_to_bind; + + return H_SUCCESS; +} + +static target_ulong h_scm_unbind_mem(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + uint32_t drc_index = args[0]; + uint64_t starting_scm_logical_addr = args[1]; + uint64_t no_of_scm_blocks_to_unbind = args[2]; + uint64_t continue_token = args[3]; + uint64_t size_to_unbind; + Range blockrange = range_empty; + Range nvdimmrange = range_empty; + SpaprDrc *drc = spapr_drc_by_index(drc_index); + NVDIMMDevice *nvdimm; + uint64_t size, addr; + + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_PARAMETER; + } + + /* continue_token should be zero as this hcall doesn't return H_BUSY. */ + if (continue_token > 0) { + return H_P4; + } + + /* Check if starting_scm_logical_addr is block aligned */ + if (!QEMU_IS_ALIGNED(starting_scm_logical_addr, + SPAPR_MINIMUM_SCM_BLOCK_SIZE)) { + return H_P2; + } + + size_to_unbind = no_of_scm_blocks_to_unbind * SPAPR_MINIMUM_SCM_BLOCK_SIZE; + if (no_of_scm_blocks_to_unbind == 0 || no_of_scm_blocks_to_unbind != + size_to_unbind / SPAPR_MINIMUM_SCM_BLOCK_SIZE) { + return H_P3; + } + + nvdimm = NVDIMM(drc->dev); + size = object_property_get_int(OBJECT(nvdimm), PC_DIMM_SIZE_PROP, + &error_abort); + addr = object_property_get_int(OBJECT(nvdimm), PC_DIMM_ADDR_PROP, + &error_abort); + + range_init_nofail(&nvdimmrange, addr, size); + range_init_nofail(&blockrange, starting_scm_logical_addr, size_to_unbind); + + if (!range_contains_range(&nvdimmrange, &blockrange)) { + return H_P3; + } + + args[1] = no_of_scm_blocks_to_unbind; + + /* let unplug take care of actual unbind */ + return H_SUCCESS; +} + +#define H_UNBIND_SCOPE_ALL 0x1 +#define H_UNBIND_SCOPE_DRC 0x2 + +static target_ulong h_scm_unbind_all(PowerPCCPU *cpu, SpaprMachineState *spapr, + target_ulong opcode, target_ulong *args) +{ + uint64_t target_scope = args[0]; + uint32_t drc_index = args[1]; + uint64_t continue_token = args[2]; + NVDIMMDevice *nvdimm; + uint64_t size; + uint64_t no_of_scm_blocks_unbound = 0; + + /* continue_token should be zero as this hcall doesn't return H_BUSY. */ + if (continue_token > 0) { + return H_P4; + } + + if (target_scope == H_UNBIND_SCOPE_DRC) { + SpaprDrc *drc = spapr_drc_by_index(drc_index); + + if (!drc || !drc->dev || + spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PMEM) { + return H_P2; + } + + nvdimm = NVDIMM(drc->dev); + size = object_property_get_int(OBJECT(nvdimm), PC_DIMM_SIZE_PROP, + &error_abort); + + no_of_scm_blocks_unbound = size / SPAPR_MINIMUM_SCM_BLOCK_SIZE; + } else if (target_scope == H_UNBIND_SCOPE_ALL) { + GSList *list, *nvdimms; + + nvdimms = nvdimm_get_device_list(); + for (list = nvdimms; list; list = list->next) { + nvdimm = list->data; + size = object_property_get_int(OBJECT(nvdimm), PC_DIMM_SIZE_PROP, + &error_abort); + + no_of_scm_blocks_unbound += size / SPAPR_MINIMUM_SCM_BLOCK_SIZE; + } + g_slist_free(nvdimms); + } else { + return H_PARAMETER; + } + + args[1] = no_of_scm_blocks_unbound; + + /* let unplug take care of actual unbind */ + return H_SUCCESS; +} + +static void spapr_scm_register_types(void) +{ + /* qemu/scm specific hcalls */ + spapr_register_hypercall(H_SCM_READ_METADATA, h_scm_read_metadata); + spapr_register_hypercall(H_SCM_WRITE_METADATA, h_scm_write_metadata); + spapr_register_hypercall(H_SCM_BIND_MEM, h_scm_bind_mem); + spapr_register_hypercall(H_SCM_UNBIND_MEM, h_scm_unbind_mem); + spapr_register_hypercall(H_SCM_UNBIND_ALL, h_scm_unbind_all); +} + +type_init(spapr_scm_register_types) diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index 883fe28465..656fdd2216 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -345,6 +345,13 @@ static void rtas_ibm_os_term(PowerPCCPU *cpu, target_ulong args, uint32_t nret, target_ulong rets) { + target_ulong msgaddr = rtas_ld(args, 0); + char msg[512]; + + cpu_physical_memory_read(msgaddr, msg, sizeof(msg) - 1); + msg[sizeof(msg) - 1] = 0; + + error_report("OS terminated: %s", msg); qemu_system_guest_panicked(NULL); rtas_st(rets, 0, RTAS_OUT_SUCCESS); diff --git a/hw/ppc/virtex_ml507.c b/hw/ppc/virtex_ml507.c index b6f4507dcf..0dacfcd236 100644 --- a/hw/ppc/virtex_ml507.c +++ b/hw/ppc/virtex_ml507.c @@ -188,6 +188,7 @@ static int xilinx_load_device_tree(hwaddr addr, if (r < 0) fprintf(stderr, "couldn't set /chosen/bootargs\n"); cpu_physical_memory_write(addr, fdt, fdt_size); + g_free(fdt); return fdt_size; } diff --git a/hw/scsi/esp.c b/hw/scsi/esp.c index f8fc30cccb..405f8b7cbc 100644 --- a/hw/scsi/esp.c +++ b/hw/scsi/esp.c @@ -293,7 +293,7 @@ static void handle_satn_stop(ESPState *s) s->dma_cb = handle_satn_stop; return; } - s->pdma_cb = satn_stop_pdma_cb;; + s->pdma_cb = satn_stop_pdma_cb; s->cmdlen = get_cmd(s, s->cmdbuf, sizeof(s->cmdbuf)); if (s->cmdlen) { trace_esp_handle_satn_stop(s->cmdlen); diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index 3b61563609..472bbd233b 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -965,7 +965,7 @@ static void virtio_scsi_device_unrealize(DeviceState *dev, Error **errp) static Property virtio_scsi_properties[] = { DEFINE_PROP_UINT32("num_queues", VirtIOSCSI, parent_obj.conf.num_queues, 1), DEFINE_PROP_UINT32("virtqueue_size", VirtIOSCSI, - parent_obj.conf.virtqueue_size, 128), + parent_obj.conf.virtqueue_size, 256), DEFINE_PROP_BOOL("seg_max_adjust", VirtIOSCSI, parent_obj.conf.seg_max_adjust, true), DEFINE_PROP_UINT32("max_sectors", VirtIOSCSI, parent_obj.conf.max_sectors, diff --git a/hw/sh4/sh_pci.c b/hw/sh4/sh_pci.c index 71afd23b67..08f2fc1dde 100644 --- a/hw/sh4/sh_pci.c +++ b/hw/sh4/sh_pci.c @@ -67,12 +67,8 @@ static void sh_pci_reg_write (void *p, hwaddr addr, uint64_t val, pcic->mbr = val & 0xff000001; break; case 0x1c8: - if ((val & 0xfffc0000) != (pcic->iobr & 0xfffc0000)) { - memory_region_del_subregion(get_system_memory(), &pcic->isa); - pcic->iobr = val & 0xfffc0001; - memory_region_add_subregion(get_system_memory(), - pcic->iobr & 0xfffc0000, &pcic->isa); - } + pcic->iobr = val & 0xfffc0001; + memory_region_set_alias_offset(&pcic->isa, val & 0xfffc0000); break; case 0x220: pci_data_write(phb->bus, pcic->par, val, 4); @@ -147,8 +143,7 @@ static void sh_pci_device_realize(DeviceState *dev, Error **errp) get_system_io(), 0, 0x40000); sysbus_init_mmio(sbd, &s->memconfig_p4); sysbus_init_mmio(sbd, &s->memconfig_a7); - s->iobr = 0xfe240000; - memory_region_add_subregion(get_system_memory(), s->iobr, &s->isa); + memory_region_add_subregion(get_system_memory(), 0xfe240000, &s->isa); s->dev = pci_create_simple(phb->bus, PCI_DEVFN(0, 0), "sh_pci_host"); } diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c index 6c9ef59779..c57850a505 100644 --- a/hw/ssi/xilinx_spips.c +++ b/hw/ssi/xilinx_spips.c @@ -576,11 +576,11 @@ static int xilinx_spips_num_dummies(XilinxQSPIPS *qs, uint8_t command) case FAST_READ: case DOR: case QOR: + case FAST_READ_4: case DOR_4: case QOR_4: return 1; case DIOR: - case FAST_READ_4: case DIOR_4: return 2; case QIOR: diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c index 8d4738565e..b22fb258be 100644 --- a/hw/usb/hcd-ehci-sysbus.c +++ b/hw/usb/hcd-ehci-sysbus.c @@ -33,6 +33,8 @@ static const VMStateDescription vmstate_ehci_sysbus = { static Property ehci_sysbus_properties[] = { DEFINE_PROP_UINT32("maxframes", EHCISysBusState, ehci.maxframes, 128), + DEFINE_PROP_BOOL("companion-enable", EHCISysBusState, ehci.companion_enable, + false), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/usb/hcd-ohci.c b/hw/usb/hcd-ohci.c index 8a94bd004a..1e6e85e86a 100644 --- a/hw/usb/hcd-ohci.c +++ b/hw/usb/hcd-ohci.c @@ -1870,21 +1870,6 @@ void ohci_sysbus_die(struct OHCIState *ohci) ohci_bus_stop(ohci); } -#define TYPE_SYSBUS_OHCI "sysbus-ohci" -#define SYSBUS_OHCI(obj) OBJECT_CHECK(OHCISysBusState, (obj), TYPE_SYSBUS_OHCI) - -typedef struct { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - OHCIState ohci; - char *masterbus; - uint32_t num_ports; - uint32_t firstport; - dma_addr_t dma_offset; -} OHCISysBusState; - static void ohci_realize_pxa(DeviceState *dev, Error **errp) { OHCISysBusState *s = SYSBUS_OHCI(dev); diff --git a/hw/usb/hcd-ohci.h b/hw/usb/hcd-ohci.h index 16e3f1e13a..5c8819aedf 100644 --- a/hw/usb/hcd-ohci.h +++ b/hw/usb/hcd-ohci.h @@ -22,6 +22,7 @@ #define HCD_OHCI_H #include "sysemu/dma.h" +#include "hw/usb.h" /* Number of Downstream Ports on the root hub: */ #define OHCI_MAX_PORTS 15 @@ -90,6 +91,21 @@ typedef struct OHCIState { void (*ohci_die)(struct OHCIState *ohci); } OHCIState; +#define TYPE_SYSBUS_OHCI "sysbus-ohci" +#define SYSBUS_OHCI(obj) OBJECT_CHECK(OHCISysBusState, (obj), TYPE_SYSBUS_OHCI) + +typedef struct { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + OHCIState ohci; + char *masterbus; + uint32_t num_ports; + uint32_t firstport; + dma_addr_t dma_offset; +} OHCISysBusState; + extern const VMStateDescription vmstate_ohci_state; void usb_ohci_init(OHCIState *ohci, DeviceState *dev, uint32_t num_ports, diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 5ca11488d6..0b3593b3c0 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -319,7 +319,7 @@ static int vfio_dma_unmap(VFIOContainer *container, unmap.size -= 1ULL << ctz64(container->pgsizes); continue; } - error_report("VFIO_UNMAP_DMA: %d", -errno); + error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); return -errno; } @@ -352,7 +352,7 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova, return 0; } - error_report("VFIO_MAP_DMA: %d", -errno); + error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); return -errno; } diff --git a/hw/vfio/display.c b/hw/vfio/display.c index a5a608c5b2..f4977c66e1 100644 --- a/hw/vfio/display.c +++ b/hw/vfio/display.c @@ -287,7 +287,7 @@ static void vfio_display_dmabuf_update(void *opaque) VFIOPCIDevice *vdev = opaque; VFIODisplay *dpy = vdev->dpy; VFIODMABuf *primary, *cursor; - bool free_bufs = false, new_cursor = false;; + bool free_bufs = false, new_cursor = false; primary = vfio_display_get_dmabuf(vdev, DRM_PLANE_TYPE_PRIMARY); if (primary == NULL) { diff --git a/hw/xtensa/xtfpga.c b/hw/xtensa/xtfpga.c index 8e2dd1327a..60ccc74f5f 100644 --- a/hw/xtensa/xtfpga.c +++ b/hw/xtensa/xtfpga.c @@ -380,6 +380,7 @@ static void xtfpga_init(const XtfpgaBoardDesc *board, MachineState *machine) cur_tagptr = put_tag(cur_tagptr, BP_TAG_FDT, sizeof(dtb_addr), &dtb_addr); cur_lowmem = QEMU_ALIGN_UP(cur_lowmem + fdt_size, 4 * KiB); + g_free(fdt); } #else if (dtb_filename) { diff --git a/include/block/aio.h b/include/block/aio.h index 7ba9bd7874..9dd61cee7e 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -42,6 +42,7 @@ void qemu_aio_unref(void *p); void qemu_aio_ref(void *p); typedef struct AioHandler AioHandler; +typedef QLIST_HEAD(, AioHandler) AioHandlerList; typedef void QEMUBHFunc(void *opaque); typedef bool AioPollFn(void *opaque); typedef void IOHandler(void *opaque); @@ -51,6 +52,19 @@ struct ThreadPool; struct LinuxAioState; struct LuringState; +/* + * Each aio_bh_poll() call carves off a slice of the BH list, so that newly + * scheduled BHs are not processed until the next aio_bh_poll() call. All + * active aio_bh_poll() calls chain their slices together in a list, so that + * nested aio_bh_poll() calls process all scheduled bottom halves. + */ +typedef QSLIST_HEAD(, QEMUBH) BHList; +typedef struct BHListSlice BHListSlice; +struct BHListSlice { + BHList bh_list; + QSIMPLEQ_ENTRY(BHListSlice) next; +}; + struct AioContext { GSource source; @@ -58,7 +72,10 @@ struct AioContext { QemuRecMutex lock; /* The list of registered AIO handlers. Protected by ctx->list_lock. */ - QLIST_HEAD(, AioHandler) aio_handlers; + AioHandlerList aio_handlers; + + /* The list of AIO handlers to be deleted. Protected by ctx->list_lock. */ + AioHandlerList deleted_aio_handlers; /* Used to avoid unnecessary event_notifier_set calls in aio_notify; * accessed with atomic primitives. If this field is 0, everything @@ -91,8 +108,11 @@ struct AioContext { */ QemuLockCnt list_lock; - /* Anchor of the list of Bottom Halves belonging to the context */ - struct QEMUBH *first_bh; + /* Bottom Halves pending aio_bh_poll() processing */ + BHList bh_list; + + /* Chained BH list slices for each nested aio_bh_poll() call */ + QSIMPLEQ_HEAD(, BHListSlice) bh_slice_list; /* Used by aio_notify. * diff --git a/include/block/block.h b/include/block/block.h index 6cd566324d..cd6b5b95aa 100644 --- a/include/block/block.h +++ b/include/block/block.h @@ -391,11 +391,6 @@ int bdrv_amend_options(BlockDriverState *bs_new, QemuOpts *opts, BlockDriverAmendStatusCB *status_cb, void *cb_opaque, Error **errp); -/* external snapshots */ -bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs, - BlockDriverState *candidate); -bool bdrv_is_first_non_filter(BlockDriverState *candidate); - /* check if a named node can be replaced when doing drive-mirror */ BlockDriverState *check_to_replace_node(BlockDriverState *parent_bs, const char *node_name, Error **errp); @@ -459,7 +454,7 @@ void bdrv_lock_medium(BlockDriverState *bs, bool locked); void bdrv_eject(BlockDriverState *bs, bool eject_flag); const char *bdrv_get_format_name(BlockDriverState *bs); BlockDriverState *bdrv_find_node(const char *node_name); -BlockDeviceInfoList *bdrv_named_nodes_list(Error **errp); +BlockDeviceInfoList *bdrv_named_nodes_list(bool flat, Error **errp); XDbgBlockGraph *bdrv_get_xdbg_block_graph(Error **errp); BlockDriverState *bdrv_lookup_bs(const char *device, const char *node_name, diff --git a/include/block/block_int.h b/include/block/block_int.h index 640fb82c78..6f9fd5e20e 100644 --- a/include/block/block_int.h +++ b/include/block/block_int.h @@ -94,14 +94,13 @@ struct BlockDriver { * must implement them and return -ENOTSUP. */ bool is_filter; - /* for snapshots block filter like Quorum can implement the - * following recursive callback. - * It's purpose is to recurse on the filter children while calling - * bdrv_recurse_is_first_non_filter on them. - * For a sample implementation look in the future Quorum block filter. + /* + * Return true if @to_replace can be replaced by a BDS with the + * same data as @bs without it affecting @bs's behavior (that is, + * without it being visible to @bs's parents). */ - bool (*bdrv_recurse_is_first_non_filter)(BlockDriverState *bs, - BlockDriverState *candidate); + bool (*bdrv_recurse_can_replace)(BlockDriverState *bs, + BlockDriverState *to_replace); int (*bdrv_probe)(const uint8_t *buf, int buf_size, const char *filename); int (*bdrv_probe_device)(const char *filename); @@ -1263,6 +1262,9 @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c, uint64_t perm, uint64_t shared, uint64_t *nperm, uint64_t *nshared); +bool bdrv_recurse_can_replace(BlockDriverState *bs, + BlockDriverState *to_replace); + /* * Default implementation for drivers to pass bdrv_co_block_status() to * their file. diff --git a/include/block/qapi.h b/include/block/qapi.h index cd9410dee3..22c7807c89 100644 --- a/include/block/qapi.h +++ b/include/block/qapi.h @@ -29,7 +29,9 @@ #include "block/snapshot.h" BlockDeviceInfo *bdrv_block_device_info(BlockBackend *blk, - BlockDriverState *bs, Error **errp); + BlockDriverState *bs, + bool flat, + Error **errp); int bdrv_query_snapshot_info_list(BlockDriverState *bs, SnapshotInfoList **p_list, Error **errp); diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index 40d0b1d9c0..8af724548f 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -8,12 +8,16 @@ #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" #include "hw/ide/ahci.h" +#include "hw/usb/hcd-ohci.h" +#include "hw/usb/hcd-ehci.h" #include "target/arm/cpu.h" #define AW_A10_SDRAM_BASE 0x40000000 +#define AW_A10_NUM_USB 2 + #define TYPE_AW_A10 "allwinner-a10" #define AW_A10(obj) OBJECT_CHECK(AwA10State, (obj), TYPE_AW_A10) @@ -28,6 +32,8 @@ typedef struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; MemoryRegion sram_a; + EHCISysBusState ehci[AW_A10_NUM_USB]; + OHCISysBusState ohci[AW_A10_NUM_USB]; } AwA10State; #endif diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h index 523a9b3d4a..4807ca615b 100644 --- a/include/hw/mem/nvdimm.h +++ b/include/hw/mem/nvdimm.h @@ -25,6 +25,7 @@ #include "hw/mem/pc-dimm.h" #include "hw/acpi/bios-linker-loader.h" +#include "qemu/uuid.h" #define NVDIMM_DEBUG 0 #define nvdimm_debug(fmt, ...) \ @@ -49,6 +50,7 @@ TYPE_NVDIMM) #define NVDIMM_LABEL_SIZE_PROP "label-size" +#define NVDIMM_UUID_PROP "uuid" #define NVDIMM_UNARMED_PROP "unarmed" struct NVDIMMDevice { @@ -83,6 +85,11 @@ struct NVDIMMDevice { * the guest write persistence. */ bool unarmed; + + /* + * The PPC64 - spapr requires each nvdimm device have a uuid. + */ + QemuUUID uuid; }; typedef struct NVDIMMDevice NVDIMMDevice; diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index a1fba95c82..09110961a5 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -162,6 +162,7 @@ struct SpaprMachineState { void *fdt_blob; long kernel_size; bool kernel_le; + uint64_t kernel_addr; uint32_t initrd_base; long initrd_size; uint64_t rtc_offset; /* Now used only during incoming migration */ @@ -300,6 +301,7 @@ struct SpaprMachineState { #define H_P7 -60 #define H_P8 -61 #define H_P9 -62 +#define H_OVERLAP -68 #define H_UNSUPPORTED_FLAG -256 #define H_MULTI_THREADS_ACTIVE -9005 @@ -507,8 +509,13 @@ struct SpaprMachineState { #define H_INT_ESB 0x3C8 #define H_INT_SYNC 0x3CC #define H_INT_RESET 0x3D0 +#define H_SCM_READ_METADATA 0x3E4 +#define H_SCM_WRITE_METADATA 0x3E8 +#define H_SCM_BIND_MEM 0x3EC +#define H_SCM_UNBIND_MEM 0x3F0 +#define H_SCM_UNBIND_ALL 0x3FC -#define MAX_HCALL_OPCODE H_INT_RESET +#define MAX_HCALL_OPCODE H_SCM_UNBIND_ALL /* The hcalls above are standardized in PAPR and implemented by pHyp * as well. diff --git a/include/hw/ppc/spapr_drc.h b/include/hw/ppc/spapr_drc.h index 83f03cc577..21af8deac1 100644 --- a/include/hw/ppc/spapr_drc.h +++ b/include/hw/ppc/spapr_drc.h @@ -78,6 +78,13 @@ #define SPAPR_DRC_PHB(obj) OBJECT_CHECK(SpaprDrc, (obj), \ TYPE_SPAPR_DRC_PHB) +#define TYPE_SPAPR_DRC_PMEM "spapr-drc-pmem" +#define SPAPR_DRC_PMEM_GET_CLASS(obj) \ + OBJECT_GET_CLASS(SpaprDrcClass, obj, TYPE_SPAPR_DRC_PMEM) +#define SPAPR_DRC_PMEM_CLASS(klass) \ + OBJECT_CLASS_CHECK(SpaprDrcClass, klass, TYPE_SPAPR_DRC_PMEM) +#define SPAPR_DRC_PMEM(obj) OBJECT_CHECK(SpaprDrc, (obj), \ + TYPE_SPAPR_DRC_PMEM) /* * Various hotplug types managed by SpaprDrc * @@ -95,6 +102,7 @@ typedef enum { SPAPR_DR_CONNECTOR_TYPE_SHIFT_VIO = 3, SPAPR_DR_CONNECTOR_TYPE_SHIFT_PCI = 4, SPAPR_DR_CONNECTOR_TYPE_SHIFT_LMB = 8, + SPAPR_DR_CONNECTOR_TYPE_SHIFT_PMEM = 9, } SpaprDrcTypeShift; typedef enum { @@ -104,6 +112,7 @@ typedef enum { SPAPR_DR_CONNECTOR_TYPE_VIO = 1 << SPAPR_DR_CONNECTOR_TYPE_SHIFT_VIO, SPAPR_DR_CONNECTOR_TYPE_PCI = 1 << SPAPR_DR_CONNECTOR_TYPE_SHIFT_PCI, SPAPR_DR_CONNECTOR_TYPE_LMB = 1 << SPAPR_DR_CONNECTOR_TYPE_SHIFT_LMB, + SPAPR_DR_CONNECTOR_TYPE_PMEM = 1 << SPAPR_DR_CONNECTOR_TYPE_SHIFT_PMEM, } SpaprDrcType; /* @@ -269,7 +278,9 @@ int spapr_dt_drc(void *fdt, int offset, Object *owner, uint32_t drc_type_mask); void spapr_drc_attach(SpaprDrc *drc, DeviceState *d, Error **errp); void spapr_drc_detach(SpaprDrc *drc); -bool spapr_drc_needed(void *opaque); + +/* Returns true if a hot plug/unplug request is pending */ +bool spapr_drc_transient(SpaprDrc *drc); static inline bool spapr_drc_unplug_requested(SpaprDrc *drc) { diff --git a/include/hw/ppc/spapr_nvdimm.h b/include/hw/ppc/spapr_nvdimm.h new file mode 100644 index 0000000000..b3330cc485 --- /dev/null +++ b/include/hw/ppc/spapr_nvdimm.h @@ -0,0 +1,37 @@ +/* + * QEMU PowerPC PAPR SCM backend definitions + * + * Copyright (c) 2020, IBM Corporation. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#ifndef HW_SPAPR_NVDIMM_H +#define HW_SPAPR_NVDIMM_H + +#include "hw/mem/nvdimm.h" +#include "hw/ppc/spapr.h" + +/* + * The nvdimm size should be aligned to SCM block size. + * The SCM block size should be aligned to SPAPR_MEMORY_BLOCK_SIZE + * inorder to have SCM regions not to overlap with dimm memory regions. + * The SCM devices can have variable block sizes. For now, fixing the + * block size to the minimum value. + */ +#define SPAPR_MINIMUM_SCM_BLOCK_SIZE SPAPR_MEMORY_BLOCK_SIZE + +/* Have an explicit check for alignment */ +QEMU_BUILD_BUG_ON(SPAPR_MINIMUM_SCM_BLOCK_SIZE % SPAPR_MEMORY_BLOCK_SIZE); + +int spapr_pmem_dt_populate(SpaprDrc *drc, SpaprMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); +int spapr_dt_nvdimm(void *fdt, int parent_offset, NVDIMMDevice *nvdimm); +void spapr_dt_persistent_memory(void *fdt); +void spapr_nvdimm_validate_opts(NVDIMMDevice *nvdimm, uint64_t size, + Error **errp); +void spapr_add_nvdimm(DeviceState *dev, uint64_t slot, Error **errp); +void spapr_create_nvdimm_dr_connectors(SpaprMachineState *spapr); + +#endif diff --git a/include/qemu/log.h b/include/qemu/log.h index e0f4e40628..f4724f7330 100644 --- a/include/qemu/log.h +++ b/include/qemu/log.h @@ -62,6 +62,8 @@ static inline bool qemu_log_separate(void) #define CPU_LOG_TB_OP_IND (1 << 16) #define CPU_LOG_TB_FPU (1 << 17) #define CPU_LOG_PLUGIN (1 << 18) +/* LOG_STRACE is used for user-mode strace logging. */ +#define LOG_STRACE (1 << 19) /* Lock output for a series of related logs. Since this is not needed * for a single qemu_log / qemu_log_mask / qemu_log_mask_and_addr, we diff --git a/include/qemu/module.h b/include/qemu/module.h index 65ba596e46..684753d808 100644 --- a/include/qemu/module.h +++ b/include/qemu/module.h @@ -46,6 +46,7 @@ typedef enum { MODULE_INIT_TRACE, MODULE_INIT_XEN_BACKEND, MODULE_INIT_LIBQOS, + MODULE_INIT_FUZZ_TARGET, MODULE_INIT_MAX } module_init_type; @@ -56,7 +57,8 @@ typedef enum { #define xen_backend_init(function) module_init(function, \ MODULE_INIT_XEN_BACKEND) #define libqos_init(function) module_init(function, MODULE_INIT_LIBQOS) - +#define fuzz_target_init(function) module_init(function, \ + MODULE_INIT_FUZZ_TARGET) #define block_module_load_one(lib) module_load_one("block-", lib) #define ui_module_load_one(lib) module_load_one("ui-", lib) #define audio_module_load_one(lib) module_load_one("audio-", lib) diff --git a/include/qemu/nvdimm-utils.h b/include/qemu/nvdimm-utils.h new file mode 100644 index 0000000000..4b8b198ba7 --- /dev/null +++ b/include/qemu/nvdimm-utils.h @@ -0,0 +1,7 @@ +#ifndef NVDIMM_UTILS_H +#define NVDIMM_UTILS_H + +#include "qemu/osdep.h" + +GSList *nvdimm_get_device_list(void); +#endif diff --git a/include/qemu/queue.h b/include/qemu/queue.h index 19425f973f..294db54eb1 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -144,6 +144,23 @@ struct { \ *(elm)->field.le_prev = (elm)->field.le_next; \ } while (/*CONSTCOND*/0) +/* + * Like QLIST_REMOVE() but safe to call when elm is not in a list + */ +#define QLIST_SAFE_REMOVE(elm, field) do { \ + if ((elm)->field.le_prev != NULL) { \ + if ((elm)->field.le_next != NULL) \ + (elm)->field.le_next->field.le_prev = \ + (elm)->field.le_prev; \ + *(elm)->field.le_prev = (elm)->field.le_next; \ + (elm)->field.le_next = NULL; \ + (elm)->field.le_prev = NULL; \ + } \ +} while (/*CONSTCOND*/0) + +/* Is elm in a list? */ +#define QLIST_IS_INSERTED(elm, field) ((elm)->field.le_prev != NULL) + #define QLIST_FOREACH(var, head, field) \ for ((var) = ((head)->lh_first); \ (var); \ @@ -211,9 +228,20 @@ struct { \ (head)->slh_first = (head)->slh_first->field.sle_next; \ } while (/*CONSTCOND*/0) -#define QSLIST_REMOVE_AFTER(slistelm, field) do { \ +#define QSLIST_REMOVE_AFTER(slistelm, field) do { \ (slistelm)->field.sle_next = \ - QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \ + QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE(head, elm, type, field) do { \ + if ((head)->slh_first == (elm)) { \ + QSLIST_REMOVE_HEAD((head), field); \ + } else { \ + struct type *curelm = (head)->slh_first; \ + while (curelm->field.sle_next != (elm)) \ + curelm = curelm->field.sle_next; \ + curelm->field.sle_next = curelm->field.sle_next->field.sle_next; \ + } \ } while (/*CONSTCOND*/0) #define QSLIST_FOREACH(var, head, field) \ diff --git a/include/qemu/rcu_queue.h b/include/qemu/rcu_queue.h index 2d386f303e..558961cc27 100644 --- a/include/qemu/rcu_queue.h +++ b/include/qemu/rcu_queue.h @@ -262,6 +262,53 @@ extern "C" { (var) && ((next) = atomic_rcu_read(&(var)->field.tqe_next), 1); \ (var) = (next)) +/* + * RCU singly-linked list + */ + +/* Singly-linked list access methods */ +#define QSLIST_EMPTY_RCU(head) (atomic_read(&(head)->slh_first) == NULL) +#define QSLIST_FIRST_RCU(head) atomic_rcu_read(&(head)->slh_first) +#define QSLIST_NEXT_RCU(elm, field) atomic_rcu_read(&(elm)->field.sle_next) + +/* Singly-linked list functions */ +#define QSLIST_INSERT_HEAD_RCU(head, elm, field) do { \ + (elm)->field.sle_next = (head)->slh_first; \ + atomic_rcu_set(&(head)->slh_first, (elm)); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_INSERT_AFTER_RCU(head, listelm, elm, field) do { \ + (elm)->field.sle_next = (listelm)->field.sle_next; \ + atomic_rcu_set(&(listelm)->field.sle_next, (elm)); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_HEAD_RCU(head, field) do { \ + atomic_set(&(head)->slh_first, (head)->slh_first->field.sle_next); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_RCU(head, elm, type, field) do { \ + if ((head)->slh_first == (elm)) { \ + QSLIST_REMOVE_HEAD_RCU((head), field); \ + } else { \ + struct type *curr = (head)->slh_first; \ + while (curr->field.sle_next != (elm)) { \ + curr = curr->field.sle_next; \ + } \ + atomic_set(&curr->field.sle_next, \ + curr->field.sle_next->field.sle_next); \ + } \ +} while (/*CONSTCOND*/0) + +#define QSLIST_FOREACH_RCU(var, head, field) \ + for ((var) = atomic_rcu_read(&(head)->slh_first); \ + (var); \ + (var) = atomic_rcu_read(&(var)->field.sle_next)) + +#define QSLIST_FOREACH_SAFE_RCU(var, head, field, next) \ + for ((var) = atomic_rcu_read(&(head)->slh_first); \ + (var) && ((next) = atomic_rcu_read(&(var)->field.sle_next), 1); \ + (var) = (next)) + #ifdef __cplusplus } #endif diff --git a/include/sysemu/qtest.h b/include/sysemu/qtest.h index 5ed09c80b1..eedd3664f0 100644 --- a/include/sysemu/qtest.h +++ b/include/sysemu/qtest.h @@ -26,4 +26,8 @@ bool qtest_driver(void); void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error **errp); +void qtest_server_set_send_handler(void (*send)(void *, const char *), + void *opaque); +void qtest_server_inproc_recv(void *opaque, const char *buf); + #endif diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index 55bdd57a9b..479d90bcea 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -113,6 +113,10 @@ QemuOpts *qemu_get_machine_opts(void); bool defaults_enabled(void); +void qemu_init(int argc, char **argv, char **envp); +void qemu_main_loop(void); +void qemu_cleanup(void); + extern QemuOptsList qemu_legacy_drive_opts; extern QemuOptsList qemu_common_drive_opts; extern QemuOptsList qemu_drive_opts; diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c index 1fae90c6df..cf618daa1c 100644 --- a/linux-user/arm/cpu_loop.c +++ b/linux-user/arm/cpu_loop.c @@ -349,8 +349,9 @@ void cpu_loop(CPUARMState *env) env->regs[0] = cpu_get_tls(env); break; default: - gemu_log("qemu: Unsupported ARM syscall: 0x%x\n", - n); + qemu_log_mask(LOG_UNIMP, + "qemu: Unsupported ARM syscall: 0x%x\n", + n); env->regs[0] = -TARGET_ENOSYS; break; } diff --git a/linux-user/elfload.c b/linux-user/elfload.c index f3080a1635..b1a895f24c 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -475,8 +475,8 @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); GET_FEATURE(ARM_FEATURE_VFP4, ARM_HWCAP_ARM_VFPv4); - GET_FEATURE_ID(arm_div, ARM_HWCAP_ARM_IDIVA); - GET_FEATURE_ID(thumb_div, ARM_HWCAP_ARM_IDIVT); + GET_FEATURE_ID(aa32_arm_div, ARM_HWCAP_ARM_IDIVA); + GET_FEATURE_ID(aa32_thumb_div, ARM_HWCAP_ARM_IDIVT); /* All QEMU's VFPv3 CPUs have 32 registers, see VFP_DREG in translate.c. * Note that the ARM_HWCAP_ARM_VFPv3D16 bit is always the inverse of * ARM_HWCAP_ARM_VFPD32 (and so always clear for QEMU); it is unrelated diff --git a/linux-user/fd-trans.c b/linux-user/fd-trans.c index 9b92386abf..c0687c52e6 100644 --- a/linux-user/fd-trans.c +++ b/linux-user/fd-trans.c @@ -514,7 +514,8 @@ static abi_long host_to_target_data_bridge_nlattr(struct nlattr *nlattr, u32[1] = tswap32(u32[1]); /* optmask */ break; default: - gemu_log("Unknown QEMU_IFLA_BR type %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown QEMU_IFLA_BR type %d\n", + nlattr->nla_type); break; } return 0; @@ -577,7 +578,8 @@ static abi_long host_to_target_slave_data_bridge_nlattr(struct nlattr *nlattr, case QEMU_IFLA_BRPORT_BRIDGE_ID: break; default: - gemu_log("Unknown QEMU_IFLA_BRPORT type %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown QEMU_IFLA_BRPORT type %d\n", + nlattr->nla_type); break; } return 0; @@ -605,7 +607,8 @@ static abi_long host_to_target_data_tun_nlattr(struct nlattr *nlattr, *u32 = tswap32(*u32); break; default: - gemu_log("Unknown QEMU_IFLA_TUN type %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown QEMU_IFLA_TUN type %d\n", + nlattr->nla_type); break; } return 0; @@ -652,7 +655,8 @@ static abi_long host_to_target_data_linkinfo_nlattr(struct nlattr *nlattr, NULL, host_to_target_data_tun_nlattr); } else { - gemu_log("Unknown QEMU_IFLA_INFO_KIND %s\n", li_context->name); + qemu_log_mask(LOG_UNIMP, "Unknown QEMU_IFLA_INFO_KIND %s\n", + li_context->name); } break; case QEMU_IFLA_INFO_SLAVE_DATA: @@ -663,12 +667,13 @@ static abi_long host_to_target_data_linkinfo_nlattr(struct nlattr *nlattr, NULL, host_to_target_slave_data_bridge_nlattr); } else { - gemu_log("Unknown QEMU_IFLA_INFO_SLAVE_KIND %s\n", + qemu_log_mask(LOG_UNIMP, "Unknown QEMU_IFLA_INFO_SLAVE_KIND %s\n", li_context->slave_name); } break; default: - gemu_log("Unknown host QEMU_IFLA_INFO type: %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown host QEMU_IFLA_INFO type: %d\n", + nlattr->nla_type); break; } @@ -690,7 +695,8 @@ static abi_long host_to_target_data_inet_nlattr(struct nlattr *nlattr, } break; default: - gemu_log("Unknown host AF_INET type: %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown host AF_INET type: %d\n", + nlattr->nla_type); } return 0; } @@ -741,7 +747,8 @@ static abi_long host_to_target_data_inet6_nlattr(struct nlattr *nlattr, } break; default: - gemu_log("Unknown host AF_INET6 type: %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown host AF_INET6 type: %d\n", + nlattr->nla_type); } return 0; } @@ -759,7 +766,8 @@ static abi_long host_to_target_data_spec_nlattr(struct nlattr *nlattr, NULL, host_to_target_data_inet6_nlattr); default: - gemu_log("Unknown host AF_SPEC type: %d\n", nlattr->nla_type); + qemu_log_mask(LOG_UNIMP, "Unknown host AF_SPEC type: %d\n", + nlattr->nla_type); break; } return 0; @@ -780,7 +788,8 @@ static abi_long host_to_target_data_xdp_nlattr(struct nlattr *nlattr, *u32 = tswap32(*u32); break; default: - gemu_log("Unknown host XDP type: %d\n", nlattr->nla_type); + qemu_log_mask( + LOG_UNIMP, "Unknown host XDP type: %d\n", nlattr->nla_type); break; } return 0; @@ -920,7 +929,8 @@ static abi_long host_to_target_data_link_rtattr(struct rtattr *rtattr) NULL, host_to_target_data_xdp_nlattr); default: - gemu_log("Unknown host QEMU_IFLA type: %d\n", rtattr->rta_type); + qemu_log_mask(LOG_UNIMP, "Unknown host QEMU_IFLA type: %d\n", + rtattr->rta_type); break; } return 0; @@ -954,7 +964,8 @@ static abi_long host_to_target_data_addr_rtattr(struct rtattr *rtattr) ci->tstamp = tswap32(ci->tstamp); break; default: - gemu_log("Unknown host IFA type: %d\n", rtattr->rta_type); + qemu_log_mask( + LOG_UNIMP, "Unknown host IFA type: %d\n", rtattr->rta_type); break; } return 0; @@ -996,7 +1007,8 @@ static abi_long host_to_target_data_route_rtattr(struct rtattr *rtattr) #endif break; default: - gemu_log("Unknown host RTA type: %d\n", rtattr->rta_type); + qemu_log_mask( + LOG_UNIMP, "Unknown host RTA type: %d\n", rtattr->rta_type); break; } return 0; @@ -1111,7 +1123,8 @@ static abi_long target_to_host_data_link_rtattr(struct rtattr *rtattr) { switch (rtattr->rta_type) { default: - gemu_log("Unknown target QEMU_IFLA type: %d\n", rtattr->rta_type); + qemu_log_mask(LOG_UNIMP, "Unknown target QEMU_IFLA type: %d\n", + rtattr->rta_type); break; } return 0; @@ -1125,7 +1138,8 @@ static abi_long target_to_host_data_addr_rtattr(struct rtattr *rtattr) case IFA_ADDRESS: break; default: - gemu_log("Unknown target IFA type: %d\n", rtattr->rta_type); + qemu_log_mask(LOG_UNIMP, "Unknown target IFA type: %d\n", + rtattr->rta_type); break; } return 0; @@ -1147,7 +1161,8 @@ static abi_long target_to_host_data_route_rtattr(struct rtattr *rtattr) *u32 = tswap32(*u32); break; default: - gemu_log("Unknown target RTA type: %d\n", rtattr->rta_type); + qemu_log_mask(LOG_UNIMP, "Unknown target RTA type: %d\n", + rtattr->rta_type); break; } return 0; @@ -1232,8 +1247,8 @@ static abi_long host_to_target_data_audit(struct nlmsghdr *nlh) { switch (nlh->nlmsg_type) { default: - gemu_log("Unknown host audit message type %d\n", - nlh->nlmsg_type); + qemu_log_mask(LOG_UNIMP, "Unknown host audit message type %d\n", + nlh->nlmsg_type); return -TARGET_EINVAL; } return 0; @@ -1253,8 +1268,8 @@ static abi_long target_to_host_data_audit(struct nlmsghdr *nlh) case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: break; default: - gemu_log("Unknown target audit message type %d\n", - nlh->nlmsg_type); + qemu_log_mask(LOG_UNIMP, "Unknown target audit message type %d\n", + nlh->nlmsg_type); return -TARGET_EINVAL; } diff --git a/linux-user/ioctls.h b/linux-user/ioctls.h index 73dcc761e6..0defa1d8c1 100644 --- a/linux-user/ioctls.h +++ b/linux-user/ioctls.h @@ -461,6 +461,27 @@ IOCTL(SOUND_MIXER_WRITE_LOUD, IOC_W, MK_PTR(TYPE_INT)) IOCTL(SOUND_MIXER_WRITE_RECSRC, IOC_W, MK_PTR(TYPE_INT)) + IOCTL(SNDRV_TIMER_IOCTL_PVERSION, IOC_R, MK_PTR(TYPE_INT)) + IOCTL(SNDRV_TIMER_IOCTL_NEXT_DEVICE, IOC_RW, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_id))) + IOCTL(SNDRV_TIMER_IOCTL_GINFO, IOC_RW, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_ginfo))) + IOCTL(SNDRV_TIMER_IOCTL_GPARAMS, IOC_W, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_gparams))) + IOCTL(SNDRV_TIMER_IOCTL_GSTATUS, IOC_RW, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_gstatus))) + IOCTL(SNDRV_TIMER_IOCTL_SELECT, IOC_W, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_select))) + IOCTL(SNDRV_TIMER_IOCTL_INFO, IOC_R, MK_PTR(MK_STRUCT(STRUCT_snd_timer_info))) + IOCTL(SNDRV_TIMER_IOCTL_PARAMS, IOC_W, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_params))) + IOCTL(SNDRV_TIMER_IOCTL_STATUS, IOC_R, + MK_PTR(MK_STRUCT(STRUCT_snd_timer_status))) + IOCTL(SNDRV_TIMER_IOCTL_START, 0, TYPE_NULL) + IOCTL(SNDRV_TIMER_IOCTL_STOP, 0, TYPE_NULL) + IOCTL(SNDRV_TIMER_IOCTL_CONTINUE, 0, TYPE_NULL) + IOCTL(SNDRV_TIMER_IOCTL_PAUSE, 0, TYPE_NULL) + IOCTL(HDIO_GETGEO, IOC_R, MK_PTR(MK_STRUCT(STRUCT_hd_geometry))) IOCTL(HDIO_GET_UNMASKINTR, IOC_R, MK_PTR(TYPE_INT)) IOCTL(HDIO_GET_MULTCOUNT, IOC_R, MK_PTR(TYPE_INT)) diff --git a/linux-user/main.c b/linux-user/main.c index fba833aac9..22578b1633 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -61,6 +61,19 @@ unsigned long guest_base; int have_guest_base; /* + * Used to implement backwards-compatibility for the `-strace`, and + * QEMU_STRACE options. Without this, the QEMU_LOG can be overwritten by + * -strace, or vice versa. + */ +static bool enable_strace; + +/* + * The last log mask given by the user in an environment variable or argument. + * Used to support command line arguments overriding environment variables. + */ +static int last_log_mask; + +/* * When running 32-on-64 we should make sure we can fit all of the possible * guest address space into a contiguous chunk of virtual host memory. * @@ -99,15 +112,6 @@ const char *qemu_uname_release; by remapping the process stack directly at the right place */ unsigned long guest_stack_size = 8 * 1024 * 1024UL; -void gemu_log(const char *fmt, ...) -{ - va_list ap; - - va_start(ap, fmt); - vfprintf(stderr, fmt, ap); - va_end(ap); -} - #if defined(TARGET_I386) int cpu_get_pic_interrupt(CPUX86State *env) { @@ -223,15 +227,11 @@ static void handle_arg_help(const char *arg) static void handle_arg_log(const char *arg) { - int mask; - - mask = qemu_str_to_log_mask(arg); - if (!mask) { + last_log_mask = qemu_str_to_log_mask(arg); + if (!last_log_mask) { qemu_print_log_usage(stdout); exit(EXIT_FAILURE); } - qemu_log_needs_buffers(); - qemu_set_log(mask); } static void handle_arg_dfilter(const char *arg) @@ -375,7 +375,7 @@ static void handle_arg_singlestep(const char *arg) static void handle_arg_strace(const char *arg) { - do_strace = 1; + enable_strace = true; } static void handle_arg_version(const char *arg) @@ -629,6 +629,7 @@ int main(int argc, char **argv, char **envp) int i; int ret; int execfd; + int log_mask; unsigned long max_reserved_va; error_init(argv[0]); @@ -661,6 +662,12 @@ int main(int argc, char **argv, char **envp) optind = parse_args(argc, argv); + log_mask = last_log_mask | (enable_strace ? LOG_STRACE : 0); + if (log_mask) { + qemu_log_needs_buffers(); + qemu_set_log(log_mask); + } + if (!trace_init_backends()) { exit(1); } diff --git a/linux-user/qemu.h b/linux-user/qemu.h index 560a68090e..792c74290f 100644 --- a/linux-user/qemu.h +++ b/linux-user/qemu.h @@ -211,7 +211,6 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5, abi_long arg6, abi_long arg7, abi_long arg8); -void gemu_log(const char *fmt, ...) GCC_FMT_ATTR(1, 2); extern __thread CPUState *thread_cpu; void cpu_loop(CPUArchState *env); const char *target_strerror(int err); @@ -386,7 +385,6 @@ void print_syscall_ret(int num, abi_long arg1); * --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} --- */ void print_taken_signal(int target_signum, const target_siginfo_t *tinfo); -extern int do_strace; /* signal.c */ void process_pending_signals(CPUArchState *cpu_env); diff --git a/linux-user/signal.c b/linux-user/signal.c index 94259dd070..8cf51ffecd 100644 --- a/linux-user/signal.c +++ b/linux-user/signal.c @@ -934,7 +934,7 @@ static void handle_pending_signal(CPUArchState *cpu_env, int sig, handler = sa->_sa_handler; } - if (do_strace) { + if (unlikely(qemu_loglevel_mask(LOG_STRACE))) { print_taken_signal(sig, &k->info); } diff --git a/linux-user/strace.c b/linux-user/strace.c index 3d4d684450..4f7130b2ff 100644 --- a/linux-user/strace.c +++ b/linux-user/strace.c @@ -12,8 +12,6 @@ #include <sched.h> #include "qemu.h" -int do_strace=0; - struct syscallname { int nr; const char *name; @@ -80,7 +78,7 @@ print_ipc_cmd(int cmd) { #define output_cmd(val) \ if( cmd == val ) { \ - gemu_log(#val); \ + qemu_log(#val); \ return; \ } @@ -120,7 +118,7 @@ if( cmd == val ) { \ output_cmd( IPC_RMID ); /* Some value we don't recognize */ - gemu_log("%d",cmd); + qemu_log("%d", cmd); } static void @@ -151,7 +149,7 @@ print_signal(abi_ulong arg, int last) print_raw_param("%ld", arg, last); return; } - gemu_log("%s%s", signal_name, get_comma(last)); + qemu_log("%s%s", signal_name, get_comma(last)); } static void print_si_code(int arg) @@ -184,10 +182,10 @@ static void print_si_code(int arg) codename = "SI_TKILL"; break; default: - gemu_log("%d", arg); + qemu_log("%d", arg); return; } - gemu_log("%s", codename); + qemu_log("%s", codename); } static void get_target_siginfo(target_siginfo_t *tinfo, @@ -288,33 +286,33 @@ static void print_siginfo(const target_siginfo_t *tinfo) int si_type = extract32(tinfo->si_code, 16, 16); int si_code = sextract32(tinfo->si_code, 0, 16); - gemu_log("{si_signo="); + qemu_log("{si_signo="); print_signal(tinfo->si_signo, 1); - gemu_log(", si_code="); + qemu_log(", si_code="); print_si_code(si_code); switch (si_type) { case QEMU_SI_KILL: - gemu_log(", si_pid=%u, si_uid=%u", + qemu_log(", si_pid=%u, si_uid=%u", (unsigned int)tinfo->_sifields._kill._pid, (unsigned int)tinfo->_sifields._kill._uid); break; case QEMU_SI_TIMER: - gemu_log(", si_timer1=%u, si_timer2=%u", + qemu_log(", si_timer1=%u, si_timer2=%u", tinfo->_sifields._timer._timer1, tinfo->_sifields._timer._timer2); break; case QEMU_SI_POLL: - gemu_log(", si_band=%d, si_fd=%d", + qemu_log(", si_band=%d, si_fd=%d", tinfo->_sifields._sigpoll._band, tinfo->_sifields._sigpoll._fd); break; case QEMU_SI_FAULT: - gemu_log(", si_addr="); + qemu_log(", si_addr="); print_pointer(tinfo->_sifields._sigfault._addr, 1); break; case QEMU_SI_CHLD: - gemu_log(", si_pid=%u, si_uid=%u, si_status=%d" + qemu_log(", si_pid=%u, si_uid=%u, si_status=%d" ", si_utime=" TARGET_ABI_FMT_ld ", si_stime=" TARGET_ABI_FMT_ld, (unsigned int)(tinfo->_sifields._sigchld._pid), @@ -324,7 +322,7 @@ static void print_siginfo(const target_siginfo_t *tinfo) tinfo->_sifields._sigchld._stime); break; case QEMU_SI_RT: - gemu_log(", si_pid=%u, si_uid=%u, si_sigval=" TARGET_ABI_FMT_ld, + qemu_log(", si_pid=%u, si_uid=%u, si_sigval=" TARGET_ABI_FMT_ld, (unsigned int)tinfo->_sifields._rt._pid, (unsigned int)tinfo->_sifields._rt._uid, tinfo->_sifields._rt._sigval.sival_ptr); @@ -332,7 +330,7 @@ static void print_siginfo(const target_siginfo_t *tinfo) default: g_assert_not_reached(); } - gemu_log("}"); + qemu_log("}"); } static void @@ -349,76 +347,76 @@ print_sockaddr(abi_ulong addr, abi_long addrlen, int last) case AF_UNIX: { struct target_sockaddr_un *un = (struct target_sockaddr_un *)sa; int i; - gemu_log("{sun_family=AF_UNIX,sun_path=\""); + qemu_log("{sun_family=AF_UNIX,sun_path=\""); for (i = 0; i < addrlen - offsetof(struct target_sockaddr_un, sun_path) && un->sun_path[i]; i++) { - gemu_log("%c", un->sun_path[i]); + qemu_log("%c", un->sun_path[i]); } - gemu_log("\"}"); + qemu_log("\"}"); break; } case AF_INET: { struct target_sockaddr_in *in = (struct target_sockaddr_in *)sa; uint8_t *c = (uint8_t *)&in->sin_addr.s_addr; - gemu_log("{sin_family=AF_INET,sin_port=htons(%d),", + qemu_log("{sin_family=AF_INET,sin_port=htons(%d),", ntohs(in->sin_port)); - gemu_log("sin_addr=inet_addr(\"%d.%d.%d.%d\")", + qemu_log("sin_addr=inet_addr(\"%d.%d.%d.