* [RFC Design Doc v2] Add vNVDIMM support for Xen @ 2016-07-18 0:29 Haozhong Zhang 2016-07-18 8:36 ` Tian, Kevin ` (3 more replies) 0 siblings, 4 replies; 24+ messages in thread From: Haozhong Zhang @ 2016-07-18 0:29 UTC (permalink / raw) To: xen-devel Cc: Juergen Gross, Zhang, Haozhong, Tian, Kevin, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, Jan Beulich, Xiao Guangrong Hi, Following is version 2 of the design doc for supporting vNVDIMM in Xen. It's basically the summary of discussion on previous v1 design (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). Any comments are welcome. The corresponding patches are WIP. Thanks, Haozhong vNVDIMM Design v2 Changes in v2: - Rewrite the the design details based on previous discussion [7]. - Add Section 3 Usage Example of vNVDIMM in Xen. - Remove content about pcommit instruction which has been deprecated [8]. Content ======= 1. Background 1.1 Access Mechanisms: Persistent Memory and Block Window 1.2 ACPI Support 1.2.1 NFIT 1.2.2 _DSM and _FIT 1.3 Namespace 1.4 clwb/clflushopt 2. NVDIMM/vNVDIMM Support in Linux Kernel/KVM/QEMU 2.1 NVDIMM Driver in Linux Kernel 2.2 vNVDIMM Implementation in KVM/QEMU 3. Usage Example of vNVDIMM in Xen 4. Design of vNVDIMM in Xen 4.1 Guest clwb/clflushopt Enabling 4.2 pmem Address Management 4.2.1 Reserve Storage for Management Structures 4.2.2 Detection of Host pmem Devices 4.2.3 Get Host Machine Address (SPA) of Host pmem Files 4.2.4 Map Host pmem to Guests 4.2.5 Misc 1: RAS 4.2.6 Misc 2: hotplug 4.3 Guest ACPI Emulation 4.3.1 Building Guest ACPI Tables 4.3.2 Emulating Guest _DSM References Non-Volatile DIMM or NVDIMM is a type of RAM device that provides persistent storage and retains data across reboot and even power failures. This document describes the design to provide virtual NVDIMM devices or vNVDIMM in Xen. The rest of this document is organized as below. - Section 1 introduces the background knowledge of NVDIMM hardware, which is used by other parts of this document. - Section 2 briefly introduces the current/future NVDIMM/vNVDIMM support in Linux kernel/KVM/QEMU. They will affect the vNVDIMM design in Xen. - Section 3 shows the basic usage example of vNVDIMM in Xen. - Section 4 proposes design details of vNVDIMM in Xen. 1. Background 1.1 Access Mechanisms: Persistent Memory and Block Window NVDIMM provides two access mechanisms: byte-addressable persistent memory (pmem) and block window (pblk). An NVDIMM can contain multiple ranges and each range can be accessed through either pmem or pblk (but not both). Byte-addressable persistent memory mechanism (pmem) maps NVDIMM or ranges of NVDIMM into the system physical address (SPA) space, so that software can access NVDIMM via normal memory loads and stores. If the virtual address is used, then MMU will translate it to the physical address. In the virtualization circumstance, we can pass through a pmem range or partial of it to a guest by mapping it in EPT (i.e. mapping guest vNVDIMM physical address to host NVDIMM physical address), so that guest accesses are applied directly to the host NVDIMM device without hypervisor's interceptions. Block window mechanism (pblk) provides one or multiple block windows (BW). Each BW is composed of a command register, a status register and a 8 Kbytes aperture register. Software fills the direction of the transfer (read/write), the start address (LBA) and size on NVDIMM it is going to transfer. If nothing goes wrong, the transferred data can be read/write via the aperture register. The status and errors of the transfer can be got from the status register. Other vendor-specific commands and status can be implemented for BW as well. Details of the block window access mechanism can be found in [3]. In the virtualization circumstance, different pblk regions on a single NVDIMM device may be accessed by different guests, so the hypervisor needs to emulate BW, which would introduce a high overhead for I/O intensive workload. Therefore, we are going to only implement pmem for vNVDIMM. The rest of this document will mostly concentrate on pmem. 1.2 ACPI Support ACPI provides two factors of support for NVDIMM. First, NVDIMM devices are described by firmware (BIOS/EFI) to OS via ACPI-defined NVDIMM Firmware Interface Table (NFIT). Second, several functions of NVDIMM, including operations on namespace labels, S.M.A.R.T and hotplug, are provided by ACPI methods (_DSM and _FIT). 1.2.1 NFIT NFIT is a new system description table added in ACPI v6 with signature "NFIT". It contains a set of structures. - System Physical Address Range Structure (SPA Range Structure) SPA range structure describes system physical address ranges occupied by NVDIMMs and types of regions. If Address Range Type GUID field of a SPA range structure is "Byte Addressable Persistent Memory (PM) Region", then the structure describes a NVDIMM region that is accessed via pmem. The System Physical Address Range Base and Length fields describe the start system physical address and the length that is occupied by that NVDIMM region. A SPA range structure is identified by a non-zero SPA range structure index. Note: [1] reserves E820 type 7: OSPM must comprehend this memory as having non-volatile attributes and handle distinct from conventional volatile memory (in Table 15-312 of [1]). The memory region supports byte-addressable non-volatility. E820 type 12 (OEM defined) may be also used for legacy NVDIMM prior to ACPI v6. Note: Besides OS, EFI firmware may also parse NFIT for booting drives (Section 9.3.6.9 of [5]). - Memory Device to System Physical Address Range Mapping Structure (Range Mapping Structure) An NVDIMM region described by a SPA range structure can be interleaved across multiple NVDIMM devices. A range mapping structure is used to describe the single mapping on each NVDIMM device. It describes the size and the offset in a SPA range that an NVDIMM device occupies. It may refer to an Interleave Structure that contains details of the entire interleave set. Those information is used in pblk by the NVDIMM driver for address translation. The NVDIMM device described by the range mapping structure is identified by an unique NFIT Device Handle. Details of NFIT and other structures can be found in Section 5.25 in [1]. 