From dcff1035dfdfb4c76634df64a5359ac18749f7ca Mon Sep 17 00:00:00 2001 From: Marc-André Lureau Date: Mon, 23 Oct 2017 15:18:07 +0100 Subject: memfd: split qemu_memfd_alloc() Add a function to only create a memfd, without mmap. The function is used in the following memory backend. Signed-off-by: Marc-André Lureau Reviewed-by: Philippe Mathieu-Daudé Message-Id: <20171023141815.17709-2-marcandre.lureau@redhat.com> Signed-off-by: Eduardo Habkost --- include/qemu/memfd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/qemu/memfd.h b/include/qemu/memfd.h index 745a8c501e..41c24d807c 100644 --- a/include/qemu/memfd.h +++ b/include/qemu/memfd.h @@ -16,6 +16,7 @@ #define F_SEAL_WRITE 0x0008 /* prevent writes */ #endif +int qemu_memfd_create(const char *name, size_t size, unsigned int seals); void *qemu_memfd_alloc(const char *name, size_t size, unsigned int seals, int *fd); void qemu_memfd_free(void *ptr, size_t size, int fd); -- cgit v1.2.3-55-g7522 From 0bd1909da606a60f50128290fc319db020fa303c Mon Sep 17 00:00:00 2001 From: Eduardo Habkost Date: Sat, 25 Nov 2017 13:16:05 -0200 Subject: machine: Replace has_dynamic_sysbus with list of allowed devices The existing has_dynamic_sysbus flag makes the machine accept every user-creatable sysbus device type on the command-line. Replace it with a list of allowed device types, so machines can easily accept some sysbus devices while rejecting others. To keep exactly the same behavior as before, the existing has_dynamic_sysbus=true assignments are replaced with a TYPE_SYS_BUS_DEVICE entry on the allowed list. Other patches will replace the TYPE_SYS_BUS_DEVICE entries with more specific lists of devices. Cc: Peter Maydell Cc: Marcel Apfelbaum Cc: "Michael S. Tsirkin" Cc: Alexander Graf Cc: David Gibson Cc: Stefano Stabellini Cc: Anthony Perard Cc: qemu-arm@nongnu.org Cc: qemu-ppc@nongnu.org Cc: xen-devel@lists.xenproject.org Signed-off-by: Eduardo Habkost Message-Id: <20171125151610.20547-2-ehabkost@redhat.com> Reviewed-by: Greg Kurz Reviewed-by: David Gibson Reviewed-by: Marc-André Lureau Reviewed-by: Marcel Apfelbaum Signed-off-by: Eduardo Habkost --- hw/arm/virt.c | 3 ++- hw/core/machine.c | 43 +++++++++++++++++++++++++++++-------------- hw/i386/pc_q35.c | 3 ++- hw/ppc/e500plat.c | 4 +++- hw/ppc/spapr.c | 3 ++- hw/xen/xen_backend.c | 7 ++++++- include/hw/boards.h | 5 ++++- 7 files changed, 48 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 543f9bd6cc..7549895fd2 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1591,7 +1591,8 @@ static void virt_machine_class_init(ObjectClass *oc, void *data) * configuration of the particular instance. */ mc->max_cpus = 255; - mc->has_dynamic_sysbus = true; + /*TODO: allow only sysbus devices that really work with this machine */ + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_SYS_BUS_DEVICE); mc->block_default_type = IF_VIRTIO; mc->no_cdrom = 1; mc->pci_allow_0_address = true; diff --git a/hw/core/machine.c b/hw/core/machine.c index c857f3f934..0320a8efa1 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -334,29 +334,44 @@ static bool machine_get_enforce_config_section(Object *obj, Error **errp) return ms->enforce_config_section; } -static void error_on_sysbus_device(SysBusDevice *sbdev, void *opaque) +void machine_class_allow_dynamic_sysbus_dev(MachineClass *mc, const char *type) { - error_report("Option '-device %s' cannot be handled by this machine", - object_class_get_name(object_get_class(OBJECT(sbdev)))); - exit(1); + strList *item = g_new0(strList, 1); + + item->value = g_strdup(type); + item->next = mc->allowed_dynamic_sysbus_devices; + mc->allowed_dynamic_sysbus_devices = item; } -static void machine_init_notify(Notifier *notifier, void *data) +static void validate_sysbus_device(SysBusDevice *sbdev, void *opaque) { - Object *machine = qdev_get_machine(); - ObjectClass *oc = object_get_class(machine); - MachineClass *mc = MACHINE_CLASS(oc); + MachineState *machine = opaque; + MachineClass *mc = MACHINE_GET_CLASS(machine); + bool allowed = false; + strList *wl; - if (mc->has_dynamic_sysbus) { - /* Our machine can handle dynamic sysbus devices, we're all good */ - return; + for (wl = mc->allowed_dynamic_sysbus_devices; + !allowed && wl; + wl = wl->next) { + allowed |= !!object_dynamic_cast(OBJECT(sbdev), wl->value); } + if (!allowed) { + error_report("Option '-device %s' cannot