%d\")", c[0], c[1], c[2], c[3]); - gemu_log("}"); + qemu_log("}"); break; } case AF_PACKET: { struct target_sockaddr_ll *ll = (struct target_sockaddr_ll *)sa; uint8_t *c = (uint8_t *)&ll->sll_addr; - gemu_log("{sll_family=AF_PACKET," + qemu_log("{sll_family=AF_PACKET," "sll_protocol=htons(0x%04x),if%d,pkttype=", ntohs(ll->sll_protocol), ll->sll_ifindex); switch (ll->sll_pkttype) { case PACKET_HOST: - gemu_log("PACKET_HOST"); + qemu_log("PACKET_HOST"); break; case PACKET_BROADCAST: - gemu_log("PACKET_BROADCAST"); + qemu_log("PACKET_BROADCAST"); break; case PACKET_MULTICAST: - gemu_log("PACKET_MULTICAST"); + qemu_log("PACKET_MULTICAST"); break; case PACKET_OTHERHOST: - gemu_log("PACKET_OTHERHOST"); + qemu_log("PACKET_OTHERHOST"); break; case PACKET_OUTGOING: - gemu_log("PACKET_OUTGOING"); + qemu_log("PACKET_OUTGOING"); break; default: - gemu_log("%d", ll->sll_pkttype); + qemu_log("%d", ll->sll_pkttype); break; } - gemu_log(",sll_addr=%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x", + qemu_log(",sll_addr=%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x", c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]); - gemu_log("}"); + qemu_log("}"); break; } case AF_NETLINK: { struct target_sockaddr_nl *nl = (struct target_sockaddr_nl *)sa; - gemu_log("{nl_family=AF_NETLINK,nl_pid=%u,nl_groups=%u}", + qemu_log("{nl_family=AF_NETLINK,nl_pid=%u,nl_groups=%u}", tswap32(nl->nl_pid), tswap32(nl->nl_groups)); break; } default: - gemu_log("{sa_family=%d, sa_data={", sa->sa_family); + qemu_log("{sa_family=%d, sa_data={", sa->sa_family); for (i = 0; i < 13; i++) { - gemu_log("%02x, ", sa->sa_data[i]); + qemu_log("%02x, ", sa->sa_data[i]); } - gemu_log("%02x}", sa->sa_data[i]); - gemu_log("}"); + qemu_log("%02x}", sa->sa_data[i]); + qemu_log("}"); break; } unlock_user(sa, addr, 0); } else { print_raw_param("0x"TARGET_ABI_FMT_lx, addr, 0); } - gemu_log(", "TARGET_ABI_FMT_ld"%s", addrlen, get_comma(last)); + qemu_log(", "TARGET_ABI_FMT_ld"%s", addrlen, get_comma(last)); } static void @@ -426,19 +424,19 @@ print_socket_domain(int domain) { switch (domain) { case PF_UNIX: - gemu_log("PF_UNIX"); + qemu_log("PF_UNIX"); break; case PF_INET: - gemu_log("PF_INET"); + qemu_log("PF_INET"); break; case PF_NETLINK: - gemu_log("PF_NETLINK"); + qemu_log("PF_NETLINK"); break; case PF_PACKET: - gemu_log("PF_PACKET"); + qemu_log("PF_PACKET"); break; default: - gemu_log("%d", domain); + qemu_log("%d", domain); break; } } @@ -448,22 +446,22 @@ print_socket_type(int type) { switch (type) { case TARGET_SOCK_DGRAM: - gemu_log("SOCK_DGRAM"); + qemu_log("SOCK_DGRAM"); break; case TARGET_SOCK_STREAM: - gemu_log("SOCK_STREAM"); + qemu_log("SOCK_STREAM"); break; case TARGET_SOCK_RAW: - gemu_log("SOCK_RAW"); + qemu_log("SOCK_RAW"); break; case TARGET_SOCK_RDM: - gemu_log("SOCK_RDM"); + qemu_log("SOCK_RDM"); break; case TARGET_SOCK_SEQPACKET: - gemu_log("SOCK_SEQPACKET"); + qemu_log("SOCK_SEQPACKET"); break; case TARGET_SOCK_PACKET: - gemu_log("SOCK_PACKET"); + qemu_log("SOCK_PACKET"); break; } } @@ -475,10 +473,10 @@ print_socket_protocol(int domain, int type, int protocol) (domain == AF_INET && type == TARGET_SOCK_PACKET)) { switch (protocol) { case 0x0003: - gemu_log("ETH_P_ALL"); + qemu_log("ETH_P_ALL"); break; default: - gemu_log("%d", protocol); + qemu_log("%d", protocol); } return; } @@ -486,25 +484,25 @@ print_socket_protocol(int domain, int type, int protocol) if (domain == PF_NETLINK) { switch (protocol) { case NETLINK_ROUTE: - gemu_log("NETLINK_ROUTE"); + qemu_log("NETLINK_ROUTE"); break; case NETLINK_AUDIT: - gemu_log("NETLINK_AUDIT"); + qemu_log("NETLINK_AUDIT"); break; case NETLINK_NETFILTER: - gemu_log("NETLINK_NETFILTER"); + qemu_log("NETLINK_NETFILTER"); break; case NETLINK_KOBJECT_UEVENT: - gemu_log("NETLINK_KOBJECT_UEVENT"); + qemu_log("NETLINK_KOBJECT_UEVENT"); break; case NETLINK_RDMA: - gemu_log("NETLINK_RDMA"); + qemu_log("NETLINK_RDMA"); break; case NETLINK_CRYPTO: - gemu_log("NETLINK_CRYPTO"); + qemu_log("NETLINK_CRYPTO"); break; default: - gemu_log("%d", protocol); + qemu_log("%d", protocol); break; } return; @@ -512,19 +510,19 @@ print_socket_protocol(int domain, int type, int protocol) switch (protocol) { case IPPROTO_IP: - gemu_log("IPPROTO_IP"); + qemu_log("IPPROTO_IP"); break; case IPPROTO_TCP: - gemu_log("IPPROTO_TCP"); + qemu_log("IPPROTO_TCP"); break; case IPPROTO_UDP: - gemu_log("IPPROTO_UDP"); + qemu_log("IPPROTO_UDP"); break; case IPPROTO_RAW: - gemu_log("IPPROTO_RAW"); + qemu_log("IPPROTO_RAW"); break; default: - gemu_log("%d", protocol); + qemu_log("%d", protocol); break; } } @@ -536,7 +534,7 @@ print_fdset(int n, abi_ulong target_fds_addr) { int i; - gemu_log("["); + qemu_log("["); if( target_fds_addr ) { abi_long *target_fds; @@ -550,11 +548,11 @@ print_fdset(int n, abi_ulong target_fds_addr) for (i=n; i>=0; i--) { if ((tswapal(target_fds[i / TARGET_ABI_BITS]) >> (i & (TARGET_ABI_BITS - 1))) & 1) - gemu_log("%d,", i ); + qemu_log("%d,", i); } unlock_user(target_fds, target_fds_addr, 0); } - gemu_log("]"); + qemu_log("]"); } #endif @@ -578,46 +576,46 @@ print_clockid(int clockid, int last) { switch (clockid) { case TARGET_CLOCK_REALTIME: - gemu_log("CLOCK_REALTIME"); + qemu_log("CLOCK_REALTIME"); break; case TARGET_CLOCK_MONOTONIC: - gemu_log("CLOCK_MONOTONIC"); + qemu_log("CLOCK_MONOTONIC"); break; case TARGET_CLOCK_PROCESS_CPUTIME_ID: - gemu_log("CLOCK_PROCESS_CPUTIME_ID"); + qemu_log("CLOCK_PROCESS_CPUTIME_ID"); break; case TARGET_CLOCK_THREAD_CPUTIME_ID: - gemu_log("CLOCK_THREAD_CPUTIME_ID"); + qemu_log("CLOCK_THREAD_CPUTIME_ID"); break; case TARGET_CLOCK_MONOTONIC_RAW: - gemu_log("CLOCK_MONOTONIC_RAW"); + qemu_log("CLOCK_MONOTONIC_RAW"); break; case TARGET_CLOCK_REALTIME_COARSE: - gemu_log("CLOCK_REALTIME_COARSE"); + qemu_log("CLOCK_REALTIME_COARSE"); break; case TARGET_CLOCK_MONOTONIC_COARSE: - gemu_log("CLOCK_MONOTONIC_COARSE"); + qemu_log("CLOCK_MONOTONIC_COARSE"); break; case TARGET_CLOCK_BOOTTIME: - gemu_log("CLOCK_BOOTTIME"); + qemu_log("CLOCK_BOOTTIME"); break; case TARGET_CLOCK_REALTIME_ALARM: - gemu_log("CLOCK_REALTIME_ALARM"); + qemu_log("CLOCK_REALTIME_ALARM"); break; case TARGET_CLOCK_BOOTTIME_ALARM: - gemu_log("CLOCK_BOOTTIME_ALARM"); + qemu_log("CLOCK_BOOTTIME_ALARM"); break; case TARGET_CLOCK_SGI_CYCLE: - gemu_log("CLOCK_SGI_CYCLE"); + qemu_log("CLOCK_SGI_CYCLE"); break; case TARGET_CLOCK_TAI: - gemu_log("CLOCK_TAI"); + qemu_log("CLOCK_TAI"); break; default: - gemu_log("%d", clockid); + qemu_log("%d", clockid); break; } - gemu_log("%s", get_comma(last)); + qemu_log("%s", get_comma(last)); } #endif @@ -638,15 +636,15 @@ print_newselect(const struct syscallname *name, abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5, abi_long arg6) { - gemu_log("%s(" TARGET_ABI_FMT_ld ",", name->name, arg1); + qemu_log("%s(" TARGET_ABI_FMT_ld ",", name->name, arg1); print_fdset(arg1, arg2); - gemu_log(","); + qemu_log(","); print_fdset(arg1, arg3); - gemu_log(","); + qemu_log(","); print_fdset(arg1, arg4); - gemu_log(","); + qemu_log(","); print_timeval(arg5, 1); - gemu_log(")"); + qemu_log(")"); /* save for use in the return output function below */ newselect_arg1=arg1; @@ -663,9 +661,10 @@ print_semctl(const struct syscallname *name, abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5, abi_long arg6) { - gemu_log("%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ",", name->name, arg1, arg2); + qemu_log("%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ",", + name->name, arg1, arg2); print_ipc_cmd(arg3); - gemu_log(",0x" TARGET_ABI_FMT_lx ")", arg4); + qemu_log(",0x" TARGET_ABI_FMT_lx ")", arg4); } #endif @@ -679,7 +678,7 @@ print_execve(const struct syscallname *name, if (!(s = lock_user_string(arg1))) return; - gemu_log("%s(\"%s\",{", name->name, s); + qemu_log("%s(\"%s\",{", name->name, s); unlock_user(s, arg1, 0); for (arg_ptr_addr = arg2; ; arg_ptr_addr += sizeof(abi_ulong)) { @@ -693,12 +692,12 @@ print_execve(const struct syscallname *name, if (!arg_addr) break; if ((s = lock_user_string(arg_addr))) { - gemu_log("\"%s\",", s); + qemu_log("\"%s\",", s); unlock_user(s, arg_addr, 0); } } - gemu_log("NULL})"); + qemu_log("NULL})"); } #ifdef TARGET_NR_ipc @@ -709,12 +708,18 @@ print_ipc(const struct syscallname *name, { switch(arg1) { case IPCOP_semctl: - gemu_log("semctl(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ",", arg1, arg2); + qemu_log("semctl(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ",", + arg1, arg2); print_ipc_cmd(arg3); - gemu_log(",0x" TARGET_ABI_FMT_lx ")", arg4); + qemu_log(",0x" TARGET_ABI_FMT_lx ")", arg4); break; default: - gemu_log("%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ")", + qemu_log(("%s(" + TARGET_ABI_FMT_ld "," + TARGET_ABI_FMT_ld "," + TARGET_ABI_FMT_ld "," + TARGET_ABI_FMT_ld + ")"), name->name, arg1, arg2, arg3, arg4); } } @@ -733,9 +738,9 @@ print_syscall_ret_addr(const struct syscallname *name, abi_long ret) errstr = target_strerror(-ret); } if (errstr) { - gemu_log(" = -1 errno=%d (%s)\n", (int)-ret, errstr); + qemu_log(" = -1 errno=%d (%s)\n", (int)-ret, errstr); } else { - gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret); + qemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret); } } @@ -743,7 +748,7 @@ print_syscall_ret_addr(const struct syscallname *name, abi_long ret) static void print_syscall_ret_raw(struct syscallname *name, abi_long ret) { - gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret); + qemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret); } #endif @@ -751,15 +756,15 @@ print_syscall_ret_raw(struct syscallname *name, abi_long ret) static void print_syscall_ret_newselect(const struct syscallname *name, abi_long ret) { - gemu_log(" = 0x" TARGET_ABI_FMT_lx " (", ret); + qemu_log(" = 0x" TARGET_ABI_FMT_lx " (", ret); print_fdset(newselect_arg1,newselect_arg2); - gemu_log(","); + qemu_log(","); print_fdset(newselect_arg1,newselect_arg3); - gemu_log(","); + qemu_log(","); print_fdset(newselect_arg1,newselect_arg4); - gemu_log(","); + qemu_log(","); print_timeval(newselect_arg5, 1); - gemu_log(")\n"); + qemu_log(")\n"); } #endif @@ -775,38 +780,38 @@ print_syscall_ret_adjtimex(const struct syscallname *name, abi_long ret) { const char *errstr = NULL; - gemu_log(" = "); + qemu_log(" = "); if (ret < 0) { - gemu_log("-1 errno=%d", errno); + qemu_log("-1 errno=%d", errno); errstr = target_strerror(-ret); if (errstr) { - gemu_log(" (%s)", errstr); + qemu_log(" (%s)", errstr); } } else { - gemu_log(TARGET_ABI_FMT_ld, ret); + qemu_log(TARGET_ABI_FMT_ld, ret); switch (ret) { case TARGET_TIME_OK: - gemu_log(" TIME_OK (clock synchronized, no leap second)"); + qemu_log(" TIME_OK (clock synchronized, no leap second)"); break; case TARGET_TIME_INS: - gemu_log(" TIME_INS (insert leap second)"); + qemu_log(" TIME_INS (insert leap second)"); break; case TARGET_TIME_DEL: - gemu_log(" TIME_DEL (delete leap second)"); + qemu_log(" TIME_DEL (delete leap second)"); break; case TARGET_TIME_OOP: - gemu_log(" TIME_OOP (leap second in progress)"); + qemu_log(" TIME_OOP (leap second in progress)"); break; case TARGET_TIME_WAIT: - gemu_log(" TIME_WAIT (leap second has occurred)"); + qemu_log(" TIME_WAIT (leap second has occurred)"); break; case TARGET_TIME_ERROR: - gemu_log(" TIME_ERROR (clock not synchronized)"); + qemu_log(" TIME_ERROR (clock not synchronized)"); break; } } - gemu_log("\n"); + qemu_log("\n"); } UNUSED static struct flags access_flags[] = { @@ -1104,12 +1109,12 @@ print_flags(const struct flags *f, abi_long flags, int last) int n; if ((flags == 0) && (f->f_value == 0)) { - gemu_log("%s%s", f->f_string, get_comma(last)); + qemu_log("%s%s", f->f_string, get_comma(last)); return; } for (n = 0; f->f_string != NULL; f++) { if ((f->f_value != 0) && ((flags & f->f_value) == f->f_value)) { - gemu_log("%s%s", sep, f->f_string); + qemu_log("%s%s", sep, f->f_string); flags &= ~f->f_value; sep = "|"; n++; @@ -1119,13 +1124,13 @@ print_flags(const struct flags *f, abi_long flags, int last) if (n > 0) { /* print rest of the flags as numeric */ if (flags != 0) { - gemu_log("%s%#x%s", sep, (unsigned int)flags, get_comma(last)); + qemu_log("%s%#x%s", sep, (unsigned int)flags, get_comma(last)); } else { - gemu_log("%s", get_comma(last)); + qemu_log("%s", get_comma(last)); } } else { /* no string version of flags found, print them in hex then */ - gemu_log("%#x%s", (unsigned int)flags, get_comma(last)); + qemu_log("%#x%s", (unsigned int)flags, get_comma(last)); } } @@ -1134,11 +1139,11 @@ print_at_dirfd(abi_long dirfd, int last) { #ifdef AT_FDCWD if (dirfd == AT_FDCWD) { - gemu_log("AT_FDCWD%s", get_comma(last)); + qemu_log("AT_FDCWD%s", get_comma(last)); return; } #endif - gemu_log("%d%s", (int)dirfd, get_comma(last)); + qemu_log("%d%s", (int)dirfd, get_comma(last)); } static void @@ -1149,7 +1154,7 @@ print_file_mode(abi_long mode, int last) for (m = &mode_flags[0]; m->f_string != NULL; m++) { if ((m->f_value & mode) == m->f_value) { - gemu_log("%s%s", m->f_string, sep); + qemu_log("%s%s", m->f_string, sep); sep = "|"; mode &= ~m->f_value; break; @@ -1159,9 +1164,9 @@ print_file_mode(abi_long mode, int last) mode &= ~S_IFMT; /* print rest of the mode as octal */ if (mode != 0) - gemu_log("%s%#o", sep, (unsigned int)mode); + qemu_log("%s%#o", sep, (unsigned int)mode); - gemu_log("%s", get_comma(last)); + qemu_log("%s", get_comma(last)); } static void @@ -1170,17 +1175,17 @@ print_open_flags(abi_long flags, int last) print_flags(open_access_flags, flags & TARGET_O_ACCMODE, 1); flags &= ~TARGET_O_ACCMODE; if (flags == 0) { - gemu_log("%s", get_comma(last)); + qemu_log("%s", get_comma(last)); return; } - gemu_log("|"); + qemu_log("|"); print_flags(open_flags, flags, last); } static void print_syscall_prologue(const struct syscallname *sc) { - gemu_log("%s(", sc->name); + qemu_log("%s(", sc->name); } /*ARGSUSED*/ @@ -1188,7 +1193,7 @@ static void print_syscall_epilogue(const struct syscallname *sc) { (void)sc; - gemu_log(")"); + qemu_log(")"); } static void @@ -1197,7 +1202,7 @@ print_string(abi_long addr, int last) char *s; if ((s = lock_user_string(addr)) != NULL) { - gemu_log("\"%s\"%s", s, get_comma(last)); + qemu_log("\"%s\"%s", s, get_comma(last)); unlock_user(s, addr, 0); } else { /* can't get string out of it, so print it as pointer */ @@ -1214,20 +1219,20 @@ print_buf(abi_long addr, abi_long len, int last) s = lock_user(VERIFY_READ, addr, len, 1); if (s) { - gemu_log("\""); + qemu_log("\""); for (i = 0; i < MAX_PRINT_BUF && i < len; i++) { if (isprint(s[i])) { - gemu_log("%c", s[i]); + qemu_log("%c", s[i]); } else { - gemu_log("\\%o", s[i]); + qemu_log("\\%o", s[i]); } } - gemu_log("\""); + qemu_log("\""); if (i != len) { - gemu_log("..."); + qemu_log("..."); } if (!last) { - gemu_log(","); + qemu_log(","); } unlock_user(s, addr, 0); } else { @@ -1245,16 +1250,16 @@ print_raw_param(const char *fmt, abi_long param, int last) char format[64]; (void) snprintf(format, sizeof (format), "%s%s", fmt, get_comma(last)); - gemu_log(format, param); + qemu_log(format, param); } static void print_pointer(abi_long p, int last) { if (p == 0) - gemu_log("NULL%s", get_comma(last)); + qemu_log("NULL%s", get_comma(last)); else - gemu_log("0x" TARGET_ABI_FMT_lx "%s", p, get_comma(last)); + qemu_log("0x" TARGET_ABI_FMT_lx "%s", p, get_comma(last)); } /* @@ -1265,12 +1270,12 @@ static void print_number(abi_long addr, int last) { if (addr == 0) { - gemu_log("NULL%s", get_comma(last)); + qemu_log("NULL%s", get_comma(last)); } else { int num; get_user_s32(num, addr); - gemu_log("[%d]%s", num, get_comma(last)); + qemu_log("[%d]%s", num, get_comma(last)); } } @@ -1285,11 +1290,11 @@ print_timeval(abi_ulong tv_addr, int last) print_pointer(tv_addr, last); return; } - gemu_log("{" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "}%s", + qemu_log("{" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "}%s", tswapal(tv->tv_sec), tswapal(tv->tv_usec), get_comma(last)); unlock_user(tv, tv_addr, 0); } else - gemu_log("NULL%s", get_comma(last)); + qemu_log("NULL%s", get_comma(last)); } static void @@ -1303,11 +1308,11 @@ print_timezone(abi_ulong tz_addr, int last) print_pointer(tz_addr, last); return; } - gemu_log("{%d,%d}%s", tswap32(tz->tz_minuteswest), + qemu_log("{%d,%d}%s", tswap32(tz->tz_minuteswest), tswap32(tz->tz_dsttime), get_comma(last)); unlock_user(tz, tz_addr, 0); } else { - gemu_log("NULL%s", get_comma(last)); + qemu_log("NULL%s", get_comma(last)); } } @@ -1515,83 +1520,83 @@ print_fcntl(const struct syscallname *name, print_raw_param("%d", arg0, 0); switch(arg1) { case TARGET_F_DUPFD: - gemu_log("F_DUPFD,"); + qemu_log("F_DUPFD,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 1); break; case TARGET_F_GETFD: - gemu_log("F_GETFD"); + qemu_log("F_GETFD"); break; case TARGET_F_SETFD: - gemu_log("F_SETFD,"); + qemu_log("F_SETFD,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 1); break; case TARGET_F_GETFL: - gemu_log("F_GETFL"); + qemu_log("F_GETFL"); break; case TARGET_F_SETFL: - gemu_log("F_SETFL,"); + qemu_log("F_SETFL,"); print_open_flags(arg2, 1); break; case TARGET_F_GETLK: - gemu_log("F_GETLK,"); + qemu_log("F_GETLK,"); print_pointer(arg2, 1); break; case TARGET_F_SETLK: - gemu_log("F_SETLK,"); + qemu_log("F_SETLK,"); print_pointer(arg2, 1); break; case TARGET_F_SETLKW: - gemu_log("F_SETLKW,"); + qemu_log("F_SETLKW,"); print_pointer(arg2, 1); break; case TARGET_F_GETOWN: - gemu_log("F_GETOWN"); + qemu_log("F_GETOWN"); break; case TARGET_F_SETOWN: - gemu_log("F_SETOWN,"); + qemu_log("F_SETOWN,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 0); break; case TARGET_F_GETSIG: - gemu_log("F_GETSIG"); + qemu_log("F_GETSIG"); break; case TARGET_F_SETSIG: - gemu_log("F_SETSIG,"); + qemu_log("F_SETSIG,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 0); break; #if TARGET_ABI_BITS == 32 case TARGET_F_GETLK64: - gemu_log("F_GETLK64,"); + qemu_log("F_GETLK64,"); print_pointer(arg2, 1); break; case TARGET_F_SETLK64: - gemu_log("F_SETLK64,"); + qemu_log("F_SETLK64,"); print_pointer(arg2, 1); break; case TARGET_F_SETLKW64: - gemu_log("F_SETLKW64,"); + qemu_log("F_SETLKW64,"); print_pointer(arg2, 1); break; #endif case TARGET_F_SETLEASE: - gemu_log("F_SETLEASE,"); + qemu_log("F_SETLEASE,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 0); break; case TARGET_F_GETLEASE: - gemu_log("F_GETLEASE"); + qemu_log("F_GETLEASE"); break; case TARGET_F_SETPIPE_SZ: - gemu_log("F_SETPIPE_SZ,"); + qemu_log("F_SETPIPE_SZ,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 1); break; case TARGET_F_GETPIPE_SZ: - gemu_log("F_GETPIPE_SZ"); + qemu_log("F_GETPIPE_SZ"); break; case TARGET_F_DUPFD_CLOEXEC: - gemu_log("F_DUPFD_CLOEXEC,"); + qemu_log("F_DUPFD_CLOEXEC,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 1); break; case TARGET_F_NOTIFY: - gemu_log("F_NOTIFY,"); + qemu_log("F_NOTIFY,"); print_raw_param(TARGET_ABI_FMT_ld, arg2, 0); break; default: @@ -1679,7 +1684,7 @@ print__llseek(const struct syscallname *name, case SEEK_CUR: whence = "SEEK_CUR"; break; case SEEK_END: whence = "SEEK_END"; break; } - gemu_log("%s",whence); + qemu_log("%s", whence); print_syscall_epilogue(name); } #endif @@ -1694,9 +1699,9 @@ print_socket(const struct syscallname *name, print_syscall_prologue(name); print_socket_domain(domain); - gemu_log(","); + qemu_log(","); print_socket_type(type); - gemu_log(","); + qemu_log(","); if (domain == AF_PACKET || (domain == AF_INET && type == TARGET_SOCK_PACKET)) { protocol = tswap16(protocol); @@ -1728,17 +1733,17 @@ static void do_print_socket(const char *name, abi_long arg1) get_user_ualx(domain, arg1, 0); get_user_ualx(type, arg1, 1); get_user_ualx(protocol, arg1, 2); - gemu_log("%s(", name); + qemu_log("%s(", name); print_socket_domain(domain); - gemu_log(","); + qemu_log(","); print_socket_type(type); - gemu_log(","); + qemu_log(","); if (domain == AF_PACKET || (domain == AF_INET && type == TARGET_SOCK_PACKET)) { protocol = tswap16(protocol); } print_socket_protocol(domain, type, protocol); - gemu_log(")"); + qemu_log(")"); } static void do_print_sockaddr(const char *name, abi_long arg1) @@ -1749,10 +1754,10 @@ static void do_print_sockaddr(const char *name, abi_long arg1) get_user_ualx(addr, arg1, 1); get_user_ualx(addrlen, arg1, 2); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); print_sockaddr(addr, addrlen, 0); - gemu_log(")"); + qemu_log(")"); } static void do_print_listen(const char *name, abi_long arg1) @@ -1762,10 +1767,10 @@ static void do_print_listen(const char *name, abi_long arg1) get_user_ualx(sockfd, arg1, 0); get_user_ualx(backlog, arg1, 1); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); print_raw_param(TARGET_ABI_FMT_ld, backlog, 1); - gemu_log(")"); + qemu_log(")"); } static void do_print_socketpair(const char *name, abi_long arg1) @@ -1777,15 +1782,15 @@ static void do_print_socketpair(const char *name, abi_long arg1) get_user_ualx(protocol, arg1, 2); get_user_ualx(tab, arg1, 3); - gemu_log("%s(", name); + qemu_log("%s(", name); print_socket_domain(domain); - gemu_log(","); + qemu_log(","); print_socket_type(type); - gemu_log(","); + qemu_log(","); print_socket_protocol(domain, type, protocol); - gemu_log(","); + qemu_log(","); print_raw_param(TARGET_ABI_FMT_lx, tab, 1); - gemu_log(")"); + qemu_log(")"); } static void do_print_sendrecv(const char *name, abi_long arg1) @@ -1797,12 +1802,12 @@ static void do_print_sendrecv(const char *name, abi_long arg1) get_user_ualx(len, arg1, 2); get_user_ualx(flags, arg1, 3); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); print_buf(msg, len, 0); print_raw_param(TARGET_ABI_FMT_ld, len, 0); print_flags(msg_flags, flags, 1); - gemu_log(")"); + qemu_log(")"); } static void do_print_msgaddr(const char *name, abi_long arg1) @@ -1816,13 +1821,13 @@ static void do_print_msgaddr(const char *name, abi_long arg1) get_user_ualx(addr, arg1, 4); get_user_ualx(addrlen, arg1, 5); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); print_buf(msg, len, 0); print_raw_param(TARGET_ABI_FMT_ld, len, 0); print_flags(msg_flags, flags, 0); print_sockaddr(addr, addrlen, 0); - gemu_log(")"); + qemu_log(")"); } static void do_print_shutdown(const char *name, abi_long arg1) @@ -1832,23 +1837,23 @@ static void do_print_shutdown(const char *name, abi_long arg1) get_user_ualx(sockfd, arg1, 0); get_user_ualx(how, arg1, 1); - gemu_log("shutdown("); + qemu_log("shutdown("); print_sockfd(sockfd, 0); switch (how) { case SHUT_RD: - gemu_log("SHUT_RD"); + qemu_log("SHUT_RD"); break; case SHUT_WR: - gemu_log("SHUT_WR"); + qemu_log("SHUT_WR"); break; case SHUT_RDWR: - gemu_log("SHUT_RDWR"); + qemu_log("SHUT_RDWR"); break; default: print_raw_param(TARGET_ABI_FMT_ld, how, 1); break; } - gemu_log(")"); + qemu_log(")"); } static void do_print_msg(const char *name, abi_long arg1) @@ -1859,11 +1864,11 @@ static void do_print_msg(const char *name, abi_long arg1) get_user_ualx(msg, arg1, 1); get_user_ualx(flags, arg1, 2); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); print_pointer(msg, 0); print_flags(msg_flags, flags, 1); - gemu_log(")"); + qemu_log(")"); } static void do_print_sockopt(const char *name, abi_long arg1) @@ -1876,113 +1881,113 @@ static void do_print_sockopt(const char *name, abi_long arg1) get_user_ualx(optval, arg1, 3); get_user_ualx(optlen, arg1, 4); - gemu_log("%s(", name); + qemu_log("%s(", name); print_sockfd(sockfd, 0); switch (level) { case SOL_TCP: - gemu_log("SOL_TCP,"); + qemu_log("SOL_TCP,"); print_raw_param(TARGET_ABI_FMT_ld, optname, 0); print_pointer(optval, 0); break; case SOL_IP: - gemu_log("SOL_IP,"); + qemu_log("SOL_IP,"); print_raw_param(TARGET_ABI_FMT_ld, optname, 0); print_pointer(optval, 0); break; case SOL_RAW: - gemu_log("SOL_RAW,"); + qemu_log("SOL_RAW,"); print_raw_param(TARGET_ABI_FMT_ld, optname, 0); print_pointer(optval, 0); break; case TARGET_SOL_SOCKET: - gemu_log("SOL_SOCKET,"); + qemu_log("SOL_SOCKET,"); switch (optname) { case TARGET_SO_DEBUG: - gemu_log("SO_DEBUG,"); + qemu_log("SO_DEBUG,"); print_optint: print_number(optval, 0); break; case TARGET_SO_REUSEADDR: - gemu_log("SO_REUSEADDR,"); + qemu_log("SO_REUSEADDR,"); goto print_optint; case TARGET_SO_REUSEPORT: - gemu_log("SO_REUSEPORT,"); + qemu_log("SO_REUSEPORT,"); goto print_optint; case TARGET_SO_TYPE: - gemu_log("SO_TYPE,"); + qemu_log("SO_TYPE,"); goto print_optint; case TARGET_SO_ERROR: - gemu_log("SO_ERROR,"); + qemu_log("SO_ERROR,"); goto print_optint; case TARGET_SO_DONTROUTE: - gemu_log("SO_DONTROUTE,"); + qemu_log("SO_DONTROUTE,"); goto print_optint; case TARGET_SO_BROADCAST: - gemu_log("SO_BROADCAST,"); + qemu_log("SO_BROADCAST,"); goto print_optint; case TARGET_SO_SNDBUF: - gemu_log("SO_SNDBUF,"); + qemu_log("SO_SNDBUF,"); goto print_optint; case TARGET_SO_RCVBUF: - gemu_log("SO_RCVBUF,"); + qemu_log("SO_RCVBUF,"); goto print_optint; case TARGET_SO_KEEPALIVE: - gemu_log("SO_KEEPALIVE,"); + qemu_log("SO_KEEPALIVE,"); goto print_optint; case TARGET_SO_OOBINLINE: - gemu_log("SO_OOBINLINE,"); + qemu_log("SO_OOBINLINE,"); goto print_optint; case TARGET_SO_NO_CHECK: - gemu_log("SO_NO_CHECK,"); + qemu_log("SO_NO_CHECK,"); goto print_optint; case TARGET_SO_PRIORITY: - gemu_log("SO_PRIORITY,"); + qemu_log("SO_PRIORITY,"); goto print_optint; case TARGET_SO_BSDCOMPAT: - gemu_log("SO_BSDCOMPAT,"); + qemu_log("SO_BSDCOMPAT,"); goto print_optint; case TARGET_SO_PASSCRED: - gemu_log("SO_PASSCRED,"); + qemu_log("SO_PASSCRED,"); goto print_optint; case TARGET_SO_TIMESTAMP: - gemu_log("SO_TIMESTAMP,"); + qemu_log("SO_TIMESTAMP,"); goto print_optint; case TARGET_SO_RCVLOWAT: - gemu_log("SO_RCVLOWAT,"); + qemu_log("SO_RCVLOWAT,"); goto print_optint; case TARGET_SO_RCVTIMEO: - gemu_log("SO_RCVTIMEO,"); + qemu_log("SO_RCVTIMEO,"); print_timeval(optval, 0); break; case TARGET_SO_SNDTIMEO: - gemu_log("SO_SNDTIMEO,"); + qemu_log("SO_SNDTIMEO,"); print_timeval(optval, 0); break; case TARGET_SO_ATTACH_FILTER: { struct target_sock_fprog *fprog; - gemu_log("SO_ATTACH_FILTER,"); + qemu_log("SO_ATTACH_FILTER,"); if (lock_user_struct(VERIFY_READ, fprog, optval, 0)) { struct target_sock_filter *filter; - gemu_log("{"); + qemu_log("{"); if (lock_user_struct(VERIFY_READ, filter, tswapal(fprog->filter), 0)) { int i; for (i = 0; i < tswap16(fprog->len) - 1; i++) { - gemu_log("[%d]{0x%x,%d,%d,0x%x},", + qemu_log("[%d]{0x%x,%d,%d,0x%x},", i, tswap16(filter[i].code), filter[i].jt, filter[i].jf, tswap32(filter[i].k)); } - gemu_log("[%d]{0x%x,%d,%d,0x%x}", + qemu_log("[%d]{0x%x,%d,%d,0x%x}", i, tswap16(filter[i].code), filter[i].jt, filter[i].jf, tswap32(filter[i].k)); } else { - gemu_log(TARGET_ABI_FMT_lx, tswapal(fprog->filter)); + qemu_log(TARGET_ABI_FMT_lx, tswapal(fprog->filter)); } - gemu_log(",%d},", tswap16(fprog->len)); + qemu_log(",%d},", tswap16(fprog->len)); unlock_user(fprog, optval, 0); } else { print_pointer(optval, 0); @@ -2002,7 +2007,7 @@ print_optint: break; } print_raw_param(TARGET_ABI_FMT_ld, optlen, 1); - gemu_log(")"); + qemu_log(")"); } #define PRINT_SOCKOP(name, func) \ @@ -2164,7 +2169,7 @@ print_rt_sigprocmask(const struct syscallname *name, case TARGET_SIG_UNBLOCK: how = "SIG_UNBLOCK"; break; case TARGET_SIG_SETMASK: how = "SIG_SETMASK"; break; } - gemu_log("%s,",how); + qemu_log("%s,", how); print_pointer(arg1, 0); print_pointer(arg2, 1); print_syscall_epilogue(name); @@ -2278,7 +2283,7 @@ print_syslog_action(abi_ulong arg, int last) return; } } - gemu_log("%s%s", type, get_comma(last)); + qemu_log("%s%s", type, get_comma(last)); } static void @@ -2683,20 +2688,20 @@ static void print_futex_op(abi_long tflag, int last) { #define print_op(val) \ if( cmd == val ) { \ - gemu_log(#val); \ + qemu_log(#val); \ return; \ } int cmd = (int)tflag; #ifdef FUTEX_PRIVATE_FLAG if (cmd & FUTEX_PRIVATE_FLAG) { - gemu_log("FUTEX_PRIVATE_FLAG|"); + qemu_log("FUTEX_PRIVATE_FLAG|"); cmd &= ~FUTEX_PRIVATE_FLAG; } #endif #ifdef FUTEX_CLOCK_REALTIME if (cmd & FUTEX_CLOCK_REALTIME) { - gemu_log("FUTEX_CLOCK_REALTIME|"); + qemu_log("FUTEX_CLOCK_REALTIME|"); cmd &= ~FUTEX_CLOCK_REALTIME; } #endif @@ -2716,7 +2721,7 @@ if( cmd == val ) { \ print_op(FUTEX_WAKE_BITSET) #endif /* unknown values */ - gemu_log("%d",cmd); + qemu_log("%d", cmd); } static void @@ -2812,22 +2817,24 @@ print_syscall(int num, int i; const char *format="%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ")"; - gemu_log("%d ", getpid() ); + qemu_log("%d ", getpid()); for(i=0;i<nsyscalls;i++) if( scnames[i].nr == num ) { if( scnames[i].call != NULL ) { - scnames[i].call(&scnames[i],arg1,arg2,arg3,arg4,arg5,arg6); + scnames[i].call( + &scnames[i], arg1, arg2, arg3, arg4, arg5, arg6); } else { /* XXX: this format system is broken because it uses host types and host pointers for strings */ if( scnames[i].format != NULL ) format = scnames[i].format; - gemu_log(format,scnames[i].name, arg1,arg2,arg3,arg4,arg5,arg6); + qemu_log(format, + scnames[i].name, arg1, arg2, arg3, arg4, arg5, arg6); } return; } - gemu_log("Unknown syscall %d\n", num); + qemu_log("Unknown syscall %d\n", num); } @@ -2840,16 +2847,16 @@ print_syscall_ret(int num, abi_long ret) for(i=0;i<nsyscalls;i++) if( scnames[i].nr == num ) { if( scnames[i].result != NULL ) { - scnames[i].result(&scnames[i],ret); + scnames[i].result(&scnames[i], ret); } else { if (ret < 0) { errstr = target_strerror(-ret); } if (errstr) { - gemu_log(" = -1 errno=" TARGET_ABI_FMT_ld " (%s)\n", + qemu_log(" = -1 errno=" TARGET_ABI_FMT_ld " (%s)\n", -ret, errstr); } else { - gemu_log(" = " TARGET_ABI_FMT_ld "\n", ret); + qemu_log(" = " TARGET_ABI_FMT_ld "\n", ret); } } break; @@ -2861,9 +2868,9 @@ void print_taken_signal(int target_signum, const target_siginfo_t *tinfo) /* Print the strace output for a signal being taken: * --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} --- */ - gemu_log("--- "); + qemu_log("--- "); print_signal(target_signum, 1); - gemu_log(" "); + qemu_log(" "); print_siginfo(tinfo); - gemu_log(" ---\n"); + qemu_log(" ---\n"); } diff --git a/linux-user/strace.list b/linux-user/strace.list index 1de4319dcf..d49a1e92a8 100644 --- a/linux-user/strace.list +++ b/linux-user/strace.list @@ -26,7 +26,7 @@ { TARGET_NR_afs_syscall, "afs_syscall" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_alarm -{ TARGET_NR_alarm, "alarm" , NULL, NULL, NULL }, +{ TARGET_NR_alarm, "alarm" , "%s(%u)", NULL, NULL }, #endif #ifdef TARGET_NR_aplib { TARGET_NR_aplib, "aplib" , NULL, NULL, NULL }, @@ -116,19 +116,19 @@ { TARGET_NR_dipc, "dipc" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_dup -{ TARGET_NR_dup, "dup" , NULL, NULL, NULL }, +{ TARGET_NR_dup, "dup" , "%s(%d)", NULL, NULL }, #endif #ifdef TARGET_NR_dup2 -{ TARGET_NR_dup2, "dup2" , NULL, NULL, NULL }, +{ TARGET_NR_dup2, "dup2" , "%s(%d,%d)", NULL, NULL }, #endif #ifdef TARGET_NR_dup3 -{ TARGET_NR_dup3, "dup3" , NULL, NULL, NULL }, +{ TARGET_NR_dup3, "dup3" , "%s(%d,%d,%d)", NULL, NULL }, #endif #ifdef TARGET_NR_epoll_create -{ TARGET_NR_epoll_create, "epoll_create" , NULL, NULL, NULL }, +{ TARGET_NR_epoll_create, "%s(%d)", NULL, NULL, NULL }, #endif #ifdef TARGET_NR_epoll_create1 -{ TARGET_NR_epoll_create1, "epoll_create1" , NULL, NULL, NULL }, +{ TARGET_NR_epoll_create1, "%s(%d)", NULL, NULL, NULL }, #endif #ifdef TARGET_NR_epoll_ctl { TARGET_NR_epoll_ctl, "epoll_ctl" , NULL, NULL, NULL }, @@ -146,10 +146,10 @@ { TARGET_NR_epoll_wait_old, "epoll_wait_old" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_eventfd -{ TARGET_NR_eventfd, "eventfd" , NULL, NULL, NULL }, +{ TARGET_NR_eventfd, "eventfd", "%s(%d)", NULL, NULL }, #endif #ifdef TARGET_NR_eventfd2 -{ TARGET_NR_eventfd2, "eventfd2" , NULL, NULL, NULL }, +{ TARGET_NR_eventfd2, "eventfd2" , "%s(%d,%d)", NULL, NULL }, #endif #ifdef TARGET_NR_execv { TARGET_NR_execv, "execv" , NULL, print_execv, NULL }, @@ -191,7 +191,7 @@ { TARGET_NR_fanotify_mark, "fanotify_mark" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_fchdir -{ TARGET_NR_fchdir, "fchdir" , NULL, NULL, NULL }, +{ TARGET_NR_fchdir, "fchdir" , "%s(%d)", NULL, NULL }, #endif #ifdef TARGET_NR_fchmod { TARGET_NR_fchmod, "fchmod" , "%s(%d,%#o)", NULL, NULL }, @@ -287,7 +287,7 @@ { TARGET_NR_getdtablesize, "getdtablesize" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_getegid -{ TARGET_NR_getegid, "getegid" , NULL, NULL, NULL }, +{ TARGET_NR_getegid, "getegid" , "%s()", NULL, NULL }, #endif #ifdef TARGET_NR_getegid32 { TARGET_NR_getegid32, "getegid32" , NULL, NULL, NULL }, @@ -299,7 +299,7 @@ { TARGET_NR_geteuid32, "geteuid32" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_getgid -{ TARGET_NR_getgid, "getgid" , NULL, NULL, NULL }, +{ TARGET_NR_getgid, "getgid" , "%s()", NULL, NULL }, #endif #ifdef TARGET_NR_getgid32 { TARGET_NR_getgid32, "getgid32" , NULL, NULL, NULL }, @@ -329,10 +329,10 @@ { TARGET_NR_getpeername, "getpeername" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_getpgid -{ TARGET_NR_getpgid, "getpgid" , NULL, NULL, NULL }, +{ TARGET_NR_getpgid, "getpgid" , "%s(%u)", NULL, NULL }, #endif #ifdef TARGET_NR_getpgrp -{ TARGET_NR_getpgrp, "getpgrp" , NULL, NULL, NULL }, +{ TARGET_NR_getpgrp, "getpgrp" , "%s()", NULL, NULL }, #endif #ifdef TARGET_NR_getpid { TARGET_NR_getpid, "getpid" , "%s()", NULL, NULL }, @@ -432,7 +432,7 @@ { TARGET_NR_io_cancel, "io_cancel" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_ioctl -{ TARGET_NR_ioctl, "ioctl" , NULL, NULL, NULL }, +{ TARGET_NR_ioctl, "ioctl" , "%s(%d,%#x,%#x)", NULL, NULL }, #endif #ifdef TARGET_NR_io_destroy { TARGET_NR_io_destroy, "io_destroy" , NULL, NULL, NULL }, @@ -1257,22 +1257,22 @@ { TARGET_NR_setdomainname, "setdomainname" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setfsgid -{ TARGET_NR_setfsgid, "setfsgid" , NULL, NULL, NULL }, +{ TARGET_NR_setfsgid, "setfsgid" , "%s(%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setfsgid32 -{ TARGET_NR_setfsgid32, "setfsgid32" , NULL, NULL, NULL }, +{ TARGET_NR_setfsgid32, "setfsgid32" , "%s(%u)" , NULL, NULL }, #endif #ifdef TARGET_NR_setfsuid -{ TARGET_NR_setfsuid, "setfsuid" , NULL, NULL, NULL }, +{ TARGET_NR_setfsuid, "setfsuid" , "%s(%u)" , NULL, NULL }, #endif #ifdef TARGET_NR_setfsuid32 { TARGET_NR_setfsuid32, "setfsuid32" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setgid -{ TARGET_NR_setgid, "setgid" , NULL, NULL, NULL }, +{ TARGET_NR_setgid, "setgid" , "%s(%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setgid32 -{ TARGET_NR_setgid32, "setgid32" , NULL, NULL, NULL }, +{ TARGET_NR_setgid32, "setgid32" , "%s(%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setgroups { TARGET_NR_setgroups, "setgroups" , NULL, NULL, NULL }, @@ -1296,7 +1296,7 @@ { TARGET_NR_setns, "setns" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setpgid -{ TARGET_NR_setpgid, "setpgid" , NULL, NULL, NULL }, +{ TARGET_NR_setpgid, "setpgid" , "%s(%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setpgrp { TARGET_NR_setpgrp, "setpgrp" , NULL, NULL, NULL }, @@ -1311,22 +1311,22 @@ { TARGET_NR_setregid32, "setregid32" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setresgid -{ TARGET_NR_setresgid, "setresgid" , NULL, NULL, NULL }, +{ TARGET_NR_setresgid, "setresgid" , "%s(%u,%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setresgid32 { TARGET_NR_setresgid32, "setresgid32" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setresuid -{ TARGET_NR_setresuid, "setresuid" , NULL, NULL, NULL }, +{ TARGET_NR_setresuid, "setresuid" , "%s(%u,%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setresuid32 -{ TARGET_NR_setresuid32, "setresuid32" , NULL, NULL, NULL }, +{ TARGET_NR_setresuid32, "setresuid32" , "%s(%u,%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setreuid -{ TARGET_NR_setreuid, "setreuid" , NULL, NULL, NULL }, +{ TARGET_NR_setreuid, "setreuid" , "%s(%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setreuid32 -{ TARGET_NR_setreuid32, "setreuid32" , NULL, NULL, NULL }, +{ TARGET_NR_setreuid32, "setreuid32" , "%s(%u,%u)", NULL, NULL }, #endif #ifdef TARGET_NR_setrlimit { TARGET_NR_setrlimit, "setrlimit" , NULL, NULL, NULL }, @@ -1335,7 +1335,7 @@ { TARGET_NR_set_robust_list, "set_robust_list" , NULL, NULL, NULL }, #endif #ifdef TARGET_NR_setsid -{ TARGET_NR_setsid, "setsid" , NULL, NULL, NULL }, +{ TARGET_NR_setsid, "setsid" , "%s()", NULL, NULL }, #endif #ifdef TARGET_NR_setsockopt { TARGET_NR_setsockopt, "setsockopt" , NULL, NULL, NULL }, diff --git a/linux-user/syscall.c b/linux-user/syscall.c index c930577686..8d27d10807 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -111,6 +111,7 @@ #include <linux/netlink.h> #include <linux/if_alg.h> #include <linux/rtc.h> +#include <sound/asound.h> #include "linux_loop.h" #include "uname.h" @@ -334,6 +335,9 @@ _syscall5(int, kcmp, pid_t, pid1, pid_t, pid2, int, type, _syscall5(int, sys_statx, int, dirfd, const char *, pathname, int, flags, unsigned int, mask, struct target_statx *, statxbuf) #endif +#if defined(TARGET_NR_membarrier) && defined(__NR_membarrier) +_syscall2(int, membarrier, int, cmd, int, flags) +#endif static bitmask_transtbl fcntl_flags_tbl[] = { { TARGET_O_ACCMODE, TARGET_O_WRONLY, O_ACCMODE, O_WRONLY, }, @@ -1560,7 +1564,11 @@ static inline abi_long target_to_host_cmsg(struct msghdr *msgh, * something more intelligent than "twice the size of the * target buffer we're reading from". */ - gemu_log("Host cmsg overflow\n"); + qemu_log_mask(LOG_UNIMP, + ("Unsupported ancillary data %d/%d: " + "unhandled msg size\n"), + tswap32(target_cmsg->cmsg_level), + tswap32(target_cmsg->cmsg_type)); break; } @@ -1590,8 +1598,8 @@ static inline abi_long target_to_host_cmsg(struct msghdr *msgh, __get_user(cred->uid, &target_cred->uid); __get_user(cred->gid, &target_cred->gid); } else { - gemu_log("Unsupported ancillary data: %d/%d\n", - cmsg->cmsg_level, cmsg->cmsg_type); + qemu_log_mask(LOG_UNIMP, "Unsupported ancillary data: %d/%d\n", + cmsg->cmsg_level, cmsg->cmsg_type); memcpy(data, target_data, len); } @@ -1812,8 +1820,8 @@ static inline abi_long host_to_target_cmsg(struct target_msghdr *target_msgh, default: unimplemented: - gemu_log("Unsupported ancillary data: %d/%d\n", - cmsg->cmsg_level, cmsg->cmsg_type); + qemu_log_mask(LOG_UNIMP, "Unsupported ancillary data: %d/%d\n", + cmsg->cmsg_level, cmsg->cmsg_type); memcpy(target_data, data, MIN(len, tgt_len)); if (tgt_len > len) { memset(target_data + len, 0, tgt_len - len); @@ -2288,7 +2296,8 @@ set_timeout: #endif /* SOL_NETLINK */ default: unimplemented: - gemu_log("Unsupported setsockopt level=%d optname=%d\n", level, optname); + qemu_log_mask(LOG_UNIMP, "Unsupported setsockopt level=%d optname=%d\n", + level, optname); ret = -TARGET_ENOPROTOOPT; } return ret; @@ -2307,10 +2316,42 @@ static abi_long do_getsockopt(int sockfd, int level, int optname, level = SOL_SOCKET; switch (optname) { /* These don't just return a single integer */ - case TARGET_SO_RCVTIMEO: - case TARGET_SO_SNDTIMEO: case TARGET_SO_PEERNAME: goto unimplemented; + case TARGET_SO_RCVTIMEO: { + struct timeval tv; + socklen_t tvlen; + + optname = SO_RCVTIMEO; + +get_timeout: + if (get_user_u32(len, optlen)) { + return -TARGET_EFAULT; + } + if (len < 0) { + return -TARGET_EINVAL; + } + + tvlen = sizeof(tv); + ret = get_errno(getsockopt(sockfd, level, optname, + &tv, &tvlen)); + if (ret < 0) { + return ret; + } + if (len > sizeof(struct target_timeval)) { + len = sizeof(struct target_timeval); + } + if (copy_to_user_timeval(optval_addr, &tv)) { + return -TARGET_EFAULT; + } + if (put_user_u32(len, optlen)) { + return -TARGET_EFAULT; + } + break; + } + case TARGET_SO_SNDTIMEO: + optname = SO_SNDTIMEO; + goto get_timeout; case TARGET_SO_PEERCRED: { struct ucred cr; socklen_t crlen; @@ -2663,8 +2704,9 @@ static abi_long do_getsockopt(int sockfd, int level, int optname, #endif /* SOL_NETLINK */ default: unimplemented: - gemu_log("getsockopt level=%d optname=%d not yet supported\n", - level, optname); + qemu_log_mask(LOG_UNIMP, + "getsockopt level=%d optname=%d not yet supported\n", + level, optname); ret = -TARGET_EOPNOTSUPP; break; } @@ -3419,7 +3461,7 @@ static abi_long do_socketcall(int num, abi_ulong vptr) case TARGET_SYS_SENDMMSG: /* sockfd, msgvec, vlen, flags */ return do_sendrecvmmsg(a[0], a[1], a[2], a[3], 1); default: - gemu_log("Unsupported socketcall: %d\n", num); + qemu_log_mask(LOG_UNIMP, "Unsupported socketcall: %d\n", num); return -TARGET_EINVAL; } } @@ -4330,7 +4372,8 @@ static abi_long do_ipc(CPUArchState *cpu_env, ret = do_shmctl(first, second, ptr); break; default: - gemu_log("Unsupported ipc call: %d (version %d)\n", call, version); + qemu_log_mask(LOG_UNIMP, "Unsupported ipc call: %d (version %d)\n", + call, version); ret = -TARGET_ENOSYS; break; } @@ -5178,7 +5221,8 @@ static abi_long do_ioctl(int fd, int cmd, abi_long arg) ie = ioctl_entries; for(;;) { if (ie->target_cmd == 0) { - gemu_log("Unsupported ioctl: cmd=0x%04lx\n", (long)cmd); + qemu_log_mask( + LOG_UNIMP, "Unsupported ioctl: cmd=0x%04lx\n", (long)cmd); return -TARGET_ENOSYS; } if (ie->target_cmd == cmd) @@ -5246,8 +5290,9 @@ static abi_long do_ioctl(int fd, int cmd, abi_long arg) } break; default: - gemu_log("Unsupported ioctl type: cmd=0x%04lx type=%d\n", - (long)cmd, arg_type[0]); + qemu_log_mask(LOG_UNIMP, + "Unsupported ioctl type: cmd=0x%04lx type=%d\n", + (long)cmd, arg_type[0]); ret = -TARGET_ENOSYS; break; } @@ -12090,6 +12135,10 @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, unlock_user(p, arg1, 0); return ret; #endif +#if defined TARGET_NR_membarrier && defined __NR_membarrier + case TARGET_NR_membarrier: + return get_errno(membarrier(arg1, arg2)); +#endif default: qemu_log_mask(LOG_UNIMP, "Unsupported syscall: %d\n", num); @@ -12123,14 +12172,15 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, record_syscall_start(cpu, num, arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8); - if (unlikely(do_strace)) { + if (unlikely(qemu_loglevel_mask(LOG_STRACE))) { print_syscall(num, arg1, arg2, arg3, arg4, arg5, arg6); - ret = do_syscall1(cpu_env, num, arg1, arg2, arg3, arg4, - arg5, arg6, arg7, arg8); + } + + ret = do_syscall1(cpu_env, num, arg1, arg2, arg3, arg4, + arg5, arg6, arg7, arg8); + + if (unlikely(qemu_loglevel_mask(LOG_STRACE))) { print_syscall_ret(num, ret); - } else { - ret = do_syscall1(cpu_env, num, arg1, arg2, arg3, arg4, - arg5, arg6, arg7, arg8); } record_syscall_return(cpu, num, ret); diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h index 9b61ae8547..152ec637cb 100644 --- a/linux-user/syscall_defs.h +++ b/linux-user/syscall_defs.h @@ -2437,6 +2437,90 @@ struct target_statfs64 { #define TARGET_SOUND_MIXER_WRITE_RECSRC TARGET_MIXER_WRITE(SOUND_MIXER_RECSRC) +struct target_snd_timer_id { + int dev_class; + int dev_sclass; + int card; + int device; + int subdevice; +}; + +struct target_snd_timer_ginfo { + struct target_snd_timer_id tid; + unsigned int flags; + int card; + unsigned char id[64]; + unsigned char name[80]; + abi_ulong reserved0; + abi_ulong resolution; + abi_ulong resolution_min; + abi_ulong resolution_max; + unsigned int clients; + unsigned char reserved[32]; +}; + +struct target_snd_timer_gparams { + struct target_snd_timer_id tid; + abi_ulong period_num; + abi_ulong period_den; + unsigned char reserved[32]; +}; + +struct target_snd_timer_gstatus { + struct target_snd_timer_id tid; + abi_ulong resolution; + abi_ulong resolution_num; + abi_ulong resolution_den; + unsigned char reserved[32]; +}; + +struct target_snd_timer_select { + struct target_snd_timer_id id; + unsigned char reserved[32]; +}; + +struct target_snd_timer_info { + unsigned int flags; + int card; + unsigned char id[64]; + unsigned char name[80]; + abi_ulong reserved0; + abi_ulong resolution; + unsigned char reserved[64]; +}; + +struct target_snd_timer_status { + struct target_timespec tstamp; + unsigned int resolution; + unsigned int lost; + unsigned int overrun; + unsigned int queue; + unsigned char reserved[64]; +}; + +/* alsa timer ioctls */ +#define TARGET_SNDRV_TIMER_IOCTL_PVERSION TARGET_IOR('T', 0x00, int) +#define TARGET_SNDRV_TIMER_IOCTL_NEXT_DEVICE TARGET_IOWR('T', 0x01, \ + struct snd_timer_id) +#define TARGET_SNDRV_TIMER_IOCTL_GINFO TARGET_IOWR('T', 0x03, \ + struct target_snd_timer_ginfo) +#define TARGET_SNDRV_TIMER_IOCTL_GPARAMS TARGET_IOW('T', 0x04, \ + struct target_snd_timer_gparams) +#define TARGET_SNDRV_TIMER_IOCTL_GSTATUS TARGET_IOWR('T', 0x05, \ + struct target_snd_timer_gstatus) +#define TARGET_SNDRV_TIMER_IOCTL_SELECT TARGET_IOW('T', 0x10, \ + struct target_snd_timer_select) +#define TARGET_SNDRV_TIMER_IOCTL_INFO TARGET_IOR('T', 0x11, \ + struct target_snd_timer_info) +#define TARGET_SNDRV_TIMER_IOCTL_PARAMS TARGET_IOW('T', 0x12, \ + struct snd_timer_params) +#define TARGET_SNDRV_TIMER_IOCTL_STATUS TARGET_IOR('T', 0x14, \ + struct target_snd_timer_status) +#define TARGET_SNDRV_TIMER_IOCTL_START TARGET_IO('T', 0xa0) +#define TARGET_SNDRV_TIMER_IOCTL_STOP TARGET_IO('T', 0xa1) +#define TARGET_SNDRV_TIMER_IOCTL_CONTINUE TARGET_IO('T', 0xa2) +#define TARGET_SNDRV_TIMER_IOCTL_PAUSE TARGET_IO('T', 0xa3) + /* vfat ioctls */ #define TARGET_VFAT_IOCTL_READDIR_BOTH TARGET_IORU('r', 1) #define TARGET_VFAT_IOCTL_READDIR_SHORT TARGET_IORU('r', 2) diff --git a/linux-user/syscall_types.h b/linux-user/syscall_types.h index 5ba4155047..4e12c1661e 100644 --- a/linux-user/syscall_types.h +++ b/linux-user/syscall_types.h @@ -83,6 +83,72 @@ STRUCT(buffmem_desc, STRUCT(mixer_info, MK_ARRAY(TYPE_CHAR, 16), MK_ARRAY(TYPE_CHAR, 32), TYPE_INT, MK_ARRAY(TYPE_INT, 10)) +STRUCT(snd_timer_id, + TYPE_INT, /* dev_class */ + TYPE_INT, /* dev_sclass */ + TYPE_INT, /* card */ + TYPE_INT, /* device */ + TYPE_INT) /* subdevice */ + +STRUCT(snd_timer_ginfo, + MK_STRUCT(STRUCT_snd_timer_id), /* tid */ + TYPE_INT, /* flags */ + TYPE_INT, /* card */ + MK_ARRAY(TYPE_CHAR, 64), /* id */ + MK_ARRAY(TYPE_CHAR, 80), /* name */ + TYPE_ULONG, /* reserved0 */ + TYPE_ULONG, /* resolution */ + TYPE_ULONG, /* resolution_min */ + TYPE_ULONG, /* resolution_max */ + TYPE_INT, /* clients */ + MK_ARRAY(TYPE_CHAR, 32)) /* reserved */ + +STRUCT(snd_timer_gparams, + MK_STRUCT(STRUCT_snd_timer_id), /* tid */ + TYPE_ULONG, /* period_num */ + TYPE_ULONG, /* period_den */ + MK_ARRAY(TYPE_CHAR, 32)) /* reserved */ + +STRUCT(snd_timer_gstatus, + MK_STRUCT(STRUCT_snd_timer_id), /* tid */ + TYPE_ULONG, /* resolution */ + TYPE_ULONG, /* resolution_num */ + TYPE_ULONG, /* resolution_den */ + MK_ARRAY(TYPE_CHAR, 32)) /* reserved */ + +STRUCT(snd_timer_select, + MK_STRUCT(STRUCT_snd_timer_id), /* id */ + MK_ARRAY(TYPE_CHAR, 32)) /* reserved */ + +STRUCT(snd_timer_info, + TYPE_INT, /* flags */ + TYPE_INT, /* card */ + MK_ARRAY(TYPE_CHAR, 64), /* id */ + MK_ARRAY(TYPE_CHAR, 80), /* name */ + TYPE_ULONG, /* reserved0 */ + TYPE_ULONG, /* resolution */ + MK_ARRAY(TYPE_CHAR, 64)) /* reserved */ + +STRUCT(snd_timer_params, + TYPE_INT, /* flags */ + TYPE_INT, /* ticks */ + TYPE_INT, /* queue_size */ + TYPE_INT, /* reserved0 */ + TYPE_INT, /* filter */ + MK_ARRAY(TYPE_CHAR, 60)) /* reserved */ + +STRUCT(timespec, + TYPE_LONG, /* tv_sec */ + TYPE_LONG) /* tv_nsec */ + +STRUCT(snd_timer_status, + MK_STRUCT(STRUCT_timespec), /* tstamp */ + TYPE_INT, /* resolution */ + TYPE_INT, /* lost */ + TYPE_INT, /* overrun */ + TYPE_INT, /* queue */ + MK_ARRAY(TYPE_CHAR, 64)) /* reserved */ + /* loop device ioctls */ STRUCT(loop_info, TYPE_INT, /* lo_number */ diff --git a/linux-user/vm86.c b/linux-user/vm86.c index 2fa7a89edc..4412522c4c 100644 --- a/linux-user/vm86.c +++ b/linux-user/vm86.c @@ -402,7 +402,8 @@ int do_vm86(CPUX86State *env, long subfunction, abi_ulong vm86_addr) case TARGET_VM86_FREE_IRQ: case TARGET_VM86_GET_IRQ_BITS: case TARGET_VM86_GET_AND_RESET_IRQ: - gemu_log("qemu: unsupported vm86 subfunction (%ld)\n", subfunction); + qemu_log_mask(LOG_UNIMP, "qemu: unsupported vm86 subfunction (%ld)\n", + subfunction); ret = -TARGET_EINVAL; goto out; case TARGET_VM86_PLUS_INSTALL_CHECK: @@ -794,10 +794,19 @@ static void address_space_update_ioeventfds(AddressSpace *as) FlatView *view; FlatRange *fr; unsigned ioeventfd_nb = 0; - MemoryRegionIoeventfd *ioeventfds = NULL; + unsigned ioeventfd_max; + MemoryRegionIoeventfd *ioeventfds; AddrRange tmp; unsigned i; + /* + * It is likely that the number of ioeventfds hasn't changed much, so use + * the previous size as the starting value, with some headroom to avoid + * gratuitous reallocations. + */ + ioeventfd_max = QEMU_ALIGN_UP(as->ioeventfd_nb, 4); + ioeventfds = g_new(MemoryRegionIoeventfd, ioeventfd_max); + view = address_space_get_flatview(as); FOR_EACH_FLAT_RANGE(fr, view) { for (i = 0; i < fr->mr->ioeventfd_nb; ++i) { @@ -806,8 +815,11 @@ static void address_space_update_ioeventfds(AddressSpace *as) int128_make64(fr->offset_in_region))); if (addrrange_intersects(fr->addr, tmp)) { ++ioeventfd_nb; - ioeventfds = g_realloc(ioeventfds, - ioeventfd_nb * sizeof(*ioeventfds)); + if (ioeventfd_nb > ioeventfd_max) { + ioeventfd_max = MAX(ioeventfd_max * 2, 4); + ioeventfds = g_realloc(ioeventfds, + ioeventfd_max * sizeof(*ioeventfds)); + } ioeventfds[ioeventfd_nb-1] = fr->mr->ioeventfds[i]; ioeventfds[ioeventfd_nb-1].addr = tmp; } diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index b237613e0d..53bc3f76c4 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -620,7 +620,7 @@ void hmp_info_block(Monitor *mon, const QDict *qdict) } /* Print node information */ - blockdev_list = qmp_query_named_block_nodes(NULL); + blockdev_list = qmp_query_named_block_nodes(false, false, NULL); for (blockdev = blockdev_list; blockdev; blockdev = blockdev->next) { assert(blockdev->value->has_node_name); if (device && strcmp(device, blockdev->value->node_name)) { diff --git a/qapi/block-core.json b/qapi/block-core.json index 13dad62f44..85e27bb61f 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -1164,7 +1164,10 @@ # for jobs, cancel the job # # @ignore: ignore the error, only report a QMP event (BLOCK_IO_ERROR -# or BLOCK_JOB_ERROR) +# or BLOCK_JOB_ERROR). The backup, mirror and commit block jobs retry +# the failing request later and may still complete successfully. The +# stream block job continues to stream and will complete with an +# error. # # @enospc: same as @stop on ENOSPC, same as @report otherwise. # @@ -1655,6 +1658,9 @@ # # @speed: the maximum speed, in bytes per second # +# @on-error: the action to take on an error. 