1.2.2 _DSM and _FIT The ACPI namespace device uses _HID of ACPI0012 to identify the root NVDIMM interface device. An ACPI namespace device is also present under the root device For each NVDIMM device. Above ACPI namespace devices are defined in SSDT. _DSM methods are present under the root device and each NVDIMM device. _DSM methods are used by drivers to access the label storage area, get health information, perform vendor-specific commands, etc. Details of all _DSM methods can be found in [4]. _FIT method is under the root device and evaluated by OSPM to get NFIT of hotplugged NVDIMM. The hotplugged NVDIMM is indicated to OS using ACPI Namespace device with PNPID of PNP0C80 and the device object notification value is 0x80. Details of NVDIMM hotplug can be found in Section 9.20 of [1]. 1.3 Namespace [2] describes a mechanism to sub-divide NVDIMMs into namespaces, which are logic units of storage similar to SCSI LUNs and NVM Express namespaces. The namespace information is describes by namespace labels stored in the persistent label storage area on each NVDIMM device. The label storage area is excluded from the the range mapped by the SPA range structure and can only be accessed via _DSM methods. There are two types of namespaces defined in [2]: the persistent memory namespace and the block namespaces. Persistent memory namespaces is built for only pmem NVDIMM regions, while block namespaces only for pblk. Only one persistent memory namespace is allowed for a pmem NVDIMM region. Besides being accessed via _DSM, namespaces are managed and interpreted by software. OS vendors may decide to not follow [2] and store other types of information in the label storage area. 1.4 clwb/clflushopt Writes to NVDIMM may be cached by caches, so certain flushing operations should be performed to make them persistent on NVDIMM. clwb is used in favor of clflushopt and clflush to flush writes from caches to memory. Details of clwb/clflushopt can be found in Chapter 10 of [6]. 2. NVDIMM/vNVDIMM Support in Linux Kernel/KVM/QEMU 2.1 NVDIMM Driver in Linux Kernel Linux kernel since 4.2 has added support for ACPI-defined NVDIMM devices. NVDIMM driver in Linux probes NVDIMM devices through ACPI (i.e. NFIT and _FIT). It is also responsible to parse the namsepace labels on each NVDIMM devices, recover namespace after power failure (as described in [2]) and handle NVDIMM hotplug. There are also some vendor drivers to perform vendor-specific operations on NVDIMMs (e.g. via _DSM). Compared to the ordinary ram, NVDIMM is used more like a persistent storage drive for its persistent aspect. For each persistent memory namespace, or a label-less pmem NVDIMM range, NVDIMM driver implements a block device interface (/dev/pmemX) for it. Userspace applications can mmap(2) the whole pmem into its own virtual address space. Linux kernel maps the system physical address space range occupied by pmem into the virtual address space, so that every normal memory loads/writes with proper flushing instructions are applied to the underlying pmem NVDIMM regions. Alternatively, a DAX file system can be made on /dev/pmemX. Files on that file system can be used in the same way as above. As Linux kernel maps the system address space range occupied by those files on NVDIMM to the virtual address space, reads/writes on those files are applied to the underlying NVDIMM regions as well. 2.2 vNVDIMM Implementation in KVM/QEMU An overview of vNVDIMM implementation in KVM (Linux kernel v4.2) / QEMU (commit 70d1fb9 and patches in-review/future) is showed by the following figure. +---------------------------------+ Guest GPA | | /dev/pmem0 | +---------------------------------+ parse evaluate ^ ^ ACPI _DSM | | | | | | -------------|------------|--------------------------------|------------|---- V V | | +-------+ +-------+ | | QEMU | vACPI | | v_DSM | | | +-------+ +-------+ | | ^ | | | Read/Write | | V | | +...+--------------------+...+-----------+ | | VA | | Label Storage Area | | buf | KVM_SET_USER_MEMORY_REGION(buf) +...+--------------------+...+-----------+ | | ^ mmap(2) ^ | | --------------------------------------|-----------|--------|------------|---- | +--------~------------+ | | | Linux/KVM +--------------------+ | | | +....+------------+ SPA | | /dev/pmem0 | +....