be handled by this machine", + object_class_get_name(object_get_class(OBJECT(sbdev)))); + exit(1); + } +} + +static void machine_init_notify(Notifier *notifier, void *data) +{ + MachineState *machine = MACHINE(qdev_get_machine()); + /* - * Loop through all dynamically created devices and check whether there - * are sysbus devices among them. If there are, error out. + * Loop through all dynamically created sysbus devices and check if they are + * all allowed. If a device is not allowed, error out. */ - foreach_dynamic_sysbus_device(error_on_sysbus_device, NULL); + foreach_dynamic_sysbus_device(validate_sysbus_device, machine); } HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine) diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index 5c6c608fcb..0505730a99 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -299,7 +299,8 @@ static void pc_q35_machine_options(MachineClass *m) m->default_machine_opts = "firmware=bios-256k.bin"; m->default_display = "std"; m->no_floppy = 1; - m->has_dynamic_sysbus = true; + /*TODO: allow only sysbus devices that really work with this machine */ + machine_class_allow_dynamic_sysbus_dev(m, TYPE_SYS_BUS_DEVICE); m->max_cpus = 288; } diff --git a/hw/ppc/e500plat.c b/hw/ppc/e500plat.c index e59e80fb9e..438118c29b 100644 --- a/hw/ppc/e500plat.c +++ b/hw/ppc/e500plat.c @@ -15,6 +15,7 @@ #include "hw/boards.h" #include "sysemu/device_tree.h" #include "sysemu/kvm.h" +#include "hw/sysbus.h" #include "hw/pci/pci.h" #include "hw/ppc/openpic.h" #include "kvm_ppc.h" @@ -63,7 +64,8 @@ static void e500plat_machine_init(MachineClass *mc) mc->desc = "generic paravirt e500 platform"; mc->init = e500plat_init; mc->max_cpus = 32; - mc->has_dynamic_sysbus = true; + /*TODO: allow only sysbus devices that really work with this machine */ + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_SYS_BUS_DEVICE); mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("e500v2_v30"); } diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 499ab647d8..5847175fd9 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -3843,7 +3843,8 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) mc->default_boot_order = ""; mc->default_ram_size = 512 * M_BYTE; mc->kvm_type = spapr_kvm_type; - mc->has_dynamic_sysbus = true; + /*TODO: allow only sysbus devices that really work with this machine */ + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_SYS_BUS_DEVICE); mc->pci_allow_0_address = true; mc->get_hotplug_handler = spapr_get_hotplug_handler; hc->pre_plug = spapr_machine_device_pre_plug; diff --git a/hw/xen/xen_backend.c b/hw/xen/xen_backend.c index 0f849a26d2..82380ea9ee 100644 --- a/hw/xen/xen_backend.c +++ b/hw/xen/xen_backend.c @@ -564,7 +564,12 @@ static void xen_set_dynamic_sysbus(void) ObjectClass *oc = object_get_class(machine); MachineClass *mc = MACHINE_CLASS(oc); - mc->has_dynamic_sysbus = true; + /* + * Emulate old mc->has_dynamic_sysbus=true assignment + * + *TODO: add only Xen devices to the list + */ + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_SYS_BUS_DEVICE); } int xen_be_register(const char *type, struct XenDevOps *ops) diff --git a/include/hw/boards.h b/include/hw/boards.h index 156b16f7a6..041bc08971 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -76,6 +76,9 @@ void machine_set_cpu_numa_node(MachineState *machine, const CpuInstanceProperties *props, Error **errp); +void machine_class_allow_dynamic_sysbus_dev(MachineClass *mc, const char *type); + + /** * CPUArchId: * @arch_id - architecture-dependent CPU ID of present or possible CPU @@ -179,7 +182,6 @@ struct MachineClass { no_floppy:1, no_cdrom:1, no_sdcard:1, - has_dynamic_sysbus:1, pci_allow_0_address:1, legacy_fw_cfg_order:1; int is_default; @@ -197,6 +199,7 @@ struct MachineClass { bool ignore_memory_transaction_failures; int numa_mem_align_shift; const char **valid_cpu_types; + strList *allowed_dynamic_sysbus_devices; bool auto_enable_numa_with_memhp; void (*numa_auto_assign_ram)(MachineClass *mc, NodeInfo *nodes, int nb_nodes, ram_addr_t size); -- cgit v1.2.3-55-g7522 From 03fcbd9dc5084ff4676c153fbe04fb0fcf939d09 Mon Sep 17 00:00:00 2001 From: Thomas Huth Date: Thu, 2 Nov 2017 11:10:06 +0100 Subject: qdev: Check for the availability of a hotplug controller before adding a device The qdev_unplug() function contains a g_assert(hotplug_ctrl) statement, so QEMU