'ignore' means that the request +# should be retried. (default: report; Since: 5.0) +# # @filter-node-name: the node name that should be assigned to the # filter driver that the commit job inserts into the graph # above @top. If this option is not given, a node name is @@ -1691,6 +1697,7 @@ 'data': { '*job-id': 'str', 'device': 'str', '*base-node': 'str', '*base': 'str', '*top-node': 'str', '*top': 'str', '*backing-file': 'str', '*speed': 'int', + '*on-error': 'BlockdevOnError', '*filter-node-name': 'str', '*auto-finalize': 'bool', '*auto-dismiss': 'bool' } } @@ -1751,6 +1758,9 @@ # # Get the named block driver list # +# @flat: Omit the nested data about backing image ("backing-image" key) if true. +# Default is false (Since 5.0) +# # Returns: the list of BlockDeviceInfo # # Since: 2.0 @@ -1804,7 +1814,9 @@ # } } ] } # ## -{ 'command': 'query-named-block-nodes', 'returns': [ 'BlockDeviceInfo' ] } +{ 'command': 'query-named-block-nodes', + 'returns': [ 'BlockDeviceInfo' ], + 'data': { '*flat': 'bool' } } ## # @XDbgBlockGraphNodeType: diff --git a/qdev-monitor.c b/qdev-monitor.c index 8ce71a206b..8a2a9538cd 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -887,6 +887,12 @@ void qmp_device_del(const char *id, Error **errp) { DeviceState *dev = find_device_state(id, errp); if (dev != NULL) { + if (dev->pending_deleted_event) { + error_setg(errp, "Device %s is already in the " + "process of unplug", id); + return; + } + qdev_unplug(dev, errp); } } diff --git a/qemu-img-cmds.hx b/qemu-img-cmds.hx index d7fbc6b1f4..c9c54de1df 100644 --- a/qemu-img-cmds.hx +++ b/qemu-img-cmds.hx @@ -39,9 +39,9 @@ SRST ERST DEF("convert", img_convert, - "convert [--object objectdef] [--image-opts] [--target-image-opts] [-U] [-C] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file] [-o options] [-l snapshot_param] [-S sparse_size] [-m num_coroutines] [-W] [--salvage] filename [filename2 [...]] output_filename") + "convert [--object objectdef] [--image-opts] [--target-image-opts] [--target-is-zero] [-U] [-C] [-c] [-p] [-q] [-n] [-f fmt] [-t cache] [-T src_cache] [-O output_fmt] [-B backing_file] [-o options] [-l snapshot_param] [-S sparse_size] [-m num_coroutines] [-W] [--salvage] filename [filename2 [...]] output_filename") SRST -.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-m NUM_COROUTINES] [-W] [--salvage] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME +.. option:: convert [--object OBJECTDEF] [--image-opts] [--target-image-opts] [--target-is-zero] [-U] [-C] [-c] [-p] [-q] [-n] [-f FMT] [-t CACHE] [-T SRC_CACHE] [-O OUTPUT_FMT] [-B BACKING_FILE] [-o OPTIONS] [-l SNAPSHOT_PARAM] [-S SPARSE_SIZE] [-m NUM_COROUTINES] [-W] [--salvage] FILENAME [FILENAME2 [...]] OUTPUT_FILENAME ERST DEF("create", img_create, diff --git a/qemu-img.c b/qemu-img.c index 2b4562b9d9..804630a368 100644 --- a/qemu-img.c +++ b/qemu-img.c @@ -70,6 +70,7 @@ enum { OPTION_PREALLOCATION = 265, OPTION_SHRINK = 266, OPTION_SALVAGE = 267, + OPTION_TARGET_IS_ZERO = 268, }; typedef enum OutputFormat { @@ -1984,10 +1985,9 @@ static int convert_do_copy(ImgConvertState *s) int64_t sector_num = 0; /* Check whether we have zero initialisation or can get it efficiently */ - if (s->target_is_new && s->min_sparse && !s->target_has_backing) { + if (!s->has_zero_init && s->target_is_new && s->min_sparse && + !s->target_has_backing) { s->has_zero_init = bdrv_has_zero_init(blk_bs(s->target)); - } else { - s->has_zero_init = false; } if (!s->has_zero_init && !s->target_has_backing && @@ -2086,6 +2086,7 @@ static int img_convert(int argc, char **argv) {"force-share", no_argument, 0, 'U'}, {"target-image-opts", no_argument, 0, OPTION_TARGET_IMAGE_OPTS}, {"salvage", no_argument, 0, OPTION_SALVAGE}, + {"target-is-zero", no_argument, 0, OPTION_TARGET_IS_ZERO}, {0, 0, 0, 0} }; c = getopt_long(argc, argv, ":hf:O:B:Cco:l:S:pt:T:qnm:WU", @@ -2209,6 +2210,14 @@ static int img_convert(int argc, char **argv) case OPTION_TARGET_IMAGE_OPTS: tgt_image_opts = true; break; + case OPTION_TARGET_IS_ZERO: + /* + * The user asserting that the target is blank has the + * same effect as the target driver supporting zero + * initialisation. + */ + s.has_zero_init = true; + break; } } @@ -2247,6 +2256,11 @@ static int img_convert(int argc, char **argv) warn_report("This will become an error in future QEMU versions."); } + if (s.has_zero_init && !skip_create) { + error_report("--target-is-zero requires use of -n flag"); + goto fail_getopt; + } + s.src_num = argc - optind - 1; out_filename = s.src_num >= 1 ? argv[argc - 1] : NULL; @@ -2380,6 +2394,12 @@ static int img_convert(int argc, char **argv) } s.target_has_backing = (bool) out_baseimg; + if (s.has_zero_init && s.target_has_backing) { + error_report("Cannot use --target-is-zero when the destination " + "image has a backing file"); + goto out; + } + if (s.src_num > 1 && out_baseimg) { error_report("Having a backing file for the target makes no sense when " "concatenating multiple input images"); @@ -2503,7 +2523,7 @@ static int img_convert(int argc, char **argv) } } - if (s.target_has_backing) { + if (s.target_has_backing && s.target_is_new) { /* Errors are treated as "backing length unknown" (which means * s.target_backing_sectors has to be negative, which it will * be automatically). The backing file length is used only @@ -27,7 +27,8 @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/cutils.h" -#ifdef TARGET_PPC64 +#include "config-devices.h" +#ifdef CONFIG_PSERIES #include "hw/ppc/spapr_rtas.h" #endif @@ -42,6 +43,8 @@ static GString *inbuf; static int irq_levels[MAX_IRQ]; static qemu_timeval start_time; static bool qtest_opened; +static void (*qtest_server_send)(void*, const char*); +static void *qtest_server_send_opaque; #define FMT_timeval "%ld.%06ld" @@ -228,8 +231,10 @@ static void GCC_FMT_ATTR(1, 2) qtest_log_send(const char *fmt, ...) va_end(ap); } -static void do_qtest_send(CharBackend *chr, const char *str, size_t len) +static void qtest_server_char_be_send(void *opaque, const char *str) { + size_t len = strlen(str); + CharBackend* chr = (CharBackend *)opaque; qemu_chr_fe_write_all(chr, (uint8_t *)str, len); if (qtest_log_fp && qtest_opened) { fprintf(qtest_log_fp, "%s", str); @@ -238,7 +243,7 @@ static void do_qtest_send(CharBackend *chr, const char *str, size_t len) static void qtest_send(CharBackend *chr, const char *str) { - do_qtest_send(chr, str, strlen(str)); + qtest_server_send(qtest_server_send_opaque, str); } static void GCC_FMT_ATTR(2, 3) qtest_sendf(CharBackend *chr, @@ -628,7 +633,7 @@ static void qtest_process_command(CharBackend *chr, gchar **words) #else qtest_sendf(chr, "OK little\n"); #endif -#ifdef TARGET_PPC64 +#ifdef CONFIG_PSERIES } else if (strcmp(words[0], "rtas") == 0) { uint64_t res, args, ret; unsigned long nargs, nret; @@ -783,9 +788,32 @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** qemu_chr_fe_set_echo(&qtest_chr, true); inbuf = g_string_new(""); + + if (!qtest_server_send) { + qtest_server_set_send_handler(qtest_server_char_be_send, &qtest_chr); + } +} + +void qtest_server_set_send_handler(void (*send)(void*, const char*), void *opaque) +{ + qtest_server_send = send; + qtest_server_send_opaque = opaque; } bool qtest_driver(void) { return qtest_chr.chr != NULL; } + +void qtest_server_inproc_recv(void *dummy, const char *buf) +{ + static GString *gstr; + if (!gstr) { + gstr = g_string_new(NULL); + } + g_string_append(gstr, buf); + if (gstr->str[gstr->len - 1] == '\n') { + qtest_process_inbuf(NULL, gstr); + g_string_truncate(gstr, 0); + } +} diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index ce43a306f8..b27e4ff5e9 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -462,7 +462,7 @@ sub top_of_kernel_tree { my @tree_check = ( "COPYING", "MAINTAINERS", "Makefile", "README.rst", "docs", "VERSION", - "vl.c" + "linux-user", "softmmu" ); foreach my $check (@tree_check) { @@ -1830,6 +1830,11 @@ sub process { ERROR("suspicious ; after while (0)\n" . $herecurr); } +# Check superfluous trailing ';' + if ($line =~ /;;$/) { + ERROR("superfluous trailing semicolon\n" . $herecurr); + } + # Check relative indent for conditionals and blocks. if ($line =~ /\b(?:(?:if|while|for)\s*\(|do\b)/ && $line !~ /^.\s*#/ && $line !~ /\}\s*while\s*/) { my ($s, $c) = ($stat, $cond); diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 27991eb1cf..271f5ff42a 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -795,7 +795,8 @@ sub top_of_tree { && (-f "${lk_path}Makefile") && (-d "${lk_path}docs") && (-f "${lk_path}VERSION") - && (-f "${lk_path}vl.c")) { + && (-d "${lk_path}linux-user/") + && (-d "${lk_path}softmmu/")) { return 1; } return 0; diff --git a/softmmu/Makefile.objs b/softmmu/Makefile.objs new file mode 100644 index 0000000000..dd15c24346 --- /dev/null +++ b/softmmu/Makefile.objs @@ -0,0 +1,3 @@ +softmmu-main-y = softmmu/main.o +obj-y += vl.o +vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS) diff --git a/softmmu/main.c b/softmmu/main.c new file mode 100644 index 0000000000..7adc530c73 --- /dev/null +++ b/softmmu/main.c @@ -0,0 +1,53 @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2020 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "sysemu/sysemu.h" + +#ifdef CONFIG_SDL +#if defined(__APPLE__) || defined(main) +#include <SDL.h> +int main(int argc, char **argv) +{ + return qemu_main(argc, argv, NULL); +} +#undef main +#define main qemu_main +#endif +#endif /* CONFIG_SDL */ + +#ifdef CONFIG_COCOA +#undef main +#define main qemu_main +#endif /* CONFIG_COCOA */ + +int main(int argc, char **argv, char **envp) +{ + qemu_init(argc, argv, envp); + qemu_main_loop(); + qemu_cleanup(); + + return 0; +} @@ -36,25 +36,6 @@ #include "sysemu/seccomp.h" #include "sysemu/tcg.h" -#ifdef CONFIG_SDL -#if defined(__APPLE__) || defined(main) -#include <SDL.h> -int qemu_main(int argc, char **argv, char **envp); -int main(int argc, char **argv) -{ - return qemu_main(argc, argv, NULL); -} -#undef main -#define main qemu_main -#endif -#endif /* CONFIG_SDL */ - -#ifdef CONFIG_COCOA -#undef main -#define main qemu_main -#endif /* CONFIG_COCOA */ - - #include "qemu/error-report.h" #include "qemu/sockets.h" #include "sysemu/accel.h" @@ -1669,7 +1650,7 @@ static bool main_loop_should_exit(void) return false; } -static void main_loop(void) +void qemu_main_loop(void) { #ifdef CONFIG_PROFILER int64_t ti; @@ -2845,7 +2826,7 @@ static void create_default_memdev(MachineState *ms, const char *path) &error_fatal); } -int main(int argc, char **argv, char **envp) +void qemu_init(int argc, char **argv, char **envp) { int i; int snapshot, linux_boot; @@ -3399,7 +3380,7 @@ int main(int argc, char **argv, char **envp) case QEMU_OPTION_watchdog: if (watchdog) { error_report("only one watchdog option may be given"); - return 1; + exit(1); } watchdog = optarg; break; @@ -3841,7 +3822,17 @@ int main(int argc, char **argv, char **envp) object_set_machine_compat_props(machine_class->compat_props); os_daemonize(); - rcu_disable_atfork(); + + /* + * If QTest is enabled, keep the rcu_atfork enabled, since system processes + * may be forked testing purposes (e.g. fork-server based fuzzing) The fork + * should happen before a signle cpu instruction is executed, to prevent + * deadlocks. See commit 73c6e40, rcu: "completely disable pthread_atfork + * callbacks as soon as possible" + */ + if (!qtest_enabled()) { + rcu_disable_atfork(); + } if (pid_file && !qemu_write_pidfile(pid_file, &err)) { error_reportf_err(err, "cannot create PID file: "); @@ -4317,7 +4308,7 @@ int main(int argc, char **argv, char **envp) create_default_memdev(current_machine, mem_path); } /* do monitor/qmp handling at preconfig state if requested */ - main_loop(); + qemu_main_loop(); audio_init_audiodevs(); @@ -4435,7 +4426,7 @@ int main(int argc, char **argv, char **envp) if (vmstate_dump_file) { /* dump and exit */ dump_vmstate_json_to_file(vmstate_dump_file); - return 0; + exit(0); } if (incoming) { @@ -4452,8 +4443,11 @@ int main(int argc, char **argv, char **envp) accel_setup_post(current_machine); os_setup_post(); - main_loop(); + return; +} +void qemu_cleanup(void) +{ gdbserver_cleanup(); /* @@ -4490,6 +4484,4 @@ int main(int argc, char **argv, char **envp) qemu_chr_cleanup(); user_creatable_cleanup(); /* TODO: unref root container, check all devices are ok */ - - return 0; } diff --git a/target/arm/cpu.c b/target/arm/cpu.c index de733aceeb..2eadf4dcb8 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -1009,11 +1009,10 @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) if (flags & CPU_DUMP_FPU) { int numvfpregs = 0; - if (arm_feature(env, ARM_FEATURE_VFP)) { - numvfpregs += 16; - } - if (arm_feature(env, ARM_FEATURE_VFP3)) { - numvfpregs += 16; + if (cpu_isar_feature(aa32_simd_r32, cpu)) { + numvfpregs = 32; + } else if (arm_feature(env, ARM_FEATURE_VFP)) { + numvfpregs = 16; } for (i = 0; i < numvfpregs; i++) { uint64_t v = *aa32_vfp_dreg(env, i); @@ -1586,7 +1585,8 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * Presence of EL2 itself is ARM_FEATURE_EL2, and of the * Security Extensions is ARM_FEATURE_EL3. */ - assert(!tcg_enabled() || no_aa32 || cpu_isar_feature(arm_div, cpu)); + assert(!tcg_enabled() || no_aa32 || + cpu_isar_feature(aa32_arm_div, cpu)); set_feature(env, ARM_FEATURE_LPAE); set_feature(env, ARM_FEATURE_V7); } @@ -1612,7 +1612,8 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (arm_feature(env, ARM_FEATURE_V6)) { set_feature(env, ARM_FEATURE_V5); if (!arm_feature(env, ARM_FEATURE_M)) { - assert(!tcg_enabled() || no_aa32 || cpu_isar_feature(jazelle, cpu)); + assert(!tcg_enabled() || no_aa32 || + cpu_isar_feature(aa32_jazelle, cpu)); set_feature(env, ARM_FEATURE_AUXCR); } } @@ -1716,8 +1717,9 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu); #endif } else { - cpu->id_aa64dfr0 &= ~0xf00; - cpu->id_dfr0 &= ~(0xf << 24); + cpu->isar.id_aa64dfr0 = + FIELD_DP64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, PMUVER, 0); + cpu->isar.id_dfr0 = FIELD_DP32(cpu->isar.id_dfr0, ID_DFR0, PERFMON, 0); cpu->pmceid0 = 0; cpu->pmceid1 = 0; } @@ -1870,10 +1872,11 @@ static void arm926_initfn(Object *obj) */ cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); /* - * Similarly, we need to set MVFR0 fields to enable double precision - * and short vector support even though ARMv5 doesn't have this register. + * Similarly, we need to set MVFR0 fields to enable vfp and short vector + * support even though ARMv5 doesn't have this register. */ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); + cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1); cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1); } @@ -1912,10 +1915,11 @@ static void arm1026_initfn(Object *obj) */ cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); /* - * Similarly, we need to set MVFR0 fields to enable double precision - * and short vector support even though ARMv5 doesn't have this register. + * Similarly, we need to set MVFR0 fields to enable vfp and short vector + * support even though ARMv5 doesn't have this register. */ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1); + cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSP, 1); cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1); { @@ -1955,11 +1959,11 @@ static void arm1136_r2_initfn(Object *obj) cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x1; - cpu->id_dfr0 = 0x2; + cpu->isar.id_dfr0 = 0x2; cpu->id_afr0 = 0x3; - cpu->id_mmfr0 = 0x01130003; - cpu->id_mmfr1 = 0x10030302; - cpu->id_mmfr2 = 0x01222110; + cpu->isar.id_mmfr0 = 0x01130003; + cpu->isar.id_mmfr1 = 0x10030302; + cpu->isar.id_mmfr2 = 0x01222110; cpu->isar.id_isar0 = 0x00140011; cpu->isar.id_isar1 = 0x12002111; cpu->isar.id_isar2 = 0x11231111; @@ -1987,11 +1991,11 @@ static void arm1136_initfn(Object *obj) cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x1; - cpu->id_dfr0 = 0x2; + cpu->isar.id_dfr0 = 0x2; cpu->id_afr0 = 0x3; - cpu->id_mmfr0 = 0x01130003; - cpu->id_mmfr1 = 0x10030302; - cpu->id_mmfr2 = 0x01222110; + cpu->isar.id_mmfr0 = 0x01130003; + cpu->isar.id_mmfr1 = 0x10030302; + cpu->isar.id_mmfr2 = 0x01222110; cpu->isar.id_isar0 = 0x00140011; cpu->isar.id_isar1 = 0x12002111; cpu->isar.id_isar2 = 0x11231111; @@ -2020,11 +2024,11 @@ static void arm1176_initfn(Object *obj) cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x11; - cpu->id_dfr0 = 0x33; + cpu->isar.id_dfr0 = 0x33; cpu->id_afr0 = 0; - cpu->id_mmfr0 = 0x01130003; - cpu->id_mmfr1 = 0x10030302; - cpu->id_mmfr2 = 0x01222100; + cpu->isar.id_mmfr0 = 0x01130003; + cpu->isar.id_mmfr1 = 0x10030302; + cpu->isar.id_mmfr2 = 0x01222100; cpu->isar.id_isar0 = 0x0140011; cpu->isar.id_isar1 = 0x12002111; cpu->isar.id_isar2 = 0x11231121; @@ -2050,11 +2054,11 @@ static void arm11mpcore_initfn(Object *obj) cpu->ctr = 0x1d192992; /* 32K icache 32K dcache */ cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x1; - cpu->id_dfr0 = 0; + cpu->isar.id_dfr0 = 0; cpu->id_afr0 = 0x2; - cpu->id_mmfr0 = 0x01100103; - cpu->id_mmfr1 = 0x10020302; - cpu->id_mmfr2 = 0x01222000; + cpu->isar.id_mmfr0 = 0x01100103; + cpu->isar.id_mmfr1 = 0x10020302; + cpu->isar.id_mmfr2 = 0x01222000; cpu->isar.id_isar0 = 0x00100011; cpu->isar.id_isar1 = 0x12002111; cpu->isar.id_isar2 = 0x11221011; @@ -2082,12 +2086,12 @@ static void cortex_m3_initfn(Object *obj) cpu->pmsav7_dregion = 8; cpu->id_pfr0 = 0x00000030; cpu->id_pfr1 = 0x00000200; - cpu->id_dfr0 = 0x00100000; + cpu->isar.id_dfr0 = 0x00100000; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x00000030; - cpu->id_mmfr1 = 0x00000000; - cpu->id_mmfr2 = 0x00000000; - cpu->id_mmfr3 = 0x00000000; + cpu->isar.id_mmfr0 = 0x00000030; + cpu->isar.id_mmfr1 = 0x00000000; + cpu->isar.id_mmfr2 = 0x00000000; + cpu->isar.id_mmfr3 = 0x00000000; cpu->isar.id_isar0 = 0x01141110; cpu->isar.id_isar1 = 0x02111000; cpu->isar.id_isar2 = 0x21112231; @@ -2113,12 +2117,12 @@ static void cortex_m4_initfn(Object *obj) cpu->isar.mvfr2 = 0x00000000; cpu->id_pfr0 = 0x00000030; cpu->id_pfr1 = 0x00000200; - cpu->id_dfr0 = 0x00100000; + cpu->isar.id_dfr0 = 0x00100000; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x00000030; - cpu->id_mmfr1 = 0x00000000; - cpu->id_mmfr2 = 0x00000000; - cpu->id_mmfr3 = 0x00000000; + cpu->isar.id_mmfr0 = 0x00000030; + cpu->isar.id_mmfr1 = 0x00000000; + cpu->isar.id_mmfr2 = 0x00000000; + cpu->isar.id_mmfr3 = 0x00000000; cpu->isar.id_isar0 = 0x01141110; cpu->isar.id_isar1 = 0x02111000; cpu->isar.id_isar2 = 0x21112231; @@ -2144,12 +2148,12 @@ static void cortex_m7_initfn(Object *obj) cpu->isar.mvfr2 = 0x00000040; cpu->id_pfr0 = 0x00000030; cpu->id_pfr1 = 0x00000200; - cpu->id_dfr0 = 0x00100000; + cpu->isar.id_dfr0 = 0x00100000; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x00100030; - cpu->id_mmfr1 = 0x00000000; - cpu->id_mmfr2 = 0x01000000; - cpu->id_mmfr3 = 0x00000000; + cpu->isar.id_mmfr0 = 0x00100030; + cpu->isar.id_mmfr1 = 0x00000000; + cpu->isar.id_mmfr2 = 0x01000000; + cpu->isar.id_mmfr3 = 0x00000000; cpu->isar.id_isar0 = 0x01101110; cpu->isar.id_isar1 = 0x02112000; cpu->isar.id_isar2 = 0x20232231; @@ -2177,12 +2181,12 @@ static void cortex_m33_initfn(Object *obj) cpu->isar.mvfr2 = 0x00000040; cpu->id_pfr0 = 0x00000030; cpu->id_pfr1 = 0x00000210; - cpu->id_dfr0 = 0x00200000; + cpu->isar.id_dfr0 = 0x00200000; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x00101F40; - cpu->id_mmfr1 = 0x00000000; - cpu->id_mmfr2 = 0x01000000; - cpu->id_mmfr3 = 0x00000000; + cpu->isar.id_mmfr0 = 0x00101F40; + cpu->isar.id_mmfr1 = 0x00000000; + cpu->isar.id_mmfr2 = 0x01000000; + cpu->isar.id_mmfr3 = 0x00000000; cpu->isar.id_isar0 = 0x01101110; cpu->isar.id_isar1 = 0x02212000; cpu->isar.id_isar2 = 0x20232232; @@ -2229,12 +2233,12 @@ static void cortex_r5_initfn(Object *obj) cpu->midr = 0x411fc153; /* r1p3 */ cpu->id_pfr0 = 0x0131; cpu->id_pfr1 = 0x001; - cpu->id_dfr0 = 0x010400; + cpu->isar.id_dfr0 = 0x010400; cpu->id_afr0 = 0x0; - cpu->id_mmfr0 = 0x0210030; - cpu->id_mmfr1 = 0x00000000; - cpu->id_mmfr2 = 0x01200000; - cpu->id_mmfr3 = 0x0211; + cpu->isar.id_mmfr0 = 0x0210030; + cpu->isar.id_mmfr1 = 0x00000000; + cpu->isar.id_mmfr2 = 0x01200000; + cpu->isar.id_mmfr3 = 0x0211; cpu->isar.id_isar0 = 0x02101111; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232141; @@ -2284,18 +2288,18 @@ static void cortex_a8_initfn(Object *obj) cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; cpu->id_pfr1 = 0x11; - cpu->id_dfr0 = 0x400; + cpu->isar.id_dfr0 = 0x400; cpu->id_afr0 = 0; - cpu->id_mmfr0 = 0x31100003; - cpu->id_mmfr1 = 0x20000000; - cpu->id_mmfr2 = 0x01202000; - cpu->id_mmfr3 = 0x11; + cpu->isar.id_mmfr0 = 0x31100003; + cpu->isar.id_mmfr1 = 0x20000000; + cpu->isar.id_mmfr2 = 0x01202000; + cpu->isar.id_mmfr3 = 0x11; cpu->isar.id_isar0 = 0x00101111; cpu->isar.id_isar1 = 0x12112111; cpu->isar.id_isar2 = 0x21232031; cpu->isar.id_isar3 = 0x11112131; cpu->isar.id_isar4 = 0x00111142; - cpu->dbgdidr = 0x15141000; + cpu->isar.dbgdidr = 0x15141000; cpu->clidr = (1 << 27) | (2 << 24) | 3; cpu->ccsidr[0] = 0xe007e01a; /* 16k L1 dcache. */ cpu->ccsidr[1] = 0x2007e01a; /* 16k L1 icache. */ @@ -2357,18 +2361,18 @@ static void cortex_a9_initfn(Object *obj) cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; cpu->id_pfr1 = 0x11; - cpu->id_dfr0 = 0x000; + cpu->isar.id_dfr0 = 0x000; cpu->id_afr0 = 0; - cpu->id_mmfr0 = 0x00100103; - cpu->id_mmfr1 = 0x20000000; - cpu->id_mmfr2 = 0x01230000; - cpu->id_mmfr3 = 0x00002111; + cpu->isar.id_mmfr0 = 0x00100103; + cpu->isar.id_mmfr1 = 0x20000000; + cpu->isar.id_mmfr2 = 0x01230000; + cpu->isar.id_mmfr3 = 0x00002111; cpu->isar.id_isar0 = 0x00101111; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232041; cpu->isar.id_isar3 = 0x11112131; cpu->isar.id_isar4 = 0x00111142; - cpu->dbgdidr = 0x35141000; + cpu->isar.dbgdidr = 0x35141000; cpu->clidr = (1 << 27) | (1 << 24) | 3; cpu->ccsidr[0] = 0xe00fe019; /* 16k L1 dcache. */ cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */ @@ -2422,12 +2426,12 @@ static void cortex_a7_initfn(Object *obj) cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; - cpu->id_dfr0 = 0x02010555; + cpu->isar.id_dfr0 = 0x02010555; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x10101105; - cpu->id_mmfr1 = 0x40000000; - cpu->id_mmfr2 = 0x01240000; - cpu->id_mmfr3 = 0x02102211; + cpu->isar.id_mmfr0 = 0x10101105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01240000; + cpu->isar.id_mmfr3 = 0x02102211; /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but * table 4-41 gives 0x02101110, which includes the arm div insns. */ @@ -2436,7 +2440,7 @@ static void cortex_a7_initfn(Object *obj) cpu->isar.id_isar2 = 0x21232041; cpu->isar.id_isar3 = 0x11112131; cpu->isar.id_isar4 = 0x10011142; - cpu->dbgdidr = 0x3515f005; + cpu->isar.dbgdidr = 0x3515f005; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */ @@ -2468,18 +2472,18 @@ static void cortex_a15_initfn(Object *obj) cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; - cpu->id_dfr0 = 0x02010555; + cpu->isar.id_dfr0 = 0x02010555; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x10201105; - cpu->id_mmfr1 = 0x20000000; - cpu->id_mmfr2 = 0x01240000; - cpu->id_mmfr3 = 0x02102211; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x20000000; + cpu->isar.id_mmfr2 = 0x01240000; + cpu->isar.id_mmfr3 = 0x02102211; cpu->isar.id_isar0 = 0x02101110; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232041; cpu->isar.id_isar3 = 0x11112131; cpu->isar.id_isar4 = 0x10011142; - cpu->dbgdidr = 0x3515f021; + cpu->isar.dbgdidr = 0x3515f021; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */ @@ -2709,13 +2713,14 @@ static void arm_max_initfn(Object *obj) t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */ cpu->isar.mvfr2 = t; - t = cpu->id_mmfr3; + t = cpu->isar.id_mmfr3; t = FIELD_DP32(t, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->id_mmfr3 = t; + cpu->isar.id_mmfr3 = t; - t = cpu->id_mmfr4; + t = cpu->isar.id_mmfr4; t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ - cpu->id_mmfr4 = t; + t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + cpu->isar.id_mmfr4 = t; } #endif } diff --git a/target/arm/cpu.h b/target/arm/cpu.h index e943ffe8a9..65171cb30e 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -853,6 +853,11 @@ struct ARMCPU { * prefix means a constant register. * Some of these registers are split out into a substructure that * is shared with the translators to control the ISA. + * + * Note that if you add an ID register to the ARMISARegisters struct + * you need to also update the 32-bit and 64-bit versions of the + * kvm_arm_get_host_cpu_features() function to correctly populate the + * field by reading the value from the KVM vCPU. */ struct ARMISARegisters { uint32_t id_isar0; @@ -862,9 +867,16 @@ struct ARMCPU { uint32_t id_isar4; uint32_t id_isar5; uint32_t id_isar6; + uint32_t id_mmfr0; + uint32_t id_mmfr1; + uint32_t id_mmfr2; + uint32_t id_mmfr3; + uint32_t id_mmfr4; uint32_t mvfr0; uint32_t mvfr1; uint32_t mvfr2; + uint32_t id_dfr0; + uint32_t dbgdidr; uint64_t id_aa64isar0; uint64_t id_aa64isar1; uint64_t id_aa64pfr0; @@ -872,6 +884,8 @@ struct ARMCPU { uint64_t id_aa64mmfr0; uint64_t id_aa64mmfr1; uint64_t id_aa64mmfr2; + uint64_t id_aa64dfr0; + uint64_t id_aa64dfr1; } isar; uint32_t midr; uint32_t revidr; @@ -880,20 +894,11 @@ struct ARMCPU { uint32_t reset_sctlr; uint32_t id_pfr0; uint32_t id_pfr1; - uint32_t id_dfr0; uint64_t pmceid0; uint64_t pmceid1; uint32_t id_afr0; - uint32_t id_mmfr0; - uint32_t id_mmfr1; - uint32_t id_mmfr2; - uint32_t id_mmfr3; - uint32_t id_mmfr4; - uint64_t id_aa64dfr0; - uint64_t id_aa64dfr1; uint64_t id_aa64afr0; uint64_t id_aa64afr1; - uint32_t dbgdidr; uint32_t clidr; uint64_t mp_affinity; /* MP ID without feature bits */ /* The elements of this array are the CCSIDR values for each cache, @@ -1821,6 +1826,16 @@ FIELD(ID_AA64MMFR2, BBM, 52, 4) FIELD(ID_AA64MMFR2, EVT, 56, 4) FIELD(ID_AA64MMFR2, E0PD, 60, 4) +FIELD(ID_AA64DFR0, DEBUGVER, 0, 4) +FIELD(ID_AA64DFR0, TRACEVER, 4, 4) +FIELD(ID_AA64DFR0, PMUVER, 8, 4) +FIELD(ID_AA64DFR0, BRPS, 12, 4) +FIELD(ID_AA64DFR0, WRPS, 20, 4) +FIELD(ID_AA64DFR0, CTX_CMPS, 28, 4) +FIELD(ID_AA64DFR0, PMSVER, 32, 4) +FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) +FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) + FIELD(ID_DFR0, COPDBG, 0, 4) FIELD(ID_DFR0, COPSDBG, 4, 4) FIELD(ID_DFR0, MMAPDBG, 8, 4) @@ -1830,6 +1845,13 @@ FIELD(ID_DFR0, MPROFDBG, 20, 4) FIELD(ID_DFR0, PERFMON, 24, 4) FIELD(ID_DFR0, TRACEFILT, 28, 4) +FIELD(DBGDIDR, SE_IMP, 12, 1) +FIELD(DBGDIDR, NSUHD_IMP, 14, 1) +FIELD(DBGDIDR, VERSION, 16, 4) +FIELD(DBGDIDR, CTX_CMPS, 20, 4) +FIELD(DBGDIDR, BRPS, 24, 4) +FIELD(DBGDIDR, WRPS, 28, 4) + FIELD(MVFR0, SIMDREG, 0, 4) FIELD(MVFR0, FPSP, 4, 4) FIELD(MVFR0, FPDP, 8, 4) @@ -3325,19 +3347,35 @@ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno) extern const uint64_t pred_esz_masks[4]; /* + * Naming convention for isar_feature functions: + * Functions which test 32-bit ID registers should have _aa32_ in + * their name. Functions which test 64-bit ID registers should have + * _aa64_ in their name. These must only be used in code where we + * know for certain that the CPU has AArch32 or AArch64 respectively + * or where the correct answer for a CPU which doesn't implement that + * CPU state is "false" (eg when generating A32 or A64 code, if adding + * system registers that are specific to that CPU state, for "should + * we let this system register bit be set" tests where the 32-bit + * flavour of the register doesn't have the bit, and so on). + * Functions which simply ask "does this feature exist at all" have + * _any_ in their name, and always return the logical OR of the _aa64_ + * and the _aa32_ function. + */ + +/* * 32-bit feature tests via id registers. */ -static inline bool isar_feature_thumb_div(const ARMISARegisters *id) +static inline bool isar_feature_aa32_thumb_div(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; } -static inline bool isar_feature_arm_div(const ARMISARegisters *id) +static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; } -static inline bool isar_feature_jazelle(const ARMISARegisters *id) +static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; } @@ -3412,21 +3450,21 @@ static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; } -static inline bool isar_feature_aa32_fp_d32(const ARMISARegisters *id) +static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) { /* Return true if D16-D31 are implemented */ - return FIELD_EX64(id->mvfr0, MVFR0, SIMDREG) >= 2; + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) >= 2; } static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr0, MVFR0, FPSHVEC) > 0; + return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; } static inline bool isar_feature_aa32_fpdp(const ARMISARegisters *id) { /* Return true if CPU supports double precision floating point */ - return FIELD_EX64(id->mvfr0, MVFR0, FPDP) > 0; + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; } /* @@ -3436,42 +3474,66 @@ static inline bool isar_feature_aa32_fpdp(const ARMISARegisters *id) */ static inline bool isar_feature_aa32_fp16_spconv(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr1, MVFR1, FPHP) > 0; + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 0; } static inline bool isar_feature_aa32_fp16_dpconv(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr1, MVFR1, FPHP) > 1; + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; } static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr2, MVFR2, FPMISC) >= 1; + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; } static inline bool isar_feature_aa32_vcvt_dr(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr2, MVFR2, FPMISC) >= 2; + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 2; } static inline bool isar_feature_aa32_vrint(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr2, MVFR2, FPMISC) >= 3; + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 3; } static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr2, MVFR2, FPMISC) >= 4; + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 4; } static inline bool isar_feature_aa32_pan(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr0, ID_MMFR3, PAN) != 0; + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) != 0; } static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id) { - return FIELD_EX64(id->mvfr0, ID_MMFR3, PAN) >= 2; + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) >= 2; +} + +static inline bool isar_feature_aa32_pmu_8_1(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 4 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_pmu_8_4(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 5 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0; +} + +static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; } /* @@ -3653,6 +3715,41 @@ static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; } +static inline bool isar_feature_aa64_pmu_8_1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_pmu_8_4(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && + FIELD_EX32(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +/* + * Feature tests for "does this exist in either 32-bit or 64-bit?" + */ +static inline bool isar_feature_any_fp16(const ARMISARegisters *id) +{ + return isar_feature_aa64_fp16(id) || isar_feature_aa32_fp16_arith(id); +} + +static inline bool isar_feature_any_predinv(const ARMISARegisters *id) +{ + return isar_feature_aa64_predinv(id) || isar_feature_aa32_predinv(id); +} + +static inline bool isar_feature_any_pmu_8_1(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmu_8_1(id) || isar_feature_aa32_pmu_8_1(id); +} + +static inline bool isar_feature_any_pmu_8_4(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmu_8_4(id) || isar_feature_aa32_pmu_8_4(id); +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index f0d98bc79d..0929401a4d 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -121,12 +121,12 @@ static void aarch64_a57_initfn(Object *obj) cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; cpu->id_pfr1 = 0x00011011; - cpu->id_dfr0 = 0x03010066; + cpu->isar.id_dfr0 = 0x03010066; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x10101105; - cpu->id_mmfr1 = 0x40000000; - cpu->id_mmfr2 = 0x01260000; - cpu->id_mmfr3 = 0x02102211; + cpu->isar.id_mmfr0 = 0x10101105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02102211; cpu->isar.id_isar0 = 0x02101110; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232042; @@ -135,10 +135,10 @@ static void aarch64_a57_initfn(Object *obj) cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_isar6 = 0; cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->id_aa64dfr0 = 0x10305106; + cpu->isar.id_aa64dfr0 = 0x10305106; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; - cpu->dbgdidr = 0x3516d000; + cpu->isar.dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */ @@ -175,12 +175,12 @@ static void aarch64_a53_initfn(Object *obj) cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; cpu->id_pfr1 = 0x00011011; - cpu->id_dfr0 = 0x03010066; + cpu->isar.id_dfr0 = 0x03010066; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x10101105; - cpu->id_mmfr1 = 0x40000000; - cpu->id_mmfr2 = 0x01260000; - cpu->id_mmfr3 = 0x02102211; + cpu->isar.id_mmfr0 = 0x10101105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02102211; cpu->isar.id_isar0 = 0x02101110; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232042; @@ -189,10 +189,10 @@ static void aarch64_a53_initfn(Object *obj) cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_isar6 = 0; cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->id_aa64dfr0 = 0x10305106; + cpu->isar.id_aa64dfr0 = 0x10305106; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */ - cpu->dbgdidr = 0x3516d000; + cpu->isar.dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */ cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */ @@ -228,12 +228,12 @@ static void aarch64_a72_initfn(Object *obj) cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; cpu->id_pfr1 = 0x00011011; - cpu->id_dfr0 = 0x03010066; + cpu->isar.id_dfr0 = 0x03010066; cpu->id_afr0 = 0x00000000; - cpu->id_mmfr0 = 0x10201105; - cpu->id_mmfr1 = 0x40000000; - cpu->id_mmfr2 = 0x01260000; - cpu->id_mmfr3 = 0x02102211; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02102211; cpu->isar.id_isar0 = 0x02101110; cpu->isar.id_isar1 = 0x13112111; cpu->isar.id_isar2 = 0x21232042; @@ -241,10 +241,10 @@ static void aarch64_a72_initfn(Object *obj) cpu->isar.id_isar4 = 0x00011142; cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->id_aa64dfr0 = 0x10305106; + cpu->isar.id_aa64dfr0 = 0x10305106; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; - cpu->dbgdidr = 0x3516d000; + cpu->isar.dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */ @@ -699,9 +699,21 @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_ISAR6, SPECRES, 1); cpu->isar.id_isar6 = u; - u = cpu->id_mmfr3; + u = cpu->isar.id_mmfr3; u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */ - cpu->id_mmfr3 = u; + cpu->isar.id_mmfr3 = u; + + u = cpu->isar.id_mmfr4; + u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ + cpu->isar.id_mmfr4 = u; + + u = cpu->isar.id_aa64dfr0; + u = FIELD_DP64(u, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ + cpu->isar.id_aa64dfr0 = u; + + u = cpu->isar.id_dfr0; + u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ + cpu->isar.id_dfr0 = u; /* * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index 2e3e90c6a5..2ff72d47d1 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -16,8 +16,8 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) { CPUARMState *env = &cpu->env; uint64_t bcr = env->cp15.dbgbcr[lbn]; - int brps = extract32(cpu->dbgdidr, 24, 4); - int ctx_cmps = extract32(cpu->dbgdidr, 20, 4); + int brps = arm_num_brps(cpu); + int ctx_cmps = arm_num_ctx_cmps(cpu); int bt; uint32_t contextidr; uint64_t hcr_el2; @@ -29,7 +29,7 @@ static bool linked_bp_matches(ARMCPU *cpu, int lbn) * case DBGWCR<n>_EL1.LBN must indicate that breakpoint). * We choose the former. */ - if (lbn > brps || lbn < (brps - ctx_cmps)) { + if (lbn >= brps || lbn < (brps - ctx_cmps)) { return false; } diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index 9e79182ab4..2f47279155 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -1574,3 +1574,5 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/helper.c b/target/arm/helper.c index 366dbcf460..79db169e04 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -25,6 +25,7 @@ #include "hw/semihosting/semihost.h" #include "sysemu/cpus.h" #include "sysemu/kvm.h" +#include "sysemu/tcg.h" #include "qemu/range.h" #include "qapi/qapi-commands-machine-target.h" #include "qapi/error.h" @@ -49,10 +50,10 @@ static void switch_mode(CPUARMState *env, int mode); static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg) { - int nregs; + ARMCPU *cpu = env_archcpu(env); + int nregs = cpu_isar_feature(aa32_simd_r32, cpu) ? 32 : 16; /* VFP data registers are always little-endian. */ - nregs = arm_feature(env, ARM_FEATURE_VFP3) ? 32 : 16; if (reg < nregs) { stq_le_p(buf, *aa32_vfp_dreg(env, reg)); return 8; @@ -77,9 +78,9 @@ static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg) static int vfp_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) { - int nregs; + ARMCPU *cpu = env_archcpu(env); + int nregs = cpu_isar_feature(aa32_simd_r32, cpu) ? 32 : 16; - nregs = arm_feature(env, ARM_FEATURE_VFP3) ? 32 : 16; if (reg < nregs) { *aa32_vfp_dreg(env, reg) = ldq_le_p(buf); return 8; @@ -905,8 +906,7 @@ static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, /* VFPv3 and upwards with NEON implement 32 double precision * registers (D0-D31). */ - if (!arm_feature(env, ARM_FEATURE_NEON) || - !arm_feature(env, ARM_FEATURE_VFP3)) { + if (!cpu_isar_feature(aa32_simd_r32, env_archcpu(env))) { /* D32DIS [30] is RAO/WI if D16-31 are not implemented. */ value |= (1 << 30); } @@ -1016,11 +1016,17 @@ static const ARMCPRegInfo v6_cp_reginfo[] = { #define PMCRN_MASK 0xf800 #define PMCRN_SHIFT 11 #define PMCRLC 0x40 -#define PMCRDP 0x10 +#define PMCRDP 0x20 +#define PMCRX 0x10 #define PMCRD 0x8 #define PMCRC 0x4 #define PMCRP 0x2 #define PMCRE 0x1 +/* + * Mask of PMCR bits writeable by guest (not including WO bits like C, P, + * which can be written as 1 to trigger behaviour but which stay RAZ). + */ +#define PMCR_WRITEABLE_MASK (PMCRLC | PMCRDP | PMCRX | PMCRD | PMCRE) #define PMXEVTYPER_P 0x80000000 #define PMXEVTYPER_U 0x40000000 @@ -1123,6 +1129,30 @@ static int64_t instructions_ns_per(uint64_t icount) } #endif +static bool pmu_8_1_events_supported(CPUARMState *env) +{ + /* For events which are supported in any v8.1 PMU */ + return cpu_isar_feature(any_pmu_8_1, env_archcpu(env)); +} + +static bool pmu_8_4_events_supported(CPUARMState *env) +{ + /* For events which are supported in any v8.1 PMU */ + return cpu_isar_feature(any_pmu_8_4, env_archcpu(env)); +} + +static uint64_t zero_event_get_count(CPUARMState *env) +{ + /* For events which on QEMU never fire, so their count is always zero */ + return 0; +} + +static int64_t zero_event_ns_per(uint64_t cycles) +{ + /* An event which never fires can never overflow */ + return -1; +} + static const pm_event pm_events[] = { { .number = 0x000, /* SW_INCR */ .supported = event_always_supported, @@ -1139,8 +1169,23 @@ static const pm_event pm_events[] = { .supported = event_always_supported, .get_count = cycles_get_count, .ns_per_count = cycles_ns_per, - } + }, #endif + { .number = 0x023, /* STALL_FRONTEND */ + .supported = pmu_8_1_events_supported, + .get_count = zero_event_get_count, + .ns_per_count = zero_event_ns_per, + }, + { .number = 0x024, /* STALL_BACKEND */ + .supported = pmu_8_1_events_supported, + .get_count = zero_event_get_count, + .ns_per_count = zero_event_ns_per, + }, + { .number = 0x03c, /* STALL */ + .supported = pmu_8_4_events_supported, + .get_count = zero_event_get_count, + .ns_per_count = zero_event_ns_per, + }, }; /* @@ -1149,7 +1194,7 @@ static const pm_event pm_events[] = { * should first be updated to something sparse instead of the current * supported_event_map[] array. */ -#define MAX_EVENT_ID 0x11 +#define MAX_EVENT_ID 0x3c #define UNSUPPORTED_EVENT UINT16_MAX static uint16_t supported_event_map[MAX_EVENT_ID + 1]; @@ -1536,9 +1581,8 @@ static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, } } - /* only the DP, X, D and E bits are writable */ - env->cp15.c9_pmcr &= ~0x39; - env->cp15.c9_pmcr |= (value & 0x39); + env->cp15.c9_pmcr &= ~PMCR_WRITEABLE_MASK; + env->cp15.c9_pmcr |= (value & PMCR_WRITEABLE_MASK); pmu_op_finish(env); } @@ -6251,26 +6295,16 @@ static void define_debug_regs(ARMCPU *cpu) ARMCPRegInfo dbgdidr = { .name = "DBGDIDR", .cp = 14, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 0, .access = PL0_R, .accessfn = access_tda, - .type = ARM_CP_CONST, .resetvalue = cpu->dbgdidr, + .type = ARM_CP_CONST, .resetvalue = cpu->isar.dbgdidr, }; /* Note that all these register fields hold "number of Xs minus 1". */ - brps = extract32(cpu->dbgdidr, 24, 4); - wrps = extract32(cpu->dbgdidr, 28, 4); - ctx_cmps = extract32(cpu->dbgdidr, 20, 4); + brps = arm_num_brps(cpu); + wrps = arm_num_wrps(cpu); + ctx_cmps = arm_num_ctx_cmps(cpu); assert(ctx_cmps <= brps); - /* The DBGDIDR and ID_AA64DFR0_EL1 define various properties - * of the debug registers such as number of breakpoints; - * check that if they both exist then they agree. - */ - if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { - assert(extract32(cpu->id_aa64dfr0, 12, 4) == brps); - assert(extract32(cpu->id_aa64dfr0, 20, 4) == wrps); - assert(extract32(cpu->id_aa64dfr0, 28, 4) == ctx_cmps); - } - define_one_arm_cp_reg(cpu, &dbgdidr); define_arm_cp_regs(cpu, debug_cp_reginfo); @@ -6278,7 +6312,7 @@ static void define_debug_regs(ARMCPU *cpu) define_arm_cp_regs(cpu, debug_lpae_cp_reginfo); } - for (i = 0; i < brps + 1; i++) { + for (i = 0; i < brps; i++) { ARMCPRegInfo dbgregs[] = { { .name = "DBGBVR", .state = ARM_CP_STATE_BOTH, .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 4, @@ -6297,7 +6331,7 @@ static void define_debug_regs(ARMCPU *cpu) define_arm_cp_regs(cpu, dbgregs); } - for (i = 0; i < wrps + 1; i++) { + for (i = 0; i < wrps; i++) { ARMCPRegInfo dbgregs[] = { { .name = "DBGWVR", .state = ARM_CP_STATE_BOTH, .cp = 14, .opc0 = 2, .opc1 = 0, .crn = 0, .crm = i, .opc2 = 6, @@ -6317,6 +6351,96 @@ static void define_debug_regs(ARMCPU *cpu) } } +static void define_pmu_regs(ARMCPU *cpu) +{ + /* + * v7 performance monitor control register: same implementor + * field as main ID register, and we implement four counters in + * addition to the cycle count register. + */ + unsigned int i, pmcrn = 4; + ARMCPRegInfo pmcr = { + .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, + .access = PL0_RW, + .type = ARM_CP_IO | ARM_CP_ALIAS, + .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmcr), + .accessfn = pmreg_access, .writefn = pmcr_write, + .raw_writefn = raw_write, + }; + ARMCPRegInfo pmcr64 = { + .name = "PMCR_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 0, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr), + .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT) | + PMCRLC, + .writefn = pmcr_write, .raw_writefn = raw_write, + }; + define_one_arm_cp_reg(cpu, &pmcr); + define_one_arm_cp_reg(cpu, &pmcr64); + for (i = 0; i < pmcrn; i++) { + char *pmevcntr_name = g_strdup_printf("PMEVCNTR%d", i); + char *pmevcntr_el0_name = g_strdup_printf("PMEVCNTR%d_EL0", i); + char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i); + char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i); + ARMCPRegInfo pmev_regs[] = { + { .name = pmevcntr_name, .cp = 15, .crn = 14, + .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .accessfn = pmreg_access }, + { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 8 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .raw_readfn = pmevcntr_rawread, + .raw_writefn = pmevcntr_rawwrite }, + { .name = pmevtyper_name, .cp = 15, .crn = 14, + .