+------------+ ^ | Host NVDIMM Driver -------------------------------------------------------------------|--------- | HW +------------+ | NVDIMM | +------------+ A part not put in above figure is enabling guest clwb/clflushopt which exposes those instructions to guest via guest cpuid. Besides instruction enabling, there are two primary parts of vNVDIMM implementation in KVM/QEMU. (1) Address Mapping As described before, the host Linux NVDIMM driver provides a block device interface (/dev/pmem0 at the bottom) for a pmem NVDIMM region. QEMU can than mmap(2) that device into its virtual address space (buf). QEMU is responsible to find a proper guest physical address space range that is large enough to hold /dev/pmem0. Then QEMU passes the virtual address of mmapped buf to a KVM API KVM_SET_USER_MEMORY_REGION that maps in EPT the host physical address range of buf to the guest physical address space range where the virtual pmem device will be. In this way, all guest writes/reads on the virtual pmem device is applied directly to the host one. Besides, above implementation also allows to back a virtual pmem device by a mmapped regular file or a piece of ordinary ram. (2) Guest ACPI Emulation As guest system physical address and the size of the virtual pmem device are determined by QEMU, QEMU is responsible to emulate the guest NFIT and SSDT. Basically, it builds the guest NFIT and its sub-structures that describes the virtual NVDIMM topology, and a guest SSDT that defines ACPI namespace devices of virtual NVDIMM in guest SSDT. As a portion of host pmem device or a regular file/ordinary file can be used to back the guest pmem device, the label storage area on host pmem cannot always be passed through to guest. Therefore, the guest reads/writes on the label storage area is emulated by QEMU. As described before, _DSM method is utilized by OSPM to access the label storage area, and therefore it is emulated by QEMU. The _DSM buffer is registered as MMIO, and its guest physical address and size are described in the guest ACPI. Every command/status read/write from guest is trapped and emulated by QEMU. Guest _FIT method will be implemented similarly in the future. 3. Usage Example of vNVDIMM in Xen Our design is to provide virtual pmem devices to HVM domains. The virtual pmem devices are backed by host pmem devices. Dom0 Linux kernel can detect the host pmem devices and create /dev/pmemXX for each detected devices. Users in Dom0 can then create DAX file system on /dev/pmemXX and create several pre-allocate files in the DAX file system. After setup the file system on the host pmem, users can add the following lines in the xl configuration files to assign the host pmem regions to domains: vnvdimm = [ 'file=/dev/pmem0' ] or vnvdimm = [ 'file=/mnt/dax/pre_allocated_file' ] The first type of configuration assigns the entire pmem device (/dev/pmem0) to the domain, while the second assigns the space allocated to /mnt/dax/pre_allocated_file on the host pmem device to the domain. When the domain starts, guest can detect the (virtual) pmem devices via ACPI and guest read/write on the virtual pmem devices are directly applied on their host backends. 4. Design of vNVDIMM in Xen As KVM/QEMU, our design currently only provides pmem vNVDIMM. Similarly to that in KVM/QEMU, enabling vNVDIMM in Xen is composed of three parts: (1) Guest clwb/clflushopt enabling, (2) pmem address management, and (3) Guest ACPI emulation. The rest of this section present the design of each part respectively. The basic design principle to reuse existing code in Linux NVDIMM driver, QEMU and Xen as much as possible. 4.1 Guest clwb/clflushopt Enabling The instruction enabling is simple and we do the same work as in KVM/QEMU: - clwb/clflushopt are exposed to guest via guest cpuid. 4.2 pmem Address Management pmem address management is primarily composed of three parts: (1) detection of pmem devices and their address ranges, which is accomplished by Dom0 Linux pmem driver and Xen hypervisor; (2) get SPA ranges of an pmem area that will be mapped to domain, which is accomplished by xl; (3) map the pmem area to a domain, which is accomplished by qemu and Xen hypervisor. Our design intends to reuse the current memory management for normal RAM in Xen to manage the mapping of pmem. Then we will come across a problem: where we store the memory management data structs for pmem. The rest of this section addresses above aspects respectively. 4.2.1 Reserve Storage for Management Structures A core data struct in Xen memory management is 'struct page_info'. For normal ram, Xen creates a page_info struct for each page. For pmem, we are going to do the same. However, for large capacity pmem devices (e.g. several terabytes or even larger), a large amount of page_info structs will occupy too much storage space that cannot fit in the normal ram. Our solution, as used by Linux kernel, is to reserve an area on pmem and place pmem's page_info structs in that reserved area. Therefore, we can always ensure there is enough space for pmem page_info structs, though the access to them is slower than directly from the normal ram. Such a pmem namespace can be created via a userspace tool ndctl and then recognized by Linux NVDIMM driver. However, they currently only reserve space for Linux kernel's page structs. Therefore, our design need to extend both Linux NVDIMM driver and ndctl to reserve arbitrary size. 4.2.2 Detection of Host pmem Devices The detection and initialize host pmem devices require a non-trivial driver to interact with the corresponding ACPI namespace devices, parse namespace labels and make necessary recovery actions. Instead of duplicating the comprehensive Linux pmem driver in Xen hypervisor, our designs leaves it to Dom0 Linux and let Dom0 Linux report detected host pmem devices to Xen hypervisor. Our design takes following steps to detect host pmem devices