crashes when the user tries to device_add + device_del a device that does not have a corresponding hotplug controller. This could be provoked for a couple of devices in the past (see commit 4c93950659487c7ad or 84ebd3e8c7d4fe955 for example), and can currently for example also be triggered like this: $ s390x-softmmu/qemu-system-s390x -M none -nographic QEMU 2.10.50 monitor - type 'help' for more information (qemu) device_add qemu-s390x-cpu,id=x (qemu) device_del x ** ERROR:qemu/qdev-monitor.c:872:qdev_unplug: assertion failed: (hotplug_ctrl) Aborted (core dumped) So devices clearly need a hotplug controller when they should be usable with device_add. The code in qdev_device_add() already checks whether the bus has a proper hotplug controller, but for devices that do not have a corresponding bus, there is no appropriate check available yet. In that case we should check whether the machine itself provides a suitable hotplug controller and refuse to plug the device if none is available. Reviewed-by: Igor Mammedov Signed-off-by: Thomas Huth Message-Id: <1509617407-21191-3-git-send-email-thuth@redhat.com> Reviewed-by: Cornelia Huck Signed-off-by: Eduardo Habkost --- hw/core/qdev.c | 28 ++++++++++++++++++++-------- include/hw/qdev-core.h | 1 + qdev-monitor.c | 5 +++++ 3 files changed, 26 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/hw/core/qdev.c b/hw/core/qdev.c index 11112951a5..f739753e3a 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -253,19 +253,31 @@ void qdev_set_legacy_instance_id(DeviceState *dev, int alias_id, dev->alias_required_for_version = required_for_version; } +HotplugHandler *qdev_get_machine_hotplug_handler(DeviceState *dev) +{ + MachineState *machine; + MachineClass *mc; + Object *m_obj = qdev_get_machine(); + + if (object_dynamic_cast(m_obj, TYPE_MACHINE)) { + machine = MACHINE(m_obj); + mc = MACHINE_GET_CLASS(machine); + if (mc->get_hotplug_handler) { + return mc->get_hotplug_handler(machine, dev); + } + } + + return NULL; +} + HotplugHandler *qdev_get_hotplug_handler(DeviceState *dev) { - HotplugHandler *hotplug_ctrl = NULL; + HotplugHandler *hotplug_ctrl; if (dev->parent_bus && dev->parent_bus->hotplug_handler) { hotplug_ctrl = dev->parent_bus->hotplug_handler; - } else if (object_dynamic_cast(qdev_get_machine(), TYPE_MACHINE)) { - MachineState *machine = MACHINE(qdev_get_machine()); - MachineClass *mc = MACHINE_GET_CLASS(machine); - - if (mc->get_hotplug_handler) { - hotplug_ctrl = mc->get_hotplug_handler(machine, dev); - } + } else { + hotplug_ctrl = qdev_get_machine_hotplug_handler(dev); } return hotplug_ctrl; } diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index 0a71bf83f0..51473eee7b 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -286,6 +286,7 @@ DeviceState *qdev_try_create(BusState *bus, const char *name); void qdev_init_nofail(DeviceState *dev); void qdev_set_legacy_instance_id(DeviceState *dev, int alias_id, int required_for_version); +HotplugHandler *qdev_get_machine_hotplug_handler(DeviceState *dev); HotplugHandler *qdev_get_hotplug_handler(DeviceState *dev); void qdev_unplug(DeviceState *dev, Error **errp); void qdev_simple_device_unplug_cb(HotplugHandler *hotplug_dev, diff --git a/qdev-monitor.c b/qdev-monitor.c index 2abb80d7e4..c436616446 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -613,6 +613,11 @@ DeviceState *qdev_device_add(QemuOpts *opts, Error **errp) if (bus) { qdev_set_parent_bus(dev, bus); + } else if (qdev_hotplug && !qdev_get_machine_hotplug_handler(dev)) { + /* No bus, no machine hotplug handler --> device is not hotpluggable */ + error_setg(&err, "Device '%s' can not be hotplugged on this machine", + driver); + goto err_del_dev; } qdev_set_id(dev, qemu_opts_id(opts)); -- cgit v1.2.3-55-g7522 From 983768431676f9ab8599a0b4813e1ca17af70838 Mon Sep 17 00:00:00 2001 From: Haozhong Zhang Date: Mon, 11 Dec 2017 15:28:04 +0800 Subject: hostmem-file: add "align" option When mmap(2) the backend files, QEMU uses the host page size (getpagesize(2)) by default as the alignment of mapping address. However, some backends may require alignments different than the page size. For example, mmap a device DAX (e.g., /dev/dax0.0) on Linux kernel 4.13 to an address, which is 4K-aligned but not 2M-aligned, fails with a kernel message like [617494.969768] dax dax0.0: qemu-system-x86: dax_mmap: fail, unaligned vma (0x7fa37c579000 - 0x7fa43c579000, 0x1fffff) Because there is no common approach to get such alignment requirement, we add the 'align' option to 'memory-backend-file', so that users or management utils, which have enough knowledge about the backend, can specify a proper alignment via this option. Signed-off-by: Haozhong Zhang Message-Id: <20171211072806.2812-2-haozhong.zhang@intel.com> Reviewed-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi [ehabkost: fixed typo, fixed error_setg() format string] Signed-off-by: Eduardo Habkost --- backends/hostmem-file.c | 41 ++++++++++++++++++++++++++++++++++++++++- docs/nvdimm.txt | 16 ++++++++++++++++ exec.c | 8 +++++++- include/exec/memory.h | 3 +++ memory.c | 2 ++ numa.c | 2 +- qemu-options.hx | 9 ++++++++- 7 files changed, 77 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c index e44c319915..e319ec1ad8 100644 --- a/backends/hostmem-file.c +++ b/backends/hostmem-file.c @@ -34,6 +34,7 @@ struct HostMemoryBackendFile { bool share; bool discard_data; char *mem_path; + uint64_t align; }; static void @@ -58,7 +59,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) path = object_get_canonical_path(OBJECT(backend)); memory_region_init_ram_from_file(&backend->mr, OBJECT(backend), path, - backend->size, fb->share, + backend->size, fb->align, fb->share, fb->mem_path, errp); g_free(path); } @@ -115,6 +116,40 @@ static void file_memory_backend_set_discard_data(Object *o, bool value, MEMORY_BACKEND_FILE(o)->discard_data = value; } +static void file_memory_backend_get_align(Object *o, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o); + uint64_t val = fb->align; + + visit_type_size(v, name, &val, errp); +} + +static void file_memory_backend_set_align(Object *o, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + HostMemoryBackend *backend = MEMORY_BACKEND(o); + HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o); + Error *local_err = NULL; + uint64_t val; + + if (host_memory_backend_mr_inited(backend)) { + error_setg(&local_err, "cannot change property value"); + goto out; + } + + visit_type_size(v, name, &val, &local_err); + if (local_err) { + goto out; + } + fb->align = val; + + out: + error_propagate(errp, local_err); +} + static void file_backend_unparent(Object *obj) { HostMemoryBackend *backend = MEMORY_BACKEND(obj); @@ -145,6 +180,10 @@ file_backend_class_init(ObjectClass *oc, void *data) object_class_property_add_str(oc, "mem-path", get_mem_path, set_mem_path, &error_abort); + object_class_property_add(oc, "align", "int", + file_memory_backend_get_align, + file_memory_backend_set_align, + NULL, NULL, &error_abort); } static void file_backend_instance_finalize(Object *o) diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt index 2d9f8c0e8c..21249dd062 100644 --- a/docs/nvdimm.txt +++ b/docs/nvdimm.txt @@ -122,3 +122,19 @@ Note: M >= size of RAM devices + size of statically plugged vNVDIMM devices + size of hotplugged vNVDIMM devices + +Alignment +--------- + +QEMU uses mmap(2) to maps vNVDIMM backends and aligns the mapping +address to the page size (getpagesize(2)) by default. However, some +types of backends may require an alignment different than the page +size. In that case, QEMU v2.12.0 and later provide 'align' option to +memory-backend-file to allow users to specify the proper alignment. + +For example, device dax require the 2 MB alignment, so we can use +following QEMU command line options to use it (/dev/dax0.0) as the +backend of vNVDIMM: + + -object memory-backend-file,id=mem1,share=on,mem-path=/dev/dax0.0,size=4G,align=2M + -device nvdimm,id=nvdimm1,memdev=mem1 diff --git a/exec.c b/exec.c index d28fc0cd3d..629a508385 100644 --- a/exec.c +++ b/exec.c @@ -1612,7 +1612,13 @@ static void *file_ram_alloc(RAMBlock *block, void *area; block->page_size = qemu_fd_getpagesize(fd); - block->mr->align = block->page_size; + if (block->mr->align % block->page_size) { + error_setg(errp, "alignment 0x%" PRIx64 + " must be multiples of page size 0x%zx", + block->mr->align, block->page_size); + return NULL; + } + block->mr->align = MAX(block->page_size, block->mr->align); #if defined(__s390x__) if (kvm_enabled()) { block->mr->align = MAX(block->mr->align, QEMU_VMALLOC_ALIGN); diff --git a/include/exec/memory.h b/include/exec/memory.h index a4cabdf44c..07c5d6d597 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -465,6 +465,8 @@ void memory_region_init_resizeable_ram(MemoryRegion *mr, * @name: Region name, becomes part of RAMBlock name used in migration stream * must be unique within any device * @size: size of the region. + * @align: alignment of the region base address; if 0, the default alignment + * (getpagesize()) will be used. * @share: %true if memory must be mmaped with the MAP_SHARED flag * @path: the path in which to allocate the RAM. * @errp: pointer to Error*, to store an error if it happens. @@ -476,6 +478,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, struct Object *owner, const char *name, uint64_t size, + uint64_t align, bool share, const char *path, Error **errp); diff --git a/memory.c b/memory.c index 4b41fb837b..449a1429b9 100644 --- a/memory.c +++ b/memory.c @@ -1570,6 +1570,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, struct Object *owner, const char *name, uint64_t size, + uint64_t align, bool share, const char *path, Error **errp) @@ -1578,6 +1579,7 @@ void memory_region_init_ram_from_file(MemoryRegion *mr, mr->ram = true; mr->terminates = true; mr->destructor = memory_region_destructor_ram; + mr->align = align; mr->ram_block = qemu_ram_alloc_from_file(size, mr, share, path, errp); mr->dirty_log_mask = tcg_enabled() ? (1 << DIRTY_MEMORY_CODE) : 0; } diff --git a/numa.c b/numa.c index 7b9c33ad12..83675a03f3 100644 --- a/numa.c +++ b/numa.c @@ -456,7 +456,7 @@ static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner, if (mem_path) { #ifdef __linux__ Error *err = NULL; - memory_region_init_ram_from_file(mr, owner, name, ram_size, false, + memory_region_init_ram_from_file(mr, owner, name, ram_size, 0, false, mem_path, &err); if (err) { error_report_err(err); diff --git a/qemu-options.hx b/qemu-options.hx index b3e03c5464..5ff741a4af 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -3974,7 +3974,7 @@ property must be set. These objects are placed in the @table @option -@item -object memory-backend-file,id=@var{id},size=@var{size},mem-path=@var{dir},share=@var{on|off},discard-data=@var{on|off},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave} +@item -object memory-backend-file,id=@var{id},size=@var{size},mem-path=@var{dir},share=@var{on|off},discard-data=@var{on|off},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave},align=@var{align} Creates a memory file backend object, which can be used to back the guest RAM with huge pages. @@ -4027,6 +4027,13 @@ restrict memory allocation to the given host node list interleave memory allocations across the given host node list @end table +The @option{align} option specifies the base address alignment when +QEMU mmap(2) @option{mem-path}, and accepts common suffixes, eg +@option{2M}. Some backend store specified by @option{mem-path} +requires an alignment different than the default one used by QEMU, eg +the device DAX /dev/dax0.0 requires 2M alignment rather than 4K. In +such cases, users can specify the required alignment via this option. + @item -object memory-backend-ram,id=@var{id},merge=@var{on|off},dump=@var{on|off},prealloc=@var{on|off},size=@var{size},host-nodes=@var{host-nodes},policy=@var{default|preferred|bind|interleave} Creates a memory backend object, which can be used to back the guest RAM. -- cgit v1.2.3-55-g7522 From da6789c27c2ea71765cfab04bad9a42b5426f0bd Mon Sep 17 00:00:00 2001 From: Haozhong Zhang Date: Mon, 11 Dec 2017 15:28:05 +0800 Subject: nvdimm: add a macro for property "label-size" Signed-off-by: Haozhong Zhang Reviewed-by: Stefan Hajnoczi Message-Id: <20171211072806.2812-3-haozhong.zhang@intel.com> Reviewed-by: Michael S. Tsirkin Signed-off-by: Eduardo Habkost --- hw/mem/nvdimm.c | 2 +- include/hw/mem/nvdimm.h | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/hw/mem/nvdimm.c b/hw/mem/nvdimm.c index 952fce5ec8..618c3d677b 100644 --- a/hw/mem/nvdimm.c +++ b/hw/mem/nvdimm.c @@ -66,7 +66,7 @@ out: static void nvdimm_init(Object *obj) { - object_property_add(obj, "label-size", "int", + object_property_add(obj, NVDIMM_LABLE_SIZE_PROP, "int", nvdimm_get_label_size, nvdimm_set_label_size, NULL, NULL, NULL); } diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h index 03e1ff9558..28e68ddf59 100644 --- a/include/hw/mem/nvdimm.h +++ b/include/hw/mem/nvdimm.h @@ -47,6 +47,9 @@ #define NVDIMM_CLASS(oc) OBJECT_CLASS_CHECK(NVDIMMClass, (oc), TYPE_NVDIMM) #define