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .accessfn = pmreg_access }, + { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 12 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .raw_writefn = pmevtyper_rawwrite }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, pmev_regs); + g_free(pmevcntr_name); + g_free(pmevcntr_el0_name); + g_free(pmevtyper_name); + g_free(pmevtyper_el0_name); + } + if (cpu_isar_feature(aa32_pmu_8_1, cpu)) { + ARMCPRegInfo v81_pmu_regs[] = { + { .name = "PMCEID2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 4, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid0, 32, 32) }, + { .name = "PMCEID3", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 5, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid1, 32, 32) }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, v81_pmu_regs); + } + if (cpu_isar_feature(any_pmu_8_4, cpu)) { + static const ARMCPRegInfo v84_pmmir = { + .name = "PMMIR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 6, + .access = PL1_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = 0 + }; + define_one_arm_cp_reg(cpu, &v84_pmmir); + } +} + /* We don't know until after realize whether there's a GICv3 * attached, and that is what registers the gicv3 sysregs. * So we have to fill in the GIC fields in ID_PFR/ID_PFR1_EL1/ID_AA64PFR0_EL1 @@ -6737,6 +6861,27 @@ static const ARMCPRegInfo ats1cp_reginfo[] = { }; #endif +/* + * ACTLR2 and HACTLR2 map to ACTLR_EL1[63:32] and + * ACTLR_EL2[63:32]. They exist only if the ID_MMFR4.AC2 field + * is non-zero, which is never for ARMv7, optionally in ARMv8 + * and mandatorily for ARMv8.2 and up. + * ACTLR2 is banked for S and NS if EL3 is AArch32. Since QEMU's + * implementation is RAZ/WI we can ignore this detail, as we + * do for ACTLR. + */ +static const ARMCPRegInfo actlr2_hactlr2_reginfo[] = { + { .name = "ACTLR2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 1, .crm = 0, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, + .resetvalue = 0 }, + { .name = "HACTLR2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 4, .crn = 1, .crm = 0, .opc2 = 3, + .access = PL2_RW, .type = ARM_CP_CONST, + .resetvalue = 0 }, + REGINFO_SENTINEL +}; + void register_cp_regs_for_features(ARMCPU *cpu) { /* Register all the coprocessor registers based on feature bits */ @@ -6775,7 +6920,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_dfr0 }, + .resetvalue = cpu->isar.id_dfr0 }, { .name = "ID_AFR0", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, @@ -6785,22 +6930,22 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_mmfr0 }, + .resetvalue = cpu->isar.id_mmfr0 }, { .name = "ID_MMFR1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 5, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_mmfr1 }, + .resetvalue = cpu->isar.id_mmfr1 }, { .name = "ID_MMFR2", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 6, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_mmfr2 }, + .resetvalue = cpu->isar.id_mmfr2 }, { .name = "ID_MMFR3", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 1, .opc2 = 7, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_mmfr3 }, + .resetvalue = cpu->isar.id_mmfr3 }, { .name = "ID_ISAR0", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, @@ -6835,7 +6980,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 6, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa32_tid3, - .resetvalue = cpu->id_mmfr4 }, + .resetvalue = cpu->isar.id_mmfr4 }, { .name = "ID_ISAR6", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 7, .access = PL1_R, .type = ARM_CP_CONST, @@ -6859,67 +7004,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, pmovsset_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_V7)) { - /* v7 performance monitor control register: same implementor - * field as main ID register, and we implement four counters in - * addition to the cycle count register. - */ - unsigned int i, pmcrn = 4; - ARMCPRegInfo pmcr = { - .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, - .access = PL0_RW, - .type = ARM_CP_IO | ARM_CP_ALIAS, - .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmcr), - .accessfn = pmreg_access, .writefn = pmcr_write, - .raw_writefn = raw_write, - }; - ARMCPRegInfo pmcr64 = { - .name = "PMCR_EL0", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 0, - .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_IO, - .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr), - .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT), - .writefn = pmcr_write, .raw_writefn = raw_write, - }; - define_one_arm_cp_reg(cpu, &pmcr); - define_one_arm_cp_reg(cpu, &pmcr64); - for (i = 0; i < pmcrn; i++) { - char *pmevcntr_name = g_strdup_printf("PMEVCNTR%d", i); - char *pmevcntr_el0_name = g_strdup_printf("PMEVCNTR%d_EL0", i); - char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i); - char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i); - ARMCPRegInfo pmev_regs[] = { - { .name = pmevcntr_name, .cp = 15, .crn = 14, - .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, - .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, - .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, - .accessfn = pmreg_access }, - { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 8 | (3 & (i >> 3)), - .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_IO, - .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, - .raw_readfn = pmevcntr_rawread, - .raw_writefn = pmevcntr_rawwrite }, - { .name = pmevtyper_name, .cp = 15, .crn = 14, - .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, - .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, - .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, - .accessfn = pmreg_access }, - { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 12 | (3 & (i >> 3)), - .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, - .type = ARM_CP_IO, - .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, - .raw_writefn = pmevtyper_rawwrite }, - REGINFO_SENTINEL - }; - define_arm_cp_regs(cpu, pmev_regs); - g_free(pmevcntr_name); - g_free(pmevcntr_el0_name); - g_free(pmevtyper_name); - g_free(pmevtyper_el0_name); - } ARMCPRegInfo clidr = { .name = "CLIDR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1, @@ -6930,24 +7014,10 @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &clidr); define_arm_cp_regs(cpu, v7_cp_reginfo); define_debug_regs(cpu); + define_pmu_regs(cpu); } else { define_arm_cp_regs(cpu, not_v7_cp_reginfo); } - if (FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) >= 4 && - FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) != 0xf) { - ARMCPRegInfo v81_pmu_regs[] = { - { .name = "PMCEID2", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 4, - .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = extract64(cpu->pmceid0, 32, 32) }, - { .name = "PMCEID3", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 5, - .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = extract64(cpu->pmceid1, 32, 32) }, - REGINFO_SENTINEL - }; - define_arm_cp_regs(cpu, v81_pmu_regs); - } if (arm_feature(env, ARM_FEATURE_V8)) { /* AArch64 ID registers, which all have impdef reset values. * Note that within the ID register ranges the unused slots @@ -7005,12 +7075,12 @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 5, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - .resetvalue = cpu->id_aa64dfr0 }, + .resetvalue = cpu->isar.id_aa64dfr0 }, { .name = "ID_AA64DFR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 5, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, .accessfn = access_aa64_tid3, - .resetvalue = cpu->id_aa64dfr1 }, + .resetvalue = cpu->isar.id_aa64dfr1 }, { .name = "ID_AA64DFR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 5, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, @@ -7358,8 +7428,8 @@ void register_cp_regs_for_features(ARMCPU *cpu) } else { define_arm_cp_regs(cpu, vmsa_pmsa_cp_reginfo); define_arm_cp_regs(cpu, vmsa_cp_reginfo); - /* TTCBR2 is introduced with ARMv8.2-A32HPD. */ - if (FIELD_EX32(cpu->id_mmfr4, ID_MMFR4, HPDS) != 0) { + /* TTCBR2 is introduced with ARMv8.2-AA32HPD. */ + if (cpu_isar_feature(aa32_hpd, cpu)) { define_one_arm_cp_reg(cpu, &ttbcr2_reginfo); } } @@ -7396,7 +7466,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_LPAE)) { define_arm_cp_regs(cpu, lpae_cp_reginfo); } - if (cpu_isar_feature(jazelle, cpu)) { + if (cpu_isar_feature(aa32_jazelle, cpu)) { define_arm_cp_regs(cpu, jazelle_regs); } /* Slightly awkwardly, the OMAP and StrongARM cores need all of @@ -7573,15 +7643,8 @@ void register_cp_regs_for_features(ARMCPU *cpu) REGINFO_SENTINEL }; define_arm_cp_regs(cpu, auxcr_reginfo); - if (arm_feature(env, ARM_FEATURE_V8)) { - /* HACTLR2 maps to ACTLR_EL2[63:32] and is not in ARMv7 */ - ARMCPRegInfo hactlr2_reginfo = { - .name = "HACTLR2", .state = ARM_CP_STATE_AA32, - .cp = 15, .opc1 = 4, .crn = 1, .crm = 0, .opc2 = 3, - .access = PL2_RW, .type = ARM_CP_CONST, - .resetvalue = 0 - }; - define_one_arm_cp_reg(cpu, &hactlr2_reginfo); + if (cpu_isar_feature(aa32_ac2, cpu)) { + define_arm_cp_regs(cpu, actlr2_hactlr2_reginfo); } } @@ -7721,14 +7784,7 @@ void register_cp_regs_for_features(ARMCPU *cpu) #endif /*CONFIG_USER_ONLY*/ #endif - /* - * While all v8.0 cpus support aarch64, QEMU does have configurations - * that do not set ID_AA64ISAR1, e.g. user-only qemu-arm -cpu max, - * which will set ID_ISAR6. - */ - if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) - ? cpu_isar_feature(aa64_predinv, cpu) - : cpu_isar_feature(aa32_predinv, cpu)) { + if (cpu_isar_feature(any_predinv, cpu)) { define_arm_cp_regs(cpu, predinv_reginfo); } @@ -7755,7 +7811,7 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) } else if (arm_feature(env, ARM_FEATURE_NEON)) { gdb_register_coprocessor(cs, vfp_gdb_get_reg, vfp_gdb_set_reg, 51, "arm-neon.xml", 0); - } else if (arm_feature(env, ARM_FEATURE_VFP3)) { + } else if (cpu_isar_feature(aa32_simd_r32, cpu)) { gdb_register_coprocessor(cs, vfp_gdb_get_reg, vfp_gdb_set_reg, 35, "arm-vfp3.xml", 0); } else if (arm_feature(env, ARM_FEATURE_VFP)) { @@ -8858,7 +8914,7 @@ static void take_aarch32_exception(CPUARMState *env, int new_mode, env->elr_el[2] = env->regs[15]; } else { /* CPSR.PAN is normally preserved preserved unless... */ - if (cpu_isar_feature(aa64_pan, env_archcpu(env))) { + if (cpu_isar_feature(aa32_pan, env_archcpu(env))) { switch (new_el) { case 3: if (!arm_is_secure_below_el3(env)) { @@ -10234,58 +10290,82 @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) } #endif /* !CONFIG_USER_ONLY */ -ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, - ARMMMUIdx mmu_idx) +static int aa64_va_parameter_tbi(uint64_t tcr, ARMMMUIdx mmu_idx) { - uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; - bool tbi, tbid, epd, hpd, using16k, using64k; - int select, tsz; + if (regime_has_2_ranges(mmu_idx)) { + return extract64(tcr, 37, 2); + } else if (mmu_idx == ARMMMUIdx_Stage2) { + return 0; /* VTCR_EL2 */ + } else { + return extract32(tcr, 20, 1); + } +} - /* - * Bit 55 is always between the two regions, and is canonical for - * determining if address tagging is enabled. - */ - select = extract64(va, 55, 1); +static int aa64_va_parameter_tbid(uint64_t tcr, ARMMMUIdx mmu_idx) +{ + if (regime_has_2_ranges(mmu_idx)) { + return extract64(tcr, 51, 2); + } else if (mmu_idx == ARMMMUIdx_Stage2) { + return 0; /* VTCR_EL2 */ + } else { + return extract32(tcr, 29, 1); + } +} + +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; + bool epd, hpd, using16k, using64k; + int select, tsz, tbi; if (!regime_has_2_ranges(mmu_idx)) { + select = 0; tsz = extract32(tcr, 0, 6); using64k = extract32(tcr, 14, 1); using16k = extract32(tcr, 15, 1); if (mmu_idx == ARMMMUIdx_Stage2) { /* VTCR_EL2 */ - tbi = tbid = hpd = false; + hpd = false; } else { - tbi = extract32(tcr, 20, 1); hpd = extract32(tcr, 24, 1); - tbid = extract32(tcr, 29, 1); } epd = false; - } else if (!select) { - tsz = extract32(tcr, 0, 6); - epd = extract32(tcr, 7, 1); - using64k = extract32(tcr, 14, 1); - using16k = extract32(tcr, 15, 1); - tbi = extract64(tcr, 37, 1); - hpd = extract64(tcr, 41, 1); - tbid = extract64(tcr, 51, 1); } else { - int tg = extract32(tcr, 30, 2); - using16k = tg == 1; - using64k = tg == 3; - tsz = extract32(tcr, 16, 6); - epd = extract32(tcr, 23, 1); - tbi = extract64(tcr, 38, 1); - hpd = extract64(tcr, 42, 1); - tbid = extract64(tcr, 52, 1); + /* + * Bit 55 is always between the two regions, and is canonical for + * determining if address tagging is enabled. + */ + select = extract64(va, 55, 1); + if (!select) { + tsz = extract32(tcr, 0, 6); + epd = extract32(tcr, 7, 1); + using64k = extract32(tcr, 14, 1); + using16k = extract32(tcr, 15, 1); + hpd = extract64(tcr, 41, 1); + } else { + int tg = extract32(tcr, 30, 2); + using16k = tg == 1; + using64k = tg == 3; + tsz = extract32(tcr, 16, 6); + epd = extract32(tcr, 23, 1); + hpd = extract64(tcr, 42, 1); + } } tsz = MIN(tsz, 39); /* TODO: ARMv8.4-TTST */ tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ + /* Present TBI as a composite with TBID. */ + tbi = aa64_va_parameter_tbi(tcr, mmu_idx); + if (!data) { + tbi &= ~aa64_va_parameter_tbid(tcr, mmu_idx); + } + tbi = (tbi >> select) & 1; + return (ARMVAParameters) { .tsz = tsz, .select = select, .tbi = tbi, - .tbid = tbid, .epd = epd, .hpd = hpd, .using16k = using16k, @@ -10293,16 +10373,6 @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, }; } -ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, - ARMMMUIdx mmu_idx, bool data) -{ - ARMVAParameters ret = aa64_va_parameters_both(env, va, mmu_idx); - - /* Present TBI as a composite with TBID. */ - ret.tbi &= (data || !ret.tbid); - return ret; -} - #ifndef CONFIG_USER_ONLY static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, ARMMMUIdx mmu_idx) @@ -10388,7 +10458,6 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, TCR *tcr = regime_tcr(env, mmu_idx); int ap, ns, xn, pxn; uint32_t el = regime_el(env, mmu_idx); - bool ttbr1_valid; uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); bool guarded = false; @@ -10403,14 +10472,11 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, param = aa64_va_parameters(env, address, mmu_idx, access_type != MMU_INST_FETCH); level = 0; - ttbr1_valid = regime_has_2_ranges(mmu_idx); addrsize = 64 - 8 * param.tbi; inputsize = 64 - param.tsz; } else { param = aa32_va_parameters(env, address, mmu_idx); level = 1; - /* There is no TTBR1 for EL2 */ - ttbr1_valid = (el != 2); addrsize = (mmu_idx == ARMMMUIdx_Stage2 ? 40 : 32); inputsize = addrsize - param.tsz; } @@ -10427,7 +10493,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, if (inputsize < addrsize) { target_ulong top_bits = sextract64(address, inputsize, addrsize - inputsize); - if (-top_bits != param.select || (param.select && !ttbr1_valid)) { + if (-top_bits != param.select) { /* The gap between the two regions is a Translation fault */ fault_type = ARMFault_Translation; goto do_fault; @@ -12136,21 +12202,15 @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, { uint32_t flags = rebuild_hflags_aprofile(env); ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); - ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; uint64_t sctlr; int tbii, tbid; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); /* Get control bits for tagged addresses. */ - if (regime_has_2_ranges(mmu_idx)) { - ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1); - tbid = (p1.tbi << 1) | p0.tbi; - tbii = tbid & ~((p1.tbid << 1) | p0.tbid); - } else { - tbid = p0.tbi; - tbii = tbid & !p0.tbid; - } + tbid = aa64_va_parameter_tbi(tcr, mmu_idx); + tbii = tbid & ~aa64_va_parameter_tbid(tcr, mmu_idx); flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); flags = FIELD_DP32(flags, TBFLAG_A64, TBID, tbid); diff --git a/target/arm/helper.h b/target/arm/helper.h index aa3d8cd08f..fcbf504121 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -303,14 +303,8 @@ DEF_HELPER_2(neon_abd_s16, i32, i32, i32) DEF_HELPER_2(neon_abd_u32, i32, i32, i32) DEF_HELPER_2(neon_abd_s32, i32, i32, i32) -DEF_HELPER_2(neon_shl_u8, i32, i32, i32) -DEF_HELPER_2(neon_shl_s8, i32, i32, i32) DEF_HELPER_2(neon_shl_u16, i32, i32, i32) DEF_HELPER_2(neon_shl_s16, i32, i32, i32) -DEF_HELPER_2(neon_shl_u32, i32, i32, i32) -DEF_HELPER_2(neon_shl_s32, i32, i32, i32) -DEF_HELPER_2(neon_shl_u64, i64, i64, i64) -DEF_HELPER_2(neon_shl_s64, i64, i64, i64) DEF_HELPER_2(neon_rshl_u8, i32, i32, i32) DEF_HELPER_2(neon_rshl_s8, i32, i32, i32) DEF_HELPER_2(neon_rshl_u16, i32, i32, i32) @@ -348,8 +342,6 @@ DEF_HELPER_2(neon_sub_u8, i32, i32, i32) DEF_HELPER_2(neon_sub_u16, i32, i32, i32) DEF_HELPER_2(neon_mul_u8, i32, i32, i32) DEF_HELPER_2(neon_mul_u16, i32, i32, i32) -DEF_HELPER_2(neon_mul_p8, i32, i32, i32) -DEF_HELPER_2(neon_mull_p8, i64, i32, i32) DEF_HELPER_2(neon_tst_u8, i32, i32, i32) DEF_HELPER_2(neon_tst_u16, i32, i32, i32) @@ -569,9 +561,6 @@ DEF_HELPER_FLAGS_3(crc32, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_FLAGS_3(crc32c, TCG_CALL_NO_RWG_SE, i32, i32, i32, i32) DEF_HELPER_2(dc_zva, void, env, i64) -DEF_HELPER_FLAGS_2(neon_pmull_64_lo, TCG_CALL_NO_RWG_SE, i64, i64, i64) -DEF_HELPER_FLAGS_2(neon_pmull_64_hi, TCG_CALL_NO_RWG_SE, i64, i64, i64) - DEF_HELPER_FLAGS_5(gvec_qrdmlah_s16, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s16, TCG_CALL_NO_RWG, @@ -697,6 +686,16 @@ DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ushl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_pmul_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(neon_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/internals.h b/target/arm/internals.h index 58c4d707c5..9f96a2359f 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -931,6 +931,48 @@ static inline uint32_t arm_debug_exception_fsr(CPUARMState *env) } } +/** + * arm_num_brps: Return number of implemented breakpoints. + * Note that the ID register BRPS field is "number of bps - 1", + * and we return the actual number of breakpoints. + */ +static inline int arm_num_brps(ARMCPU *cpu) +{ + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + return FIELD_EX64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, BRPS) + 1; + } else { + return FIELD_EX32(cpu->isar.dbgdidr, DBGDIDR, BRPS) + 1; + } +} + +/** + * arm_num_wrps: Return number of implemented watchpoints. + * Note that the ID register WRPS field is "number of wps - 1", + * and we return the actual number of watchpoints. + */ +static inline int arm_num_wrps(ARMCPU *cpu) +{ + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + return FIELD_EX64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, WRPS) + 1; + } else { + return FIELD_EX32(cpu->isar.dbgdidr, DBGDIDR, WRPS) + 1; + } +} + +/** + * arm_num_ctx_cmps: Return number of implemented context comparators. + * Note that the ID register CTX_CMPS field is "number of cmps - 1", + * and we return the actual number of comparators. + */ +static inline int arm_num_ctx_cmps(ARMCPU *cpu) +{ + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { + return FIELD_EX64(cpu->isar.id_aa64dfr0, ID_AA64DFR0, CTX_CMPS) + 1; + } else { + return FIELD_EX32(cpu->isar.dbgdidr, DBGDIDR, CTX_CMPS) + 1; + } +} + /* Note make_memop_idx reserves 4 bits for mmu_idx, and MO_BSWAP is bit 3. * Thus a TCGMemOpIdx, without any MO_ALIGN bits, fits in 8 bits. */ @@ -1091,7 +1133,7 @@ static inline uint32_t aarch32_cpsr_valid_mask(uint64_t features, if ((features >> ARM_FEATURE_THUMB2) & 1) { valid |= CPSR_IT; } - if (isar_feature_jazelle(id)) { + if (isar_feature_aa32_jazelle(id)) { valid |= CPSR_J; } if (isar_feature_aa32_pan(id)) { @@ -1127,15 +1169,12 @@ typedef struct ARMVAParameters { unsigned tsz : 8; unsigned select : 1; bool tbi : 1; - bool tbid : 1; bool epd : 1; bool hpd : 1; bool using16k : 1; bool using64k : 1; } ARMVAParameters; -ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, - ARMMMUIdx mmu_idx); ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data); diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index 3a8b437eef..7981ae3bc4 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -97,6 +97,9 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ahcf->isar.id_isar6 = 0; } + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_dfr0, + ARM_CP15_REG32(0, 0, 1, 2)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr0, KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR0); @@ -108,6 +111,28 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) * Fortunately there is not yet anything in there that affects migration. */ + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr0, + ARM_CP15_REG32(0, 0, 1, 4)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr1, + ARM_CP15_REG32(0, 0, 1, 5)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr2, + ARM_CP15_REG32(0, 0, 1, 6)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr3, + ARM_CP15_REG32(0, 0, 1, 7)); + if (read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr4, + ARM_CP15_REG32(0, 0, 2, 6))) { + /* + * Older kernels don't support reading ID_MMFR4 (a new in v8 + * register); assume it's zero. + */ + ahcf->isar.id_mmfr4 = 0; + } + + /* + * There is no way to read DBGDIDR, because currently 32-bit KVM + * doesn't implement debug at all. Leave it at zero. + */ + kvm_arm_destroy_scratch_host_vcpu(fdarray); if (err < 0) { diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index 3bae9e4a66..0ad96c3500 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -541,6 +541,10 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) } else { err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64pfr1, ARM64_SYS_REG(3, 0, 0, 4, 1)); + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64dfr0, + ARM64_SYS_REG(3, 0, 0, 5, 0)); + err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64dfr1, + ARM64_SYS_REG(3, 0, 0, 5, 1)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar0, ARM64_SYS_REG(3, 0, 0, 6, 0)); err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64isar1, @@ -559,6 +563,16 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) * than skipping the reads and leaving 0, as we must avoid * considering the values in every case. */ + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_dfr0, + ARM64_SYS_REG(3, 0, 0, 1, 2)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr0, + ARM64_SYS_REG(3, 0, 0, 1, 4)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr1, + ARM64_SYS_REG(3, 0, 0, 1, 5)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr2, + ARM64_SYS_REG(3, 0, 0, 1, 6)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr3, + ARM64_SYS_REG(3, 0, 0, 1, 7)); err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar0, ARM64_SYS_REG(3, 0, 0, 2, 0)); err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar1, @@ -571,6 +585,8 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ARM64_SYS_REG(3, 0, 0, 2, 4)); err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar5, ARM64_SYS_REG(3, 0, 0, 2, 5)); + err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_mmfr4, + ARM64_SYS_REG(3, 0, 0, 2, 6)); err |= read_sys_reg32(fdarray[2], &ahcf->isar.id_isar6, ARM64_SYS_REG(3, 0, 0, 2, 7)); @@ -580,6 +596,36 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) ARM64_SYS_REG(3, 0, 0, 3, 1)); err |= read_sys_reg32(fdarray[2], &ahcf->isar.mvfr2, ARM64_SYS_REG(3, 0, 0, 3, 2)); + + /* + * DBGDIDR is a bit complicated because the kernel doesn't + * provide an accessor for it in 64-bit mode, which is what this + * scratch VM is in, and there's no architected "64-bit sysreg + * which reads the same as the 32-bit register" the way there is + * for other ID registers. Instead we synthesize a value from the + * AArch64 ID_AA64DFR0, the same way the kernel code in + * arch/arm64/kvm/sys_regs.c:trap_dbgidr() does. + * We only do this if the CPU supports AArch32 at EL1. + */ + if (FIELD_EX32(ahcf->isar.id_aa64pfr0, ID_AA64PFR0, EL1) >= 2) { + int wrps = FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, WRPS); + int brps = FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, BRPS); + int ctx_cmps = + FIELD_EX64(ahcf->isar.id_aa64dfr0, ID_AA64DFR0, CTX_CMPS); + int version = 6; /* ARMv8 debug architecture */ + bool has_el3 = + !!FIELD_EX32(ahcf->isar.id_aa64pfr0, ID_AA64PFR0, EL3); + uint32_t dbgdidr = 0; + + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, WRPS, wrps); + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, BRPS, brps); + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, CTX_CMPS, ctx_cmps); + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, VERSION, version); + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, NSUHD_IMP, has_el3); + dbgdidr = FIELD_DP32(dbgdidr, DBGDIDR, SE_IMP, has_el3); + dbgdidr |= (1 << 15); /* RES1 bit */ + ahcf->isar.dbgdidr = dbgdidr; + } } sve_supported = ioctl(fdarray[0], KVM_CHECK_EXTENSION, KVM_CAP_ARM_SVE) > 0; diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index 4259056723..c7a8438b42 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -615,24 +615,9 @@ NEON_VOP(abd_u32, neon_u32, 1) } else { \ dest = src1 << tmp; \ }} while (0) -NEON_VOP(shl_u8, neon_u8, 4) NEON_VOP(shl_u16, neon_u16, 2) -NEON_VOP(shl_u32, neon_u32, 1) #undef NEON_FN -uint64_t HELPER(neon_shl_u64)(uint64_t val, uint64_t shiftop) -{ - int8_t shift = (int8_t)shiftop; - if (shift >= 64 || shift <= -64) { - val = 0; - } else if (shift < 0) { - val >>= -shift; - } else { - val <<= shift; - } - return val; -} - #define NEON_FN(dest, src1, src2) do { \ int8_t tmp; \ tmp = (int8_t)src2; \ @@ -645,27 +630,9 @@ uint64_t HELPER(neon_shl_u64)(uint64_t val, uint64_t shiftop) } else { \ dest = src1 << tmp; \ }} while (0) -NEON_VOP(shl_s8, neon_s8, 4) NEON_VOP(shl_s16, neon_s16, 2) -NEON_VOP(shl_s32, neon_s32, 1) #undef NEON_FN -uint64_t HELPER(neon_shl_s64)(uint64_t valop, uint64_t shiftop) -{ - int8_t shift = (int8_t)shiftop; - int64_t val = valop; - if (shift >= 64) { - val = 0; - } else if (shift <= -64) { - val >>= 63; - } else if (shift < 0) { - val >>= -shift; - } else { - val <<= shift; - } - return val; -} - #define NEON_FN(dest, src1, src2) do { \ int8_t tmp; \ tmp = (int8_t)src2; \ @@ -1162,60 +1129,6 @@ NEON_VOP(mul_u8, neon_u8, 4) NEON_VOP(mul_u16, neon_u16, 2) #undef NEON_FN -/* Polynomial multiplication is like integer multiplication except the - partial products are XORed, not added. */ -uint32_t HELPER(neon_mul_p8)(uint32_t op1, uint32_t op2) -{ - uint32_t mask; - uint32_t result; - result = 0; - while (op1) { - mask = 0; - if (op1 & 1) - mask |= 0xff; - if (op1 & (1 << 8)) - mask |= (0xff << 8); - if (op1 & (1 << 16)) - mask |= (0xff << 16); - if (op1 & (1 << 24)) - mask |= (0xff << 24); - result ^= op2 & mask; - op1 = (op1 >> 1) & 0x7f7f7f7f; - op2 = (op2 << 1) & 0xfefefefe; - } - return result; -} - -uint64_t HELPER(neon_mull_p8)(uint32_t op1, uint32_t op2) -{ - uint64_t result = 0; - uint64_t mask; - uint64_t op2ex = op2; - op2ex = (op2ex & 0xff) | - ((op2ex & 0xff00) << 8) | - ((op2ex & 0xff0000) << 16) | - ((op2ex & 0xff000000) << 24); - while (op1) { - mask = 0; - if (op1 & 1) { - mask |= 0xffff; - } - if (op1 & (1 << 8)) { - mask |= (0xffffU << 16); - } - if (op1 & (1 << 16)) { - mask |= (0xffffULL << 32); - } - if (op1 & (1 << 24)) { - mask |= (0xffffULL << 48); - } - result ^= op2ex & mask; - op1 = (op1 >> 1) & 0x7f7f7f7f; - op2ex <<= 1; - } - return result; -} - #define NEON_FN(dest, src1, src2) dest = (src1 & src2) ? -1 : 0 NEON_VOP(tst_u8, neon_u8, 4) NEON_VOP(tst_u16, neon_u16, 2) @@ -2207,33 +2120,3 @@ void HELPER(neon_zip16)(void *vd, void *vm) rm[0] = m0; rd[0] = d0; } - -/* Helper function for 64 bit polynomial multiply case: - * perform PolynomialMult(op1, op2) and return either the top or - * bottom half of the 128 bit result. - */ -uint64_t HELPER(neon_pmull_64_lo)(uint64_t op1, uint64_t op2) -{ - int bitnum; - uint64_t res = 0; - - for (bitnum = 0; bitnum < 64; bitnum++) { - if (op1 & (1ULL << bitnum)) { - res ^= op2 << bitnum; - } - } - return res; -} -uint64_t HELPER(neon_pmull_64_hi)(uint64_t op1, uint64_t op2) -{ - int bitnum; - uint64_t res = 0; - - /* bit 0 of op1 can't influence the high 64 bits at all */ - for (bitnum = 1; bitnum < 64; bitnum++) { - if (op1 & (1ULL << bitnum)) { - res ^= op2 >> (64 - bitnum); - } - } - return res; -} diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c index 9746e32bf8..b909630317 100644 --- a/target/arm/pauth_helper.c +++ b/target/arm/pauth_helper.c @@ -320,7 +320,8 @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) { - uint64_t extfield = -param.select; + /* Note that bit 55 is used whether or not the regime has 2 ranges. */ + uint64_t extfield = sextract64(ptr, 55, 1); int bot_pac_bit = 64 - param.tsz; int top_pac_bit = 64 - 8 * param.tbi; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 7c26c3bfeb..596bf4cf73 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -6895,6 +6895,7 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resl); write_vec_element(s, tcg_resh, rd, 1, MO_64); tcg_temp_free_i64(tcg_resh); + clear_vec_high(s, true, rd); } /* TBL/TBX @@ -6963,6 +6964,7 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resl); write_vec_element(s, tcg_resh, rd, 1, MO_64); tcg_temp_free_i64(tcg_resh); + clear_vec_high(s, true, rd); } /* ZIP/UZP/TRN @@ -7052,6 +7054,7 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_resl); write_vec_element(s, tcg_resh, rd, 1, MO_64); tcg_temp_free_i64(tcg_resh); + clear_vec_high(s, true, rd); } /* @@ -7409,6 +7412,9 @@ static void handle_simd_inse(DisasContext *s, int rd, int rn, write_vec_element(s, tmp, rd, dst_index, size); tcg_temp_free_i64(tmp); + + /* INS is considered a 128-bit write for SVE. */ + clear_vec_high(s, true, rd); } @@ -7438,6 +7444,9 @@ static void handle_simd_insg(DisasContext *s, int rd, int rn, int imm5) idx = extract32(imm5, 1 + size, 4 - size); write_vec_element(s, cpu_reg(s, rn), rd, idx, size); + + /* INS is considered a 128-bit write for SVE. */ + clear_vec_high(s, true, rd); } /* @@ -8735,9 +8744,9 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u, break; case 0x8: /* SSHL, USHL */ if (u) { - gen_helper_neon_shl_u64(tcg_rd, tcg_rn, tcg_rm); + gen_ushl_i64(tcg_rd, tcg_rn, tcg_rm); } else { - gen_helper_neon_shl_s64(tcg_rd, tcg_rn, tcg_rm); + gen_sshl_i64(tcg_rd, tcg_rn, tcg_rm); } break; case 0x9: /* SQSHL, UQSHL */ @@ -10533,10 +10542,6 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size, gen_helper_neon_addl_saturate_s32(tcg_passres, cpu_env, tcg_passres, tcg_passres); break; - case 14: /* PMULL */ - assert(size == 0); - gen_helper_neon_mull_p8(tcg_passres, tcg_op1, tcg_op2); - break; default: g_assert_not_reached(); } @@ -10648,30 +10653,6 @@ static void handle_3rd_narrowing(DisasContext *s, int is_q, int is_u, int size, clear_vec_high(s, is_q, rd); } -static void handle_pmull_64(DisasContext *s, int is_q, int rd, int rn, int rm) -{ - /* PMULL of 64 x 64 -> 128 is an odd special case because it - * is the only three-reg-diff instruction which produces a - * 128-bit wide result from a single operation. However since - * it's possible to calculate the two halves more or less - * separately we just use two helper calls. - */ - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op1, rn, is_q, MO_64); - read_vec_element(s, tcg_op2, rm, is_q, MO_64); - gen_helper_neon_pmull_64_lo(tcg_res, tcg_op1, tcg_op2); - write_vec_element(s, tcg_res, rd, 0, MO_64); - gen_helper_neon_pmull_64_hi(tcg_res, tcg_op1, tcg_op2); - write_vec_element(s, tcg_res, rd, 1, MO_64); - - tcg_temp_free_i64(tcg_op1); - tcg_temp_free_i64(tcg_op2); - tcg_temp_free_i64(tcg_res); -} - /* AdvSIMD three different * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+-----+------+------+ @@ -10724,11 +10705,21 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) handle_3rd_narrowing(s, is_q, is_u, size, opcode, rd, rn, rm); break; case 14: /* PMULL, PMULL2 */ - if (is_u || size == 1 || size == 2) { + if (is_u) { unallocated_encoding(s); return; } - if (size == 3) { + switch (size) { + case 0: /* PMULL.P8 */ + if (!fp_access_check(s)) { + return; + } + /* The Q field specifies lo/hi half input for this insn. */ + gen_gvec_op3_ool(s, true, rd, rn, rm, is_q, + gen_helper_neon_pmull_h); + break; + + case 3: /* PMULL.P64 */ if (!dc_isar_feature(aa64_pmull, s)) { unallocated_encoding(s); return; @@ -10736,10 +10727,16 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) if (!fp_access_check(s)) { return; } - handle_pmull_64(s, is_q, rd, rn, rm); - return; + /* The Q field specifies lo/hi half input for this insn. */ + gen_gvec_op3_ool(s, true, rd, rn, rm, is_q, + gen_helper_gvec_pmull_q); + break; + + default: + unallocated_encoding(s); + break; } - goto is_widening; + return; case 9: /* SQDMLAL, SQDMLAL2 */ case 11: /* SQDMLSL, SQDMLSL2 */ case 13: /* SQDMULL, SQDMULL2 */ @@ -10760,7 +10757,6 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - is_widening: if (!fp_access_check(s)) { return; } @@ -11132,6 +11128,10 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) is_q ? 16 : 8, vec_full_reg_size(s), (u ? uqsub_op : sqsub_op) + size); return; + case 0x08: /* SSHL, USHL */ + gen_gvec_op3(s, is_q, rd, rn, rm, + u ? &ushl_op[size] : &sshl_op[size]); + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -11156,9 +11156,10 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) case 0x13: /* MUL, PMUL */ if (!u) { /* MUL */ gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_mul, size); - return; + } else { /* PMUL */ + gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, gen_helper_gvec_pmul_b); } - break; + return; case 0x12: /* MLA, MLS */ if (u) { gen_gvec_op3(s, is_q, rd, rn, rm, &mls_op[size]); @@ -11247,16 +11248,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x8: /* SSHL, USHL */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_shl_s8, gen_helper_neon_shl_u8 }, - { gen_helper_neon_shl_s16, gen_helper_neon_shl_u16 }, - { gen_helper_neon_shl_s32, gen_helper_neon_shl_u32 }, - }; - genfn = fns[size][u]; - break; - } case 0x9: /* SQSHL, UQSHL */ { static NeonGenTwoOpEnvFn * const fns[3][2] = { @@ -11298,11 +11289,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x13: /* MUL, PMUL */ - assert(u); /* PMUL */ - assert(size == 0); - genfn = gen_helper_neon_mul_p8; - break; case 0x16: /* SQDMULH, SQRDMULH */ { static NeonGenTwoOpEnvFn * const fns[2][2] = { diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index bf90ac0e5b..ba46e2557a 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -201,7 +201,7 @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_fp_d32, s) && + if (dp && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -334,7 +334,7 @@ static bool trans_VMINMAXNM(DisasContext *s, arg_VMINMAXNM *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_fp_d32, s) && + if (dp && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -420,7 +420,7 @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_fp_d32, s) && + if (dp && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vd) & 0x10)) { return false; } @@ -484,7 +484,7 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (dp && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -556,7 +556,7 @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) uint32_t offset; /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vn & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vn & 0x10)) { return false; } @@ -615,7 +615,7 @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) uint32_t offset; /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vn & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vn & 0x10)) { return false; } @@ -662,7 +662,7 @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vn & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vn & 0x10)) { return false; } @@ -912,7 +912,7 @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) */ /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -978,7 +978,7 @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) TCGv_i64 tmp; /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -1101,7 +1101,7 @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd + n) > 16) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd + n) > 16) { return false; } @@ -1309,7 +1309,7 @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, TCGv_ptr fpst; /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((vd | vn | vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vn | vm) & 0x10)) { return false; } @@ -1458,7 +1458,7 @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) TCGv_i64 f0, fd; /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((vd | vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vm) & 0x10)) { return false; } @@ -1822,7 +1822,8 @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vn | a->vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { return false; } @@ -1921,7 +1922,7 @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) vd = a->vd; /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (vd & 0x10)) { return false; } @@ -2065,7 +2066,7 @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((a->vd | a->vm) & 0x10)) { return false; } @@ -2138,7 +2139,7 @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -2204,7 +2205,7 @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -2264,7 +2265,7 @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((a->vd | a->vm) & 0x10)) { return false; } @@ -2325,7 +2326,7 @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((a->vd | a->vm) & 0x10)) { return false; } @@ -2384,7 +2385,7 @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && ((a->vd | a->vm) & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && ((a->vd | a->vm) & 0x10)) { return false; } @@ -2412,7 +2413,7 @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) TCGv_i32 vm; /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -2440,7 +2441,7 @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) TCGv_i32 vd; /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -2494,7 +2495,7 @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) TCGv_ptr fpst; /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -2534,7 +2535,7 @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -2627,7 +2628,7 @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) } /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -2723,7 +2724,7 @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) TCGv_ptr fpst; /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } diff --git a/target/arm/translate.c b/target/arm/translate.c index 20f89ace2f..79880adaad 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -42,7 +42,7 @@ #define ENABLE_ARCH_5 arm_dc_feature(s, ARM_FEATURE_V5) /* currently all emulated v5 cores are also v5TE, so don't bother */ #define ENABLE_ARCH_5TE arm_dc_feature(s, ARM_FEATURE_V5) -#define ENABLE_ARCH_5J dc_isar_feature(jazelle, s) +#define ENABLE_ARCH_5J dc_isar_feature(aa32_jazelle, s) #define ENABLE_ARCH_6 arm_dc_feature(s, ARM_FEATURE_V6) #define ENABLE_ARCH_6K arm_dc_feature(s, ARM_FEATURE_V6K) #define ENABLE_ARCH_6T2 arm_dc_feature(s, ARM_FEATURE_THUMB2) @@ -2612,7 +2612,7 @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) #define VFP_SREG(insn, bigbit, smallbit) \ ((VFP_REG_SHR(insn, bigbit - 1) & 0x1e) | (((insn) >> (smallbit)) & 1)) #define VFP_DREG(reg, insn, bigbit, smallbit) do { \ - if (arm_dc_feature(s, ARM_FEATURE_VFP3)) { \ + if (dc_isar_feature(aa32_simd_r32, s)) { \ reg = (((insn) >> (bigbit)) & 0x0f) \ | (((insn) >> ((smallbit) - 4)) & 0x10); \ } else { \ @@ -3575,13 +3575,13 @@ static inline void gen_neon_shift_narrow(int size, TCGv_i32 var, TCGv_i32 shift, if (u) { switch (size) { case 1: gen_helper_neon_shl_u16(var, var, shift); break; - case 2: gen_helper_neon_shl_u32(var, var, shift); break; + case 2: gen_ushl_i32(var, var, shift); break; default: abort(); } } else { switch (size) { case 1: gen_helper_neon_shl_s16(var, var, shift); break; - case 2: gen_helper_neon_shl_s32(var, var, shift); break; + case 2: gen_sshl_i32(var, var, shift); break; default: abort(); } } @@ -4384,6 +4384,280 @@ const GVecGen3 cmtst_op[4] = { .vece = MO_64 }, }; +void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) +{ + TCGv_i32 lval = tcg_temp_new_i32(); + TCGv_i32 rval = tcg_temp_new_i32(); + TCGv_i32 lsh = tcg_temp_new_i32(); + TCGv_i32 rsh = tcg_temp_new_i32(); + TCGv_i32 zero = tcg_const_i32(0); + TCGv_i32 max = tcg_const_i32(32); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i32(lsh, shift); + tcg_gen_neg_i32(rsh, lsh); + tcg_gen_shl_i32(lval, src, lsh); + tcg_gen_shr_i32(rval, src, rsh); + tcg_gen_movcond_i32(TCG_COND_LTU, dst, lsh, max, lval, zero); + tcg_gen_movcond_i32(TCG_COND_LTU, dst, rsh, max, rval, dst); + + tcg_temp_free_i32(lval); + tcg_temp_free_i32(rval); + tcg_temp_free_i32(lsh); + tcg_temp_free_i32(rsh); + tcg_temp_free_i32(zero); + tcg_temp_free_i32(max); +} + +void gen_ushl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) +{ + TCGv_i64 lval = tcg_temp_new_i64(); + TCGv_i64 rval = tcg_temp_new_i64(); + TCGv_i64 lsh = tcg_temp_new_i64(); + TCGv_i64 rsh = tcg_temp_new_i64(); + TCGv_i64 zero = tcg_const_i64(0); + TCGv_i64 max = tcg_const_i64(64); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i64(lsh, shift); + tcg_gen_neg_i64(rsh, lsh); + tcg_gen_shl_i64(lval, src, lsh); + tcg_gen_shr_i64(rval, src, rsh); + tcg_gen_movcond_i64(TCG_COND_LTU, dst, lsh, max, lval, zero); + tcg_gen_movcond_i64(TCG_COND_LTU, dst, rsh, max, rval, dst); + + tcg_temp_free_i64(lval); + tcg_temp_free_i64(rval); + tcg_temp_free_i64(lsh); + tcg_temp_free_i64(rsh); + tcg_temp_free_i64(zero); + tcg_temp_free_i64(max); +} + +static void gen_ushl_vec(unsigned vece, TCGv_vec dst, + TCGv_vec src, TCGv_vec shift) +{ + TCGv_vec lval = tcg_temp_new_vec_matching(dst); + TCGv_vec rval = tcg_temp_new_vec_matching(dst); + TCGv_vec lsh = tcg_temp_new_vec_matching(dst); + TCGv_vec rsh = tcg_temp_new_vec_matching(dst); + TCGv_vec msk, max; + + tcg_gen_neg_vec(vece, rsh, shift); + if (vece == MO_8) { + tcg_gen_mov_vec(lsh, shift); + } else { + msk = tcg_temp_new_vec_matching(dst); + tcg_gen_dupi_vec(vece, msk, 0xff); + tcg_gen_and_vec(vece, lsh, shift, msk); + tcg_gen_and_vec(vece, rsh, rsh, msk); + tcg_temp_free_vec(msk); + } + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_shlv_vec(vece, lval, src, lsh); + tcg_gen_shrv_vec(vece, rval, src, rsh); + + max = tcg_temp_new_vec_matching(dst); + tcg_gen_dupi_vec(vece, max, 8 << vece); + + /* + * The choice of LT (signed) and GEU (unsigned) are biased toward + * the instructions of the x86_64 host. For MO_8, the whole byte + * is significant so we must use an unsigned compare; otherwise we + * have already masked to a byte and so a signed compare works. + * Other tcg hosts have a full set of comparisons and do not care. + */ + if (vece == MO_8) { + tcg_gen_cmp_vec(TCG_COND_GEU, vece, lsh, lsh, max); + tcg_gen_cmp_vec(TCG_COND_GEU, vece, rsh, rsh, max); + tcg_gen_andc_vec(vece, lval, lval, lsh); + tcg_gen_andc_vec(vece, rval, rval, rsh); + } else { + tcg_gen_cmp_vec(TCG_COND_LT, vece, lsh, lsh, max); + tcg_gen_cmp_vec(TCG_COND_LT, vece, rsh, rsh, max); + tcg_gen_and_vec(vece, lval, lval, lsh); + tcg_gen_and_vec(vece, rval, rval, rsh); + } + tcg_gen_or_vec(vece, dst, lval, rval); + + tcg_temp_free_vec(max); + tcg_temp_free_vec(lval); + tcg_temp_free_vec(rval); + tcg_temp_free_vec(lsh); + tcg_temp_free_vec(rsh); +} + +static const TCGOpcode ushl_list[] = { + INDEX_op_neg_vec, INDEX_op_shlv_vec, + INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0 +}; + +const GVecGen3 ushl_op[4] = { + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_b, + .opt_opc = ushl_list, + .vece = MO_8 }, + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_h, + .opt_opc = ushl_list, + .vece = MO_16 }, + { .fni4 = gen_ushl_i32, + .fniv = gen_ushl_vec, + .opt_opc = ushl_list, + .vece = MO_32 }, + { .fni8 = gen_ushl_i64, + .fniv = gen_ushl_vec, + .opt_opc = ushl_list, + .vece = MO_64 }, +}; + +void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) +{ + TCGv_i32 lval = tcg_temp_new_i32(); + TCGv_i32 rval = tcg_temp_new_i32(); + TCGv_i32 lsh = tcg_temp_new_i32(); + TCGv_i32 rsh = tcg_temp_new_i32(); + TCGv_i32 zero = tcg_const_i32(0); + TCGv_i32 max = tcg_const_i32(31); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i32(lsh, shift); + tcg_gen_neg_i32(rsh, lsh); + tcg_gen_shl_i32(lval, src, lsh); + tcg_gen_umin_i32(rsh, rsh, max); + tcg_gen_sar_i32(rval, src, rsh); + tcg_gen_movcond_i32(TCG_COND_LEU, lval, lsh, max, lval, zero); + tcg_gen_movcond_i32(TCG_COND_LT, dst, lsh, zero, rval, lval); + + tcg_temp_free_i32(lval); + tcg_temp_free_i32(rval); + tcg_temp_free_i32(lsh); + tcg_temp_free_i32(rsh); + tcg_temp_free_i32(zero); + tcg_temp_free_i32(max); +} + +void gen_sshl_i64(TCGv_i64 dst, TCGv_i64 src, TCGv_i64 shift) +{ + TCGv_i64 lval = tcg_temp_new_i64(); + TCGv_i64 rval = tcg_temp_new_i64(); + TCGv_i64 lsh = tcg_temp_new_i64(); + TCGv_i64 rsh = tcg_temp_new_i64(); + TCGv_i64 zero = tcg_const_i64(0); + TCGv_i64 max = tcg_const_i64(63); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_ext8s_i64(lsh, shift); + tcg_gen_neg_i64(rsh, lsh); + tcg_gen_shl_i64(lval, src, lsh); + tcg_gen_umin_i64(rsh, rsh, max); + tcg_gen_sar_i64(rval, src, rsh); + tcg_gen_movcond_i64(TCG_COND_LEU, lval, lsh, max, lval, zero); + tcg_gen_movcond_i64(TCG_COND_LT, dst, lsh, zero, rval, lval); + + tcg_temp_free_i64(lval); + tcg_temp_free_i64(rval); + tcg_temp_free_i64(lsh); + tcg_temp_free_i64(rsh); + tcg_temp_free_i64(zero); + tcg_temp_free_i64(max); +} + +static void gen_sshl_vec(unsigned vece, TCGv_vec dst, + TCGv_vec src, TCGv_vec shift) +{ + TCGv_vec lval = tcg_temp_new_vec_matching(dst); + TCGv_vec rval = tcg_temp_new_vec_matching(dst); + TCGv_vec lsh = tcg_temp_new_vec_matching(dst); + TCGv_vec rsh = tcg_temp_new_vec_matching(dst); + TCGv_vec tmp = tcg_temp_new_vec_matching(dst); + + /* + * Rely on the TCG guarantee that out of range shifts produce + * unspecified results, not undefined behaviour (i.e. no trap). + * Discard out-of-range results after the fact. + */ + tcg_gen_neg_vec(vece, rsh, shift); + if (vece == MO_8) { + tcg_gen_mov_vec(lsh, shift); + } else { + tcg_gen_dupi_vec(vece, tmp, 0xff); + tcg_gen_and_vec(vece, lsh, shift, tmp); + tcg_gen_and_vec(vece, rsh, rsh, tmp); + } + + /* Bound rsh so out of bound right shift gets -1. */ + tcg_gen_dupi_vec(vece, tmp, (8 << vece) - 1); + tcg_gen_umin_vec(vece, rsh, rsh, tmp); + tcg_gen_cmp_vec(TCG_COND_GT, vece, tmp, lsh, tmp); + + tcg_gen_shlv_vec(vece, lval, src, lsh); + tcg_gen_sarv_vec(vece, rval, src, rsh); + + /* Select in-bound left shift. */ + tcg_gen_andc_vec(vece, lval, lval, tmp); + + /* Select between left and right shift. */ + if (vece == MO_8) { + tcg_gen_dupi_vec(vece, tmp, 0); + tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, rval, lval); + } else { + tcg_gen_dupi_vec(vece, tmp, 0x80); + tcg_gen_cmpsel_vec(TCG_COND_LT, vece, dst, lsh, tmp, lval, rval); + } + + tcg_temp_free_vec(lval); + tcg_temp_free_vec(rval); + tcg_temp_free_vec(lsh); + tcg_temp_free_vec(rsh); + tcg_temp_free_vec(tmp); +} + +static const TCGOpcode sshl_list[] = { + INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec, + INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0 +}; + +const GVecGen3 sshl_op[4] = { + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_b, + .opt_opc = sshl_list, + .vece = MO_8 }, + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_h, + .opt_opc = sshl_list, + .vece = MO_16 }, + { .fni4 = gen_sshl_i32, + .fniv = gen_sshl_vec, + .opt_opc = sshl_list, + .vece = MO_32 }, + { .fni8 = gen_sshl_i64, + .fniv = gen_sshl_vec, + .opt_opc = sshl_list, + .vece = MO_64 }, +}; + static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b) { @@ -4733,16 +5007,17 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VMUL: /* VMUL */ if (u) { - /* Polynomial case allows only P8 and is handled below. */ + /* Polynomial case allows only P8. */ if (size != 0) { return 1; } + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, + 0, gen_helper_gvec_pmul_b); } else { tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); - return 0; } - break; + return 0; case NEON_3R_VML: /* VMLA, VMLS */ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, @@ -4787,6 +5062,12 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) vec_size, vec_size); } return 0; + + case NEON_3R_VSHL: + /* Note the operation is vshl vd,vm,vn */ + tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, + u ? &ushl_op[size] : &sshl_op[size]); + return 0; } if (size == 3) { @@ -4795,13 +5076,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rn + pass); neon_load_reg64(cpu_V1, rm + pass); switch (op) { - case NEON_3R_VSHL: - if (u) { - gen_helper_neon_shl_u64(cpu_V0, cpu_V1, cpu_V0); - } else { - gen_helper_neon_shl_s64(cpu_V0, cpu_V1, cpu_V0); - } - break; case NEON_3R_VQSHL: if (u) { gen_helper_neon_qshl_u64(cpu_V0, cpu_env, @@ -4836,7 +5110,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } pairwise = 0; switch (op) { - case NEON_3R_VSHL: case NEON_3R_VQSHL: case NEON_3R_VRSHL: case NEON_3R_VQRSHL: @@ -4916,9 +5189,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VHSUB: GEN_NEON_INTEGER_OP(hsub); break; - case NEON_3R_VSHL: - GEN_NEON_INTEGER_OP(shl); - break; case NEON_3R_VQSHL: GEN_NEON_INTEGER_OP_ENV(qshl); break; @@ -4937,10 +5207,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); break; - case NEON_3R_VMUL: - /* VMUL.P8; other cases already eliminated. */ - gen_helper_neon_mul_p8(tmp, tmp, tmp2); - break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); break; @@ -5327,9 +5593,9 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } } else { if (input_unsigned) { - gen_helper_neon_shl_u64(cpu_V0, in, tmp64); + gen_ushl_i64(cpu_V0, in, tmp64); } else { - gen_helper_neon_shl_s64(cpu_V0, in, tmp64); + gen_sshl_i64(cpu_V0, in, tmp64); } } tmp = tcg_temp_new_i32(); @@ -5600,27 +5866,20 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } - /* Handle VMULL.P64 (Polynomial 64x64 to 128 bit multiply) - * outside the loop below as it only performs a single pass. - */ - if (op == 14 && size == 2) { - TCGv_i64 tcg_rn, tcg_rm, tcg_rd; - - if (!dc_isar_feature(aa32_pmull, s)) { - return 1; + /* Handle polynomial VMULL in a single pass. */ + if (op == 14) { + if (size == 0) { + /* VMULL.P8 */ + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, 16, 16, + 0, gen_helper_neon_pmull_h); + } else { + /* VMULL.P64 */ + if (!dc_isar_feature(aa32_pmull, s)) { + return 1; + } + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, 16, 16, + 0, gen_helper_gvec_pmull_q); } - tcg_rn = tcg_temp_new_i64(); - tcg_rm = tcg_temp_new_i64(); - tcg_rd = tcg_temp_new_i64(); - neon_load_reg64(tcg_rn, rn); - neon_load_reg64(tcg_rm, rm); - gen_helper_neon_pmull_64_lo(tcg_rd, tcg_rn, tcg_rm); - neon_store_reg64(tcg_rd, rd); - gen_helper_neon_pmull_64_hi(tcg_rd, tcg_rn, tcg_rm); - neon_store_reg64(tcg_rd, rd + 1); - tcg_temp_free_i64(tcg_rn); - tcg_temp_free_i64(tcg_rm); - tcg_temp_free_i64(tcg_rd); return 0; } @@ -5698,11 +5957,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* VMLAL, VQDMLAL, VMLSL, VQDMLSL, VMULL, VQDMULL */ gen_neon_mull(cpu_V0, tmp, tmp2, size, u); break; - case 14: /* Polynomial VMULL */ - gen_helper_neon_mull_p8(cpu_V0, tmp, tmp2); - tcg_temp_free_i32(tmp2); - tcg_temp_free_i32(tmp); - break; default: /* 15 is RESERVED: caught earlier */ abort(); } @@ -9845,8 +10099,8 @@ static bool op_div(DisasContext *s, arg_rrr *a, bool u) TCGv_i32 t1, t2; if (s->thumb - ? !dc_isar_feature(thumb_div, s) - : !dc_isar_feature(arm_div, s)) { + ? !dc_isar_feature(aa32_thumb_div, s) + : !dc_isar_feature(aa32_arm_div, s)) { return false; } diff --git a/target/arm/translate.h b/target/arm/translate.h index 5b167c416a..d9ea0c99cc 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -278,6 +278,8 @@ uint64_t vfp_expand_imm(int size, uint8_t imm8); extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; +extern const GVecGen3 sshl_op[4]; +extern const GVecGen3 ushl_op[4]; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; @@ -287,6 +289,10 @@ extern const GVecGen4 sqadd_op[4]; extern const GVecGen4 uqsub_op[4]; extern const GVecGen4 sqsub_op[4]; void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); +void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index dedef62403..8017bd88c4 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -1046,3 +1046,214 @@ void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, do_fmlal_idx(vd, vn, vm, &env->vfp.fp_status, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } + +void HELPER(gvec_sshl_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + int8_t mm = m[i]; + int8_t nn = n[i]; + int8_t res = 0; + if (mm >= 0) { + if (mm < 8) { + res = nn << mm; + } + } else { + res = nn >> (mm > -8 ? -mm : 7); + } + d[i] = res; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_sshl_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + int16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + int8_t mm = m[i]; /* only 8 bits of shift are significant */ + int16_t nn = n[i]; + int16_t res = 0; + if (mm >= 0) { + if (mm < 16) { + res = nn << mm; + } + } else { + res = nn >> (mm > -16 ? -mm : 15); + } + d[i] = res; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_ushl_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint8_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz; ++i) { + int8_t mm = m[i]; + uint8_t nn = n[i]; + uint8_t res = 0; + if (mm >= 0) { + if (mm < 8) { + res = nn << mm; + } + } else { + if (mm > -8) { + res = nn >> -mm; + } + } + d[i] = res; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_ushl_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint16_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 2; ++i) { + int8_t mm = m[i]; /* only 8 bits of shift are significant */ + uint16_t nn = n[i]; + uint16_t res = 0; + if (mm >= 0) { + if (mm < 16) { + res = nn << mm; + } + } else { + if (mm > -16) { + res = nn >> -mm; + } + } + d[i] = res; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +/* + * 8x8->8 polynomial multiply. + * + * Polynomial multiplication is like integer multiplication except the + * partial products are XORed, not added. + * + * TODO: expose this as a generic vector operation, as it is a common + * crypto building block. + */ +void HELPER(gvec_pmul_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + uint64_t nn = n[i]; + uint64_t mm = m[i]; + uint64_t rr = 0; + + for (j = 0; j < 8; ++j) { + uint64_t mask = (nn & 0x0101010101010101ull) * 0xff; + rr ^= mm & mask; + mm = (mm << 1) & 0xfefefefefefefefeull; + nn >>= 1; + } + d[i] = rr; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +/* + * 64x64->128 polynomial multiply. + * Because of the lanes are not accessed in strict columns, + * this probably cannot be turned into a generic helper. + */ +void HELPER(gvec_pmull_q)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + intptr_t hi = simd_data(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; i += 2) { + uint64_t nn = n[i + hi]; + uint64_t mm = m[i + hi]; + uint64_t rhi = 0; + uint64_t rlo = 0; + + /* Bit 0 can only influence the low 64-bit result. */ + if (nn & 1) { + rlo = mm; + } + + for (j = 1; j < 64; ++j) { + uint64_t mask = -((nn >> j) & 1); + rlo ^= (mm << j) & mask; + rhi ^= (mm >> (64 - j)) & mask; + } + d[i] = rlo; + d[i + 1] = rhi; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +/* + * 8x8->16 polynomial multiply. + * + * The byte inputs are expanded to (or extracted from) half-words. + * Note that neon and sve2 get the inputs from different positions. + * This allows 4 bytes to be processed in parallel with uint64_t. + */ + +static uint64_t expand_byte_to_half(uint64_t x) +{ + return (x & 0x000000ff) + | ((x & 0x0000ff00) << 8) + | ((x & 0x00ff0000) << 16) + | ((x & 0xff000000) << 24); +} + +static uint64_t pmull_h(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; + + for (i = 0; i < 8; ++i) { + uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff; + result ^= op2 & mask; + op1 >>= 1; + op2 <<= 1; + } + return result; +} + +void HELPER(neon_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + int hi = simd_data(desc); + uint64_t *d = vd, *n = vn, *m = vm; + uint64_t nn = n[hi], mm = m[hi]; + + d[0] = pmull_h(expand_byte_to_half(nn), expand_byte_to_half(mm)); + nn >>= 32; + mm >>= 32; + d[1] = pmull_h(expand_byte_to_half(nn), expand_byte_to_half(mm)); + + clear_tail(d, 16, simd_maxsz(desc)); +} + +#ifdef TARGET_AARCH64 +void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + int shift = simd_data(desc) * 8; + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + uint64_t nn = (n[i] >> shift) & 0x00ff00ff00ff00ffull; + uint64_t mm = (m[i] >> shift) & 0x00ff00ff00ff00ffull; + + d[i] = pmull_h(nn, mm); + } +} +#endif diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index 0ae7d4f34a..930d6e747f 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -185,7 +185,7 @@ uint32_t vfp_get_fpscr(CPUARMState *env) void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) { /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!cpu_isar_feature(aa64_fp16, env_archcpu(env))) { + if (!cpu_isar_feature(any_fp16, env_archcpu(env))) { val &= ~FPCR_FZ16; } diff --git a/target/i386/fpu_helper.c b/target/i386/fpu_helper.c index 99f28f267f..792a128a6d 100644 --- a/target/i386/fpu_helper.c +++ b/target/i386/fpu_helper.c @@ -991,7 +991,11 @@ void helper_fxam_ST0(CPUX86State *env) env->fpus |= 0x200; /* C1 <-- 1 */ } - /* XXX: test fptags too */ + if (env->fptags[env->fpstt]) { + env->fpus |= 0x4100; /* Empty */ + return; + } + expdif = EXPD(temp); if (expdif == MAXEXPD) { if (MANTD(temp) == 0x8000000000000000ULL) { diff --git a/target/i386/whpx-all.c b/target/i386/whpx-all.c index 3ed2aa1892..35601b8176 100644 --- a/target/i386/whpx-all.c +++ b/target/i386/whpx-all.c @@ -511,7 +511,7 @@ static void whpx_get_registers(CPUState *cpu) /* WHvX64RegisterPat - Skipped */ assert(whpx_register_names[idx] == WHvX64RegisterSysenterCs); - env->sysenter_cs = vcxt.values[idx++].Reg64;; + env->sysenter_cs = vcxt.values[idx++].Reg64; assert(whpx_register_names[idx] == WHvX64RegisterSysenterEip); env->sysenter_eip = vcxt.values[idx++].Reg64; assert(whpx_register_names[idx] == WHvX64RegisterSysenterEsp); diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 3a1eb76004..b283042515 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -23,8 +23,6 @@ #include "qemu/int128.h" #include "exec/cpu-defs.h" #include "cpu-qom.h" -#include "exec/cpu-defs.h" -#include "cpu-qom.h" /* #define PPC_EMULATE_32BITS_HYPV */ @@ -962,117 +960,88 @@ struct ppc_radix_page_info { #define PPC_CPU_INDIRECT_OPCODES_LEN 0x20 struct CPUPPCState { - /* - * First are the most commonly used resources during translated - * code execution - */ - /* general purpose registers */ - target_ulong gpr[32]; - /* Storage for GPR MSB, used by the SPE extension */ - target_ulong gprh[32]; - /* LR */ + /* Most commonly used resources during translated code execution first */ + target_ulong gpr[32]; /* general purpose registers */ + target_ulong gprh[32]; /* storage for GPR MSB, used by the SPE extension */ target_ulong lr; - /* CTR */ target_ulong ctr; - /* condition register */ - uint32_t crf[8]; + uint32_t crf[8]; /* condition register */ #if defined(TARGET_PPC64) - /* CFAR */ target_ulong cfar; #endif - /* XER (with SO, OV, CA split out) */ - target_ulong xer; + target_ulong xer; /* XER (with SO, OV, CA split out) */ target_ulong so; target_ulong ov; target_ulong ca; target_ulong ov32; target_ulong ca32; - /* Reservation address */ - target_ulong reserve_addr; - /* Reservation value */ - target_ulong reserve_val; - target_ulong reserve_val2; - - /* Those ones are used in supervisor mode only */ - /* machine state register */ - target_ulong msr; - /* temporary general purpose registers */ - target_ulong tgpr[4]; /* Used to speed-up TLB assist handlers */ - /* Floating point execution context */ - float_status fp_status; - /* floating point status and control register */ - target_ulong fpscr; + target_ulong reserve_addr; /* Reservation address */ + target_ulong reserve_val; /* Reservation value */ + target_ulong reserve_val2; - /* Next instruction pointer */ - target_ulong nip; + /* These are used in supervisor mode only */ + target_ulong msr; /* machine state register */ + target_ulong tgpr[4]; /* temporary general purpose registers, */ + /* used to speed-up TLB assist handlers */ - /* High part of 128-bit helper return. */ - uint64_t retxh; + target_ulong nip; /* next instruction pointer */ + uint64_t retxh; /* high part of 128-bit helper return */ /* when a memory exception occurs, the access type is stored here */ int access_type; - /* MMU context - only relevant for full system emulation */ #if !defined(CONFIG_USER_ONLY) + /* MMU context, only relevant for full system emulation */ #if defined(TARGET_PPC64) - /* PowerPC 64 SLB area */ - ppc_slb_t slb[MAX_SLB_ENTRIES]; - /* tcg TLB needs flush (deferred slb inval instruction typically) */ + ppc_slb_t slb[MAX_SLB_ENTRIES]; /* PowerPC 64 SLB area */ #endif - /* segment registers */ - target_ulong sr[32]; - /* BATs */ - uint32_t nb_BATs; + target_ulong sr[32]; /* segment registers */ + uint32_t nb_BATs; /* number of BATs */ target_ulong DBAT[2][8]; target_ulong IBAT[2][8]; /* PowerPC TLB registers (for 4xx, e500 and 60x software driven TLBs) */ - int32_t nb_tlb; /* Total number of TLB */ + int32_t nb_tlb; /* Total number of TLB */ int tlb_per_way; /* Speed-up helper: used to avoid divisions at run time */ - int nb_ways; /* Number of ways in the TLB set */ - int last_way; /* Last used way used to allocate TLB in a LRU way */ + int nb_ways; /* Number of ways in the TLB set */ + int last_way; /* Last used way used to allocate TLB in a LRU way */ int id_tlbs; /* If 1, MMU has separated TLBs for instructions & data */ - int nb_pids; /* Number of available PID registers */ - int tlb_type; /* Type of TLB we're dealing with */ - ppc_tlb_t tlb; /* TLB is optional. Allocate them only if needed */ - /* 403 dedicated access protection registers */ - target_ulong pb[4]; - bool tlb_dirty; /* Set to non-zero when modifying TLB */ - bool kvm_sw_tlb; /* non-zero if KVM SW TLB API is active */ + int nb_pids; /* Number of available PID registers */ + int tlb_type; /* Type of TLB we're dealing with */ + ppc_tlb_t tlb; /* TLB is optional. Allocate them only if needed */ + target_ulong pb[4]; /* 403 dedicated access protection registers */ + bool tlb_dirty; /* Set to non-zero when modifying TLB */ + bool kvm_sw_tlb; /* non-zero if KVM SW TLB API is active */ uint32_t tlb_need_flush; /* Delayed flush needed */ #define TLB_NEED_LOCAL_FLUSH 0x1 #define TLB_NEED_GLOBAL_FLUSH 0x2 #endif /* Other registers */ - /* Special purpose registers */ - target_ulong spr[1024]; + target_ulong spr[1024]; /* special purpose registers */ ppc_spr_t spr_cb[1024]; - /* Vector status and control register, minus VSCR_SAT. */ + /* Vector status and control register, minus VSCR_SAT */ uint32_t vscr; /* VSX registers (including FP and AVR) */ ppc_vsr_t vsr[64] QEMU_ALIGNED(16); - /* Non-zero if and only if VSCR_SAT should be set. */ + /* Non-zero if and only if VSCR_SAT should be set */ ppc_vsr_t vscr_sat QEMU_ALIGNED(16); /* SPE registers */ uint64_t spe_acc; uint32_t spe_fscr; - /* - * SPE and Altivec can share a status since they will never be - * used simultaneously - */ + /* SPE and Altivec share status as they'll never be used simultaneously */ float_status vec_status; + float_status fp_status; /* Floating point execution context */ + target_ulong fpscr; /* Floating point status and control register */ /* Internal devices resources */ - /* Time base and decrementer */ - ppc_tb_t *tb_env; - /* Device control registers */ - ppc_dcr_t *dcr_env; + ppc_tb_t *tb_env; /* Time base and decrementer */ + ppc_dcr_t *dcr_env; /* Device control registers */ int dcache_line_size; int icache_line_size; - /* Those resources are used during exception processing */ + /* These resources are used during exception processing */ /* CPU model definition */ target_ulong msr_mask; powerpc_mmu_t mmu_model; @@ -1091,58 +1060,49 @@ struct CPUPPCState { uint32_t pending_interrupts; #if !defined(CONFIG_USER_ONLY) /* - * This is the IRQ controller, which is implementation dependent - * and only relevant when emulating a complete machine. Note that - * this isn't used by recent Book3s compatible CPUs (POWER7 and - * newer). + * This is the IRQ controller, which is implementation dependent and only + * relevant when emulating a complete machine. Note that this isn't used + * by recent Book3s compatible CPUs (POWER7 and newer). */ uint32_t irq_input_state; void **irq_inputs; - /* Exception vectors */ - target_ulong excp_vectors[POWERPC_EXCP_NB]; + + target_ulong excp_vectors[POWERPC_EXCP_NB]; /* Exception vectors */ target_ulong excp_prefix; target_ulong ivor_mask; target_ulong ivpr_mask; target_ulong hreset_vector; hwaddr mpic_iack; - /* true when the external proxy facility mode is enabled */ - bool mpic_proxy; - /* - * set when the processor has an HV mode, thus HV priv - * instructions and SPRs are diallowed if MSR:HV is 0 - */ - bool has_hv_mode; - + bool mpic_proxy; /* true if the external proxy facility mode is enabled */ + bool has_hv_mode; /* set when the processor has an HV mode, thus HV priv */ + /* instructions and SPRs are diallowed if MSR:HV is 0 */ /* - * On P7/P8/P9, set when in PM state, we need to handle resume in - * a special way (such as routing some resume causes to 0x100, ie, - * sreset), so flag this here. + * On P7/P8/P9, set when in PM state so we need to handle resume in a + * special way (such as routing some resume causes to 0x100, i.e. sreset). */ bool resume_as_sreset; #endif - /* Those resources are used only in QEMU core */ - target_ulong hflags; /* hflags is a MSR & HFLAGS_MASK */ + /* These resources are used only in QEMU core */ + target_ulong hflags; /* hflags is MSR & HFLAGS_MASK */ target_ulong hflags_nmsr; /* specific hflags, not coming from MSR */ - int immu_idx; /* precomputed MMU index to speed up insn access */ - int dmmu_idx; /* precomputed MMU index to speed up data accesses */ + int immu_idx; /* precomputed MMU index to speed up insn accesses */ + int dmmu_idx; /* precomputed MMU index to speed up data accesses */ /* Power management */ int (*check_pow)(CPUPPCState *env); #if !defined(CONFIG_USER_ONLY) - void *load_info; /* Holds boot loading state. */ + void *load_info; /* holds boot loading state */ #endif /* booke timers */ /* - * Specifies bit locations of the Time Base used to signal a fixed - * timer exception on a transition from 0 to 1. (watchdog or - * fixed-interval timer) + * Specifies bit locations of the Time Base used to signal a fixed timer + * exception on a transition from 0 to 1 (watchdog or fixed-interval timer) * - * 0 selects the least significant bit. - * 63 selects the most significant bit. + * 0 selects the least significant bit, 63 selects the most significant bit */ uint8_t fit_period[4]; uint8_t wdt_period[4]; diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index dc383242f7..ae43b08eb5 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -293,7 +293,7 @@ static void float_invalid_op_vxvc(CPUPPCState *env, bool set_fpcc, env->error_code = POWERPC_EXCP_FP | POWERPC_EXCP_FP_VXVC; /* Update the floating-point enabled exception summary */ env->fpscr |= FP_FEX; - /* Exception is differed */ + /* Exception is deferred */ } } @@ -644,7 +644,7 @@ static void do_float_check_status(CPUPPCState *env, uintptr_t raddr) if (cs->exception_index == POWERPC_EXCP_PROGRAM && (env->error_code & POWERPC_EXCP_FP)) { - /* Differred floating-point exception after target FPR update */ + /* Deferred floating-point exception after target FPR update */ if (fp_exceptions_enabled(env)) { raise_exception_err_ra(env, cs->exception_index, env->error_code, raddr); diff --git a/target/ppc/translate/fp-impl.inc.c b/target/ppc/translate/fp-impl.inc.c index d8e27bf4d5..9f7868ee28 100644 --- a/target/ppc/translate/fp-impl.inc.c +++ b/target/ppc/translate/fp-impl.inc.c @@ -781,7 +781,7 @@ static void gen_mtfsb1(DisasContext *ctx) tcg_gen_trunc_tl_i32(cpu_crf[1], cpu_fpscr); tcg_gen_shri_i32(cpu_crf[1], cpu_crf[1], FPSCR_OX); } - /* We can raise a differed exception */ + /* We can raise a deferred exception */ gen_helper_float_check_status(cpu_env); } @@ -817,7 +817,7 @@ static void gen_mtfsf(DisasContext *ctx) tcg_gen_trunc_tl_i32(cpu_crf[1], cpu_fpscr); tcg_gen_shri_i32(cpu_crf[1], cpu_crf[1], FPSCR_OX); } - /* We can raise a differed exception */ + /* We can raise a deferred exception */ gen_helper_float_check_status(cpu_env); tcg_temp_free_i64(t1); } @@ -850,7 +850,7 @@ static void gen_mtfsfi(DisasContext *ctx) tcg_gen_trunc_tl_i32(cpu_crf[1], cpu_fpscr); tcg_gen_shri_i32(cpu_crf[1], cpu_crf[1], FPSCR_OX); } - /* We can raise a differed exception */ + /* We can raise a deferred exception */ gen_helper_float_check_status(cpu_env); } diff --git a/tests/Makefile.include b/tests/Makefile.include index 2f1cafed72..edcbd475aa 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -98,6 +98,7 @@ check-unit-y += tests/rcutorture$(EXESUF) check-unit-y += tests/test-rcu-list$(EXESUF) check-unit-y += tests/test-rcu-simpleq$(EXESUF) check-unit-y += tests/test-rcu-tailq$(EXESUF) +check-unit-y += tests/test-rcu-slist$(EXESUF) check-unit-y += tests/test-qdist$(EXESUF) check-unit-y += tests/test-qht$(EXESUF) check-unit-y += tests/test-qht-par$(EXESUF) @@ -415,6 +416,7 @@ tests/rcutorture$(EXESUF): tests/rcutorture.o $(test-util-obj-y) tests/test-rcu-list$(EXESUF): tests/test-rcu-list.o $(test-util-obj-y) tests/test-rcu-simpleq$(EXESUF): tests/test-rcu-simpleq.o $(test-util-obj-y) tests/test-rcu-tailq$(EXESUF): tests/test-rcu-tailq.o $(test-util-obj-y) +tests/test-rcu-slist$(EXESUF): tests/test-rcu-slist.o $(test-util-obj-y) tests/test-qdist$(EXESUF): tests/test-qdist.o $(test-util-obj-y) tests/test-qht$(EXESUF): tests/test-qht.o $(test-util-obj-y) tests/test-qht-par$(EXESUF): tests/test-qht-par.o tests/qht-bench$(EXESUF) $(test-util-obj-y) diff --git a/tests/qemu-iotests/040 b/tests/qemu-iotests/040 index 2e7ee0e84f..32c82b4ec6 100755 --- a/tests/qemu-iotests/040 +++ b/tests/qemu-iotests/040 @@ -430,6 +430,289 @@ class TestReopenOverlay(ImageCommitTestCase): def test_reopen_overlay(self): self.run_commit_test(self.img1, self.img0) +class TestErrorHandling(iotests.QMPTestCase): + image_len = 2 * 1024 * 1024 + + def setUp(self): + iotests.create_image(backing_img, self.image_len) + qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % backing_img, mid_img) + qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % mid_img, test_img) + + qemu_io('-f', iotests.imgfmt, '-c', 'write -P 0x11 0 512k', mid_img) + qemu_io('-f', iotests.imgfmt, '-c', 'write -P 0x22 0 512k', test_img) + + self.vm = iotests.VM() + self.vm.launch() + + self.blkdebug_file = iotests.file_path("blkdebug.conf") + + def tearDown(self): + self.vm.shutdown() + os.remove(test_img) + os.remove(mid_img) + os.remove(backing_img) + + def blockdev_add(self, **kwargs): + result = self.vm.qmp('blockdev-add', **kwargs) + self.assert_qmp(result, 'return', {}) + + def add_block_nodes(self, base_debug=None, mid_debug=None, top_debug=None): + self.blockdev_add(node_name='base-file', driver='file', + filename=backing_img) + self.blockdev_add(node_name='mid-file', driver='file', + filename=mid_img) + self.blockdev_add(node_name='top-file', driver='file', + filename=test_img) + + if base_debug: + self.blockdev_add(node_name='base-dbg', driver='blkdebug', + image='base-file', inject_error=base_debug) + if mid_debug: + self.blockdev_add(node_name='mid-dbg', driver='blkdebug', + image='mid-file', inject_error=mid_debug) + if top_debug: + self.blockdev_add(node_name='top-dbg', driver='blkdebug', + image='top-file', inject_error=top_debug) + + self.blockdev_add(node_name='base-fmt', driver='raw', + file=('base-dbg' if base_debug else 'base-file')) + self.blockdev_add(node_name='mid-fmt', driver=iotests.imgfmt, + file=('mid-dbg' if mid_debug else 'mid-file'), + backing='base-fmt') + self.blockdev_add(node_name='top-fmt', driver=iotests.imgfmt, + file=('top-dbg' if top_debug else 'top-file'), + backing='mid-fmt') + + def run_job(self, expected_events, error_pauses_job=False): + match_device = {'data': {'device': 'job0'}} + events = [ + ('BLOCK_JOB_COMPLETED', match_device), + ('BLOCK_JOB_CANCELLED', match_device), + ('BLOCK_JOB_ERROR', match_device), + ('BLOCK_JOB_READY', match_device), + ] + + completed = False + log = [] + while not completed: + ev = self.vm.events_wait(events, timeout=5.0) + if ev['event'] == 'BLOCK_JOB_COMPLETED': + 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', {}) + elif ev['event'] == 'BLOCK_JOB_READY': + result = self.vm.qmp('block-job-complete', device='job0') + self.assert_qmp(result, 'return', {}) + else: + self.fail("Unexpected event: %s" % ev) + log.append(iotests.filter_qmp_event(ev)) + + self.maxDiff = None + self.assertEqual(expected_events, log) + + def event_error(self, op, action): + return { + 'event': 'BLOCK_JOB_ERROR', + 'data': {'action': action, 'device': 'job0', 'operation': op}, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'} + } + + def event_ready(self): + return { + 'event': 'BLOCK_JOB_READY', + 'data': {'device': 'job0', + 'len': 524288, + 'offset': 524288, + 'speed': 0, + 'type': 'commit'}, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'}, + } + + def event_completed(self, errmsg=None, active=True): + max_len = 524288 if active else self.image_len + data = { + 'device': 'job0', + 'len': max_len, + 'offset': 0 if errmsg else max_len, + 'speed': 0, + 'type': 'commit' + } + if errmsg: + data['error'] = errmsg + + return { + 'event': 'BLOCK_JOB_COMPLETED', + 'data': data, + 'timestamp': {'microseconds': 'USECS', 'seconds': 'SECS'}, + } + + def blkdebug_event(self, event, is_raw=False): + if event: + return [{ + 'event': event, + 'sector': 512 if is_raw else 1024, + 'once': True, + }] + return None + + def prepare_and_start_job(self, on_error, active=True, + top_event=None, mid_event=None, base_event=None): + + top_debug = self.blkdebug_event(top_event) + mid_debug = self.blkdebug_event(mid_event) + base_debug = self.blkdebug_event(base_event, True) + + 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', {}) + + def testActiveReadErrorReport(self): + self.prepare_and_start_job('report', top_event='read_aio') + self.run_job([ + self.event_error('read', 'report'), + self.event_completed('Input/output error') + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(test_img, mid_img), + 'target image matches source after error') + + def testActiveReadErrorStop(self): + self.prepare_and_start_job('stop', top_event='read_aio') + self.run_job([ + self.event_error('read', 'stop'), + self.event_ready(), + self.event_completed() + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveReadErrorIgnore(self): + self.prepare_and_start_job('ignore', top_event='read_aio') + self.run_job([ + self.event_error('read', 'ignore'), + self.event_ready(), + self.event_completed() + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveWriteErrorReport(self): + self.prepare_and_start_job('report', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'report'), + self.event_completed('Input/output error') + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(test_img, mid_img), + 'target image matches source after error') + + def testActiveWriteErrorStop(self): + self.prepare_and_start_job('stop', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'stop'), + self.event_ready(), + self.event_completed() + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testActiveWriteErrorIgnore(self): + self.prepare_and_start_job('ignore', mid_event='write_aio') + self.run_job([ + self.event_error('write', 'ignore'), + self.event_ready(), + self.event_completed() + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(test_img, mid_img), + 'target image does not match source after commit') + + def testIntermediateReadErrorReport(self): + self.prepare_and_start_job('report', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'report'), + self.event_completed('Input/output error', active=False) + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image matches source after error') + + def testIntermediateReadErrorStop(self): + self.prepare_and_start_job('stop', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'stop'), + self.event_completed(active=False) + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateReadErrorIgnore(self): + self.prepare_and_start_job('ignore', active=False, mid_event='read_aio') + self.run_job([ + self.event_error('read', 'ignore'), + self.event_completed(active=False) + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateWriteErrorReport(self): + self.prepare_and_start_job('report', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'report'), + self.event_completed('Input/output error', active=False) + ]) + + self.vm.shutdown() + self.assertFalse(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image matches source after error') + + def testIntermediateWriteErrorStop(self): + self.prepare_and_start_job('stop', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'stop'), + self.event_completed(active=False) + ], error_pauses_job=True) + + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + + def testIntermediateWriteErrorIgnore(self): + self.prepare_and_start_job('ignore', active=False, base_event='write_aio') + self.run_job([ + self.event_error('write', 'ignore'), + self.event_completed(active=False) + ]) + + # For commit, 'ignore' actually means retry, so this will succeed + self.vm.shutdown() + self.assertTrue(iotests.compare_images(mid_img, backing_img, fmt2='raw'), + 'target image does not match source after commit') + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed'], supported_protocols=['file']) diff --git a/tests/qemu-iotests/040.out b/tests/qemu-iotests/040.out index 220a5fa82c..6a917130b6 100644 --- a/tests/qemu-iotests/040.out +++ b/tests/qemu-iotests/040.out @@ -1,5 +1,5 @@ -............................................... +........................................................... ---------------------------------------------------------------------- -Ran 47 tests +Ran 59 tests OK diff --git a/tests/qemu-iotests/041 b/tests/qemu-iotests/041 index 43556b9727..5d67bf14bf 100755 --- a/tests/qemu-iotests/041 +++ b/tests/qemu-iotests/041 @@ -20,6 +20,7 @@ import time import os +import re import iotests from iotests import qemu_img, qemu_io @@ -34,6 +35,8 @@ quorum_img3 = os.path.join(iotests.test_dir, 'quorum3.img') quorum_repair_img = os.path.join(iotests.test_dir, 'quorum_repair.img') quorum_snapshot_file = os.path.join(iotests.test_dir, 'quorum_snapshot.img') +nbd_sock_path = os.path.join(iotests.test_dir, 'nbd.sock') + class TestSingleDrive(iotests.QMPTestCase): image_len = 1 * 1024 * 1024 # MB qmp_cmd = 'drive-mirror' @@ -80,7 +83,6 @@ class TestSingleDrive(iotests.QMPTestCase): self.cancel_and_wait(force=True) result = self.vm.qmp('query-block') self.assert_qmp(result, 'return[0]/inserted/file', test_img) - self.vm.shutdown() def test_cancel_after_ready(self): self.assert_no_active_block_jobs() @@ -201,8 +203,6 @@ class TestSingleDrive(iotests.QMPTestCase): self.assert_qmp(result, 'return[0]/node-name', 'top') self.assert_qmp(result, 'return[0]/backing/node-name', 'base') - self.vm.shutdown() - def test_medium_not_found(self): if iotests.qemu_default_machine != 'pc': return @@ -455,7 +455,6 @@ new_state = "1" self.assert_qmp(event, 'data/id', 'drive0') self.assert_no_active_block_jobs() - self.vm.shutdown() def test_ignore_read(self): self.assert_no_active_block_jobs() @@ -475,7 +474,6 @@ new_state = "1" result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/paused', False) self.complete_and_wait() - self.vm.shutdown() def test_large_cluster(self): self.assert_no_active_block_jobs() @@ -540,7 +538,6 @@ new_state = "1" self.complete_and_wait(wait_ready=False) self.assert_no_active_block_jobs() - self.vm.shutdown() class TestWriteErrors(iotests.QMPTestCase): image_len = 2 * 1024 * 1024 # MB @@ -614,7 +611,6 @@ new_state = "1" completed = True self.assert_no_active_block_jobs() - self.vm.shutdown() def test_ignore_write(self): self.assert_no_active_block_jobs() @@ -631,7 +627,6 @@ new_state = "1" result = self.vm.qmp('query-block-jobs') self.assert_qmp(result, 'return[0]/paused', False) self.complete_and_wait() - self.vm.shutdown() def test_stop_write(self): self.assert_no_active_block_jobs() @@ -667,7 +662,6 @@ new_state = "1" self.complete_and_wait(wait_ready=False) self.assert_no_active_block_jobs() - self.vm.shutdown() class TestSetSpeed(iotests.QMPTestCase): image_len = 80 * 1024 * 1024 # MB @@ -881,11 +875,14 @@ class TestRepairQuorum(iotests.QMPTestCase): # Add each individual quorum images for i in self.IMAGES: qemu_img('create', '-f', iotests.imgfmt, i, - str(TestSingleDrive.image_len)) + str(self.image_len)) # Assign a node name to each quorum image in order to manipulate # them opts = "node-name=img%i" % self.IMAGES.index(i) - self.vm = self.vm.add_drive(i, opts) + opts += ',driver=%s' % iotests.imgfmt + opts += ',file.driver=file' + opts += ',file.filename=%s' % i + self.vm = self.vm.add_blockdev(opts) self.vm.launch() @@ -898,7 +895,8 @@ class TestRepairQuorum(iotests.QMPTestCase): def tearDown(self): self.vm.shutdown() - for i in self.IMAGES + [ quorum_repair_img, quorum_snapshot_file ]: + for i in self.IMAGES + [ quorum_repair_img, quorum_snapshot_file, + nbd_sock_path ]: # Do a try/except because the test may have deleted some images try: os.remove(i) @@ -915,8 +913,7 @@ class TestRepairQuorum(iotests.QMPTestCase): self.complete_and_wait(drive="job0") self.assert_has_block_node("repair0", quorum_repair_img) - # TODO: a better test requiring some QEMU infrastructure will be added - # to check that this file is really driven by quorum + self.vm.assert_block_path('quorum0', '/children.1', 'repair0') self.vm.shutdown() self.assertTrue(iotests.compare_images(quorum_img2, quorum_repair_img), 'target image does not match source after mirroring') @@ -933,7 +930,6 @@ class TestRepairQuorum(iotests.QMPTestCase): # here we check that the last registered quorum file has not been # swapped out and unref self.assert_has_block_node(None, quorum_img3) - self.vm.shutdown() def test_cancel_after_ready(self): self.assert_no_active_block_jobs() @@ -1038,9 +1034,71 @@ class TestRepairQuorum(iotests.QMPTestCase): self.complete_and_wait('job0') self.assert_has_block_node("repair0", quorum_repair_img) - # TODO: a better test requiring some QEMU infrastructure will be added - # to check that this file is really driven by quorum + self.vm.assert_block_path('quorum0', '/children.1', 'repair0') + + def test_with_other_parent(self): + """ + 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', {}) + + result = self.vm.qmp('nbd-server-add', device='img1') + self.assert_qmp(result, 'return', {}) + + 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, 'error/desc', + "Cannot replace 'img1' by a node mirrored from " + "'quorum0', because it cannot be guaranteed that doing " + "so would not lead to an abrupt change of visible data") + + def test_with_other_parents_after_mirror_start(self): + """ + 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', {}) + + 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', {}) + + result = self.vm.qmp('nbd-server-add', device='img1') + self.assert_qmp(result, 'return', {}) + + # The full error message goes to stderr, we will check it later + self.complete_and_wait('mirror', + completion_error='Operation not permitted') + + # Should not have been replaced + self.vm.assert_block_path('quorum0', '/children.1', 'img1') + + # Check the full error message now self.vm.shutdown() + log = self.vm.get_log() + log = re.sub(r'^\[I \d+\.\d+\] OPENED\n', '', log) + log = re.sub(r'^Formatting.*\n', '', log) + log = re.sub(r'\n\[I \+\d+\.\d+\] CLOSED\n?$', '', log) + log = re.sub(r'^%s: ' % os.path.basename(iotests.qemu_prog), '', log) + + self.assertEqual(log, + "Can no longer replace 'img1' by 'repair0', because " + + "it can no longer be guaranteed that doing so would " + + "not lead to an abrupt change of visible data") + # Test mirroring with a source that does not have any parents (not even a # BlockBackend) @@ -1132,6 +1190,52 @@ class TestOrphanedSource(iotests.QMPTestCase): self.assertFalse('mirror-filter' in nodes, 'Mirror filter node did not disappear') +# Test cases for @replaces that do not necessarily involve Quorum +class TestReplaces(iotests.QMPTestCase): + # Each of these test cases needs their own block graph, so do not + # create any nodes here + def setUp(self): + self.vm = iotests.VM() + self.vm.launch() + + def tearDown(self): + self.vm.shutdown() + for img in (test_img, target_img): + try: + os.remove(img) + except OSError: + pass + + @iotests.skip_if_unsupported(['copy-on-read']) + def test_replace_filter(self): + """ + 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.complete_and_wait('mirror') + + self.vm.assert_block_path('filter0', '/file', 'target') + if __name__ == '__main__': iotests.main(supported_fmts=['qcow2', 'qed'], supported_protocols=['file'], diff --git a/tests/qemu-iotests/041.out b/tests/qemu-iotests/041.out index f496be9197..877b76fd31 100644 --- a/tests/qemu-iotests/041.out +++ b/tests/qemu-iotests/041.out @@ -1,5 +1,5 @@ -........................................................................................... +.............................................................................................. ---------------------------------------------------------------------- -Ran 91 tests +Ran 94 tests OK diff --git a/tests/qemu-iotests/122 b/tests/qemu-iotests/122 index dfa350936f..f7a3ae684a 100755 --- a/tests/qemu-iotests/122 +++ b/tests/qemu-iotests/122 @@ -276,6 +276,20 @@ $QEMU_IMG convert -O $IMGFMT -n "$TEST_IMG" "$TEST_IMG".orig $QEMU_IMG compare "$TEST_IMG" "$TEST_IMG".orig +echo +echo '=== -n -B to an image without a backing file ===' +echo + +# Base for the output +TEST_IMG="$TEST_IMG".base _make_test_img 64M + +# Output that does have $TEST_IMG.base set as its (implicit) backing file +TEST_IMG="$TEST_IMG".orig _make_test_img 64M + +# Convert with -n, which should not confuse -B with "target BDS has a +# backing file" +$QEMU_IMG convert -O $IMGFMT -B "$TEST_IMG".base -n "$TEST_IMG" "$TEST_IMG".orig + # success, all done echo '*** done' rm -f $seq.full diff --git a/tests/qemu-iotests/122.out b/tests/qemu-iotests/122.out index 849b6cc2ef..1a35951a80 100644 --- a/tests/qemu-iotests/122.out +++ b/tests/qemu-iotests/122.out @@ -228,4 +228,9 @@ Formatting 'TEST_DIR/t.IMGFMT.orig', fmt=IMGFMT size=67108864 wrote 65536/65536 bytes at offset 0 64 KiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) Images are identical. + +=== -n -B to an image without a backing file === + +Formatting 'TEST_DIR/t.IMGFMT.base', fmt=IMGFMT size=67108864 +Formatting 'TEST_DIR/t.IMGFMT.orig', fmt=IMGFMT size=67108864 *** done diff --git a/tests/qemu-iotests/139 b/tests/qemu-iotests/139 index 6b1a444364..7120d3142b 100755 --- a/tests/qemu-iotests/139 +++ b/tests/qemu-iotests/139 @@ -344,9 +344,6 @@ class TestBlockdevDel(iotests.QMPTestCase): @iotests.skip_if_unsupported(['quorum']) def testQuorum(self): - if not iotests.supports_quorum(): - return - self.addQuorum('quorum0', 'node0', 'node1') # We cannot remove the children of a Quorum device self.delBlockDriverState('node0', expect_error = True) diff --git a/tests/qemu-iotests/147 b/tests/qemu-iotests/147 index f4b0a11dba..d7a9f31089 100755 --- a/tests/qemu-iotests/147 +++ b/tests/qemu-iotests/147 @@ -134,7 +134,7 @@ class BuiltinNBD(NBDBlockdevAddBase): self.server.add_drive_raw('if=none,id=nbd-export,' + 'file=%s,' % test_img + 'format=%s,' % imgfmt + - 'cache=%s' % cachemode + + 'cache=%s,' % cachemode + 'aio=%s' % aiomode) self.server.launch() diff --git a/tests/qemu-iotests/155 b/tests/qemu-iotests/155 index e35b1d534b..f237868710 100755 --- a/tests/qemu-iotests/155 +++ b/tests/qemu-iotests/155 @@ -163,12 +163,7 @@ class MirrorBaseClass(BaseClass): self.assert_qmp(result, 'return', {}) - self.vm.event_wait('BLOCK_JOB_READY') - - result = self.vm.qmp('block-job-complete', device='mirror-job') - self.assert_qmp(result, 'return', {}) - - self.vm.event_wait('BLOCK_JOB_COMPLETED') + self.complete_and_wait('mirror-job') def testFull(self): self.runMirror('full') diff --git a/tests/qemu-iotests/244 b/tests/qemu-iotests/244 index 0d1efee6ef..2ec1815e6f 100755 --- a/tests/qemu-iotests/244 +++ b/tests/qemu-iotests/244 @@ -197,6 +197,20 @@ $QEMU_IO -c 'read -P 0x11 0 1M' -f $IMGFMT "$TEST_IMG" | _filter_qemu_io $QEMU_IMG map --output=human "$TEST_IMG" | _filter_testdir $QEMU_IMG map --output=json "$TEST_IMG" +echo +echo "=== Copy offloading ===" +echo + +# Make use of copy offloading if the test host can provide it +_make_test_img -o "data_file=$TEST_IMG.data" 64M +$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG" +$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG" + +# blkdebug doesn't support copy offloading, so this tests the error path +$QEMU_IMG amend -f $IMGFMT -o "data_file=blkdebug::$TEST_IMG.data" "$TEST_IMG" +$QEMU_IMG convert -f $IMGFMT -O $IMGFMT -n -C "$TEST_IMG.src" "$TEST_IMG" +$QEMU_IMG compare -f $IMGFMT -F $IMGFMT "$TEST_IMG.src" "$TEST_IMG" + # success, all done echo "*** done" rm -f $seq.full diff --git a/tests/qemu-iotests/244.out b/tests/qemu-iotests/244.out index 6a3d0067cc..e6f4dc7993 100644 --- a/tests/qemu-iotests/244.out +++ b/tests/qemu-iotests/244.out @@ -122,4 +122,10 @@ Offset Length Mapped to File 0 0x100000 0 TEST_DIR/t.qcow2.data [{ "start": 0, "length": 1048576, "depth": 0, "zero": false, "data": true, "offset": 0}, { "start": 1048576, "length": 66060288, "depth": 0, "zero": true, "data": false}] + +=== Copy offloading === + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 data_file=TEST_DIR/t.IMGFMT.data +Images are identical. +Images are identical. *** done diff --git a/tests/qemu-iotests/259 b/tests/qemu-iotests/259 new file mode 100755 index 0000000000..62e29af05f --- /dev/null +++ b/tests/qemu-iotests/259 @@ -0,0 +1,62 @@ +#!