when Xen boots. (1) As booting on bare metal, host pmem devices are detected by Dom0 Linux NVDIMM driver. (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes of the pmem devices and reserved areas to Xen hypervisor via a new hypercall. (3) Xen hypervisor then checks - whether SPA and size of the newly reported pmem device is overlap with any previously reported pmem devices; - whether the reserved area can fit in the pmem device and is large enough to hold page_info structs for itself. If any checks fail, the reported pmem device will be ignored by Xen hypervisor and hence will not be used by any guests. Otherwise, Xen hypervisor will recorded the reported parameters and create page_info structs in the reserved area. (4) Because the reserved area is now used by Xen hypervisor, it should not be accessible by Dom0 any more. Therefore, if a host pmem device is recorded by Xen hypervisor, Xen will unmap its reserved area from Dom0. Our design also needs to extend Linux NVDIMM driver to "balloon out" the reserved area after it successfully reports a pmem device to Xen hypervisor. 4.2.3 Get Host Machine Address (SPA) of Host pmem Files Before a pmem file is assigned to a domain, we need to know the host SPA ranges that are allocated to this file. We do this work in xl. If a pmem device /dev/pmem0 is given, xl will read /sys/block/pmem0/device/{resource,size} respectively for the start SPA and size of the pmem device. If a pre-allocated file /mnt/dax/file is given, (1) xl first finds the host pmem device where /mnt/dax/file is. Then it uses the method above to get the start SPA of the host pmem device. (2) xl then uses fiemap ioctl to get the extend mappings of /mnt/dax/file, and adds the corresponding physical offsets and lengths in each mapping entries to above start SPA to get the SPA ranges pre-allocated for this file. The resulting host SPA ranges will be passed to QEMU which allocates guest address space for vNVDIMM devices and calls Xen hypervisor to map the guest address to the host SPA ranges. 4.2.4 Map Host pmem to Guests Our design reuses the existing address mapping in Xen for the normal ram to map pmem. We will still initiate the mapping for pmem from QEMU, and there is one difference from the mapping of normal ram: - For the normal ram, QEMU only needs to provide gpfn, and the actual host memory where gpfn is mapped is allocated by Xen hypervisor. - For pmem, QEMU provides both gpfn and mfn where gpfn is expected to be mapped to. mfn is provided by xl as described in Section 4.2.3. Our design introduce a new XENMEM op for the pmem mapping, which finally calls guest_physmap_add_page() to add the host pmem page to a domain's address space. 4.2.5 Misc 1: RAS Machine check can occur from NVDIMM as normal ram, so that we follow the current machine check handling in Xen for MC# from NVDIMM. 4.2.6 Misc 2: hotplug The hotplugged host NVDIMM devices is detected via _FIT method under the root ACPI namespace device for NVDIMM. We rely on Dom0 Linux kernel to discover the hotplugged NVDIMM devices and follow steps in Section 4.2.2 to report the hotplugged devices to Xen hypervisor. 4.3 Guest ACPI Emulation Guest ACPI emulation is composed of two parts: building guest NFIT and SSDT that defines ACPI namespace devices for NVDIMM, and emulating guest _DSM. As QEMU has already implemented ACPI support for vNVDIMM on KVM, our design intends to reuse its implementation. 4.3.1 Building Guest ACPI Tables Two tables for vNVDIMM need to be built: - NFIT, which defines the basic parameters of vNVDIMM devices and does not contain any AML code. - SSDT, which defines ACPI namespace devices for vNVDIMM in AML code. The contents of both tables are affected by some parameters (e.g. address and size of vNVDIMM devices) that cannot be determined until a guest configuration is given. However, all AML code in guest ACPI are currently generated at compile time fro pre-crafted .asl files, which is not feasible for ACPI namespace devices for vNVDIMM. We could either introduce an AML builder to generate AML code at runtime like what QEMU is currently doing, or pass vNVDIMM ACPI tables from QEMU to Xen. In order to reduce the duplicated code (to AML builder in QEMU), our design takes the latter approach. Basically, our design takes the following steps: 1) The current QEMU does not build any ACPI stuffs when it runs as the Xen device model, so we need to patch it to generate NFIT and AML code of ACPI namespace devices for vNVDIMM. 2) QEMU then copies above NFIT and ACPI namespace devices to an area at the end of guest memory below 4G. The guest physical address and size of this area are written to xenstore keys (/local/domain/domid/hvmloader/dm-acpi/{address,length}) The detailed format of data in this area is explained later. 3) hvmloader reads above xenstore keys to probe the passed-in ACPI tables and ACPI namespace devices, and detects the potential collisions as explained later. 4) If no collisions are found, hvmloader will (1) append the passed-in ACPI tables to the end of existing guest ACPI tables, like what current construct_passthrough_tables() does. (2) construct a SSDT for each passed-in ACPI namespace devices and append to the end of existing guest ACPI tables. Passing arbitrary ACPI tables and AML code from QEMU could introduce at least two types of collisions: 1) a passed-in table and a Xen-built table have the same signature 2) a passed-in ACPI namespace device and a Xen-built ACPI namespace device have the same device name. Our design takes the following method to avoid and detect collisions. 