NVDIMM_GET_CLASS(obj) OBJECT_GET_CLASS(NVDIMMClass, (obj), \ TYPE_NVDIMM) + +#define NVDIMM_LABLE_SIZE_PROP "label-size" + struct NVDIMMDevice { /* private */ PCDIMMDevice parent_obj; -- cgit v1.2.3-55-g7522 From cb836434cda103fac3c06174e70bf5c9b7083b8e Mon Sep 17 00:00:00 2001 From: Haozhong Zhang Date: Mon, 11 Dec 2017 15:28:06 +0800 Subject: nvdimm: add 'unarmed' option Currently the only vNVDIMM backend can guarantee the guest write persistence is device DAX on Linux, because no host-side kernel cache is involved in the guest access to it. The approach to detect whether the backend is device DAX needs to access sysfs, which may not work with SELinux. Instead, we add the 'unarmed' option to device 'nvdimm', so that users or management utils, which have enough knowledge about the backend, can control the unarmed flag in guest ACPI NFIT via this option. The guest Linux NVDIMM driver, for example, will mark the corresponding vNVDIMM device read-only if the unarmed flag in guest NFIT is set. The default value of 'unarmed' option is 'off' in order to keep the backwards compatibility. Signed-off-by: Haozhong Zhang Message-Id: <20171211072806.2812-4-haozhong.zhang@intel.com> Reviewed-by: Michael S. Tsirkin Reviewed-by: Stefan Hajnoczi Signed-off-by: Eduardo Habkost --- docs/nvdimm.txt | 15 +++++++++++++++ hw/acpi/nvdimm.c | 7 +++++++ hw/mem/nvdimm.c | 26 ++++++++++++++++++++++++++ include/hw/mem/nvdimm.h | 9 +++++++++ 4 files changed, 57 insertions(+) (limited to 'include') diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt index 21249dd062..e903d8bb09 100644 --- a/docs/nvdimm.txt +++ b/docs/nvdimm.txt @@ -138,3 +138,18 @@ backend of vNVDIMM: -object memory-backend-file,id=mem1,share=on,mem-path=/dev/dax0.0,size=4G,align=2M -device nvdimm,id=nvdimm1,memdev=mem1 + +Guest Data Persistence +---------------------- + +Though QEMU supports multiple types of vNVDIMM backends on Linux, +currently the only one that can guarantee the guest write persistence +is the device DAX on the real NVDIMM device (e.g., /dev/dax0.0), to +which all guest access do not involve any host-side kernel cache. + +When using other types of backends, it's suggested to set 'unarmed' +option of '-device nvdimm' to 'on', which sets the unarmed flag of the +guest NVDIMM region mapping structure. This unarmed flag indicates +guest software that this vNVDIMM device contains a region that cannot +accept persistent writes. In result, for example, the guest Linux +NVDIMM driver, marks such vNVDIMM device as read-only. diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index 6ceea196e7..59d6e4254c 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -138,6 +138,8 @@ struct NvdimmNfitMemDev { } QEMU_PACKED; typedef struct NvdimmNfitMemDev NvdimmNfitMemDev; +#define ACPI_NFIT_MEM_NOT_ARMED (1 << 3) + /* * NVDIMM Control Region Structure * @@ -284,6 +286,7 @@ static void nvdimm_build_structure_memdev(GArray *structures, DeviceState *dev) { NvdimmNfitMemDev *nfit_memdev; + NVDIMMDevice *nvdimm = NVDIMM(OBJECT(dev)); uint64_t size = object_property_get_uint(OBJECT(dev), PC_DIMM_SIZE_PROP, NULL); int slot = object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP, @@ -312,6 +315,10 @@ nvdimm_build_structure_memdev(GArray *structures, DeviceState *dev) /* Only one interleave for PMEM. */ nfit_memdev->interleave_ways = cpu_to_le16(1); + + if (nvdimm->unarmed) { + nfit_memdev->flags |= cpu_to_le16(ACPI_NFIT_MEM_NOT_ARMED); + } } /* diff --git a/hw/mem/nvdimm.c b/hw/mem/nvdimm.c index 618c3d677b..61e677f92f 100644 --- a/hw/mem/nvdimm.c +++ b/hw/mem/nvdimm.c @@ -25,6 +25,7 @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include "qapi-visit.h" #include "hw/mem/nvdimm.h" static void nvdimm_get_label_size(Object *obj, Visitor *v, const char *name, @@ -64,11 +65,36 @@ out: error_propagate(errp, local_err); } +static bool nvdimm_get_unarmed(Object *obj, Error **errp) +{ + NVDIMMDevice *nvdimm = NVDIMM(obj); + + return nvdimm->unarmed; +} + +static void nvdimm_set_unarmed(Object *obj, bool value, Error **errp) +{ + NVDIMMDevice *nvdimm = NVDIMM(obj); + Error *local_err = NULL; + + if (memory_region_size(&nvdimm->nvdimm_mr)) { + error_setg(&local_err, "cannot change property value"); + goto out; + } + + nvdimm->unarmed = value; + + out: + error_propagate(errp, local_err); +} + static void nvdimm_init(Object *obj) { object_property_add(obj, NVDIMM_LABLE_SIZE_PROP, "int", nvdimm_get_label_size, nvdimm_set_label_size, NULL, NULL, NULL); + object_property_add_bool(obj, NVDIMM_UNARMED_PROP, + nvdimm_get_unarmed, nvdimm_set_unarmed, NULL); } static MemoryRegion *nvdimm_get_memory_region(PCDIMMDevice *dimm, Error **errp) diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h index 28e68ddf59..7fd87c4e1c 100644 --- a/include/hw/mem/nvdimm.h +++ b/include/hw/mem/nvdimm.h @@ -49,6 +49,7 @@ TYPE_NVDIMM) #define NVDIMM_LABLE_SIZE_PROP "label-size" +#define NVDIMM_UNARMED_PROP "unarmed" struct NVDIMMDevice { /* private */ @@ -74,6 +75,14 @@ struct NVDIMMDevice { * guest via ACPI NFIT and _FIT method if NVDIMM hotplug is supported. */ MemoryRegion nvdimm_mr; + + /* + * The 'on' value results in the unarmed flag set in ACPI NFIT, + * which can be used to notify guest implicitly that the host + * backend (e.g., files on HDD, /dev/pmemX, etc.) cannot guarantee + * the guest write persistence. + */ + bool unarmed; }; typedef struct NVDIMMDevice NVDIMMDevice; -- cgit v1.2.3-55-g7522 From d342eb7662bcfe47c26615b67025ae59a383489d Mon Sep 17 00:00:00 2001 From: Igor Mammedov Date: Wed, 10 Jan 2018 16:22:50 +0100 Subject: possible_cpus: add CPUArchId::type field Remove dependency of possible_cpus on 1st CPU instance, which decouples configuration data from CPU instances that are created using that data. Also later it would be used for enabling early cpu to numa node configuration at runtime qmp_query_hotpluggable_cpus() should provide a list of available cpu slots at early stage, before machine_init() is called and the 1st cpu is created, so that mgmt might be able to call it and use output to set numa mapping. Use MachineClass::possible_cpu_arch_ids() callback to set cpu type info, along with the rest of possible cpu properties, to let machine define which cpu type* will be used. * for SPAPR it will be a spapr core type and for ARM/s390x/x86 a respective descendant of CPUClass. Move parse_numa_opts() in vl.c after cpu_model is parsed into cpu_type so that possible_cpu_arch_ids() would know which cpu_type to use during layout initialization. Signed-off-by: Igor Mammedov Reviewed-by: David Gibson Message-Id: <1515597770-268979-1-git-send-email-imammedo@redhat.com> Signed-off-by: Eduardo Habkost --- hw/arm/virt.c | 3 ++- hw/core/machine.c | 12 ++++++------ hw/i386/pc.c | 4 +++- hw/ppc/spapr.c | 13 ++++++++----- hw/s390x/s390-virtio-ccw.c | 1 + include/hw/boards.h | 2 ++ vl.c | 3 +-- 7 files changed, 23 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 4a6fdcc4f5..a4537af400 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1359,7 +1359,7 @@ static void machvirt_init(MachineState *machine) break; } - cpuobj = object_new(machine->cpu_type); + cpuobj = object_new(possible_cpus->cpus[n].type); object_property_set_int(cpuobj, possible_cpus->cpus[n].arch_id, "mp-affinity", NULL); @@ -1575,6 +1575,7 @@ static const CPUArchIdList *virt_possible_cpu_arch_ids(MachineState *ms) sizeof(CPUArchId) * max_cpus); ms->possible_cpus->len = max_cpus; for (n = 0; n < ms->possible_cpus->len; n++) { + ms->possible_cpus->cpus[n].type = ms->cpu_type; ms->possible_cpus->cpus[n].arch_id = virt_cpu_mp_affinity(vms, n); ms->possible_cpus->cpus[n].props.has_thread_id = true; diff --git a/hw/core/machine.c b/hw/core/machine.c index 0320a8efa1..cdc1163dc6 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -377,18 +377,18 @@ static void machine_init_notify(Notifier *notifier, void *data) HotpluggableCPUList *machine_query_hotpluggable_cpus(MachineState *machine) { int i; - Object *cpu; HotpluggableCPUList *head = NULL; - const char *cpu_type; + MachineClass *mc = MACHINE_GET_CLASS(machine); + + /* force board to initialize possible_cpus if it hasn't been done yet */ + mc->possible_cpu_arch_ids(machine); - cpu = machine->possible_cpus->cpus[0].cpu; - assert(cpu); /* Boot cpu is always present */ - cpu_type = object_get_typename(cpu); for (i = 0; i < machine->possible_cpus->len; i++) { + Object *cpu; HotpluggableCPUList *list_item = g_new0(typeof(*list_item), 1); HotpluggableCPU *cpu_item = g_new0(typeof(*cpu_item), 1); - cpu_item->type = g_strdup(cpu_type); + cpu_item->type = g_strdup(machine->possible_cpus->cpus[i].type); cpu_item->vcpus_count = machine->possible_cpus->cpus[i].vcpus_count; cpu_item->props = g_memdup(&machine->possible_cpus->cpus[i].props, sizeof(*cpu_item->props)); diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 55686bf5d8..ccc50baa85 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -1148,7 +1148,8 @@ void pc_cpus_init(PCMachineState *pcms) pcms->apic_id_limit = x86_cpu_apic_id_from_index(max_cpus - 1) + 1; possible_cpus = mc->possible_cpu_arch_ids(ms); for (i = 0; i < smp_cpus; i++) { - pc_new_cpu(ms->cpu_type, possible_cpus->cpus[i].arch_id, &error_fatal); + pc_new_cpu(possible_cpus->cpus[i].type, possible_cpus->cpus[i].arch_id, + &error_fatal); } } @@ -2307,6 +2308,7 @@ static const CPUArchIdList *pc_possible_cpu_arch_ids(MachineState *ms) for (i = 0; i < ms->possible_cpus->len; i++) { X86CPUTopoInfo topo; + ms->possible_cpus->cpus[i].type = ms->cpu_type; ms->possible_cpus->cpus[i].vcpus_count = 1; ms->possible_cpus->cpus[i].arch_id = x86_cpu_apic_id_from_index(i); x86_topo_ids_from_apicid(ms->possible_cpus->cpus[i].arch_id, diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 278f9de1e7..a781dd22e7 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -2226,11 +2226,6 @@ static void spapr_init_cpus(sPAPRMachineState *spapr) int boot_cores_nr = smp_cpus / smp_threads; int i; - if (!type) { - error_report("Unable to find sPAPR CPU Core definition"); - exit(1); - } - possible_cpus = mc->possible_cpu_arch_ids(machine); if (mc->has_hotpluggable_cpus) { if (smp_cpus % smp_threads) { @@ -3545,6 +3540,7 @@ static int64_t spapr_get_default_cpu_node_id(const MachineState *ms, int idx) static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine) { int i; + const char *core_type; int spapr_max_cores = max_cpus / smp_threads; MachineClass *mc = MACHINE_GET_CLASS(machine); @@ -3556,12 +3552,19 @@ static const CPUArchIdList *spapr_possible_cpu_arch_ids(MachineState *machine) return machine->possible_cpus; } + core_type = spapr_get_cpu_core_type(machine->cpu_type); + if (!core_type) { + error_report("Unable to find sPAPR CPU Core definition"); + exit(1); + } + machine->possible_cpus = g_malloc0(sizeof(CPUArchIdList) + sizeof(CPUArchId) * spapr_max_cores); machine->possible_cpus->len = spapr_max_cores; for (i = 0; i < machine->possible_cpus->len; i++) { int core_id = i * smp_threads; + machine->possible_cpus->cpus[i].type = core_type; machine->possible_cpus->cpus[i].vcpus_count = smp_threads; machine->possible_cpus->cpus[i].arch_id = core_id; machine->possible_cpus->cpus[i].props.has_core_id = true; diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 35df7e19c5..3807dcb097 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -414,6 +414,7 @@ static const CPUArchIdList *s390_possible_cpu_arch_ids(MachineState *ms) sizeof(CPUArchId) * max_cpus); ms->possible_cpus->len = max_cpus; for (i = 0; i < ms->possible_cpus->len; i++) { + ms->possible_cpus->cpus[i].type = ms->cpu_type; ms->possible_cpus->cpus[i].vcpus_count = 1; ms->possible_cpus->cpus[i].arch_id = i; ms->possible_cpus->cpus[i].props.has_core_id = true; diff --git a/include/hw/boards.h b/include/hw/boards.h index 041bc08971..efb0a9edfd 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -83,6 +83,7 @@ void machine_class_allow_dynamic_sysbus_dev(MachineClass *mc, const char *type); * CPUArchId: * @arch_id - architecture-dependent CPU ID of present or possible CPU * @cpu - pointer to corresponding CPU object if it's present on NULL otherwise + * @type - QOM class name of possible @cpu object * @props - CPU object properties, initialized by board * #vcpus_count - number of threads provided by @cpu object */ @@ -91,6 +92,7 @@ typedef struct { int64_t vcpus_count; CpuInstanceProperties props; Object *cpu; + const char *type; } CPUArchId; /** diff --git a/vl.c b/vl.c index 2586f25952..e725ecbc08 100644 --- a/vl.c +++ b/vl.c @@ -4611,8 +4611,6 @@ int main(int argc, char **argv, char **envp) current_machine->boot_order = boot_order; current_machine->cpu_model = cpu_model; - parse_numa_opts(current_machine); - /* parse features once if machine provides default cpu_type */ if (machine_class->default_cpu_type) { current_machine->cpu_type = machine_class->default_cpu_type; @@ -4621,6 +4619,7 @@ int main(int argc, char **argv, char **envp) cpu_parse_cpu_model(machine_class->default_cpu_type, cpu_model); } } + parse_numa_opts(current_machine); machine_run_board_init(current_machine); -- cgit v1.2.3-55-g7522