/usr/bin/env bash +# +# Test generic image creation fallback (by using NBD) +# +# Copyright (C) 2019 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=mreitz@redhat.com + +seq=$(basename $0) +echo "QA output created by $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt raw +_supported_proto nbd +_supported_os Linux + + +_make_test_img 64M + +echo +echo '--- Testing creation ---' + +$QEMU_IMG create -f qcow2 "$TEST_IMG" 64M | _filter_img_create +$QEMU_IMG info "$TEST_IMG" | _filter_img_info + +echo +echo '--- Testing creation for which the node would need to grow ---' + +# NBD does not support resizing, so this will fail +$QEMU_IMG create -f qcow2 -o preallocation=metadata "$TEST_IMG" 64M 2>&1 \ + | _filter_img_create + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/259.out b/tests/qemu-iotests/259.out new file mode 100644 index 0000000000..ffed19c2a0 --- /dev/null +++ b/tests/qemu-iotests/259.out @@ -0,0 +1,14 @@ +QA output created by 259 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 + +--- Testing creation --- +Formatting 'TEST_DIR/t.IMGFMT', fmt=qcow2 size=67108864 +image: TEST_DIR/t.IMGFMT +file format: qcow2 +virtual size: 64 MiB (67108864 bytes) +disk size: unavailable + +--- Testing creation for which the node would need to grow --- +qemu-img: TEST_DIR/t.IMGFMT: Could not resize image: Image format driver does not support resize +Formatting 'TEST_DIR/t.IMGFMT', fmt=qcow2 size=67108864 preallocation=metadata +*** done diff --git a/tests/qemu-iotests/279 b/tests/qemu-iotests/279 index 6682376808..30d29b1cb2 100755 --- a/tests/qemu-iotests/279 +++ b/tests/qemu-iotests/279 @@ -38,6 +38,8 @@ trap "_cleanup; exit \$status" 0 1 2 3 15 _supported_fmt qcow qcow2 vmdk qed _supported_proto file _supported_os Linux +_unsupported_imgopts "subformat=monolithicFlat" \ + "subformat=twoGbMaxExtentFlat" \ TEST_IMG="$TEST_IMG.base" _make_test_img 64M TEST_IMG="$TEST_IMG.mid" _make_test_img -b "$TEST_IMG.base" @@ -45,11 +47,12 @@ _make_test_img -b "$TEST_IMG.mid" echo echo '== qemu-img info --backing-chain ==' -_img_info --backing-chain | _filter_img_info +_img_info --backing-chain | _filter_img_info | grep -v 'backing file format' echo echo '== qemu-img info --backing-chain --image-opts ==' -TEST_IMG="driver=qcow2,file.driver=file,file.filename=$TEST_IMG" _img_info --backing-chain --image-opts | _filter_img_info +TEST_IMG="driver=$IMGFMT,file.driver=file,file.filename=$TEST_IMG" _img_info --backing-chain --image-opts \ + | _filter_img_info | grep -v 'backing file format' # success, all done echo "*** done" diff --git a/tests/qemu-iotests/284 b/tests/qemu-iotests/284 new file mode 100755 index 0000000000..071e89b33e --- /dev/null +++ b/tests/qemu-iotests/284 @@ -0,0 +1,97 @@ +#!/usr/bin/env bash +# +# Test ref count checks on encrypted images +# +# Copyright (C) 2019 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +# creator +owner=berrange@redhat.com + +seq=`basename $0` +echo "QA output created by $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter + +_supported_fmt qcow2 +_supported_proto generic +_supported_os Linux + + +size=1M + +SECRET="secret,id=sec0,data=astrochicken" + +IMGSPEC="driver=$IMGFMT,file.filename=$TEST_IMG,encrypt.key-secret=sec0" +QEMU_IO_OPTIONS=$QEMU_IO_OPTIONS_NO_FMT + +_run_test() +{ + IMGOPTSSYNTAX=true + OLD_TEST_IMG="$TEST_IMG" + TEST_IMG="driver=$IMGFMT,file.filename=$TEST_IMG,encrypt.key-secret=sec0" + QEMU_IMG_EXTRA_ARGS="--image-opts --object $SECRET" + + echo + echo "== cluster size $csize" + echo "== checking image refcounts ==" + _check_test_img + + echo + echo "== writing some data ==" + $QEMU_IO -c "write -P 0x9 0 1" $QEMU_IMG_EXTRA_ARGS $TEST_IMG | _filter_qemu_io | _filter_testdir + echo + echo "== rechecking image refcounts ==" + _check_test_img + + echo + echo "== writing some more data ==" + $QEMU_IO -c "write -P 0x9 $csize 1" $QEMU_IMG_EXTRA_ARGS $TEST_IMG | _filter_qemu_io | _filter_testdir + echo + echo "== rechecking image refcounts ==" + _check_test_img + + TEST_IMG="$OLD_TEST_IMG" + QEMU_IMG_EXTRA_ARGS= + IMGOPTSSYNTAX= +} + + +echo +echo "testing LUKS qcow2 encryption" +echo + +for csize in 512 2048 32768 +do + _make_test_img --object $SECRET -o "encrypt.format=luks,encrypt.key-secret=sec0,encrypt.iter-time=10,cluster_size=$csize" $size + _run_test + _cleanup_test_img +done + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/284.out b/tests/qemu-iotests/284.out new file mode 100644 index 0000000000..48216f5742 --- /dev/null +++ b/tests/qemu-iotests/284.out @@ -0,0 +1,62 @@ +QA output created by 284 + +testing LUKS qcow2 encryption + +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10 + +== cluster size 512 +== checking image refcounts == +No errors were found on the image. + +== writing some data == +wrote 1/1 bytes at offset 0 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. + +== writing some more data == +wrote 1/1 bytes at offset 512 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10 + +== cluster size 2048 +== checking image refcounts == +No errors were found on the image. + +== writing some data == +wrote 1/1 bytes at offset 0 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. + +== writing some more data == +wrote 1/1 bytes at offset 2048 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1048576 encrypt.format=luks encrypt.key-secret=sec0 encrypt.iter-time=10 + +== cluster size 32768 +== checking image refcounts == +No errors were found on the image. + +== writing some data == +wrote 1/1 bytes at offset 0 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. + +== writing some more data == +wrote 1/1 bytes at offset 32768 +1 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +== rechecking image refcounts == +No errors were found on the image. +*** done diff --git a/tests/qemu-iotests/286 b/tests/qemu-iotests/286 new file mode 100755 index 0000000000..f14445ba4a --- /dev/null +++ b/tests/qemu-iotests/286 @@ -0,0 +1,76 @@ +#!/usr/bin/env bash +# +# Test qemu-img snapshot -l +# +# Copyright (C) 2019 Red Hat, Inc. +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. +# + +seq=$(basename "$0") +echo "QA output created by $seq" + +status=1 # failure is the default! + +_cleanup() +{ + _cleanup_test_img +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + +# get standard environment, filters and checks +. ./common.rc +. ./common.filter +. ./common.qemu + +_supported_fmt qcow2 +_supported_proto file +# Internal snapshots are (currently) impossible with refcount_bits=1, +# and generally impossible with external data files +_unsupported_imgopts 'refcount_bits=1[^0-9]' data_file + +_make_test_img 64M + +# Should be so long as to take up the whole field width +sn_name=abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz + +# More memory will give us a larger VM state, i.e. one above 1 MB. +# This way, we get a number with a decimal point. +qemu_comm_method=monitor _launch_qemu -m 512 "$TEST_IMG" + +_send_qemu_cmd $QEMU_HANDLE "savevm $sn_name" '(qemu)' +_send_qemu_cmd $QEMU_HANDLE 'quit' '(qemu)' +wait=yes _cleanup_qemu + +# Check that all fields are separated by spaces. +# We first collapse all space sequences into one space each; +# then we turn every space-separated field into a '.'; +# and finally, we name the '.'s so the output is not just a confusing +# sequence of dots. + +echo 'Output structure:' +$QEMU_IMG snapshot -l "$TEST_IMG" | tail -n 1 | tr -s ' ' \ + | sed -e 's/\S\+/./g' \ + | sed -e 's/\./(snapshot ID)/' \ + -e 's/\./(snapshot name)/' \ + -e 's/\./(VM state size value)/' \ + -e 's/\./(VM state size unit)/' \ + -e 's/\./(snapshot date)/' \ + -e 's/\./(snapshot time)/' \ + -e 's/\./(VM clock)/' + +# success, all done +echo "*** done" +rm -f $seq.full +status=0 diff --git a/tests/qemu-iotests/286.out b/tests/qemu-iotests/286.out new file mode 100644 index 0000000000..39ff07e12c --- /dev/null +++ b/tests/qemu-iotests/286.out @@ -0,0 +1,8 @@ +QA output created by 286 +Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=67108864 +QEMU X.Y.Z monitor - type 'help' for more information +(qemu) savevm abcdefghijklmnopqrstuvwxyzabcdefghijklmnopqrstuvwxyz +(qemu) quit +Output structure: +(snapshot ID) (snapshot name) (VM state size value) (VM state size unit) (snapshot date) (snapshot time) (VM clock) +*** done diff --git a/tests/qemu-iotests/group b/tests/qemu-iotests/group index 1904223020..0317667695 100644 --- a/tests/qemu-iotests/group +++ b/tests/qemu-iotests/group @@ -273,6 +273,7 @@ 256 rw auto quick 257 rw 258 rw quick +259 rw auto quick 260 rw quick 261 rw 262 rw quick migration @@ -290,3 +291,5 @@ 280 rw migration quick 281 rw quick 283 auto quick +284 rw +286 rw quick diff --git a/tests/qemu-iotests/iotests.py b/tests/qemu-iotests/iotests.py index 0473e824ed..8815052eb5 100644 --- a/tests/qemu-iotests/iotests.py +++ b/tests/qemu-iotests/iotests.py @@ -714,6 +714,65 @@ class VM(qtest.QEMUQtestMachine): return fields.items() <= ret.items() + def assert_block_path(self, root, path, expected_node, graph=None): + """ + Check whether the node under the given path in the block graph + is @expected_node. + + @root is the node name of the node where the @path is rooted. + + @path is a string that consists of child names separated by + slashes. It must begin with a slash. + + Examples for @root + @path: + - root="qcow2-node", path="/backing/file" + - root="quorum-node", path="/children.2/file" + + Hypothetically, @path could be empty, in which case it would + point to @root. However, in practice this case is not useful + and hence not allowed. + + @expected_node may be None. (All elements of the path but the + leaf must still exist.) + + @graph may be None or the result of an x-debug-query-block-graph + call that has already been performed. + """ + if graph is None: + graph = self.qmp('x-debug-query-block-graph')['return'] + + iter_path = iter(path.split('/')) + + # Must start with a / + assert next(iter_path) == '' + + node = next((node for node in graph['nodes'] if node['name'] == root), + None) + + # An empty @path is not allowed, so the root node must be present + assert node is not None, 'Root node %s not found' % root + + for child_name in iter_path: + assert node is not None, 'Cannot follow path %s%s' % (root, path) + + try: + node_id = next(edge['child'] for edge in graph['edges'] \ + if edge['parent'] == node['id'] and + edge['name'] == child_name) + + node = next(node for node in graph['nodes'] \ + if node['id'] == node_id) + except StopIteration: + node = None + + if node is None: + assert expected_node is None, \ + 'No node found under %s (but expected %s)' % \ + (path, expected_node) + else: + assert node['name'] == expected_node, \ + 'Found node %s under %s (but expected %s)' % \ + (node['name'], path, expected_node) index_re = re.compile(r'([^\[]+)\[([^\]]+)\]') diff --git a/tests/qtest/Makefile.include b/tests/qtest/Makefile.include index eb0f23b108..e769c1ad70 100644 --- a/tests/qtest/Makefile.include +++ b/tests/qtest/Makefile.include @@ -157,52 +157,54 @@ check-qtest-s390x-y += migration-test # libqos / qgraph : libqgraph-obj-y = tests/qtest/libqos/qgraph.o -libqos-obj-y = $(libqgraph-obj-y) tests/qtest/libqos/pci.o tests/qtest/libqos/fw_cfg.o -libqos-obj-y += tests/qtest/libqos/malloc.o -libqos-obj-y += tests/qtest/libqos/libqos.o -libqos-spapr-obj-y = $(libqos-obj-y) tests/qtest/libqos/malloc-spapr.o +libqos-core-obj-y = $(libqgraph-obj-y) tests/qtest/libqos/pci.o tests/qtest/libqos/fw_cfg.o +libqos-core-obj-y += tests/qtest/libqos/malloc.o +libqos-core-obj-y += tests/qtest/libqos/libqos.o +libqos-spapr-obj-y = $(libqos-core-obj-y) tests/qtest/libqos/malloc-spapr.o libqos-spapr-obj-y += tests/qtest/libqos/libqos-spapr.o libqos-spapr-obj-y += tests/qtest/libqos/rtas.o libqos-spapr-obj-y += tests/qtest/libqos/pci-spapr.o -libqos-pc-obj-y = $(libqos-obj-y) tests/qtest/libqos/pci-pc.o +libqos-pc-obj-y = $(libqos-core-obj-y) tests/qtest/libqos/pci-pc.o libqos-pc-obj-y += tests/qtest/libqos/malloc-pc.o tests/qtest/libqos/libqos-pc.o libqos-pc-obj-y += tests/qtest/libqos/ahci.o libqos-usb-obj-y = $(libqos-spapr-obj-y) $(libqos-pc-obj-y) tests/qtest/libqos/usb.o # qos devices: -qos-test-obj-y = tests/qtest/qos-test.o $(libqgraph-obj-y) -qos-test-obj-y += $(libqos-pc-obj-y) $(libqos-spapr-obj-y) -qos-test-obj-y += tests/qtest/libqos/e1000e.o -qos-test-obj-y += tests/qtest/libqos/i2c.o -qos-test-obj-y += tests/qtest/libqos/i2c-imx.o -qos-test-obj-y += tests/qtest/libqos/i2c-omap.o -qos-test-obj-y += tests/qtest/libqos/sdhci.o -qos-test-obj-y += tests/qtest/libqos/tpci200.o -qos-test-obj-y += tests/qtest/libqos/virtio.o -qos-test-obj-$(CONFIG_VIRTFS) += tests/qtest/libqos/virtio-9p.o -qos-test-obj-y += tests/qtest/libqos/virtio-balloon.o -qos-test-obj-y += tests/qtest/libqos/virtio-blk.o -qos-test-obj-y += tests/qtest/libqos/virtio-mmio.o -qos-test-obj-y += tests/qtest/libqos/virtio-net.o -qos-test-obj-y += tests/qtest/libqos/virtio-pci.o -qos-test-obj-y += tests/qtest/libqos/virtio-pci-modern.o -qos-test-obj-y += tests/qtest/libqos/virtio-rng.o -qos-test-obj-y += tests/qtest/libqos/virtio-scsi.o -qos-test-obj-y += tests/qtest/libqos/virtio-serial.o +libqos-obj-y = $(libqgraph-obj-y) +libqos-obj-y += $(libqos-pc-obj-y) $(libqos-spapr-obj-y) +libqos-obj-y += tests/qtest/libqos/qos_external.o +libqos-obj-y += tests/qtest/libqos/e1000e.o +libqos-obj-y += tests/qtest/libqos/i2c.o +libqos-obj-y += tests/qtest/libqos/i2c-imx.o +libqos-obj-y += tests/qtest/libqos/i2c-omap.o +libqos-obj-y += tests/qtest/libqos/sdhci.o +libqos-obj-y += tests/qtest/libqos/tpci200.o +libqos-obj-y += tests/qtest/libqos/virtio.o +libqos-obj-$(CONFIG_VIRTFS) += tests/qtest/libqos/virtio-9p.o +libqos-obj-y += tests/qtest/libqos/virtio-balloon.o +libqos-obj-y += tests/qtest/libqos/virtio-blk.o +libqos-obj-y += tests/qtest/libqos/virtio-mmio.o +libqos-obj-y += tests/qtest/libqos/virtio-net.o +libqos-obj-y += tests/qtest/libqos/virtio-pci.o +libqos-obj-y += tests/qtest/libqos/virtio-pci-modern.o +libqos-obj-y += tests/qtest/libqos/virtio-rng.o +libqos-obj-y += tests/qtest/libqos/virtio-scsi.o +libqos-obj-y += tests/qtest/libqos/virtio-serial.o # qos machines: -qos-test-obj-y += tests/qtest/libqos/aarch64-xlnx-zcu102-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-imx25-pdk-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-n800-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-raspi2-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-sabrelite-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-smdkc210-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-virt-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-xilinx-zynq-a9-machine.o -qos-test-obj-y += tests/qtest/libqos/ppc64_pseries-machine.o -qos-test-obj-y += tests/qtest/libqos/x86_64_pc-machine.o +libqos-obj-y += tests/qtest/libqos/aarch64-xlnx-zcu102-machine.o +libqos-obj-y += tests/qtest/libqos/arm-imx25-pdk-machine.o +libqos-obj-y += tests/qtest/libqos/arm-n800-machine.o +libqos-obj-y += tests/qtest/libqos/arm-raspi2-machine.o +libqos-obj-y += tests/qtest/libqos/arm-sabrelite-machine.o +libqos-obj-y += tests/qtest/libqos/arm-smdkc210-machine.o +libqos-obj-y += tests/qtest/libqos/arm-virt-machine.o +libqos-obj-y += tests/qtest/libqos/arm-xilinx-zynq-a9-machine.o +libqos-obj-y += tests/qtest/libqos/ppc64_pseries-machine.o +libqos-obj-y += tests/qtest/libqos/x86_64_pc-machine.o # qos tests: +qos-test-obj-y += tests/qtest/qos-test.o qos-test-obj-y += tests/qtest/ac97-test.o qos-test-obj-y += tests/qtest/ds1338-test.o qos-test-obj-y += tests/qtest/e1000-test.o @@ -234,7 +236,7 @@ check-unit-y += tests/test-qgraph$(EXESUF) tests/test-qgraph$(EXESUF): tests/test-qgraph.o $(libqgraph-obj-y) check-qtest-generic-y += qos-test -tests/qtest/qos-test$(EXESUF): $(qos-test-obj-y) +tests/qtest/qos-test$(EXESUF): $(qos-test-obj-y) $(libqos-obj-y) # QTest dependencies: tests/qtest/qmp-test$(EXESUF): tests/qtest/qmp-test.o diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include new file mode 100644 index 0000000000..cde3e9636c --- /dev/null +++ b/tests/qtest/fuzz/Makefile.include @@ -0,0 +1,18 @@ +QEMU_PROG_FUZZ=qemu-fuzz-$(TARGET_NAME)$(EXESUF) + +fuzz-obj-y += tests/qtest/libqtest.o +fuzz-obj-y += $(libqos-obj-y) +fuzz-obj-y += tests/qtest/fuzz/fuzz.o # Fuzzer skeleton +fuzz-obj-y += tests/qtest/fuzz/fork_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/qos_fuzz.o + +# Targets +fuzz-obj-y += tests/qtest/fuzz/i440fx_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/virtio_net_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/virtio_scsi_fuzz.o + +FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest + +# Linker Script to force coverage-counters into known regions which we can mark +# shared +FUZZ_LDFLAGS += -Xlinker -T$(SRC_PATH)/tests/qtest/fuzz/fork_fuzz.ld diff --git a/tests/qtest/fuzz/fork_fuzz.c b/tests/qtest/fuzz/fork_fuzz.c new file mode 100644 index 0000000000..2bd0851903 --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.c @@ -0,0 +1,55 @@ +/* + * Fork-based fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "fork_fuzz.h" + + +void counter_shm_init(void) +{ + char *shm_path = g_strdup_printf("/qemu-fuzz-cntrs.%d", getpid()); + int fd = shm_open(shm_path, O_CREAT | O_RDWR, S_IRUSR | S_IWUSR); + g_free(shm_path); + + if (fd == -1) { + perror("Error: "); + exit(1); + } + if (ftruncate(fd, &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START) == -1) { + perror("Error: "); + exit(1); + } + /* Copy what's in the counter region to the shm.. */ + void *rptr = mmap(NULL , + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START, + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + memcpy(rptr, + &__FUZZ_COUNTERS_START, + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START); + + munmap(rptr, &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START); + + /* And map the shm over the counter region */ + rptr = mmap(&__FUZZ_COUNTERS_START, + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START, + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED, fd, 0); + + close(fd); + + if (!rptr) { + perror("Error: "); + exit(1); + } +} + + diff --git a/tests/qtest/fuzz/fork_fuzz.h b/tests/qtest/fuzz/fork_fuzz.h new file mode 100644 index 0000000000..9ecb8b58ef --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.h @@ -0,0 +1,23 @@ +/* + * Fork-based fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef FORK_FUZZ_H +#define FORK_FUZZ_H + +extern uint8_t __FUZZ_COUNTERS_START; +extern uint8_t __FUZZ_COUNTERS_END; + +void counter_shm_init(void); + +#endif + diff --git a/tests/qtest/fuzz/fork_fuzz.ld b/tests/qtest/fuzz/fork_fuzz.ld new file mode 100644 index 0000000000..b23a59f194 --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.ld @@ -0,0 +1,37 @@ +/* We adjust linker script modification to place all of the stuff that needs to + * persist across fuzzing runs into a contiguous seciton of memory. Then, it is + * easy to re-map the counter-related memory as shared. +*/ + +SECTIONS +{ + .data.fuzz_start : ALIGN(4K) + { + __FUZZ_COUNTERS_START = .; + __start___sancov_cntrs = .; + *(_*sancov_cntrs); + __stop___sancov_cntrs = .; + + /* Lowest stack counter */ + *(__sancov_lowest_stack); + } + .data.fuzz_ordered : + { + /* Coverage counters. They're not necessary for fuzzing, but are useful + * for analyzing the fuzzing performance + */ + __start___llvm_prf_cnts = .; + *(*llvm_prf_cnts); + __stop___llvm_prf_cnts = .; + + /* Internal Libfuzzer TracePC object which contains the ValueProfileMap */ + FuzzerTracePC*(.bss*); + } + .data.fuzz_end : ALIGN(4K) + { + __FUZZ_COUNTERS_END = .; + } +} +/* Dont overwrite the SECTIONS in the default linker script. Instead insert the + * above into the default script */ +INSERT AFTER .data; diff --git a/tests/qtest/fuzz/fuzz.c b/tests/qtest/fuzz/fuzz.c new file mode 100644 index 0000000000..0d78ac8d36 --- /dev/null +++ b/tests/qtest/fuzz/fuzz.c @@ -0,0 +1,179 @@ +/* + * fuzzing driver + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include <wordexp.h> + +#include "sysemu/qtest.h" +#include "sysemu/runstate.h" +#include "sysemu/sysemu.h" +#include "qemu/main-loop.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/qgraph.h" +#include "fuzz.h" + +#define MAX_EVENT_LOOPS 10 + +typedef struct FuzzTargetState { + FuzzTarget *target; + QSLIST_ENTRY(FuzzTargetState) target_list; +} FuzzTargetState; + +typedef QSLIST_HEAD(, FuzzTargetState) FuzzTargetList; + +static const char *fuzz_arch = TARGET_NAME; + +static FuzzTargetList *fuzz_target_list; +static FuzzTarget *fuzz_target; +static QTestState *fuzz_qts; + + + +void flush_events(QTestState *s) +{ + int i = MAX_EVENT_LOOPS; + while (g_main_context_pending(NULL) && i-- > 0) { + main_loop_wait(false); + } +} + +static QTestState *qtest_setup(void) +{ + qtest_server_set_send_handler(&qtest_client_inproc_recv, &fuzz_qts); + return qtest_inproc_init(&fuzz_qts, false, fuzz_arch, + &qtest_server_inproc_recv); +} + +void fuzz_add_target(const FuzzTarget *target) +{ + FuzzTargetState *tmp; + FuzzTargetState *target_state; + if (!fuzz_target_list) { + fuzz_target_list = g_new0(FuzzTargetList, 1); + } + + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + if (g_strcmp0(tmp->target->name, target->name) == 0) { + fprintf(stderr, "Error: Fuzz target name %s already in use\n", + target->name); + abort(); + } + } + target_state = g_new0(FuzzTargetState, 1); + target_state->target = g_new0(FuzzTarget, 1); + *(target_state->target) = *target; + QSLIST_INSERT_HEAD(fuzz_target_list, target_state, target_list); +} + + + +static void usage(char *path) +{ + printf("Usage: %s --fuzz-target=FUZZ_TARGET [LIBFUZZER ARGUMENTS]\n", path); + printf("where FUZZ_TARGET is one of:\n"); + FuzzTargetState *tmp; + if (!fuzz_target_list) { + fprintf(stderr, "Fuzz target list not initialized\n"); + abort(); + } + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + printf(" * %s : %s\n", tmp->target->name, + tmp->target->description); + } + exit(0); +} + +static FuzzTarget *fuzz_get_target(char* name) +{ + FuzzTargetState *tmp; + if (!fuzz_target_list) { + fprintf(stderr, "Fuzz target list not initialized\n"); + abort(); + } + + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + if (strcmp(tmp->target->name, name) == 0) { + return tmp->target; + } + } + return NULL; +} + + +/* Executed for each fuzzing-input */ +int LLVMFuzzerTestOneInput(const unsigned char *Data, size_t Size) +{ + /* + * Do the pre-fuzz-initialization before the first fuzzing iteration, + * instead of before the actual fuzz loop. This is needed since libfuzzer + * may fork off additional workers, prior to the fuzzing loop, and if + * pre_fuzz() sets up e.g. shared memory, this should be done for the + * individual worker processes + */ + static int pre_fuzz_done; + if (!pre_fuzz_done && fuzz_target->pre_fuzz) { + fuzz_target->pre_fuzz(fuzz_qts); + pre_fuzz_done = true; + } + + fuzz_target->fuzz(fuzz_qts, Data, Size); + return 0; +} + +/* Executed once, prior to fuzzing */ +int LLVMFuzzerInitialize(int *argc, char ***argv, char ***envp) +{ + + char *target_name; + + /* Initialize qgraph and modules */ + qos_graph_init(); + module_call_init(MODULE_INIT_FUZZ_TARGET); + module_call_init(MODULE_INIT_QOM); + module_call_init(MODULE_INIT_LIBQOS); + + if (*argc <= 1) { + usage(**argv); + } + + /* Identify the fuzz target */ + target_name = (*argv)[1]; + if (!strstr(target_name, "--fuzz-target=")) { + usage(**argv); + } + + target_name += strlen("--fuzz-target="); + + fuzz_target = fuzz_get_target(target_name); + if (!fuzz_target) { + usage(**argv); + } + + fuzz_qts = qtest_setup(); + + if (fuzz_target->pre_vm_init) { + fuzz_target->pre_vm_init(); + } + + /* Run QEMU's softmmu main with the fuzz-target dependent arguments */ + const char *init_cmdline = fuzz_target->get_init_cmdline(fuzz_target); + + /* Split the runcmd into an argv and argc */ + wordexp_t result; + wordexp(init_cmdline, &result, 0); + + qemu_init(result.we_wordc, result.we_wordv, NULL); + + return 0; +} diff --git a/tests/qtest/fuzz/fuzz.h b/tests/qtest/fuzz/fuzz.h new file mode 100644 index 0000000000..03901d414e --- /dev/null +++ b/tests/qtest/fuzz/fuzz.h @@ -0,0 +1,95 @@ +/* + * fuzzing driver + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef FUZZER_H_ +#define FUZZER_H_ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" + +#include "tests/qtest/libqtest.h" + +/** + * A libfuzzer fuzzing target + * + * The QEMU fuzzing binary is built with all available targets, each + * with a unique @name that can be specified on the command-line to + * select which target should run. + * + * A target must implement ->fuzz() to process a random input. If QEMU + * crashes in ->fuzz() then libfuzzer will record a failure. + * + * Fuzzing targets are registered with fuzz_add_target(): + * + * static const FuzzTarget fuzz_target = { + * .name = "my-device-fifo", + * .description = "Fuzz the FIFO buffer registers of my-device", + * ... + * }; + * + * static void register_fuzz_target(void) + * { + * fuzz_add_target(&fuzz_target); + * } + * fuzz_target_init(register_fuzz_target); + */ +typedef struct FuzzTarget { + const char *name; /* target identifier (passed to --fuzz-target=)*/ + const char *description; /* help text */ + + + /* + * returns the arg-list that is passed to qemu/softmmu init() + * Cannot be NULL + */ + const char* (*get_init_cmdline)(struct FuzzTarget *); + + /* + * will run once, prior to running qemu/softmmu init. + * eg: set up shared-memory for communication with the child-process + * Can be NULL + */ + void(*pre_vm_init)(void); + + /* + * will run once, after QEMU has been initialized, prior to the fuzz-loop. + * eg: detect the memory map + * Can be NULL + */ + void(*pre_fuzz)(QTestState *); + + /* + * accepts and executes an input from libfuzzer. this is repeatedly + * executed during the fuzzing loop. Its should handle setup, input + * execution and cleanup. + * Cannot be NULL + */ + void(*fuzz)(QTestState *, const unsigned char *, size_t); + +} FuzzTarget; + +void flush_events(QTestState *); +void reboot(QTestState *); + +/* + * makes a copy of *target and adds it to the target-list. + * i.e. fine to set up target on the caller's stack + */ +void fuzz_add_target(const FuzzTarget *target); + +int LLVMFuzzerTestOneInput(const unsigned char *Data, size_t Size); +int LLVMFuzzerInitialize(int *argc, char ***argv, char ***envp); + +#endif + diff --git a/tests/qtest/fuzz/i440fx_fuzz.c b/tests/qtest/fuzz/i440fx_fuzz.c new file mode 100644 index 0000000000..ab5f112584 --- /dev/null +++ b/tests/qtest/fuzz/i440fx_fuzz.c @@ -0,0 +1,193 @@ +/* + * I440FX Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "qemu/main-loop.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/pci.h" +#include "tests/qtest/libqos/pci-pc.h" +#include "fuzz.h" +#include "fuzz/qos_fuzz.h" +#include "fuzz/fork_fuzz.h" + + +#define I440FX_PCI_HOST_BRIDGE_CFG 0xcf8 +#define I440FX_PCI_HOST_BRIDGE_DATA 0xcfc + +/* + * the input to the fuzzing functions below is a buffer of random bytes. we + * want to convert these bytes into a sequence of qtest or qos calls. to do + * this we define some opcodes: + */ +enum action_id { + WRITEB, + WRITEW, + WRITEL, + READB, + READW, + READL, + ACTION_MAX +}; + +static void i440fx_fuzz_qtest(QTestState *s, + const unsigned char *Data, size_t Size) { + /* + * loop over the Data, breaking it up into actions. each action has an + * opcode, address offset and value + */ + typedef struct QTestFuzzAction { + uint8_t opcode; + uint8_t addr; + uint32_t value; + } QTestFuzzAction; + QTestFuzzAction a; + + while (Size >= sizeof(a)) { + /* make a copy of the action so we can normalize the values in-place */ + memcpy(&a, Data, sizeof(a)); + /* select between two i440fx Port IO addresses */ + uint16_t addr = a.addr % 2 ? I440FX_PCI_HOST_BRIDGE_CFG : + I440FX_PCI_HOST_BRIDGE_DATA; + switch (a.opcode % ACTION_MAX) { + case WRITEB: + qtest_outb(s, addr, (uint8_t)a.value); + break; + case WRITEW: + qtest_outw(s, addr, (uint16_t)a.value); + break; + case WRITEL: + qtest_outl(s, addr, (uint32_t)a.value); + break; + case READB: + qtest_inb(s, addr); + break; + case READW: + qtest_inw(s, addr); + break; + case READL: + qtest_inl(s, addr); + break; + } + /* Move to the next operation */ + Size -= sizeof(a); + Data += sizeof(a); + } + flush_events(s); +} + +static void i440fx_fuzz_qos(QTestState *s, + const unsigned char *Data, size_t Size) { + /* + * Same as i440fx_fuzz_qtest, but using QOS. devfn is incorporated into the + * value written over Port IO + */ + typedef struct QOSFuzzAction { + uint8_t opcode; + uint8_t offset; + int devfn; + uint32_t value; + } QOSFuzzAction; + + static QPCIBus *bus; + if (!bus) { + bus = qpci_new_pc(s, fuzz_qos_alloc); + } + + QOSFuzzAction a; + while (Size >= sizeof(a)) { + memcpy(&a, Data, sizeof(a)); + switch (a.opcode % ACTION_MAX) { + case WRITEB: + bus->config_writeb(bus, a.devfn, a.offset, (uint8_t)a.value); + break; + case WRITEW: + bus->config_writew(bus, a.devfn, a.offset, (uint16_t)a.value); + break; + case WRITEL: + bus->config_writel(bus, a.devfn, a.offset, (uint32_t)a.value); + break; + case READB: + bus->config_readb(bus, a.devfn, a.offset); + break; + case READW: + bus->config_readw(bus, a.devfn, a.offset); + break; + case READL: + bus->config_readl(bus, a.devfn, a.offset); + break; + } + Size -= sizeof(a); + Data += sizeof(a); + } + flush_events(s); +} + +static void i440fx_fuzz_qos_fork(QTestState *s, + const unsigned char *Data, size_t Size) { + if (fork() == 0) { + i440fx_fuzz_qos(s, Data, Size); + _Exit(0); + } else { + wait(NULL); + } +} + +static const char *i440fx_qtest_argv = TARGET_NAME " -machine accel=qtest" + "-m 0 -display none"; +static const char *i440fx_argv(FuzzTarget *t) +{ + return i440fx_qtest_argv; +} + +static void fork_init(void) +{ + counter_shm_init(); +} + +static void register_pci_fuzz_targets(void) +{ + /* Uses simple qtest commands and reboots to reset state */ + fuzz_add_target(&(FuzzTarget){ + .name = "i440fx-qtest-reboot-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .get_init_cmdline = i440fx_argv, + .fuzz = i440fx_fuzz_qtest}); + + /* Uses libqos and forks to prevent state leakage */ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "i440fx-qos-fork-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .pre_vm_init = &fork_init, + .fuzz = i440fx_fuzz_qos_fork,}, + "i440FX-pcihost", + &(QOSGraphTestOptions){} + ); + + /* + * Uses libqos. Doesn't do anything to reset state. Note that if we were to + * reboot after each run, we would also have to redo the qos-related + * initialization (qos_init_path) + */ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "i440fx-qos-noreset-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .fuzz = i440fx_fuzz_qos,}, + "i440FX-pcihost", + &(QOSGraphTestOptions){} + ); +} + +fuzz_target_init(register_pci_fuzz_targets); diff --git a/tests/qtest/fuzz/qos_fuzz.c b/tests/qtest/fuzz/qos_fuzz.c new file mode 100644 index 0000000000..bbb17470ff --- /dev/null +++ b/tests/qtest/fuzz/qos_fuzz.c @@ -0,0 +1,234 @@ +/* + * QOS-assisted fuzzing helpers + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "exec/memory.h" +#include "exec/address-spaces.h" +#include "sysemu/sysemu.h" +#include "qemu/main-loop.h" + +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/malloc.h" +#include "tests/qtest/libqos/qgraph.h" +#include "tests/qtest/libqos/qgraph_internal.h" +#include "tests/qtest/libqos/qos_external.h" + +#include "fuzz.h" +#include "qos_fuzz.h" + +#include "qapi/qapi-commands-machine.h" +#include "qapi/qapi-commands-qom.h" +#include "qapi/qmp/qlist.h" + + +void *fuzz_qos_obj; +QGuestAllocator *fuzz_qos_alloc; + +static const char *fuzz_target_name; +static char **fuzz_path_vec; + +/* + * Replaced the qmp commands with direct qmp_marshal calls. + * Probably there is a better way to do this + */ +static void qos_set_machines_devices_available(void) +{ + QDict *req = qdict_new(); + QObject *response; + QDict *args = qdict_new(); + QList *lst; + Error *err = NULL; + + qmp_marshal_query_machines(NULL, &response, &err); + assert(!err); + lst = qobject_to(QList, response); + apply_to_qlist(lst, true); + + qobject_unref(response); + + + qdict_put_str(req, "execute", "qom-list-types"); + qdict_put_str(args, "implements", "device"); + qdict_put_bool(args, "abstract", true); + qdict_put_obj(req, "arguments", (QObject *) args); + + qmp_marshal_qom_list_types(args, &response, &err); + assert(!err); + lst = qobject_to(QList, response); + apply_to_qlist(lst, false); + qobject_unref(response); + qobject_unref(req); +} + +static char **current_path; + +void *qos_allocate_objects(QTestState *qts, QGuestAllocator **p_alloc) +{ + return allocate_objects(qts, current_path + 1, p_alloc); +} + +static const char *qos_build_main_args(void) +{ + char **path = fuzz_path_vec; + QOSGraphNode *test_node; + GString *cmd_line = g_string_new(path[0]); + void *test_arg; + + if (!path) { + fprintf(stderr, "QOS Path not found\n"); + abort(); + } + + /* Before test */ + current_path = path; + test_node = qos_graph_get_node(path[(g_strv_length(path) - 1)]); + test_arg = test_node->u.test.arg; + if (test_node->u.test.before) { + test_arg = test_node->u.test.before(cmd_line, test_arg); + } + /* Prepend the arguments that we need */ + g_string_prepend(cmd_line, + TARGET_NAME " -display none -machine accel=qtest -m 64 "); + return cmd_line->str; +} + +/* + * This function is largely a copy of qos-test.c:walk_path. Since walk_path + * is itself a callback, its a little annoying to add another argument/layer of + * indirection + */ +static void walk_path(QOSGraphNode *orig_path, int len) +{ + QOSGraphNode *path; + QOSGraphEdge *edge; + + /* etype set to QEDGE_CONSUMED_BY so that machine can add to the command line */ + QOSEdgeType etype = QEDGE_CONSUMED_BY; + + /* twice QOS_PATH_MAX_ELEMENT_SIZE since each edge can have its arg */ + char **path_vec = g_new0(char *, (QOS_PATH_MAX_ELEMENT_SIZE * 2)); + int path_vec_size = 0; + + char *after_cmd, *before_cmd, *after_device; + GString *after_device_str = g_string_new(""); + char *node_name = orig_path->name, *path_str; + + GString *cmd_line = g_string_new(""); + GString *cmd_line2 = g_string_new(""); + + path = qos_graph_get_node(node_name); /* root */ + node_name = qos_graph_edge_get_dest(path->path_edge); /* machine name */ + + path_vec[path_vec_size++] = node_name; + path_vec[path_vec_size++] = qos_get_machine_type(node_name); + + for (;;) { + path = qos_graph_get_node(node_name); + if (!path->path_edge) { + break; + } + + node_name = qos_graph_edge_get_dest(path->path_edge); + + /* append node command line + previous edge command line */ + if (path->command_line && etype == QEDGE_CONSUMED_BY) { + g_string_append(cmd_line, path->command_line); + g_string_append(cmd_line, after_device_str->str); + g_string_truncate(after_device_str, 0); + } + + path_vec[path_vec_size++] = qos_graph_edge_get_name(path->path_edge); + /* detect if edge has command line args */ + after_cmd = qos_graph_edge_get_after_cmd_line(path->path_edge); + after_device = qos_graph_edge_get_extra_device_opts(path->path_edge); + before_cmd = qos_graph_edge_get_before_cmd_line(path->path_edge); + edge = qos_graph_get_edge(path->name, node_name); + etype = qos_graph_edge_get_type(edge); + + if (before_cmd) { + g_string_append(cmd_line, before_cmd); + } + if (after_cmd) { + g_string_append(cmd_line2, after_cmd); + } + if (after_device) { + g_string_append(after_device_str, after_device); + } + } + + path_vec[path_vec_size++] = NULL; + g_string_append(cmd_line, after_device_str->str); + g_string_free(after_device_str, true); + + g_string_append(cmd_line, cmd_line2->str); + g_string_free(cmd_line2, true); + + /* + * here position 0 has <arch>/<machine>, position 1 has <machine>. + * The path must not have the <arch>, qtest_add_data_func adds it. + */ + path_str = g_strjoinv("/", path_vec + 1); + + /* Check that this is the test we care about: */ + char *test_name = strrchr(path_str, '/') + 1; + if (strcmp(test_name, fuzz_target_name) == 0) { + /* + * put arch/machine in position 1 so run_one_test can do its work + * and add the command line at position 0. + */ + path_vec[1] = path_vec[0]; + path_vec[0] = g_string_free(cmd_line, false); + + fuzz_path_vec = path_vec; + } else { + g_free(path_vec); + } + + g_free(path_str); +} + +static const char *qos_get_cmdline(FuzzTarget *t) +{ + /* + * Set a global variable that we use to identify the qos_path for our + * fuzz_target + */ + fuzz_target_name = t->name; + qos_set_machines_devices_available(); + qos_graph_foreach_test_path(walk_path); + return qos_build_main_args(); +} + +void fuzz_add_qos_target( + FuzzTarget *fuzz_opts, + const char *interface, + QOSGraphTestOptions *opts + ) +{ + qos_add_test(fuzz_opts->name, interface, NULL, opts); + fuzz_opts->get_init_cmdline = qos_get_cmdline; + fuzz_add_target(fuzz_opts); +} + +void qos_init_path(QTestState *s) +{ + fuzz_qos_obj = qos_allocate_objects(s , &fuzz_qos_alloc); +} diff --git a/tests/qtest/fuzz/qos_fuzz.h b/tests/qtest/fuzz/qos_fuzz.h new file mode 100644 index 0000000000..477f11b02b --- /dev/null +++ b/tests/qtest/fuzz/qos_fuzz.h @@ -0,0 +1,33 @@ +/* + * QOS-assisted fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef _QOS_FUZZ_H_ +#define _QOS_FUZZ_H_ + +#include "tests/qtest/fuzz/fuzz.h" +#include "tests/qtest/libqos/qgraph.h" + +int qos_fuzz(const unsigned char *Data, size_t Size); +void qos_setup(void); + +extern void *fuzz_qos_obj; +extern QGuestAllocator *fuzz_qos_alloc; + +void fuzz_add_qos_target( + FuzzTarget *fuzz_opts, + const char *interface, + QOSGraphTestOptions *opts + ); + +void qos_init_path(QTestState *); + +#endif diff --git a/tests/qtest/fuzz/virtio_net_fuzz.c b/tests/qtest/fuzz/virtio_net_fuzz.c new file mode 100644 index 0000000000..d08a47e278 --- /dev/null +++ b/tests/qtest/fuzz/virtio_net_fuzz.c @@ -0,0 +1,198 @@ +/* + * virtio-net Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "standard-headers/linux/virtio_config.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/virtio-net.h" +#include "fuzz.h" +#include "fork_fuzz.h" +#include "qos_fuzz.h" + + +#define QVIRTIO_NET_TIMEOUT_US (30 * 1000 * 1000) +#define QVIRTIO_RX_VQ 0 +#define QVIRTIO_TX_VQ 1 +#define QVIRTIO_CTRL_VQ 2 + +static int sockfds[2]; +static bool sockfds_initialized; + +static void virtio_net_fuzz_multi(QTestState *s, + const unsigned char *Data, size_t Size, bool check_used) +{ + typedef struct vq_action { + uint8_t queue; + uint8_t length; + uint8_t write; + uint8_t next; + uint8_t rx; + } vq_action; + + uint32_t free_head = 0; + + QGuestAllocator *t_alloc = fuzz_qos_alloc; + + QVirtioNet *net_if = fuzz_qos_obj; + QVirtioDevice *dev = net_if->vdev; + QVirtQueue *q; + vq_action vqa; + while (Size >= sizeof(vqa)) { + memcpy(&vqa, Data, sizeof(vqa)); + Data += sizeof(vqa); + Size -= sizeof(vqa); + + q = net_if->queues[vqa.queue % 3]; + + vqa.length = vqa.length >= Size ? Size : vqa.length; + + /* + * Only attempt to write incoming packets, when using the socket + * backend. Otherwise, always place the input on a virtqueue. + */ + if (vqa.rx && sockfds_initialized) { + write(sockfds[0], Data, vqa.length); + } else { + vqa.rx = 0; + uint64_t req_addr = guest_alloc(t_alloc, vqa.length); + /* + * If checking used ring, ensure that the fuzzer doesn't trigger + * trivial asserion failure on zero-zied buffer + */ + qtest_memwrite(s, req_addr, Data, vqa.length); + + + free_head = qvirtqueue_add(s, q, req_addr, vqa.length, + vqa.write, vqa.next); + qvirtqueue_add(s, q, req_addr, vqa.length, vqa.write , vqa.next); + qvirtqueue_kick(s, dev, q, free_head); + } + + /* Run the main loop */ + qtest_clock_step(s, 100); + flush_events(s); + + /* Wait on used descriptors */ + if (check_used && !vqa.rx) { + gint64 start_time = g_get_monotonic_time(); + /* + * normally, we could just use qvirtio_wait_used_elem, but since we + * must manually run the main-loop for all the bhs to run, we use + * this hack with flush_events(), to run the main_loop + */ + while (!vqa.rx && q != net_if->queues[QVIRTIO_RX_VQ]) { + uint32_t got_desc_idx; + /* Input led to a virtio_error */ + if (dev->bus->get_status(dev) & VIRTIO_CONFIG_S_NEEDS_RESET) { + break; + } + if (dev->bus->get_queue_isr_status(dev, q) && + qvirtqueue_get_buf(s, q, &got_desc_idx, NULL)) { + g_assert_cmpint(got_desc_idx, ==, free_head); + break; + } + g_assert(g_get_monotonic_time() - start_time + <= QVIRTIO_NET_TIMEOUT_US); + + /* Run the main loop */ + qtest_clock_step(s, 100); + flush_events(s); + } + } + Data += vqa.length; + Size -= vqa.length; + } +} + +static void virtio_net_fork_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + if (fork() == 0) { + virtio_net_fuzz_multi(s, Data, Size, false); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_net_fork_fuzz_check_used(QTestState *s, + const unsigned char *Data, size_t Size) +{ + if (fork() == 0) { + virtio_net_fuzz_multi(s, Data, Size, true); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_net_pre_fuzz(QTestState *s) +{ + qos_init_path(s); + counter_shm_init(); +} + +static void *virtio_net_test_setup_socket(GString *cmd_line, void *arg) +{ + int ret = socketpair(PF_UNIX, SOCK_STREAM, 0, sockfds); + g_assert_cmpint(ret, !=, -1); + fcntl(sockfds[0], F_SETFL, O_NONBLOCK); + sockfds_initialized = true; + g_string_append_printf(cmd_line, " -netdev socket,fd=%d,id=hs0 ", + sockfds[1]); + return arg; +} + +static void *virtio_net_test_setup_user(GString *cmd_line, void *arg) +{ + g_string_append_printf(cmd_line, " -netdev user,id=hs0 "); + return arg; +} + +static void register_virtio_net_fuzz_targets(void) +{ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-socket", + .description = "Fuzz the virtio-net virtual queues. Fuzz incoming " + "traffic using the socket backend", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_socket} + ); + + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-socket-check-used", + .description = "Fuzz the virtio-net virtual queues. Wait for the " + "descriptors to be used. Timeout may indicate improperly handled " + "input", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz_check_used,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_socket} + ); + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-slirp", + .description = "Fuzz the virtio-net virtual queues with the slirp " + " backend. Warning: May result in network traffic emitted from the " + " process. Run in an isolated network environment.", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_user} + ); +} + +fuzz_target_init(register_virtio_net_fuzz_targets); diff --git a/tests/qtest/fuzz/virtio_scsi_fuzz.c b/tests/qtest/fuzz/virtio_scsi_fuzz.c new file mode 100644 index 0000000000..3b95247f12 --- /dev/null +++ b/tests/qtest/fuzz/virtio_scsi_fuzz.c @@ -0,0 +1,213 @@ +/* + * virtio-serial Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "tests/qtest/libqtest.h" +#include "libqos/virtio-scsi.h" +#include "libqos/virtio.h" +#include "libqos/virtio-pci.h" +#include "standard-headers/linux/virtio_ids.h" +#include "standard-headers/linux/virtio_pci.h" +#include "standard-headers/linux/virtio_scsi.h" +#include "fuzz.h" +#include "fork_fuzz.h" +#include "qos_fuzz.h" + +#define PCI_SLOT 0x02 +#define PCI_FN 0x00 +#define QVIRTIO_SCSI_TIMEOUT_US (1 * 1000 * 1000) + +#define MAX_NUM_QUEUES 64 + +/* Based on tests/virtio-scsi-test.c */ +typedef struct { + int num_queues; + QVirtQueue *vq[MAX_NUM_QUEUES + 2]; +} QVirtioSCSIQueues; + +static QVirtioSCSIQueues *qvirtio_scsi_init(QVirtioDevice *dev, uint64_t mask) +{ + QVirtioSCSIQueues *vs; + uint64_t feat; + int i; + + vs = g_new0(QVirtioSCSIQueues, 1); + + feat = qvirtio_get_features(dev); + if (mask) { + feat &= ~QVIRTIO_F_BAD_FEATURE | mask; + } else { + feat &= ~(QVIRTIO_F_BAD_FEATURE | (1ull << VIRTIO_RING_F_EVENT_IDX)); + } + qvirtio_set_features(dev, feat); + + vs->num_queues = qvirtio_config_readl(dev, 0); + + for (i = 0; i < vs->num_queues + 2; i++) { + vs->vq[i] = qvirtqueue_setup(dev, fuzz_qos_alloc, i); + } + + qvirtio_set_driver_ok(dev); + + return vs; +} + +static void virtio_scsi_fuzz(QTestState *s, QVirtioSCSIQueues* queues, + const unsigned char *Data, size_t Size) +{ + /* + * Data is a sequence of random bytes. We split them up into "actions", + * followed by data: + * [vqa][dddddddd][vqa][dddd][vqa][dddddddddddd] ... + * The length of the data is specified by the preceding vqa.length + */ + typedef struct vq_action { + uint8_t queue; + uint8_t length; + uint8_t write; + uint8_t next; + uint8_t kick; + } vq_action; + + /* Keep track of the free head for each queue we interact with */ + bool vq_touched[MAX_NUM_QUEUES + 2] = {0}; + uint32_t free_head[MAX_NUM_QUEUES + 2]; + + QGuestAllocator *t_alloc = fuzz_qos_alloc; + + QVirtioSCSI *scsi = fuzz_qos_obj; + QVirtioDevice *dev = scsi->vdev; + QVirtQueue *q; + vq_action vqa; + while (Size >= sizeof(vqa)) { + /* Copy the action, so we can normalize length, queue and flags */ + memcpy(&vqa, Data, sizeof(vqa)); + + Data += sizeof(vqa); + Size -= sizeof(vqa); + + vqa.queue = vqa.queue % queues->num_queues; + /* Cap length at the number of remaining bytes in data */ + vqa.length = vqa.length >= Size ? Size : vqa.length; + vqa.write = vqa.write & 1; + vqa.next = vqa.next & 1; + vqa.kick = vqa.kick & 1; + + + q = queues->vq[vqa.queue]; + + /* Copy the data into ram, and place it on the virtqueue */ + uint64_t req_addr = guest_alloc(t_alloc, vqa.length); + qtest_memwrite(s, req_addr, Data, vqa.length); + if (vq_touched[vqa.queue] == 0) { + vq_touched[vqa.queue] = 1; + free_head[vqa.queue] = qvirtqueue_add(s, q, req_addr, vqa.length, + vqa.write, vqa.next); + } else { + qvirtqueue_add(s, q, req_addr, vqa.length, vqa.write , vqa.next); + } + + if (vqa.kick) { + qvirtqueue_kick(s, dev, q, free_head[vqa.queue]); + free_head[vqa.queue] = 0; + } + Data += vqa.length; + Size -= vqa.length; + } + /* In the end, kick each queue we interacted with */ + for (int i = 0; i < MAX_NUM_QUEUES + 2; i++) { + if (vq_touched[i]) { + qvirtqueue_kick(s, dev, queues->vq[i], free_head[i]); + } + } +} + +static void virtio_scsi_fork_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + QVirtioSCSI *scsi = fuzz_qos_obj; + static QVirtioSCSIQueues *queues; + if (!queues) { + queues = qvirtio_scsi_init(scsi->vdev, 0); + } + if (fork() == 0) { + virtio_scsi_fuzz(s, queues, Data, Size); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_scsi_with_flag_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + QVirtioSCSI *scsi = fuzz_qos_obj; + static QVirtioSCSIQueues *queues; + + if (fork() == 0) { + if (Size >= sizeof(uint64_t)) { + queues = qvirtio_scsi_init(scsi->vdev, *(uint64_t *)Data); + virtio_scsi_fuzz(s, queues, + Data + sizeof(uint64_t), Size - sizeof(uint64_t)); + flush_events(s); + } + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_scsi_pre_fuzz(QTestState *s) +{ + qos_init_path(s); + counter_shm_init(); +} + +static void *virtio_scsi_test_setup(GString *cmd_line, void *arg) +{ + g_string_append(cmd_line, + " -drive file=blkdebug::null-co://," + "file.image.read-zeroes=on," + "if=none,id=dr1,format=raw,file.align=4k " + "-device scsi-hd,drive=dr1,lun=0,scsi-id=1"); + return arg; +} + + +static void register_virtio_scsi_fuzz_targets(void) +{ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-scsi-fuzz", + .description = "Fuzz the virtio-scsi virtual queues, forking" + "for each fuzz run", + .pre_vm_init = &counter_shm_init, + .pre_fuzz = &virtio_scsi_pre_fuzz, + .fuzz = virtio_scsi_fork_fuzz,}, + "virtio-scsi", + &(QOSGraphTestOptions){.before = virtio_scsi_test_setup} + ); + + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-scsi-flags-fuzz", + .description = "Fuzz the virtio-scsi virtual queues, forking" + "for each fuzz run (also fuzzes the virtio flags)", + .pre_vm_init = &counter_shm_init, + .pre_fuzz = &virtio_scsi_pre_fuzz, + .fuzz = virtio_scsi_with_flag_fuzz,}, + "virtio-scsi", + &(QOSGraphTestOptions){.before = virtio_scsi_test_setup} + ); +} + +fuzz_target_init(register_virtio_scsi_fuzz_targets); diff --git a/tests/qtest/libqos/i2c.c b/tests/qtest/libqos/i2c.c index 156114e745..38f800dbab 100644 --- a/tests/qtest/libqos/i2c.c +++ b/tests/qtest/libqos/i2c.c @@ -10,12 +10,12 @@ #include "libqos/i2c.h" #include "libqtest.h" -void i2c_send(QI2CDevice *i2cdev, const uint8_t *buf, uint16_t len) +void qi2c_send(QI2CDevice *i2cdev, const uint8_t *buf, uint16_t len) { i2cdev->bus->send(i2cdev->bus, i2cdev->addr, buf, len); } -void i2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) +void qi2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) { i2cdev->bus->recv(i2cdev->bus, i2cdev->addr, buf, len); } @@ -23,8 +23,8 @@ void i2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) void i2c_read_block(QI2CDevice *i2cdev, uint8_t reg, uint8_t *buf, uint16_t len) { - i2c_send(i2cdev, ®, 1); - i2c_recv(i2cdev, buf, len); + qi2c_send(i2cdev, ®, 1); + qi2c_recv(i2cdev, buf, len); } void i2c_write_block(QI2CDevice *i2cdev, uint8_t reg, @@ -33,7 +33,7 @@ void i2c_write_block(QI2CDevice *i2cdev, uint8_t reg, uint8_t *cmd = g_malloc(len + 1); cmd[0] = reg; memcpy(&cmd[1], buf, len); - i2c_send(i2cdev, cmd, len + 1); + qi2c_send(i2cdev, cmd, len + 1); g_free(cmd); } diff --git a/tests/qtest/libqos/i2c.h b/tests/qtest/libqos/i2c.h index 945b65b34c..c65f087834 100644 --- a/tests/qtest/libqos/i2c.h +++ b/tests/qtest/libqos/i2c.h @@ -47,8 +47,8 @@ struct QI2CDevice { void *i2c_device_create(void *i2c_bus, QGuestAllocator *alloc, void *addr); void add_qi2c_address(QOSGraphEdgeOptions *opts, QI2CAddress *addr); -void i2c_send(QI2CDevice *dev, const uint8_t *buf, uint16_t len); -void i2c_recv(QI2CDevice *dev, uint8_t *buf, uint16_t len); +void qi2c_send(QI2CDevice *dev, const uint8_t *buf, uint16_t len); +void qi2c_recv(QI2CDevice *dev, uint8_t *buf, uint16_t len); void i2c_read_block(QI2CDevice *dev, uint8_t reg, uint8_t *buf, uint16_t len); diff --git a/tests/qtest/libqos/qgraph.c b/tests/qtest/libqos/qgraph.c index 7a7ae2a19e..ca01de0743 100644 --- a/tests/qtest/libqos/qgraph.c +++ b/tests/qtest/libqos/qgraph.c @@ -474,7 +474,7 @@ QOSEdgeType qos_graph_edge_get_type(QOSGraphEdge *edge) if (!edge) { return -1; } - return edge->type;; + return edge->type; } char *qos_graph_edge_get_dest(QOSGraphEdge *edge) @@ -590,7 +590,7 @@ void qos_add_test(const char *name, const char *interface, QOSTestFunc test_func, QOSGraphTestOptions *opts) { QOSGraphNode *node; - char *test_name = g_strdup_printf("%s-tests/%s", interface, name);; + char *test_name = g_strdup_printf("%s-tests/%s", interface, name); QOSGraphTestOptions def_opts = { }; if (!opts) { diff --git a/tests/qtest/libqos/qos_external.c b/tests/qtest/libqos/qos_external.c new file mode 100644 index 0000000000..398556dde0 --- /dev/null +++ b/tests/qtest/libqos/qos_external.c @@ -0,0 +1,168 @@ +/* + * libqos driver framework + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#include "qemu/osdep.h" +#include <getopt.h> +#include "libqtest.