1) The data layout of area where QEMU copies its NFIT and ACPI namespace devices is organized as below: 1 byte 4 bytes length bytes +------+--------+-----------+------+--------+-----------+----- | type | length | data blob | type | length | data blob | ... +------+--------+-----------+------+--------+-----------+----- type: 0 - data blob contains a complete ACPI table 1 - data blob contains AML code for an ACPI namespace device length: the number of bytes of data blob data blob: type 0 - a complete ACPI table type 1 - composed as below: 4 bytes (length - 4) bytes +---------+------------------+ | name[4] | AML code snippet | +---------+------------------+ name[4] : name of ACPI namespace device AML code snippet: AML code inside "Device(name[4])" e.g. for an ACPI namespace device defined by Device(NVDR) { Name (_HID, "ACPI0012") ... } QEMU builds a data blob like +--------------------+-----------------------------+ | 'N', 'V', 'D', 'R' | Name (_HID, "ACPI0012") ... | +--------------------+-----------------------------+ 2) hvmloader stores signatures of its own guest ACPI tables in an array builtin_table_sigs[], and names of its own guest ACPI namespace devices in an array builtin_nd_names[]. Because there are only a few guest ACPI tables and namespace devices built by Xen, we can hardcode their signatures or names in hvmloader. 3) When hvmloader loads a type 0 entry, it extracts the signature from the data blob and search for it in builtin_table_sigs[]. If found anyone, hvmloader will report an error and stop. Otherwise, it will append it to the end of loaded guest ACPI. 4) When hvmloader loads a type 1 entry, it extracts the device name from the data blob and search for it in builtin_nd_names[]. If found anyone, hvmloader will report and error and stop. Otherwise, it will wrap the AML code snippet by "Device (name[4]) {...}" and include it in a new SSDT which is then appended to the end of loaded guest ACPI. 4.3.2 Emulating Guest _DSM Our design leaves the emulation of guest _DSM to QEMU. Just as what it does with KVM, QEMU registers the _DSM buffer as MMIO region with Xen and then all guest evaluations of _DSM are trapped and emulated by QEMU. References: [1] ACPI Specification v6, http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf [2] NVDIMM Namespace Specification, http://pmem.io/documents/NVDIMM_Namespace_Spec.pdf [3] NVDIMM Block Window Driver Writer's Guide, http://pmem.io/documents/NVDIMM_Driver_Writers_Guide.pdf [4] NVDIMM DSM Interface Example, http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf [5] UEFI Specification v2.6, http://www.uefi.org/sites/default/files/resources/UEFI%20Spec%202_6.pdf [6] Intel Architecture Instruction Set Extensions Programming Reference, https://software.intel.com/sites/default/files/managed/07/b7/319433-023.pdf [7] https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html [8] https://lists.xen.org/archives/html/xen-devel/2016-06/msg00606.html _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 0:29 [RFC Design Doc v2] Add vNVDIMM support for Xen Haozhong Zhang @ 2016-07-18 8:36 ` Tian, Kevin 2016-07-18 9:01 ` Zhang, Haozhong 2016-07-19 1:57 ` Bob Liu ` (2 subsequent siblings) 3 siblings, 1 reply; 24+ messages in thread From: Tian, Kevin @ 2016-07-18 8:36 UTC (permalink / raw) To: Zhang, Haozhong, xen-devel Cc: Juergen Gross, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, Jan Beulich, Xiao Guangrong > From: Zhang, Haozhong > Sent: Monday, July 18, 2016 8:29 AM > > Hi, > > Following is version 2 of the design doc for supporting vNVDIMM in > Xen. It's basically the summary of discussion on previous v1 design > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > Any comments are welcome. The corresponding patches are WIP. > > Thanks, > Haozhong It's a very clear doc. Thanks a lot! > > 4.2.2 Detection of Host pmem Devices > > The detection and initialize host pmem devices require a non-trivial > driver to interact with the corresponding ACPI namespace devices, > parse namespace labels and make necessary recovery actions. Instead > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > our designs leaves it to Dom0 Linux and let Dom0 Linux report > detected host pmem devices to Xen hypervisor. > > Our design takes following steps to detect host pmem devices when Xen > boots. > (1) As booting on bare metal, host pmem devices are detected by Dom0 > Linux NVDIMM driver. > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > of the pmem devices and reserved areas to Xen hypervisor via a > new hypercall. Does Linux need to provide reserved area to Xen? Why not leaving Xen to decide reserved area within reported pmem regions and then return reserved info to Dom0 NVDIMM driver to balloon out? > > (3) Xen hypervisor then checks > - whether SPA and size of the newly reported pmem device is overlap > with any previously reported pmem devices; > - whether the reserved area can fit in the pmem device and is > large enough to hold page_info structs for itself. > > If any checks fail, the reported pmem device will be ignored by > Xen hypervisor and hence will not be used by any > guests. Otherwise, Xen hypervisor will recorded the reported > parameters and create page_info structs in the reserved area. > > (4) Because the reserved area is now used by Xen hypervisor, it > should not be accessible by Dom0 any more. Therefore, if a host > pmem device is recorded by Xen hypervisor, Xen will unmap its > reserved area from Dom0. Our design also needs to extend Linux > NVDIMM driver to "balloon out" the reserved area after it > successfully reports a pmem device to Xen hypervisor. Then both ndctl and Xen become source of requesting reserved area to Linux NVDIMM driver. You don't need change ndctl as described in 4.2.1. User can still use ndctl to reserve for Dom0's own purpose. Thanks Kevin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 8:36 ` Tian, Kevin @ 2016-07-18 9:01 ` Zhang, Haozhong 2016-07-19 0:58 ` Tian, Kevin 0 siblings, 1 reply; 24+ messages in thread From: Zhang, Haozhong @ 2016-07-18 9:01 UTC (permalink / raw) To: Tian, Kevin Cc: Juergen Gross, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong On 07/18/16 16:36, Tian, Kevin wrote: > > From: Zhang, Haozhong > > Sent: Monday, July 18, 2016 8:29 AM > > > > Hi, > > > > Following is version 2 of the design doc for supporting vNVDIMM in > > Xen. It's basically the summary of discussion on previous v1 design > > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > > Any comments are welcome. The corresponding patches are WIP. > > > > Thanks, > > Haozhong > > It's a very clear doc. Thanks a lot! > > > > > 4.2.2 Detection of Host pmem Devices > > > > The detection and initialize host pmem devices require a non-trivial > > driver to interact with the corresponding ACPI namespace devices, > > parse namespace labels and make necessary recovery actions. Instead > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > detected host pmem devices to Xen hypervisor. > > > > Our design takes following steps to detect host pmem devices when Xen > > boots. > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > Linux NVDIMM driver. > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > of the pmem devices and reserved areas to Xen hypervisor via a > > new hypercall. > > Does Linux need to provide reserved area to Xen? Why not leaving Xen > to decide reserved area within reported pmem regions and then return > reserved info to Dom0 NVDIMM driver to balloon out? > NVDIMM can be used as a persistent storage like a disk drive, so the reservation should be done out of Xen and Dom0, for example, by an administrator who is expected to make necessary data backup in advance. Therefore, dom0 linux actually reports (instead of providing) the reserved area to Xen, and the latter checks if the reserved area is large enough and (if yes) asks dom0 to balloon out the reserved area. > > > > (3) Xen hypervisor then checks > > - whether SPA and size of the newly reported pmem device is overlap > > with any previously reported pmem devices; > > - whether the reserved area can fit in the pmem device and is > > large enough to hold page_info structs for itself. > > > > If any checks fail, the reported pmem device will be ignored by > > Xen hypervisor and hence will not be used by any > > guests. Otherwise, Xen hypervisor will recorded the reported > > parameters and create page_info structs in the reserved area. > > > > (4) Because the reserved area is now used by Xen hypervisor, it > > should not be accessible by Dom0 any more. Therefore, if a host > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > reserved area from Dom0. Our design also needs to extend Linux > > NVDIMM driver to "balloon out" the reserved area after it > > successfully reports a pmem device to Xen hypervisor. > > Then both ndctl and Xen become source of requesting reserved area > to Linux NVDIMM driver. You don't need change ndctl as described in > 4.2.1. User can still use ndctl to reserve for Dom0's own purpose. > I missed something here: Dom0 pmem driver should also prevent further operations on host namespace after it successfully reports to Xen. In this way, we can prevent uerspace tools like ndctl to break the host pmem device. Thanks. Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 9:01 ` Zhang, Haozhong @ 2016-07-19 0:58 ` Tian, Kevin 2016-07-19 2:10 ` Zhang, Haozhong 0 siblings, 1 reply; 24+ messages in thread From: Tian, Kevin @ 2016-07-19 0:58 UTC (permalink / raw) To: Zhang, Haozhong Cc: Juergen Gross, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong > From: Zhang, Haozhong > Sent: Monday, July 18, 2016 5:02 PM > > On 07/18/16 16:36, Tian, Kevin wrote: > > > From: Zhang, Haozhong > > > Sent: Monday, July 18, 2016 8:29 AM > > > > > > Hi, > > > > > > Following is version 2 of the design doc for supporting vNVDIMM in > > > Xen. It's basically the summary of discussion on previous v1 design > > > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > > > Any comments are welcome. The corresponding patches are WIP. > > > > > > Thanks, > > > Haozhong > > > > It's a very clear doc. Thanks a lot! > > > > > > > > 4.2.2 Detection of Host pmem Devices > > > > > > The detection and initialize host pmem devices require a non-trivial > > > driver to interact with the corresponding ACPI namespace devices, > > > parse namespace labels and make necessary recovery actions. Instead > > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > > detected host pmem devices to Xen hypervisor. > > > > > > Our design takes following steps to detect host pmem devices when Xen > > > boots. > > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > > Linux NVDIMM driver. > > > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > > of the pmem devices and reserved areas to Xen hypervisor via a > > > new hypercall. > > > > Does