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qbool.h" +#include "qapi/qmp/qstring.h" +#include "qemu/module.h" +#include "qapi/qmp/qlist.h" +#include "libqos/malloc.h" +#include "libqos/qgraph.h" +#include "libqos/qgraph_internal.h" +#include "libqos/qos_external.h" + + + +void apply_to_node(const char *name, bool is_machine, bool is_abstract) +{ + char *machine_name = NULL; + if (is_machine) { + const char *arch = qtest_get_arch(); + machine_name = g_strconcat(arch, "/", name, NULL); + name = machine_name; + } + qos_graph_node_set_availability(name, true); + if (is_abstract) { + qos_delete_cmd_line(name); + } + g_free(machine_name); +} + +/** + * apply_to_qlist(): using QMP queries QEMU for a list of + * machines and devices available, and sets the respective node + * as true. If a node is found, also all its produced and contained + * child are marked available. + * + * See qos_graph_node_set_availability() for more info + */ +void apply_to_qlist(QList *list, bool is_machine) +{ + const QListEntry *p; + const char *name; + bool abstract; + QDict *minfo; + QObject *qobj; + QString *qstr; + QBool *qbool; + + for (p = qlist_first(list); p; p = qlist_next(p)) { + minfo = qobject_to(QDict, qlist_entry_obj(p)); + qobj = qdict_get(minfo, "name"); + qstr = qobject_to(QString, qobj); + name = qstring_get_str(qstr); + + qobj = qdict_get(minfo, "abstract"); + if (qobj) { + qbool = qobject_to(QBool, qobj); + abstract = qbool_get_bool(qbool); + } else { + abstract = false; + } + + apply_to_node(name, is_machine, abstract); + qobj = qdict_get(minfo, "alias"); + if (qobj) { + qstr = qobject_to(QString, qobj); + name = qstring_get_str(qstr); + apply_to_node(name, is_machine, abstract); + } + } +} + +QGuestAllocator *get_machine_allocator(QOSGraphObject *obj) +{ + return obj->get_driver(obj, "memory"); +} + +/** + * allocate_objects(): given an array of nodes @arg, + * walks the path invoking all constructors and + * passing the corresponding parameter in order to + * continue the objects allocation. + * Once the test is reached, return the object it consumes. + * + * Since the machine and QEDGE_CONSUMED_BY nodes allocate + * memory in the constructor, g_test_queue_destroy is used so + * that after execution they can be safely free'd. (The test's + * ->before callback is also welcome to use g_test_queue_destroy). + * + * Note: as specified in walk_path() too, @arg is an array of + * char *, where arg[0] is a pointer to the command line + * string that will be used to properly start QEMU when executing + * the test, and the remaining elements represent the actual objects + * that will be allocated. + */ +void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc) +{ + int current = 0; + QGuestAllocator *alloc; + QOSGraphObject *parent = NULL; + QOSGraphEdge *edge; + QOSGraphNode *node; + void *edge_arg; + void *obj; + + node = qos_graph_get_node(path[current]); + g_assert(node->type == QNODE_MACHINE); + + obj = qos_machine_new(node, qts); + qos_object_queue_destroy(obj); + + alloc = get_machine_allocator(obj); + if (p_alloc) { + *p_alloc = alloc; + } + + for (;;) { + if (node->type != QNODE_INTERFACE) { + qos_object_start_hw(obj); + parent = obj; + } + + /* follow edge and get object for next node constructor */ + current++; + edge = qos_graph_get_edge(path[current - 1], path[current]); + node = qos_graph_get_node(path[current]); + + if (node->type == QNODE_TEST) { + g_assert(qos_graph_edge_get_type(edge) == QEDGE_CONSUMED_BY); + return obj; + } + + switch (qos_graph_edge_get_type(edge)) { + case QEDGE_PRODUCES: + obj = parent->get_driver(parent, path[current]); + break; + + case QEDGE_CONSUMED_BY: + edge_arg = qos_graph_edge_get_arg(edge); + obj = qos_driver_new(node, obj, alloc, edge_arg); + qos_object_queue_destroy(obj); + break; + + case QEDGE_CONTAINS: + obj = parent->get_device(parent, path[current]); + break; + } + } +} + diff --git a/tests/qtest/libqos/qos_external.h b/tests/qtest/libqos/qos_external.h new file mode 100644 index 0000000000..7b44930c55 --- /dev/null +++ b/tests/qtest/libqos/qos_external.h @@ -0,0 +1,28 @@ +/* + * libqos driver framework + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#ifndef QOS_EXTERNAL_H +#define QOS_EXTERNAL_H +#include "libqos/qgraph.h" + +void apply_to_node(const char *name, bool is_machine, bool is_abstract); +void apply_to_qlist(QList *list, bool is_machine); +QGuestAllocator *get_machine_allocator(QOSGraphObject *obj); +void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc); + +#endif diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index 76c9f8eade..49075b55a1 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -35,6 +35,23 @@ #define SOCKET_TIMEOUT 50 #define SOCKET_MAX_FDS 16 + +typedef void (*QTestSendFn)(QTestState *s, const char *buf); +typedef void (*ExternalSendFn)(void *s, const char *buf); +typedef GString* (*QTestRecvFn)(QTestState *); + +typedef struct QTestClientTransportOps { + QTestSendFn send; /* for sending qtest commands */ + + /* + * use external_send to send qtest command strings through functions which + * do not accept a QTestState as the first parameter. + */ + ExternalSendFn external_send; + + QTestRecvFn recv_line; /* for receiving qtest command responses */ +} QTestTransportOps; + struct QTestState { int fd; @@ -45,6 +62,7 @@ struct QTestState bool big_endian; bool irq_level[MAX_IRQ]; GString *rx; + QTestTransportOps ops; }; static GHookList abrt_hooks; @@ -52,6 +70,14 @@ static struct sigaction sigact_old; static int qtest_query_target_endianness(QTestState *s); +static void qtest_client_socket_send(QTestState*, const char *buf); +static void socket_send(int fd, const char *buf, size_t size); + +static GString *qtest_client_socket_recv_line(QTestState *); + +static void qtest_client_set_tx_handler(QTestState *s, QTestSendFn send); +static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv); + static int init_socket(const char *socket_path) { struct sockaddr_un addr; @@ -234,6 +260,9 @@ QTestState *qtest_init_without_qmp_handshake(const char *extra_args) sock = init_socket(socket_path); qmpsock = init_socket(qmp_socket_path); + qtest_client_set_rx_handler(s, qtest_client_socket_recv_line); + qtest_client_set_tx_handler(s, qtest_client_socket_send); + qtest_add_abrt_handler(kill_qemu_hook_func, s); command = g_strdup_printf("exec %s " @@ -379,13 +408,9 @@ static void socket_send(int fd, const char *buf, size_t size) } } -static void socket_sendf(int fd, const char *fmt, va_list ap) +static void qtest_client_socket_send(QTestState *s, const char *buf) { - gchar *str = g_strdup_vprintf(fmt, ap); - size_t size = strlen(str); - - socket_send(fd, str, size); - g_free(str); + socket_send(s->fd, buf, strlen(buf)); } static void GCC_FMT_ATTR(2, 3) qtest_sendf(QTestState *s, const char *fmt, ...) @@ -393,8 +418,11 @@ static void GCC_FMT_ATTR(2, 3) qtest_sendf(QTestState *s, const char *fmt, ...) va_list ap; va_start(ap, fmt); - socket_sendf(s->fd, fmt, ap); + gchar *str = g_strdup_vprintf(fmt, ap); va_end(ap); + + s->ops.send(s, str); + g_free(str); } /* Sends a message and file descriptors to the socket. @@ -431,7 +459,7 @@ static void socket_send_fds(int socket_fd, int *fds, size_t fds_num, g_assert_cmpint(ret, >, 0); } -static GString *qtest_recv_line(QTestState *s) +static GString *qtest_client_socket_recv_line(QTestState *s) { GString *line; size_t offset; @@ -468,7 +496,7 @@ static gchar **qtest_rsp(QTestState *s, int expected_args) int i; redo: - line = qtest_recv_line(s); + line = s->ops.recv_line(s); words = g_strsplit(line->str, " ", 0); g_string_free(line, TRUE); @@ -1058,8 +1086,8 @@ void qtest_bufwrite(QTestState *s, uint64_t addr, const void *data, size_t size) bdata = g_base64_encode(data, size); qtest_sendf(s, "b64write 0x%" PRIx64 " 0x%zx ", addr, size); - socket_send(s->fd, bdata, strlen(bdata)); - socket_send(s->fd, "\n", 1); + s->ops.send(s, bdata); + s->ops.send(s, "\n"); qtest_rsp(s, 0); g_free(bdata); } @@ -1337,3 +1365,72 @@ void qmp_assert_error_class(QDict *rsp, const char *class) qobject_unref(rsp); } + +static void qtest_client_set_tx_handler(QTestState *s, + QTestSendFn send) +{ + s->ops.send = send; +} +static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv) +{ + s->ops.recv_line = recv; +} +/* A type-safe wrapper for s->send() */ +static void send_wrapper(QTestState *s, const char *buf) +{ + s->ops.external_send(s, buf); +} + +static GString *qtest_client_inproc_recv_line(QTestState *s) +{ + GString *line; + size_t offset; + char *eol; + + eol = strchr(s->rx->str, '\n'); + offset = eol - s->rx->str; + line = g_string_new_len(s->rx->str, offset); + g_string_erase(s->rx, 0, offset + 1); + return line; +} + +QTestState *qtest_inproc_init(QTestState **s, bool log, const char* arch, + void (*send)(void*, const char*)) +{ + QTestState *qts; + qts = g_new0(QTestState, 1); + *s = qts; /* Expose qts early on, since the query endianness relies on it */ + qts->wstatus = 0; + for (int i = 0; i < MAX_IRQ; i++) { + qts->irq_level[i] = false; + } + + qtest_client_set_rx_handler(qts, qtest_client_inproc_recv_line); + + /* send() may not have a matching protoype, so use a type-safe wrapper */ + qts->ops.external_send = send; + qtest_client_set_tx_handler(qts, send_wrapper); + + qts->big_endian = qtest_query_target_endianness(qts); + + /* + * Set a dummy path for QTEST_QEMU_BINARY. Doesn't need to exist, but this + * way, qtest_get_arch works for inproc qtest. + */ + gchar *bin_path = g_strconcat("/qemu-system-", arch, NULL); + setenv("QTEST_QEMU_BINARY", bin_path, 0); + g_free(bin_path); + + return qts; +} + +void qtest_client_inproc_recv(void *opaque, const char *str) +{ + QTestState *qts = *(QTestState **)opaque; + + if (!qts->rx) { + qts->rx = g_string_new(NULL); + } + g_string_append(qts->rx, str); + return; +} diff --git a/tests/qtest/libqtest.h b/tests/qtest/libqtest.h index c9e21e05b3..f5cf93c386 100644 --- a/tests/qtest/libqtest.h +++ b/tests/qtest/libqtest.h @@ -729,4 +729,8 @@ bool qtest_probe_child(QTestState *s); */ void qtest_set_expected_status(QTestState *s, int status); +QTestState *qtest_inproc_init(QTestState **s, bool log, const char* arch, + void (*send)(void*, const char*)); + +void qtest_client_inproc_recv(void *opaque, const char *str); #endif diff --git a/tests/qtest/pca9552-test.c b/tests/qtest/pca9552-test.c index 4b800d3c3e..d80ed93cd3 100644 --- a/tests/qtest/pca9552-test.c +++ b/tests/qtest/pca9552-test.c @@ -32,22 +32,22 @@ static void receive_autoinc(void *obj, void *data, QGuestAllocator *alloc) pca9552_init(i2cdev); - i2c_send(i2cdev, ®, 1); + qi2c_send(i2cdev, ®, 1); /* PCA9552_LS0 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x54); /* PCA9552_LS1 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x55); /* PCA9552_LS2 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x55); /* PCA9552_LS3 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x54); } diff --git a/tests/qtest/qos-test.c b/tests/qtest/qos-test.c index fd70d73ea5..ad193f43a5 100644 --- a/tests/qtest/qos-test.c +++ b/tests/qtest/qos-test.c @@ -27,65 +27,11 @@ #include "libqos/malloc.h" #include "libqos/qgraph.h" #include "libqos/qgraph_internal.h" +#include "libqos/qos_external.h" static char *old_path; -static void apply_to_node(const char *name, bool is_machine, bool is_abstract) -{ - char *machine_name = NULL; - if (is_machine) { - const char *arch = qtest_get_arch(); - machine_name = g_strconcat(arch, "/", name, NULL); - name = machine_name; - } - qos_graph_node_set_availability(name, true); - if (is_abstract) { - qos_delete_cmd_line(name); - } - g_free(machine_name); -} -/** - * apply_to_qlist(): using QMP queries QEMU for a list of - * machines and devices available, and sets the respective node - * as true. If a node is found, also all its produced and contained - * child are marked available. - * - * See qos_graph_node_set_availability() for more info - */ -static void apply_to_qlist(QList *list, bool is_machine) -{ - const QListEntry *p; - const char *name; - bool abstract; - QDict *minfo; - QObject *qobj; - QString *qstr; - QBool *qbool; - - for (p = qlist_first(list); p; p = qlist_next(p)) { - minfo = qobject_to(QDict, qlist_entry_obj(p)); - qobj = qdict_get(minfo, "name"); - qstr = qobject_to(QString, qobj); - name = qstring_get_str(qstr); - - qobj = qdict_get(minfo, "abstract"); - if (qobj) { - qbool = qobject_to(QBool, qobj); - abstract = qbool_get_bool(qbool); - } else { - abstract = false; - } - - apply_to_node(name, is_machine, abstract); - qobj = qdict_get(minfo, "alias"); - if (qobj) { - qstr = qobject_to(QString, qobj); - name = qstring_get_str(qstr); - apply_to_node(name, is_machine, abstract); - } - } -} /** * qos_set_machines_devices_available(): sets availability of qgraph @@ -129,10 +75,6 @@ static void qos_set_machines_devices_available(void) qobject_unref(response); } -static QGuestAllocator *get_machine_allocator(QOSGraphObject *obj) -{ - return obj->get_driver(obj, "memory"); -} static void restart_qemu_or_continue(char *path) { @@ -159,78 +101,6 @@ void qos_invalidate_command_line(void) old_path = NULL; } -/** - * allocate_objects(): given an array of nodes @arg, - * walks the path invoking all constructors and - * passing the corresponding parameter in order to - * continue the objects allocation. - * Once the test is reached, return the object it consumes. - * - * Since the machine and QEDGE_CONSUMED_BY nodes allocate - * memory in the constructor, g_test_queue_destroy is used so - * that after execution they can be safely free'd. (The test's - * ->before callback is also welcome to use g_test_queue_destroy). - * - * Note: as specified in walk_path() too, @arg is an array of - * char *, where arg[0] is a pointer to the command line - * string that will be used to properly start QEMU when executing - * the test, and the remaining elements represent the actual objects - * that will be allocated. - */ -static void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc) -{ - int current = 0; - QGuestAllocator *alloc; - QOSGraphObject *parent = NULL; - QOSGraphEdge *edge; - QOSGraphNode *node; - void *edge_arg; - void *obj; - - node = qos_graph_get_node(path[current]); - g_assert(node->type == QNODE_MACHINE); - - obj = qos_machine_new(node, qts); - qos_object_queue_destroy(obj); - - alloc = get_machine_allocator(obj); - if (p_alloc) { - *p_alloc = alloc; - } - - for (;;) { - if (node->type != QNODE_INTERFACE) { - qos_object_start_hw(obj); - parent = obj; - } - - /* follow edge and get object for next node constructor */ - current++; - edge = qos_graph_get_edge(path[current - 1], path[current]); - node = qos_graph_get_node(path[current]); - - if (node->type == QNODE_TEST) { - g_assert(qos_graph_edge_get_type(edge) == QEDGE_CONSUMED_BY); - return obj; - } - - switch (qos_graph_edge_get_type(edge)) { - case QEDGE_PRODUCES: - obj = parent->get_driver(parent, path[current]); - break; - - case QEDGE_CONSUMED_BY: - edge_arg = qos_graph_edge_get_arg(edge); - obj = qos_driver_new(node, obj, alloc, edge_arg); - qos_object_queue_destroy(obj); - break; - - case QEDGE_CONTAINS: - obj = parent->get_device(parent, path[current]); - break; - } - } -} /* The argument to run_one_test, which is the test function that is registered * with GTest, is a vector of strings. The first item is the initial command diff --git a/tests/test-aio.c b/tests/test-aio.c index 86fb73b3d5..8a46078463 100644 --- a/tests/test-aio.c +++ b/tests/test-aio.c @@ -615,7 +615,8 @@ static void test_source_bh_delete_from_cb(void) g_assert_cmpint(data1.n, ==, data1.max); g_assert(data1.bh == NULL); - g_assert(!g_main_context_iteration(NULL, false)); + assert(g_main_context_iteration(NULL, false)); + assert(!g_main_context_iteration(NULL, false)); } static void test_source_bh_delete_from_cb_many(void) diff --git a/tests/test-rcu-list.c b/tests/test-rcu-list.c index 6f076473e0..1442c0c982 100644 --- a/tests/test-rcu-list.c +++ b/tests/test-rcu-list.c @@ -93,6 +93,8 @@ struct list_element { QSIMPLEQ_ENTRY(list_element) entry; #elif TEST_LIST_TYPE == 3 QTAILQ_ENTRY(list_element) entry; +#elif TEST_LIST_TYPE == 4 + QSLIST_ENTRY(list_element) entry; #else #error Invalid TEST_LIST_TYPE #endif @@ -144,6 +146,20 @@ static QTAILQ_HEAD(, list_element) Q_list_head; #define TEST_LIST_INSERT_HEAD_RCU QTAILQ_INSERT_HEAD_RCU #define TEST_LIST_FOREACH_RCU QTAILQ_FOREACH_RCU #define TEST_LIST_FOREACH_SAFE_RCU QTAILQ_FOREACH_SAFE_RCU + +#elif TEST_LIST_TYPE == 4 +static QSLIST_HEAD(, list_element) Q_list_head; + +#define TEST_NAME "qslist" +#define TEST_LIST_REMOVE_RCU(el, f) \ + QSLIST_REMOVE_RCU(&Q_list_head, el, list_element, f) + +#define TEST_LIST_INSERT_AFTER_RCU(list_el, el, f) \ + QSLIST_INSERT_AFTER_RCU(&Q_list_head, list_el, el, f) + +#define TEST_LIST_INSERT_HEAD_RCU QSLIST_INSERT_HEAD_RCU +#define TEST_LIST_FOREACH_RCU QSLIST_FOREACH_RCU +#define TEST_LIST_FOREACH_SAFE_RCU QSLIST_FOREACH_SAFE_RCU #else #error Invalid TEST_LIST_TYPE #endif diff --git a/tests/test-rcu-slist.c b/tests/test-rcu-slist.c new file mode 100644 index 0000000000..868e1e472e --- /dev/null +++ b/tests/test-rcu-slist.c @@ -0,0 +1,2 @@ +#define TEST_LIST_TYPE 4 +#include "test-rcu-list.c" diff --git a/tools/virtiofsd/fuse.h b/tools/virtiofsd/fuse.h deleted file mode 100644 index aba13fef2d..0000000000 --- a/tools/virtiofsd/fuse.h +++ /dev/null @@ -1,1229 +0,0 @@ -/* - * FUSE: Filesystem in Userspace - * Copyright (C) 2001-2007 Miklos Szeredi <miklos@szeredi.hu> - * - * This program can be distributed under the terms of the GNU LGPLv2. - * See the file COPYING.LIB. - */ - -#ifndef FUSE_H_ -#define FUSE_H_ - -/* - * - * This file defines the library interface of FUSE - * - * IMPORTANT: you should define FUSE_USE_VERSION before including this header. - */ - -#include "fuse_common.h" - -#include <fcntl.h> -#include <sys/stat.h> -#include <sys/statvfs.h> -#include <sys/types.h> -#include <sys/uio.h> -#include <time.h> - -/* - * Basic FUSE API - */ - -/** Handle for a FUSE filesystem */ -struct fuse; - -/** - * Readdir flags, passed to ->readdir() - */ -enum fuse_readdir_flags { - /** - * "Plus" mode. - * - * The kernel wants to prefill the inode cache during readdir. The - * filesystem may honour this by filling in the attributes and setting - * FUSE_FILL_DIR_FLAGS for the filler function. The filesystem may also - * just ignore this flag completely. - */ - FUSE_READDIR_PLUS = (1 << 0), -}; - -enum fuse_fill_dir_flags { - /** - * "Plus" mode: all file attributes are valid - * - * The attributes are used by the kernel to prefill the inode cache - * during a readdir. - * - * It is okay to set FUSE_FILL_DIR_PLUS if FUSE_READDIR_PLUS is not set - * and vice versa. - */ - FUSE_FILL_DIR_PLUS = (1 << 1), -}; - -/** - * Function to add an entry in a readdir() operation - * - * The *off* parameter can be any non-zero value that enables the - * filesystem to identify the current point in the directory - * stream. It does not need to be the actual physical position. A - * value of zero is reserved to indicate that seeking in directories - * is not supported. - * - * @param buf the buffer passed to the readdir() operation - * @param name the file name of the directory entry - * @param stat file attributes, can be NULL - * @param off offset of the next entry or zero - * @param flags fill flags - * @return 1 if buffer is full, zero otherwise - */ -typedef int (*fuse_fill_dir_t)(void *buf, const char *name, - const struct stat *stbuf, off_t off, - enum fuse_fill_dir_flags flags); -/** - * Configuration of the high-level API - * - * This structure is initialized from the arguments passed to - * fuse_new(), and then passed to the file system's init() handler - * which should ensure that the configuration is compatible with the - * file system implementation. - */ -struct fuse_config { - /** - * If `set_gid` is non-zero, the st_gid attribute of each file - * is overwritten with the value of `gid`. - */ - int set_gid; - unsigned int gid; - - /** - * If `set_uid` is non-zero, the st_uid attribute of each file - * is overwritten with the value of `uid`. - */ - int set_uid; - unsigned int uid; - - /** - * If `set_mode` is non-zero, the any permissions bits set in - * `umask` are unset in the st_mode attribute of each file. - */ - int set_mode; - unsigned int umask; - - /** - * The timeout in seconds for which name lookups will be - * cached. - */ - double entry_timeout; - - /** - * The timeout in seconds for which a negative lookup will be - * cached. This means, that if file did not exist (lookup - * retuned ENOENT), the lookup will only be redone after the - * timeout, and the file/directory will be assumed to not - * exist until then. A value of zero means that negative - * lookups are not cached. - */ - double negative_timeout; - - /** - * The timeout in seconds for which file/directory attributes - * (as returned by e.g. the `getattr` handler) are cached. - */ - double attr_timeout; - - /** - * Allow requests to be interrupted - */ - int intr; - - /** - * Specify which signal number to send to the filesystem when - * a request is interrupted. The default is hardcoded to - * USR1. - */ - int intr_signal; - - /** - * Normally, FUSE assigns inodes to paths only for as long as - * the kernel is aware of them. With this option inodes are - * instead remembered for at least this many seconds. This - * will require more memory, but may be necessary when using - * applications that make use of inode numbers. - * - * A number of -1 means that inodes will be remembered for the - * entire life-time of the file-system process. - */ - int remember; - - /** - * The default behavior is that if an open file is deleted, - * the file is renamed to a hidden file (.fuse_hiddenXXX), and - * only removed when the file is finally released. This - * relieves the filesystem implementation of having to deal - * with this problem. This option disables the hiding - * behavior, and files are removed immediately in an unlink - * operation (or in a rename operation which overwrites an - * existing file). - * - * It is recommended that you not use the hard_remove - * option. When hard_remove is set, the following libc - * functions fail on unlinked files (returning errno of - * ENOENT): read(2), write(2), fsync(2), close(2), f*xattr(2), - * ftruncate(2), fstat(2), fchmod(2), fchown(2) - */ - int hard_remove; - - /** - * Honor the st_ino field in the functions getattr() and - * fill_dir(). This value is used to fill in the st_ino field - * in the stat(2), lstat(2), fstat(2) functions and the d_ino - * field in the readdir(2) function. The filesystem does not - * have to guarantee uniqueness, however some applications - * rely on this value being unique for the whole filesystem. - * - * Note that this does *not* affect the inode that libfuse - * and the kernel use internally (also called the "nodeid"). - */ - int use_ino; - - /** - * If use_ino option is not given, still try to fill in the - * d_ino field in readdir(2). If the name was previously - * looked up, and is still in the cache, the inode number - * found there will be used. Otherwise it will be set to -1. - * If use_ino option is given, this option is ignored. - */ - int readdir_ino; - - /** - * This option disables the use of page cache (file content cache) - * in the kernel for this filesystem. This has several affects: - * - * 1. Each read(2) or write(2) system call will initiate one - * or more read or write operations, data will not be - * cached in the kernel. - * - * 2. The return value of the read() and write() system calls - * will correspond to the return values of the read and - * write operations. This is useful for example if the - * file size is not known in advance (before reading it). - * - * Internally, enabling this option causes fuse to set the - * `direct_io` field of `struct fuse_file_info` - overwriting - * any value that was put there by the file system. - */ - int direct_io; - - /** - * This option disables flushing the cache of the file - * contents on every open(2). This should only be enabled on - * filesystems where the file data is never changed - * externally (not through the mounted FUSE filesystem). Thus - * it is not suitable for network filesystems and other - * intermediate filesystems. - * - * NOTE: if this option is not specified (and neither - * direct_io) data is still cached after the open(2), so a - * read(2) system call will not always initiate a read - * operation. - * - * Internally, enabling this option causes fuse to set the - * `keep_cache` field of `struct fuse_file_info` - overwriting - * any value that was put there by the file system. - */ - int kernel_cache; - - /** - * This option is an alternative to `kernel_cache`. Instead of - * unconditionally keeping cached data, the cached data is - * invalidated on open(2) if if the modification time or the - * size of the file has changed since it was last opened. - */ - int auto_cache; - - /** - * The timeout in seconds for which file attributes are cached - * for the purpose of checking if auto_cache should flush the - * file data on open. - */ - int ac_attr_timeout_set; - double ac_attr_timeout; - - /** - * If this option is given the file-system handlers for the - * following operations will not receive path information: - * read, write, flush, release, fsync, readdir, releasedir, - * fsyncdir, lock, ioctl and poll. - * - * For the truncate, getattr, chmod, chown and utimens - * operations the path will be provided only if the struct - * fuse_file_info argument is NULL. - */ - int nullpath_ok; - - /** - * The remaining options are used by libfuse internally and - * should not be touched. - */ - int show_help; - char *modules; - int debug; -}; - - -/** - * The file system operations: - * - * Most of these should work very similarly to the well known UNIX - * file system operations. A major exception is that instead of - * returning an error in 'errno', the operation should return the - * negated error value (-errno) directly. - * - * All methods are optional, but some are essential for a useful - * filesystem (e.g. getattr). Open, flush, release, fsync, opendir, - * releasedir, fsyncdir, access, create, truncate, lock, init and - * destroy are special purpose methods, without which a full featured - * filesystem can still be implemented. - * - * In general, all methods are expected to perform any necessary - * permission checking. However, a filesystem may delegate this task - * to the kernel by passing the `default_permissions` mount option to - * `fuse_new()`. In this case, methods will only be called if - * the kernel's permission check has succeeded. - * - * Almost all operations take a path which can be of any length. - */ -struct fuse_operations { - /** - * Get file attributes. - * - * Similar to stat(). The 'st_dev' and 'st_blksize' fields are - * ignored. The 'st_ino' field is ignored except if the 'use_ino' - * mount option is given. In that case it is passed to userspace, - * but libfuse and the kernel will still assign a different - * inode for internal use (called the "nodeid"). - * - * `fi` will always be NULL if the file is not currently open, but - * may also be NULL if the file is open. - */ - int (*getattr)(const char *, struct stat *, struct fuse_file_info *fi); - - /** - * Read the target of a symbolic link - * - * The buffer should be filled with a null terminated string. The - * buffer size argument includes the space for the terminating - * null character. If the linkname is too long to fit in the - * buffer, it should be truncated. The return value should be 0 - * for success. - */ - int (*readlink)(const char *, char *, size_t); - - /** - * Create a file node - * - * This is called for creation of all non-directory, non-symlink - * nodes. If the filesystem defines a create() method, then for - * regular files that will be called instead. - */ - int (*mknod)(const char *, mode_t, dev_t); - - /** - * Create a directory - * - * Note that the mode argument may not have the type specification - * bits set, i.e. S_ISDIR(mode) can be false. To obtain the - * correct directory type bits use mode|S_IFDIR - */ - int (*mkdir)(const char *, mode_t); - - /** Remove a file */ - int (*unlink)(const char *); - - /** Remove a directory */ - int (*rmdir)(const char *); - - /** Create a symbolic link */ - int (*symlink)(const char *, const char *); - - /** - * Rename a file - * - * *flags* may be `RENAME_EXCHANGE` or `RENAME_NOREPLACE`. If - * RENAME_NOREPLACE is specified, the filesystem must not - * overwrite *newname* if it exists and return an error - * instead. If `RENAME_EXCHANGE` is specified, the filesystem - * must atomically exchange the two files, i.e. both must - * exist and neither may be deleted. - */ - int (*rename)(const char *, const char *, unsigned int flags); - - /** Create a hard link to a file */ - int (*link)(const char *, const char *); - - /** - * Change the permission bits of a file - * - * `fi` will always be NULL if the file is not currenlty open, but - * may also be NULL if the file is open. - */ - int (*chmod)(const char *, mode_t, struct fuse_file_info *fi); - - /** - * Change the owner and group of a file - * - * `fi` will always be NULL if the file is not currenlty open, but - * may also be NULL if the file is open. - * - * Unless FUSE_CAP_HANDLE_KILLPRIV is disabled, this method is - * expected to reset the setuid and setgid bits. - */ - int (*chown)(const char *, uid_t, gid_t, struct fuse_file_info *fi); - - /** - * Change the size of a file - * - * `fi` will always be NULL if the file is not currenlty open, but - * may also be NULL if the file is open. - * - * Unless FUSE_CAP_HANDLE_KILLPRIV is disabled, this method is - * expected to reset the setuid and setgid bits. - */ - int (*truncate)(const char *, off_t, struct fuse_file_info *fi); - - /** - * Open a file - * - * Open flags are available in fi->flags. The following rules - * apply. - * - * - Creation (O_CREAT, O_EXCL, O_NOCTTY) flags will be - * filtered out / handled by the kernel. - * - * - Access modes (O_RDONLY, O_WRONLY, O_RDWR, O_EXEC, O_SEARCH) - * should be used by the filesystem to check if the operation is - * permitted. If the ``-o default_permissions`` mount option is - * given, this check is already done by the kernel before calling - * open() and may thus be omitted by the filesystem. - * - * - When writeback caching is enabled, the kernel may send - * read requests even for files opened with O_WRONLY. The - * filesystem should be prepared to handle this. - * - * - When writeback caching is disabled, the filesystem is - * expected to properly handle the O_APPEND flag and ensure - * that each write is appending to the end of the file. - * - * - When writeback caching is enabled, the kernel will - * handle O_APPEND. However, unless all changes to the file - * come through the kernel this will not work reliably. The - * filesystem should thus either ignore the O_APPEND flag - * (and let the kernel handle it), or return an error - * (indicating that reliably O_APPEND is not available). - * - * Filesystem may store an arbitrary file handle (pointer, - * index, etc) in fi->fh, and use this in other all other file - * operations (read, write, flush, release, fsync). - * - * Filesystem may also implement stateless file I/O and not store - * anything in fi->fh. - * - * There are also some flags (direct_io, keep_cache) which the - * filesystem may set in fi, to change the way the file is opened. - * See fuse_file_info structure in <fuse_common.h> for more details. - * - * If this request is answered with an error code of ENOSYS - * and FUSE_CAP_NO_OPEN_SUPPORT is set in - * `fuse_conn_info.capable`, this is treated as success and - * future calls to open will also succeed without being send - * to the filesystem process. - * - */ - int (*open)(const char *, struct fuse_file_info *); - - /** - * Read data from an open file - * - * Read should return exactly the number of bytes requested except - * on EOF or error, otherwise the rest of the data will be - * substituted with zeroes. An exception to this is when the - * 'direct_io' mount option is specified, in which case the return - * value of the read system call will reflect the return value of - * this operation. - */ - int (*read)(const char *, char *, size_t, off_t, struct fuse_file_info *); - - /** - * Write data to an open file - * - * Write should return exactly the number of bytes requested - * except on error. An exception to this is when the 'direct_io' - * mount option is specified (see read operation). - * - * Unless FUSE_CAP_HANDLE_KILLPRIV is disabled, this method is - * expected to reset the setuid and setgid bits. - */ - int (*write)(const char *, const char *, size_t, off_t, - struct fuse_file_info *); - - /** - * Get file system statistics - * - * The 'f_favail', 'f_fsid' and 'f_flag' fields are ignored - */ - int (*statfs)(const char *, struct statvfs *); - - /** - * Possibly flush cached data - * - * BIG NOTE: This is not equivalent to fsync(). It's not a - * request to sync dirty data. - * - * Flush is called on each close() of a file descriptor, as opposed to - * release which is called on the close of the last file descriptor for - * a file. Under Linux, errors returned by flush() will be passed to - * userspace as errors from close(), so flush() is a good place to write - * back any cached dirty data. However, many applications ignore errors - * on close(), and on non-Linux systems, close() may succeed even if flush() - * returns an error. For these reasons, filesystems should not assume - * that errors returned by flush will ever be noticed or even - * delivered. - * - * NOTE: The flush() method may be called more than once for each - * open(). This happens if more than one file descriptor refers to an - * open file handle, e.g. due to dup(), dup2() or fork() calls. It is - * not possible to determine if a flush is final, so each flush should - * be treated equally. Multiple write-flush sequences are relatively - * rare, so this shouldn't be a problem. - * - * Filesystems shouldn't assume that flush will be called at any - * particular point. It may be called more times than expected, or not - * at all. - * - * [close]: - * http://pubs.opengroup.org/onlinepubs/9699919799/functions/close.html - */ - int (*flush)(const char *, struct fuse_file_info *); - - /** - * Release an open file - * - * Release is called when there are no more references to an open - * file: all file descriptors are closed and all memory mappings - * are unmapped. - * - * For every open() call there will be exactly one release() call - * with the same flags and file handle. It is possible to - * have a file opened more than once, in which case only the last - * release will mean, that no more reads/writes will happen on the - * file. The return value of release is ignored. - */ - int (*release)(const char *, struct fuse_file_info *); - - /* - * Synchronize file contents - * - * If the datasync parameter is non-zero, then only the user data - * should be flushed, not the meta data. - */ - int (*fsync)(const char *, int, struct fuse_file_info *); - - /** Set extended attributes */ - int (*setxattr)(const char *, const char *, const char *, size_t, int); - - /** Get extended attributes */ - int (*getxattr)(const char *, const char *, char *, size_t); - - /** List extended attributes */ - int (*listxattr)(const char *, char *, size_t); - - /** Remove extended attributes */ - int (*removexattr)(const char *, const char *); - - /* - * Open directory - * - * Unless the 'default_permissions' mount option is given, - * this method should check if opendir is permitted for this - * directory. Optionally opendir may also return an arbitrary - * filehandle in the fuse_file_info structure, which will be - * passed to readdir, releasedir and fsyncdir. - */ - int (*opendir)(const char *, struct fuse_file_info *); - - /* - * Read directory - * - * The filesystem may choose between two modes of operation: - * - * 1) The readdir implementation ignores the offset parameter, and - * passes zero to the filler function's offset. The filler - * function will not return '1' (unless an error happens), so the - * whole directory is read in a single readdir operation. - * - * 2) The readdir implementation keeps track of the offsets of the - * directory entries. It uses the offset parameter and always - * passes non-zero offset to the filler function. When the buffer - * is full (or an error happens) the filler function will return - * '1'. - */ - int (*readdir)(const char *, void *, fuse_fill_dir_t, off_t, - struct fuse_file_info *, enum fuse_readdir_flags); - - /** - * Release directory - */ - int (*releasedir)(const char *, struct fuse_file_info *); - - /** - * Synchronize directory contents - * - * If the datasync parameter is non-zero, then only the user data - * should be flushed, not the meta data - */ - int (*fsyncdir)(const char *, int, struct fuse_file_info *); - - /** - * Initialize filesystem - * - * The return value will passed in the `private_data` field of - * `struct fuse_context` to all file operations, and as a - * parameter to the destroy() method. It overrides the initial - * value provided to fuse_main() / fuse_new(). - */ - void *(*init)(struct fuse_conn_info *conn, struct fuse_config *cfg); - - /** - * Clean up filesystem - * - * Called on filesystem exit. - */ - void (*destroy)(void *private_data); - - /** - * Check file access permissions - * - * This will be called for the access() system call. If the - * 'default_permissions' mount option is given, this method is not - * called. - * - * This method is not called under Linux kernel versions 2.4.x - */ - int (*access)(const char *, int); - - /** - * Create and open a file - * - * If the file does not exist, first create it with the specified - * mode, and then open it. - * - * If this method is not implemented or under Linux kernel - * versions earlier than 2.6.15, the mknod() and open() methods - * will be called instead. - */ - int (*create)(const char *, mode_t, struct fuse_file_info *); - - /** - * Perform POSIX file locking operation - * - * The cmd argument will be either F_GETLK, F_SETLK or F_SETLKW. - * - * For the meaning of fields in 'struct flock' see the man page - * for fcntl(2). The l_whence field will always be set to - * SEEK_SET. - * - * For checking lock ownership, the 'fuse_file_info->owner' - * argument must be used. - * - * For F_GETLK operation, the library will first check currently - * held locks, and if a conflicting lock is found it will return - * information without calling this method. This ensures, that - * for local locks the l_pid field is correctly filled in. The - * results may not be accurate in case of race conditions and in - * the presence of hard links, but it's unlikely that an - * application would rely on accurate GETLK results in these - * cases. If a conflicting lock is not found, this method will be - * called, and the filesystem may fill out l_pid by a meaningful - * value, or it may leave this field zero. - * - * For F_SETLK and F_SETLKW the l_pid field will be set to the pid - * of the process performing the locking operation. - * - * Note: if this method is not implemented, the kernel will still - * allow file locking to work locally. Hence it is only - * interesting for network filesystems and similar. - */ - int (*lock)(const char *, struct fuse_file_info *, int cmd, struct flock *); - - /** - * Change the access and modification times of a file with - * nanosecond resolution - * - * This supersedes the old utime() interface. New applications - * should use this. - * - * `fi` will always be NULL if the file is not currenlty open, but - * may also be NULL if the file is open. - * - * See the utimensat(2) man page for details. - */ - int (*utimens)(const char *, const struct timespec tv[2], - struct fuse_file_info *fi); - - /** - * Map block index within file to block index within device - * - * Note: This makes sense only for block device backed filesystems - * mounted with the 'blkdev' option - */ - int (*bmap)(const char *, size_t blocksize, uint64_t *idx); - - /** - * Ioctl - * - * flags will have FUSE_IOCTL_COMPAT set for 32bit ioctls in - * 64bit environment. The size and direction of data is - * determined by _IOC_*() decoding of cmd. For _IOC_NONE, - * data will be NULL, for _IOC_WRITE data is out area, for - * _IOC_READ in area and if both are set in/out area. In all - * non-NULL cases, the area is of _IOC_SIZE(cmd) bytes. - * - * If flags has FUSE_IOCTL_DIR then the fuse_file_info refers to a - * directory file handle. - * - * Note : the unsigned long request submitted by the application - * is truncated to 32 bits. - */ - int (*ioctl)(const char *, unsigned int cmd, void *arg, - struct fuse_file_info *, unsigned int flags, void *data); - - /** - * Poll for IO readiness events - * - * Note: If ph is non-NULL, the client should notify - * when IO readiness events occur by calling - * fuse_notify_poll() with the specified ph. - * - * Regardless of the number of times poll with a non-NULL ph - * is received, single notification is enough to clear