Linux need to provide reserved area to Xen? Why not leaving Xen > > to decide reserved area within reported pmem regions and then return > > reserved info to Dom0 NVDIMM driver to balloon out? > > > > NVDIMM can be used as a persistent storage like a disk drive, so the > reservation should be done out of Xen and Dom0, for example, by an > administrator who is expected to make necessary data backup in > advance. What prevents NVDIMM driver from reserving some region itself before reporting to user space? > > Therefore, dom0 linux actually reports (instead of providing) the > reserved area to Xen, and the latter checks if the reserved area is > large enough and (if yes) asks dom0 to balloon out the reserved area. It looks non-intuitive since administrator doesn't know the actual requirement of Xen. Then administrator has to guess and try. Even it finally works, the reserved size may not be optimal. If Dom0 NVDIMM driver does reservation itself and notify Xen, at least there is a way for Xen to return a failure with required size and then at the 2nd time the NVDIMM driver can adjust the reservation as desired. Did I misunderstand the flow here? > > > > > > > (3) Xen hypervisor then checks > > > - whether SPA and size of the newly reported pmem device is overlap > > > with any previously reported pmem devices; > > > - whether the reserved area can fit in the pmem device and is > > > large enough to hold page_info structs for itself. > > > > > > If any checks fail, the reported pmem device will be ignored by > > > Xen hypervisor and hence will not be used by any > > > guests. Otherwise, Xen hypervisor will recorded the reported > > > parameters and create page_info structs in the reserved area. > > > > > > (4) Because the reserved area is now used by Xen hypervisor, it > > > should not be accessible by Dom0 any more. Therefore, if a host > > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > > reserved area from Dom0. Our design also needs to extend Linux > > > NVDIMM driver to "balloon out" the reserved area after it > > > successfully reports a pmem device to Xen hypervisor. > > > > Then both ndctl and Xen become source of requesting reserved area > > to Linux NVDIMM driver. You don't need change ndctl as described in > > 4.2.1. User can still use ndctl to reserve for Dom0's own purpose. > > > > I missed something here: Dom0 pmem driver should also prevent > further operations on host namespace after it successfully reports to > Xen. In this way, we can prevent uerspace tools like ndctl to break > the host pmem device. > yes, Dom0 driver is expected to reserve the region allocated for Xen. Thanks Kevin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-19 0:58 ` Tian, Kevin @ 2016-07-19 2:10 ` Zhang, Haozhong 0 siblings, 0 replies; 24+ messages in thread From: Zhang, Haozhong @ 2016-07-19 2:10 UTC (permalink / raw) To: Tian, Kevin Cc: Juergen Gross, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong On 07/19/16 08:58, Tian, Kevin wrote: > > From: Zhang, Haozhong > > Sent: Monday, July 18, 2016 5:02 PM > > > > On 07/18/16 16:36, Tian, Kevin wrote: > > > > From: Zhang, Haozhong > > > > Sent: Monday, July 18, 2016 8:29 AM > > > > > > > > Hi, > > > > > > > > Following is version 2 of the design doc for supporting vNVDIMM in > > > > Xen. It's basically the summary of discussion on previous v1 design > > > > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > > > > Any comments are welcome. The corresponding patches are WIP. > > > > > > > > Thanks, > > > > Haozhong > > > > > > It's a very clear doc. Thanks a lot! > > > > > > > > > > > 4.2.2 Detection of Host pmem Devices > > > > > > > > The detection and initialize host pmem devices require a non-trivial > > > > driver to interact with the corresponding ACPI namespace devices, > > > > parse namespace labels and make necessary recovery actions. Instead > > > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > > > detected host pmem devices to Xen hypervisor. > > > > > > > > Our design takes following steps to detect host pmem devices when Xen > > > > boots. > > > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > > > Linux NVDIMM driver. > > > > > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > > > of the pmem devices and reserved areas to Xen hypervisor via a > > > > new hypercall. > > > > > > Does Linux need to provide reserved area to Xen? Why not leaving Xen > > > to decide reserved area within reported pmem regions and then return > > > reserved info to Dom0 NVDIMM driver to balloon out? > > > > > > > NVDIMM can be used as a persistent storage like a disk drive, so the > > reservation should be done out of Xen and Dom0, for example, by an > > administrator who is expected to make necessary data backup in > > advance. > > What prevents NVDIMM driver from reserving some region itself before > reporting to user space? > Nothing in theory prevents the driver doing reservations. I just mean the reservation should be initiated by someone which can ensure, for example, the current data on pmem is either useless or properly backup. The reservation is of course finally done by the driver. > > > > Therefore, dom0 linux actually reports (instead of providing) the > > reserved area to Xen, and the latter checks if the reserved area is > > large enough and (if yes) asks dom0 to balloon out the reserved area. > > It looks non-intuitive since administrator doesn't know the actual requirement > of Xen. Then administrator