all. - * Notifying more times incurs overhead but doesn't harm - * correctness. - * - * The callee is responsible for destroying ph with - * fuse_pollhandle_destroy() when no longer in use. - */ - int (*poll)(const char *, struct fuse_file_info *, - struct fuse_pollhandle *ph, unsigned *reventsp); - - /* - * Write contents of buffer to an open file - * - * Similar to the write() method, but data is supplied in a - * generic buffer. Use fuse_buf_copy() to transfer data to - * the destination. - * - * Unless FUSE_CAP_HANDLE_KILLPRIV is disabled, this method is - * expected to reset the setuid and setgid bits. - */ - int (*write_buf)(const char *, struct fuse_bufvec *buf, off_t off, - struct fuse_file_info *); - - /* - * Store data from an open file in a buffer - * - * Similar to the read() method, but data is stored and - * returned in a generic buffer. - * - * No actual copying of data has to take place, the source - * file descriptor may simply be stored in the buffer for - * later data transfer. - * - * The buffer must be allocated dynamically and stored at the - * location pointed to by bufp. If the buffer contains memory - * regions, they too must be allocated using malloc(). The - * allocated memory will be freed by the caller. - */ - int (*read_buf)(const char *, struct fuse_bufvec **bufp, size_t size, - off_t off, struct fuse_file_info *); - /** - * Perform BSD file locking operation - * - * The op argument will be either LOCK_SH, LOCK_EX or LOCK_UN - * - * Nonblocking requests will be indicated by ORing LOCK_NB to - * the above operations - * - * For more information see the flock(2) manual page. - * - * Additionally fi->owner will be set to a value unique to - * this open file. This same value will be supplied to - * ->release() when the file is released. - * - * Note: if this method is not implemented, the kernel will still - * allow file locking to work locally. Hence it is only - * interesting for network filesystems and similar. - */ - int (*flock)(const char *, struct fuse_file_info *, int op); - - /** - * Allocates space for an open file - * - * This function ensures that required space is allocated for specified - * file. If this function returns success then any subsequent write - * request to specified range is guaranteed not to fail because of lack - * of space on the file system media. - */ - int (*fallocate)(const char *, int, off_t, off_t, struct fuse_file_info *); - - /** - * Copy a range of data from one file to another - * - * Performs an optimized copy between two file descriptors without the - * additional cost of transferring data through the FUSE kernel module - * to user space (glibc) and then back into the FUSE filesystem again. - * - * In case this method is not implemented, glibc falls back to reading - * data from the source and writing to the destination. Effectively - * doing an inefficient copy of the data. - */ - ssize_t (*copy_file_range)(const char *path_in, - struct fuse_file_info *fi_in, off_t offset_in, - const char *path_out, - struct fuse_file_info *fi_out, off_t offset_out, - size_t size, int flags); - - /** - * Find next data or hole after the specified offset - */ - off_t (*lseek)(const char *, off_t off, int whence, - struct fuse_file_info *); -}; - -/* - * Extra context that may be needed by some filesystems - * - * The uid, gid and pid fields are not filled in case of a writepage - * operation. - */ -struct fuse_context { - /** Pointer to the fuse object */ - struct fuse *fuse; - - /** User ID of the calling process */ - uid_t uid; - - /** Group ID of the calling process */ - gid_t gid; - - /** Process ID of the calling thread */ - pid_t pid; - - /** Private filesystem data */ - void *private_data; - - /** Umask of the calling process */ - mode_t umask; -}; - -/** - * Main function of FUSE. - * - * This is for the lazy. This is all that has to be called from the - * main() function. - * - * This function does the following: - * - parses command line options, and handles --help and - * --version - * - installs signal handlers for INT, HUP, TERM and PIPE - * - registers an exit handler to unmount the filesystem on program exit - * - creates a fuse handle - * - registers the operations - * - calls either the single-threaded or the multi-threaded event loop - * - * Most file systems will have to parse some file-system specific - * arguments before calling this function. It is recommended to do - * this with fuse_opt_parse() and a processing function that passes - * through any unknown options (this can also be achieved by just - * passing NULL as the processing function). That way, the remaining - * options can be passed directly to fuse_main(). - * - * fuse_main() accepts all options that can be passed to - * fuse_parse_cmdline(), fuse_new(), or fuse_session_new(). - * - * Option parsing skips argv[0], which is assumed to contain the - * program name. This element must always be present and is used to - * construct a basic ``usage: `` message for the --help - * output. argv[0] may also be set to the empty string. In this case - * the usage message is suppressed. This can be used by file systems - * to print their own usage line first. See hello.c for an example of - * how to do this. - * - * Note: this is currently implemented as a macro. - * - * The following error codes may be returned from fuse_main(): - * 1: Invalid option arguments - * 2: No mount point specified - * 3: FUSE setup failed - * 4: Mounting failed - * 5: Failed to daemonize (detach from session) - * 6: Failed to set up signal handlers - * 7: An error occured during the life of the file system - * - * @param argc the argument counter passed to the main() function - * @param argv the argument vector passed to the main() function - * @param op the file system operation - * @param private_data Initial value for the `private_data` - * field of `struct fuse_context`. May be overridden by the - * `struct fuse_operations.init` handler. - * @return 0 on success, nonzero on failure - * - * Example usage, see hello.c - */ -/* - * int fuse_main(int argc, char *argv[], const struct fuse_operations *op, - * void *private_data); - */ -#define fuse_main(argc, argv, op, private_data) \ - fuse_main_real(argc, argv, op, sizeof(*(op)), private_data) - -/* - * More detailed API - */ - -/** - * Print available options (high- and low-level) to stdout. This is - * not an exhaustive list, but includes only those options that may be - * of interest to an end-user of a file system. - * - * The function looks at the argument vector only to determine if - * there are additional modules to be loaded (module=foo option), - * and attempts to call their help functions as well. - * - * @param args the argument vector. - */ -void fuse_lib_help(struct fuse_args *args); - -/** - * Create a new FUSE filesystem. - * - * This function accepts most file-system independent mount options - * (like context, nodev, ro - see mount(8)), as well as the - * FUSE-specific mount options from mount.fuse(8). - * - * If the --help option is specified, the function writes a help text - * to stdout and returns NULL. - * - * Option parsing skips argv[0], which is assumed to contain the - * program name. This element must always be present and is used to - * construct a basic ``usage: `` message for the --help output. If - * argv[0] is set to the empty string, no usage message is included in - * the --help output. - * - * If an unknown option is passed in, an error message is written to - * stderr and the function returns NULL. - * - * @param args argument vector - * @param op the filesystem operations - * @param op_size the size of the fuse_operations structure - * @param private_data Initial value for the `private_data` - * field of `struct fuse_context`. May be overridden by the - * `struct fuse_operations.init` handler. - * @return the created FUSE handle - */ -#if FUSE_USE_VERSION == 30 -struct fuse *fuse_new_30(struct fuse_args *args, - const struct fuse_operations *op, size_t op_size, - void *private_data); -#define fuse_new(args, op, size, data) fuse_new_30(args, op, size, data) -#else -struct fuse *fuse_new(struct fuse_args *args, const struct fuse_operations *op, - size_t op_size, void *private_data); -#endif - -/** - * Mount a FUSE file system. - * - * @param mountpoint the mount point path - * @param f the FUSE handle - * - * @return 0 on success, -1 on failure. - **/ -int fuse_mount(struct fuse *f, const char *mountpoint); - -/** - * Unmount a FUSE file system. - * - * See fuse_session_unmount() for additional information. - * - * @param f the FUSE handle - **/ -void fuse_unmount(struct fuse *f); - -/** - * Destroy the FUSE handle. - * - * NOTE: This function does not unmount the filesystem. If this is - * needed, call fuse_unmount() before calling this function. - * - * @param f the FUSE handle - */ -void fuse_destroy(struct fuse *f); - -/** - * FUSE event loop. - * - * Requests from the kernel are processed, and the appropriate - * operations are called. - * - * For a description of the return value and the conditions when the - * event loop exits, refer to the documentation of - * fuse_session_loop(). - * - * @param f the FUSE handle - * @return see fuse_session_loop() - * - * See also: fuse_loop_mt() - */ -int fuse_loop(struct fuse *f); - -/** - * Flag session as terminated - * - * This function will cause any running event loops to exit on - * the next opportunity. - * - * @param f the FUSE handle - */ -void fuse_exit(struct fuse *f); - -/** - * Get the current context - * - * The context is only valid for the duration of a filesystem - * operation, and thus must not be stored and used later. - * - * @return the context - */ -struct fuse_context *fuse_get_context(void); - -/** - * Check if the current request has already been interrupted - * - * @return 1 if the request has been interrupted, 0 otherwise - */ -int fuse_interrupted(void); - -/** - * Invalidates cache for the given path. - * - * This calls fuse_lowlevel_notify_inval_inode internally. - * - * @return 0 on successful invalidation, negative error value otherwise. - * This routine may return -ENOENT to indicate that there was - * no entry to be invalidated, e.g., because the path has not - * been seen before or has been forgotten; this should not be - * considered to be an error. - */ -int fuse_invalidate_path(struct fuse *f, const char *path); - -/** - * The real main function - * - * Do not call this directly, use fuse_main() - */ -int fuse_main_real(int argc, char *argv[], const struct fuse_operations *op, - size_t op_size, void *private_data); - -/** - * Start the cleanup thread when using option "remember". - * - * This is done automatically by fuse_loop_mt() - * @param fuse struct fuse pointer for fuse instance - * @return 0 on success and -1 on error - */ -int fuse_start_cleanup_thread(struct fuse *fuse); - -/** - * Stop the cleanup thread when using option "remember". - * - * This is done automatically by fuse_loop_mt() - * @param fuse struct fuse pointer for fuse instance - */ -void fuse_stop_cleanup_thread(struct fuse *fuse); - -/** - * Iterate over cache removing stale entries - * use in conjunction with "-oremember" - * - * NOTE: This is already done for the standard sessions - * - * @param fuse struct fuse pointer for fuse instance - * @return the number of seconds until the next cleanup - */ -int fuse_clean_cache(struct fuse *fuse); - -/* - * Stacking API - */ - -/** - * Fuse filesystem object - * - * This is opaque object represents a filesystem layer - */ -struct fuse_fs; - -/* - * These functions call the relevant filesystem operation, and return - * the result. - * - * If the operation is not defined, they return -ENOSYS, with the - * exception of fuse_fs_open, fuse_fs_release, fuse_fs_opendir, - * fuse_fs_releasedir and fuse_fs_statfs, which return 0. - */ - -int fuse_fs_getattr(struct fuse_fs *fs, const char *path, struct stat *buf, - struct fuse_file_info *fi); -int fuse_fs_rename(struct fuse_fs *fs, const char *oldpath, const char *newpath, - unsigned int flags); -int fuse_fs_unlink(struct fuse_fs *fs, const char *path); -int fuse_fs_rmdir(struct fuse_fs *fs, const char *path); -int fuse_fs_symlink(struct fuse_fs *fs, const char *linkname, const char *path); -int fuse_fs_link(struct fuse_fs *fs, const char *oldpath, const char *newpath); -int fuse_fs_release(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi); -int fuse_fs_open(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi); -int fuse_fs_read(struct fuse_fs *fs, const char *path, char *buf, size_t size, - off_t off, struct fuse_file_info *fi); -int fuse_fs_read_buf(struct fuse_fs *fs, const char *path, - struct fuse_bufvec **bufp, size_t size, off_t off, - struct fuse_file_info *fi); -int fuse_fs_write(struct fuse_fs *fs, const char *path, const char *buf, - size_t size, off_t off, struct fuse_file_info *fi); -int fuse_fs_write_buf(struct fuse_fs *fs, const char *path, - struct fuse_bufvec *buf, off_t off, - struct fuse_file_info *fi); -int fuse_fs_fsync(struct fuse_fs *fs, const char *path, int datasync, - struct fuse_file_info *fi); -int fuse_fs_flush(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi); -int fuse_fs_statfs(struct fuse_fs *fs, const char *path, struct statvfs *buf); -int fuse_fs_opendir(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi); -int fuse_fs_readdir(struct fuse_fs *fs, const char *path, void *buf, - fuse_fill_dir_t filler, off_t off, - struct fuse_file_info *fi, enum fuse_readdir_flags flags); -int fuse_fs_fsyncdir(struct fuse_fs *fs, const char *path, int datasync, - struct fuse_file_info *fi); -int fuse_fs_releasedir(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi); -int fuse_fs_create(struct fuse_fs *fs, const char *path, mode_t mode, - struct fuse_file_info *fi); -int fuse_fs_lock(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi, int cmd, struct flock *lock); -int fuse_fs_flock(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi, int op); -int fuse_fs_chmod(struct fuse_fs *fs, const char *path, mode_t mode, - struct fuse_file_info *fi); -int fuse_fs_chown(struct fuse_fs *fs, const char *path, uid_t uid, gid_t gid, - struct fuse_file_info *fi); -int fuse_fs_truncate(struct fuse_fs *fs, const char *path, off_t size, - struct fuse_file_info *fi); -int fuse_fs_utimens(struct fuse_fs *fs, const char *path, - const struct timespec tv[2], struct fuse_file_info *fi); -int fuse_fs_access(struct fuse_fs *fs, const char *path, int mask); -int fuse_fs_readlink(struct fuse_fs *fs, const char *path, char *buf, - size_t len); -int fuse_fs_mknod(struct fuse_fs *fs, const char *path, mode_t mode, - dev_t rdev); -int fuse_fs_mkdir(struct fuse_fs *fs, const char *path, mode_t mode); -int fuse_fs_setxattr(struct fuse_fs *fs, const char *path, const char *name, - const char *value, size_t size, int flags); -int fuse_fs_getxattr(struct fuse_fs *fs, const char *path, const char *name, - char *value, size_t size); -int fuse_fs_listxattr(struct fuse_fs *fs, const char *path, char *list, - size_t size); -int fuse_fs_removexattr(struct fuse_fs *fs, const char *path, const char *name); -int fuse_fs_bmap(struct fuse_fs *fs, const char *path, size_t blocksize, - uint64_t *idx); -int fuse_fs_ioctl(struct fuse_fs *fs, const char *path, unsigned int cmd, - void *arg, struct fuse_file_info *fi, unsigned int flags, - void *data); -int fuse_fs_poll(struct fuse_fs *fs, const char *path, - struct fuse_file_info *fi, struct fuse_pollhandle *ph, - unsigned *reventsp); -int fuse_fs_fallocate(struct fuse_fs *fs, const char *path, int mode, - off_t offset, off_t length, struct fuse_file_info *fi); -ssize_t fuse_fs_copy_file_range(struct fuse_fs *fs, const char *path_in, - struct fuse_file_info *fi_in, off_t off_in, - const char *path_out, - struct fuse_file_info *fi_out, off_t off_out, - size_t len, int flags); -off_t fuse_fs_lseek(struct fuse_fs *fs, const char *path, off_t off, int whence, - struct fuse_file_info *fi); -void fuse_fs_init(struct fuse_fs *fs, struct fuse_conn_info *conn, - struct fuse_config *cfg); -void fuse_fs_destroy(struct fuse_fs *fs); - -int fuse_notify_poll(struct fuse_pollhandle *ph); - -/** - * Create a new fuse filesystem object - * - * This is usually called from the factory of a fuse module to create - * a new instance of a filesystem. - * - * @param op the filesystem operations - * @param op_size the size of the fuse_operations structure - * @param private_data Initial value for the `private_data` - * field of `struct fuse_context`. May be overridden by the - * `struct fuse_operations.init` handler. - * @return a new filesystem object - */ -struct fuse_fs *fuse_fs_new(const struct fuse_operations *op, size_t op_size, - void *private_data); - -/** - * Factory for creating filesystem objects - * - * The function may use and remove options from 'args' that belong - * to this module. - * - * For now the 'fs' vector always contains exactly one filesystem. - * This is the filesystem which will be below the newly created - * filesystem in the stack. - * - * @param args the command line arguments - * @param fs NULL terminated filesystem object vector - * @return the new filesystem object - */ -typedef struct fuse_fs *(*fuse_module_factory_t)(struct fuse_args *args, - struct fuse_fs *fs[]); -/** - * Register filesystem module - * - * If the "-omodules=*name*_:..." option is present, filesystem - * objects are created and pushed onto the stack with the *factory_* - * function. - * - * @param name_ the name of this filesystem module - * @param factory_ the factory function for this filesystem module - */ -#define FUSE_REGISTER_MODULE(name_, factory_) \ - fuse_module_factory_t fuse_module_##name_##_factory = factory_ - -/** Get session from fuse object */ -struct fuse_session *fuse_get_session(struct fuse *f); - -/** - * Open a FUSE file descriptor and set up the mount for the given - * mountpoint and flags. - * - * @param mountpoint reference to the mount in the file system - * @param options mount options - * @return the FUSE file descriptor or -1 upon error - */ -int fuse_open_channel(const char *mountpoint, const char *options); - -#endif /* FUSE_H_ */ diff --git a/tools/virtiofsd/fuse_i.h b/tools/virtiofsd/fuse_i.h index 4e47e5880d..1240828208 100644 --- a/tools/virtiofsd/fuse_i.h +++ b/tools/virtiofsd/fuse_i.h @@ -10,7 +10,6 @@ #define FUSE_I_H #define FUSE_USE_VERSION 31 -#include "fuse.h" #include "fuse_lowlevel.h" struct fv_VuDev; @@ -82,21 +81,6 @@ struct fuse_chan { struct fv_QueueInfo *qi; }; -/** - * Filesystem module - * - * Filesystem modules are registered with the FUSE_REGISTER_MODULE() - * macro. - * - */ -struct fuse_module { - char *name; - fuse_module_factory_t factory; - struct fuse_module *next; - struct fusemod_so *so; - int ctr; -}; - int fuse_send_reply_iov_nofree(fuse_req_t req, int error, struct iovec *iov, int count); void fuse_free_req(fuse_req_t req); diff --git a/tools/virtiofsd/fuse_lowlevel.c b/tools/virtiofsd/fuse_lowlevel.c index 704c0369b2..2dd36ec03b 100644 --- a/tools/virtiofsd/fuse_lowlevel.c +++ b/tools/virtiofsd/fuse_lowlevel.c @@ -192,7 +192,7 @@ int fuse_send_reply_iov_nofree(fuse_req_t req, int error, struct iovec *iov, if (error <= -1000 || error > 0) { fuse_log(FUSE_LOG_ERR, "fuse: bad error value: %i\n", error); - error = -ERANGE; + out.error = -ERANGE; } iov[0].iov_base = &out; diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c index 0801cf752c..819c2bc13c 100644 --- a/tools/virtiofsd/helper.c +++ b/tools/virtiofsd/helper.c @@ -165,7 +165,7 @@ void fuse_cmdline_help(void) " enable/disable readirplus\n" " default: readdirplus except with " "cache=none\n" - " -o timeout=<number> I/O timeout (second)\n" + " -o timeout=<number> I/O timeout (seconds)\n" " default: depends on cache= option.\n" " -o writeback|no_writeback enable/disable writeback cache\n" " default: no_writeback\n" diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c index c635fc8820..02ff01fad0 100644 --- a/tools/virtiofsd/passthrough_ll.c +++ b/tools/virtiofsd/passthrough_ll.c @@ -922,7 +922,6 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name, inode = lo_find(lo, &e->attr); if (inode) { close(newfd); - newfd = -1; } else { inode = calloc(1, sizeof(struct lo_inode)); if (!inode) { @@ -939,7 +938,6 @@ static int lo_do_lookup(fuse_req_t req, fuse_ino_t parent, const char *name, inode->nlookup = 1; inode->fd = newfd; - newfd = -1; inode->key.ino = e->attr.st_ino; inode->key.dev = e->attr.st_dev; pthread_mutex_init(&inode->plock_mutex, NULL); @@ -1080,8 +1078,6 @@ static void lo_mknod_symlink(fuse_req_t req, fuse_ino_t parent, return; } - saverr = ENOMEM; - saverr = lo_change_cred(req, &old); if (saverr) { goto out; diff --git a/ui/input-barrier.c b/ui/input-barrier.c index fe35049b83..527c75e130 100644 --- a/ui/input-barrier.c +++ b/ui/input-barrier.c @@ -455,7 +455,7 @@ static gboolean writecmd(InputBarrier *ib, struct barrierMsg *msg) break; default: write_cmd(p, barrierCmdEUnknown, avail); - break;; + break; } len = MAX_HELLO_LENGTH - avail - sizeof(int); diff --git a/util/Makefile.objs b/util/Makefile.objs index 11262aafaf..6b38b67cf1 100644 --- a/util/Makefile.objs +++ b/util/Makefile.objs @@ -20,6 +20,7 @@ util-obj-y += envlist.o path.o module.o util-obj-y += host-utils.o util-obj-y += bitmap.o bitops.o hbitmap.o util-obj-y += fifo8.o +util-obj-y += nvdimm-utils.o util-obj-y += cacheinfo.o util-obj-y += error.o qemu-error.o util-obj-y += qemu-print.o diff --git a/util/aio-posix.c b/util/aio-posix.c index a4977f538e..9e1befc0c0 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -15,6 +15,7 @@ #include "qemu/osdep.h" #include "block/block.h" +#include "qemu/rcu.h" #include "qemu/rcu_queue.h" #include "qemu/sockets.h" #include "qemu/cutils.h" @@ -31,12 +32,23 @@ struct AioHandler AioPollFn *io_poll; IOHandler *io_poll_begin; IOHandler *io_poll_end; - int deleted; void *opaque; bool is_external; QLIST_ENTRY(AioHandler) node; + QLIST_ENTRY(AioHandler) node_ready; /* only used during aio_poll() */ + QLIST_ENTRY(AioHandler) node_deleted; }; +/* Add a handler to a ready list */ +static void add_ready_handler(AioHandlerList *ready_list, + AioHandler *node, + int revents) +{ + QLIST_SAFE_REMOVE(node, node_ready); /* remove from nested parent's list */ + node->pfd.revents = revents; + QLIST_INSERT_HEAD(ready_list, node, node_ready); +} + #ifdef CONFIG_EPOLL_CREATE1 /* The fd number threshold to switch to epoll */ @@ -67,7 +79,7 @@ static bool aio_epoll_try_enable(AioContext *ctx) QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { int r; - if (node->deleted || !node->pfd.events) { + if (QLIST_IS_INSERTED(node, node_deleted) || !node->pfd.events) { continue; } event.events = epoll_events_from_pfd(node->pfd.events); @@ -104,17 +116,22 @@ static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new) } } -static int aio_epoll(AioContext *ctx, GPollFD *pfds, - unsigned npfd, int64_t timeout) +static int aio_epoll(AioContext *ctx, AioHandlerList *ready_list, + int64_t timeout) { + GPollFD pfd = { + .fd = ctx->epollfd, + .events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR, + }; AioHandler *node; int i, ret = 0; struct epoll_event events[128]; - assert(npfd == 1); - assert(pfds[0].fd == ctx->epollfd); if (timeout > 0) { - ret = qemu_poll_ns(pfds, npfd, timeout); + ret = qemu_poll_ns(&pfd, 1, timeout); + if (ret > 0) { + timeout = 0; + } } if (timeout <= 0 || ret > 0) { ret = epoll_wait(ctx->epollfd, events, @@ -125,11 +142,13 @@ static int aio_epoll(AioContext *ctx, GPollFD *pfds, } for (i = 0; i < ret; i++) { int ev = events[i].events; + int revents = (ev & EPOLLIN ? G_IO_IN : 0) | + (ev & EPOLLOUT ? G_IO_OUT : 0) | + (ev & EPOLLHUP ? G_IO_HUP : 0) | + (ev & EPOLLERR ? G_IO_ERR : 0); + node = events[i].data.ptr; - node->pfd.revents = (ev & EPOLLIN ? G_IO_IN : 0) | - (ev & EPOLLOUT ? G_IO_OUT : 0) | - (ev & EPOLLHUP ? G_IO_HUP : 0) | - (ev & EPOLLERR ? G_IO_ERR : 0); + add_ready_handler(ready_list, node, revents); } } out: @@ -167,8 +186,8 @@ static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new) { } -static int aio_epoll(AioContext *ctx, GPollFD *pfds, - unsigned npfd, int64_t timeout) +static int aio_epoll(AioContext *ctx, AioHandlerList *ready_list, + int64_t timeout) { assert(false); } @@ -191,9 +210,11 @@ static AioHandler *find_aio_handler(AioContext *ctx, int fd) AioHandler *node; QLIST_FOREACH(node, &ctx->aio_handlers, node) { - if (node->pfd.fd == fd) - if (!node->deleted) + if (node->pfd.fd == fd) { + if (!QLIST_IS_INSERTED(node, node_deleted)) { return node; + } + } } return NULL; @@ -212,7 +233,7 @@ static bool aio_remove_fd_handler(AioContext *ctx, AioHandler *node) /* If a read is in progress, just mark the node as deleted */ if (qemu_lockcnt_count(&ctx->list_lock)) { - node->deleted = 1; + QLIST_INSERT_HEAD_RCU(&ctx->deleted_aio_handlers, node, node_deleted); node->pfd.revents = 0; return false; } @@ -354,7 +375,7 @@ static void poll_set_started(AioContext *ctx, bool started) QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { IOHandler *fn; - if (node->deleted) { + if (QLIST_IS_INSERTED(node, node_deleted)) { continue; } @@ -411,43 +432,82 @@ bool aio_pending(AioContext *ctx) return result; } -static bool aio_dispatch_handlers(AioContext *ctx) +static void aio_free_deleted_handlers(AioContext *ctx) { - AioHandler *node, *tmp; - bool progress = false; + AioHandler *node; - QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { - int revents; + if (QLIST_EMPTY_RCU(&ctx->deleted_aio_handlers)) { + return; + } + if (!qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { + return; /* we are nested, let the parent do the freeing */ + } - revents = node->pfd.revents & node->pfd.events; - node->pfd.revents = 0; + while ((node = QLIST_FIRST_RCU(&ctx->deleted_aio_handlers))) { + QLIST_REMOVE(node, node); + QLIST_REMOVE(node, node_deleted); + g_free(node); + } - if (!node->deleted && - (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && - aio_node_check(ctx, node->is_external) && - node->io_read) { - node->io_read(node->opaque); + qemu_lockcnt_inc_and_unlock(&ctx->list_lock); +} - /* aio_notify() does not count as progress */ - if (node->opaque != &ctx->notifier) { - progress = true; - } - } - if (!node->deleted && - (revents & (G_IO_OUT | G_IO_ERR)) && - aio_node_check(ctx, node->is_external) && - node->io_write) { - node->io_write(node->opaque); +static bool aio_dispatch_handler(AioContext *ctx, AioHandler *node) +{ + bool progress = false; + int revents; + + revents = node->pfd.revents & node->pfd.events; + node->pfd.revents = 0; + + if (!QLIST_IS_INSERTED(node, node_deleted) && + (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && + aio_node_check(ctx, node->is_external) && + node->io_read) { + node->io_read(node->opaque); + + /* aio_notify() does not count as progress */ + if (node->opaque != &ctx->notifier) { progress = true; } + } + if (!QLIST_IS_INSERTED(node, node_deleted) && + (revents & (G_IO_OUT | G_IO_ERR)) && + aio_node_check(ctx, node->is_external) && + node->io_write) { + node->io_write(node->opaque); + progress = true; + } - if (node->deleted) { - if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { - QLIST_REMOVE(node, node); - g_free(node); - qemu_lockcnt_inc_and_unlock(&ctx->list_lock); - } - } + return progress; +} + +/* + * If we have a list of ready handlers then this is more efficient than + * scanning all handlers with aio_dispatch_handlers(). + */ +static bool aio_dispatch_ready_handlers(AioContext *ctx, + AioHandlerList *ready_list) +{ + bool progress = false; + AioHandler *node; + + while ((node = QLIST_FIRST(ready_list))) { + QLIST_SAFE_REMOVE(node, node_ready); + progress = aio_dispatch_handler(ctx, node) || progress; + } + + return progress; +} + +/* Slower than aio_dispatch_ready_handlers() but only used via glib */ +static bool aio_dispatch_handlers(AioContext *ctx) +{ + AioHandler *node, *tmp; + bool progress = false; + + QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { + progress = aio_dispatch_handler(ctx, node) || progress; } return progress; @@ -458,6 +518,7 @@ void aio_dispatch(AioContext *ctx) qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); aio_dispatch_handlers(ctx); + aio_free_deleted_handlers(ctx); qemu_lockcnt_dec(&ctx->list_lock); timerlistgroup_run_timers(&ctx->tlg); @@ -514,8 +575,18 @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout) bool progress = false; AioHandler *node; + /* + * Optimization: ->io_poll() handlers often contain RCU read critical + * sections and we therefore see many rcu_read_lock() -> rcu_read_unlock() + * -> rcu_read_lock() -> ... sequences with expensive memory + * synchronization primitives. Make the entire polling loop an RCU + * critical section because nested rcu_read_lock()/rcu_read_unlock() calls + * are cheap. + */ + RCU_READ_LOCK_GUARD(); + QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { - if (!node->deleted && node->io_poll && + if (!QLIST_IS_INSERTED(node, node_deleted) && node->io_poll && aio_node_check(ctx, node->is_external) && node->io_poll(node->opaque)) { /* @@ -609,6 +680,7 @@ static bool try_poll_mode(AioContext *ctx, int64_t *timeout) bool aio_poll(AioContext *ctx, bool blocking) { + AioHandlerList ready_list = QLIST_HEAD_INITIALIZER(ready_list); AioHandler *node; int i; int ret = 0; @@ -649,7 +721,7 @@ bool aio_poll(AioContext *ctx, bool blocking) if (!aio_epoll_enabled(ctx)) { QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { - if (!node->deleted && node->pfd.events + if (!QLIST_IS_INSERTED(node, node_deleted) && node->pfd.events && aio_node_check(ctx, node->is_external)) { add_pollfd(node); } @@ -658,13 +730,8 @@ bool aio_poll(AioContext *ctx, bool blocking) /* wait until next event */ if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { - AioHandler epoll_handler; - - epoll_handler.pfd.fd = ctx->epollfd; - epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR; - npfd = 0; - add_pollfd(&epoll_handler); - ret = aio_epoll(ctx, pollfds, npfd, timeout); + npfd = 0; /* pollfds[] is not being used */ + ret = aio_epoll(ctx, &ready_list, timeout); } else { ret = qemu_poll_ns(pollfds, npfd, timeout); } @@ -719,7 +786,11 @@ bool aio_poll(AioContext *ctx, bool blocking) /* if we have any readable fds, dispatch event */ if (ret > 0) { for (i = 0; i < npfd; i++) { - nodes[i]->pfd.revents = pollfds[i].revents; + int revents = pollfds[i].revents; + + if (revents) { + add_ready_handler(&ready_list, nodes[i], revents); + } } } @@ -728,9 +799,11 @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_bh_poll(ctx); if (ret > 0) { - progress |= aio_dispatch_handlers(ctx); + progress |= aio_dispatch_ready_handlers(ctx, &ready_list); } + aio_free_deleted_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); progress |= timerlistgroup_run_timers(&ctx->tlg); diff --git a/util/async.c b/util/async.c index c192a24a61..b94518b948 100644 --- a/util/async.c +++ b/util/async.c @@ -29,6 +29,7 @@ #include "block/thread-pool.h" #include "qemu/main-loop.h" #include "qemu/atomic.h" +#include "qemu/rcu_queue.h" #include "block/raw-aio.h" #include "qemu/coroutine_int.h" #include "trace.h" @@ -36,16 +37,76 @@ /***********************************************************/ /* bottom halves (can be seen as timers which expire ASAP) */ +/* QEMUBH::flags values */ +enum { + /* Already enqueued and waiting for aio_bh_poll() */ + BH_PENDING = (1 << 0), + + /* Invoke the callback */ + BH_SCHEDULED = (1 << 1), + + /* Delete without invoking callback */ + BH_DELETED = (1 << 2), + + /* Delete after invoking callback */ + BH_ONESHOT = (1 << 3), + + /* Schedule periodically when the event loop is idle */ + BH_IDLE = (1 << 4), +}; + struct QEMUBH { AioContext *ctx; QEMUBHFunc *cb; void *opaque; - QEMUBH *next; - bool scheduled; - bool idle; - bool deleted; + QSLIST_ENTRY(QEMUBH) next; + unsigned flags; }; +/* Called concurrently from any thread */ +static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags) +{ + AioContext *ctx = bh->ctx; + unsigned old_flags; + + /* + * The memory barrier implicit in atomic_fetch_or makes sure that: + * 1. idle & any writes needed by the callback are done before the + * locations are read in the aio_bh_poll. + * 2. ctx is loaded before the callback has a chance to execute and bh + * could be freed. + */ + old_flags = atomic_fetch_or(&bh->flags, BH_PENDING | new_flags); + if (!(old_flags & BH_PENDING)) { + QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next); + } + + aio_notify(ctx); +} + +/* Only called from aio_bh_poll() and aio_ctx_finalize() */ +static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags) +{ + QEMUBH *bh = QSLIST_FIRST_RCU(head); + + if (!bh) { + return NULL; + } + + QSLIST_REMOVE_HEAD(head, next); + + /* + * The atomic_and is paired with aio_bh_enqueue(). The implicit memory + * barrier ensures that the callback sees all writes done by the scheduling + * thread. It also ensures that the scheduling thread sees the cleared + * flag before bh->cb has run, and thus will call aio_notify again if + * necessary. + */ + *flags = atomic_fetch_and(&bh->flags, + ~(BH_PENDING | BH_SCHEDULED | BH_IDLE)); + return bh; +} + void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque) { QEMUBH *bh; @@ -55,15 +116,7 @@ void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque) .cb = cb, .opaque = opaque, }; - qemu_lockcnt_lock(&ctx->list_lock); - bh->next = ctx->first_bh; - bh->scheduled = 1; - bh->deleted = 1; - /* Make sure that the members are ready before putting bh into list */ - smp_wmb(); - ctx->first_bh = bh; - qemu_lockcnt_unlock(&ctx->list_lock); - aio_notify(ctx); + aio_bh_enqueue(bh, BH_SCHEDULED | BH_ONESHOT); } QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque) @@ -75,12 +128,6 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque) .cb = cb, .opaque = opaque, }; - qemu_lockcnt_lock(&ctx->list_lock); - bh->next = ctx->first_bh; - /* Make sure that the members are ready before putting bh into list */ - smp_wmb(); - ctx->first_bh = bh; - qemu_lockcnt_unlock(&ctx->list_lock); return bh; } @@ -89,91 +136,56 @@ void aio_bh_call(QEMUBH *bh) bh->cb(bh->opaque); } -/* Multiple occurrences of aio_bh_poll cannot be called concurrently. - * The count in ctx->list_lock is incremented before the call, and is - * not affected by the call. - */ +/* Multiple occurrences of aio_bh_poll cannot be called concurrently. */ int aio_bh_poll(AioContext *ctx) { - QEMUBH *bh, **bhp, *next; - int ret; - bool deleted = false; - - ret = 0; - for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) { - next = atomic_rcu_read(&bh->next); - /* The atomic_xchg is paired with the one in qemu_bh_schedule. The - * implicit memory barrier ensures that the callback sees all writes - * done by the scheduling thread. It also ensures that the scheduling - * thread sees the zero before bh->cb has run, and thus will call - * aio_notify again if necessary. - */ - if (atomic_xchg(&bh->scheduled, 0)) { + BHListSlice slice; + BHListSlice *s; + int ret = 0; + + QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list); + QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next); + + while ((s = QSIMPLEQ_FIRST(&ctx->bh_slice_list))) { + QEMUBH *bh; + unsigned flags; + + bh = aio_bh_dequeue(&s->bh_list, &flags); + if (!bh) { + QSIMPLEQ_REMOVE_HEAD(&ctx->bh_slice_list, next); + continue; + } + + if ((flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { /* Idle BHs don't count as progress */ - if (!bh->idle) { + if (!(flags & BH_IDLE)) { ret = 1; } - bh->idle = 0; aio_bh_call(bh); } - if (bh->deleted) { - deleted = true; + if (flags & (BH_DELETED | BH_ONESHOT)) { + g_free(bh); } } - /* remove deleted bhs */ - if (!deleted) { - return ret; - } - - if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { - bhp = &ctx->first_bh; - while (*bhp) { - bh = *bhp; - if (bh->deleted && !bh->scheduled) { - *bhp = bh->next; - g_free(bh); - } else { - bhp = &bh->next; - } - } - qemu_lockcnt_inc_and_unlock(&ctx->list_lock); - } return ret; } void qemu_bh_schedule_idle(QEMUBH *bh) { - bh->idle = 1; - /* Make sure that idle & any writes needed by the callback are done - * before the locations are read in the aio_bh_poll. - */ - atomic_mb_set(&bh->scheduled, 1); + aio_bh_enqueue(bh, BH_SCHEDULED | BH_IDLE); } void qemu_bh_schedule(QEMUBH *bh) { - AioContext *ctx; - - ctx = bh->ctx; - bh->idle = 0; - /* The memory barrier implicit in atomic_xchg makes sure that: - * 1. idle & any writes needed by the callback are done before the - * locations are read in the aio_bh_poll. - * 2. ctx is loaded before scheduled is set and the callback has a chance - * to execute. - */ - if (atomic_xchg(&bh->scheduled, 1) == 0) { - aio_notify(ctx); - } + aio_bh_enqueue(bh, BH_SCHEDULED); } - /* This func is async. */ void qemu_bh_cancel(QEMUBH *bh) { - atomic_mb_set(&bh->scheduled, 0); + atomic_and(&bh->flags, ~BH_SCHEDULED); } /* This func is async.The bottom half will do the delete action at the finial @@ -181,21 +193,16 @@ void qemu_bh_cancel(QEMUBH *bh) */ void qemu_bh_delete(QEMUBH *bh) { - bh->scheduled = 0; - bh->deleted = 1; + aio_bh_enqueue(bh, BH_DELETED); } -int64_t -aio_compute_timeout(AioContext *ctx) +static int64_t aio_compute_bh_timeout(BHList *head, int timeout) { - int64_t deadline; - int timeout = -1; QEMUBH *bh; - for (bh = atomic_rcu_read(&ctx->first_bh); bh; - bh = atomic_rcu_read(&bh->next)) { - if (bh->scheduled) { - if (bh->idle) { + QSLIST_FOREACH_RCU(bh, head, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { + if (bh->flags & BH_IDLE) { /* idle bottom halves will be polled at least * every 10ms */ timeout = 10000000; @@ -207,6 +214,28 @@ aio_compute_timeout(AioContext *ctx) } } + return timeout; +} + +int64_t +aio_compute_timeout(AioContext *ctx) +{ + BHListSlice *s; + int64_t deadline; + int timeout = -1; + + timeout = aio_compute_bh_timeout(&ctx->bh_list, timeout); + if (timeout == 0) { + return 0; + } + + QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) { + timeout = aio_compute_bh_timeout(&s->bh_list, timeout); + if (timeout == 0) { + return 0; + } + } + deadline = timerlistgroup_deadline_ns(&ctx->tlg); if (deadline == 0) { return 0; @@ -237,15 +266,24 @@ aio_ctx_check(GSource *source) { AioContext *ctx = (AioContext *) source; QEMUBH *bh; + BHListSlice *s; atomic_and(&ctx->notify_me, ~1); aio_notify_accept(ctx); - for (bh = ctx->first_bh; bh; bh = bh->next) { - if (bh->scheduled) { + QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { return true; } } + + QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) { + QSLIST_FOREACH_RCU(bh, &s->bh_list, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { + return true; + } + } + } return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0); } @@ -265,6 +303,8 @@ static void aio_ctx_finalize(GSource *source) { AioContext *ctx = (AioContext *) source; + QEMUBH *bh; + unsigned flags; thread_pool_free(ctx->thread_pool); @@ -287,18 +327,15 @@ aio_ctx_finalize(GSource *source) assert(QSLIST_EMPTY(&ctx->scheduled_coroutines)); qemu_bh_delete(ctx->co_schedule_bh); - qemu_lockcnt_lock(&ctx->list_lock); - assert(!qemu_lockcnt_count(&ctx->list_lock)); - while (ctx->first_bh) { - QEMUBH *next = ctx->first_bh->next; + /* There must be no aio_bh_poll() calls going on */ + assert(QSIMPLEQ_EMPTY(&ctx->bh_slice_list)); + while ((bh = aio_bh_dequeue(&ctx->bh_list, &flags))) { /* qemu_bh_delete() must have been called on BHs in this AioContext */ - assert(ctx->first_bh->deleted); + assert(flags & BH_DELETED); - g_free(ctx->first_bh); - ctx->first_bh = next; + g_free(bh); } - qemu_lockcnt_unlock(&ctx->list_lock); aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL); event_notifier_cleanup(&ctx->notifier); @@ -445,6 +482,8 @@ AioContext *aio_context_new(Error **errp) AioContext *ctx; ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext)); + QSLIST_INIT(&ctx->bh_list); + QSIMPLEQ_INIT(&ctx->bh_slice_list); aio_context_setup(ctx); ret = event_notifier_init(&ctx->notifier, false); diff --git a/util/log.c b/util/log.c index 47f2827397..2da6cb31dc 100644 --- a/util/log.c +++ b/util/log.c @@ -332,6 +332,8 @@ const QEMULogItem qemu_log_items[] = { #ifdef CONFIG_PLUGIN { CPU_LOG_PLUGIN, "plugin", "output from TCG plugins\n"}, #endif + { LOG_STRACE, "strace", + "log every user-mode syscall, its input, and its result" }, { 0, NULL, NULL }, }; diff --git a/util/module.c b/util/module.c index 8c5315a7a3..236a7bb52a 100644 --- a/util/module.c +++ b/util/module.c @@ -30,6 +30,7 @@ typedef struct ModuleEntry typedef QTAILQ_HEAD(, ModuleEntry) ModuleTypeList; static ModuleTypeList init_type_list[MODULE_INIT_MAX]; +static bool modules_init_done[MODULE_INIT_MAX]; static ModuleTypeList dso_init_list; @@ -91,11 +92,17 @@ void module_call_init(module_init_type type) ModuleTypeList *l; ModuleEntry *e; + if (modules_init_done[type]) { + return; + } + l = find_type(type); QTAILQ_FOREACH(e, l, node) { e->init(); } + + modules_init_done[type] = true; } #ifdef CONFIG_MODULES diff --git a/util/nvdimm-utils.c b/util/nvdimm-utils.c new file mode 100644 index 0000000000..5cc768ca47 --- /dev/null +++ b/util/nvdimm-utils.c @@ -0,0 +1,29 @@ +#include "qemu/nvdimm-utils.h" +#include "hw/mem/nvdimm.h" + +static int nvdimm_device_list(Object *obj, void *opaque) +{ + GSList **list = opaque; + + if (object_dynamic_cast(obj, TYPE_NVDIMM)) { + *list = g_slist_append(*list, DEVICE(obj)); + } + + object_child_foreach(obj, nvdimm_device_list, opaque); + return 0; +} + +/* + * inquire NVDIMM devices and link them into the list which is + * returned to the caller. + * + * Note: it is the caller's responsibility to free the list to avoid + * memory leak. + */ +GSList *nvdimm_get_device_list(void) +{ + GSList *list = NULL; + + object_child_foreach(qdev_get_machine(), nvdimm_device_list, &list); + return list; +} diff --git a/util/oslib-posix.c b/util/oslib-posix.c index 5a291cc982..897e8f3ba6 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -76,6 +76,10 @@ static MemsetThread *memset_thread; static int memset_num_threads; static bool memset_thread_failed; +static QemuMutex page_mutex; +static QemuCond page_cond; +static bool threads_created_flag; + int qemu_get_thread_id(void) { #if defined(__linux__) @@ -403,6 +407,17 @@ static void *do_touch_pages(void *arg) MemsetThread *memset_args = (MemsetThread *)arg; sigset_t set, oldset; + /* + * On Linux, the page faults from the loop below can cause mmap_sem + * contention with allocation of the thread stacks. Do not start + * clearing until all threads have been created. + */ + qemu_mutex_lock(&page_mutex); + while(!threads_created_flag){ + qemu_cond_wait(&page_cond, &page_mutex); + } + qemu_mutex_unlock(&page_mutex); + /* unblock SIGBUS */ sigemptyset(&set); sigaddset(&set, SIGBUS); @@ -451,27 +466,28 @@ static inline int get_memset_num_threads(int smp_cpus) static bool touch_all_pages(char *area, size_t hpagesize, size_t numpages, int smp_cpus) { - size_t numpages_per_thread; - size_t size_per_thread; + size_t numpages_per_thread, leftover; char *addr = area; int i = 0; memset_thread_failed = false; + threads_created_flag = false; memset_num_threads = get_memset_num_threads(smp_cpus); memset_thread = g_new0(MemsetThread, memset_num_threads); - numpages_per_thread = (numpages / memset_num_threads); - size_per_thread = (hpagesize * numpages_per_thread); + numpages_per_thread = numpages / memset_num_threads; + leftover = numpages % memset_num_threads; for (i = 0; i < memset_num_threads; i++) { memset_thread[i].addr = addr; - memset_thread[i].numpages = (i == (memset_num_threads - 1)) ? - numpages : numpages_per_thread; + memset_thread[i].numpages = numpages_per_thread + (i < leftover); memset_thread[i].hpagesize = hpagesize; qemu_thread_create(&memset_thread[i].pgthread, "touch_pages", do_touch_pages, &memset_thread[i], QEMU_THREAD_JOINABLE); - addr += size_per_thread; - numpages -= numpages_per_thread; + addr += memset_thread[i].numpages * hpagesize; } + threads_created_flag = true; + qemu_cond_broadcast(&page_cond); + for (i = 0; i < memset_num_threads; i++) { qemu_thread_join(&memset_thread[i].pgthread); } diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c index 813f7ec564..ddd9a96e76 100644 --- a/util/vfio-helpers.c +++ b/util/vfio-helpers.c @@ -545,7 +545,7 @@ static int qemu_vfio_do_mapping(QEMUVFIOState *s, void *host, size_t size, trace_qemu_vfio_do_mapping(s, host, size, iova); if (ioctl(s->container, VFIO_IOMMU_MAP_DMA, &dma_map)) { - error_report("VFIO_MAP_DMA: %d", -errno); + error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); return -errno; } return 0; @@ -570,7 +570,7 @@ static void qemu_vfio_undo_mapping(QEMUVFIOState *s, IOVAMapping *mapping, assert(QEMU_IS_ALIGNED(mapping->size, qemu_real_host_page_size)); assert(index >= 0 && index < s->nr_mappings); if (ioctl(s->container, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - error_setg(errp, "VFIO_UNMAP_DMA failed: %d", -errno); + error_setg_errno(errp, errno, "VFIO_UNMAP_DMA failed"); } memmove(mapping, &s->mappings[index + 1], sizeof(s->mappings[0]) * (s->nr_mappings - index - 1)); @@ -669,7 +669,7 @@ int qemu_vfio_dma_reset_temporary(QEMUVFIOState *s) trace_qemu_vfio_dma_reset_temporary(s); qemu_mutex_lock(&s->lock); if (ioctl(s->container, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - error_report("VFIO_UNMAP_DMA: %d", -errno); + error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); qemu_mutex_unlock(&s->lock); return -errno; } |