has to guess and try. Even it finally works, the > reserved size may not be optimal. > > If Dom0 NVDIMM driver does reservation itself and notify Xen, at least there > is a way for Xen to return a failure with required size and then at the 2nd time > the NVDIMM driver can adjust the reservation as desired. > > Did I misunderstand the flow here? > I designed to let the administrator calculate the reserved size and pass to the driver. Now, you are right, I think it's better to let Xen advise the reserved size to NVDIMM driver in dom0 and therefore no need for manually calculated size. Thanks, Haozhong > > > > > > > > > > (3) Xen hypervisor then checks > > > > - whether SPA and size of the newly reported pmem device is overlap > > > > with any previously reported pmem devices; > > > > - whether the reserved area can fit in the pmem device and is > > > > large enough to hold page_info structs for itself. > > > > > > > > If any checks fail, the reported pmem device will be ignored by > > > > Xen hypervisor and hence will not be used by any > > > > guests. Otherwise, Xen hypervisor will recorded the reported > > > > parameters and create page_info structs in the reserved area. > > > > > > > > (4) Because the reserved area is now used by Xen hypervisor, it > > > > should not be accessible by Dom0 any more. Therefore, if a host > > > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > > > reserved area from Dom0. Our design also needs to extend Linux > > > > NVDIMM driver to "balloon out" the reserved area after it > > > > successfully reports a pmem device to Xen hypervisor. > > > > > > Then both ndctl and Xen become source of requesting reserved area > > > to Linux NVDIMM driver. You don't need change ndctl as described in > > > 4.2.1. User can still use ndctl to reserve for Dom0's own purpose. > > > > > > > I missed something here: Dom0 pmem driver should also prevent > > further operations on host namespace after it successfully reports to > > Xen. In this way, we can prevent uerspace tools like ndctl to break > > the host pmem device. > > > > yes, Dom0 driver is expected to reserve the region allocated for Xen. > > Thanks > Kevin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 0:29 [RFC Design Doc v2] Add vNVDIMM support for Xen Haozhong Zhang 2016-07-18 8:36 ` Tian, Kevin @ 2016-07-19 1:57 ` Bob Liu 2016-07-19 2:40 ` Haozhong Zhang 2016-08-02 14:46 ` Jan Beulich 2016-08-03 21:25 ` Konrad Rzeszutek Wilk 3 siblings, 1 reply; 24+ messages in thread From: Bob Liu @ 2016-07-19 1:57 UTC (permalink / raw) To: xen-devel, Jan Beulich, Konrad Rzeszutek Wilk, George Dunlap, Andrew Cooper, Ian Jackson, Stefano Stabellini, Juergen Gross, Wei Liu, Tian, Kevin, Xiao Guangrong, Nakajima, Jun Hey Haozhong, On 07/18/2016 08:29 AM, Haozhong Zhang wrote: > Hi, > > Following is version 2 of the design doc for supporting vNVDIMM in This version is really good, very clear and included almost everything I'd like to know. > Xen. It's basically the summary of discussion on previous v1 design > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > Any comments are welcome. The corresponding patches are WIP. > So are you(or Intel) going to write all the patches? Is there any task the community to take part in? [..snip..] > 3. Usage Example of vNVDIMM in Xen > > Our design is to provide virtual pmem devices to HVM domains. The > virtual pmem devices are backed by host pmem devices. > > Dom0 Linux kernel can detect the host pmem devices and create > /dev/pmemXX for each detected devices. Users in Dom0 can then create > DAX file system on /dev/pmemXX and create several pre-allocate files > in the DAX file system. > > After setup the file system on the host pmem, users can add the > following lines in the xl configuration files to assign the host pmem > regions to domains: > vnvdimm = [ 'file=/dev/pmem0' ] > or > vnvdimm = [ 'file=/mnt/dax/pre_allocated_file' ] > Could you please also consider the case when driver domain gets involved? E.g vnvdimm = [ 'file=/dev/pmem0', backend='xxx' ]? > The first type of configuration assigns the entire pmem device > (/dev/pmem0) to the domain, while the second assigns the space > allocated to /mnt/dax/pre_allocated_file on the host pmem device to > the domain. > ..[snip..] > > 4.2.2 Detection of Host pmem Devices > > The detection and initialize host pmem devices require a non-trivial > driver to interact with the corresponding ACPI namespace devices, > parse namespace labels and make necessary recovery actions. Instead > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > our designs leaves it to Dom0 Linux and let Dom0 Linux report > detected host pmem devices to Xen hypervisor. > > Our design takes following steps to detect host pmem devices when Xen > boots. > (1) As booting on bare metal, host pmem devices are detected by Dom0 > Linux NVDIMM driver. > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > of the pmem devices and reserved areas to Xen hypervisor via a > new hypercall. > > (3) Xen hypervisor then checks > - whether SPA and size of the newly reported pmem device is overlap > with any previously reported pmem devices; > - whether the reserved area can fit in the pmem device and is > large enough to hold page_info structs for itself. > > If any checks fail, the reported pmem device will be ignored by > Xen hypervisor and hence will not be used by any > guests. Otherwise, Xen hypervisor will recorded the reported > parameters and create page_info structs in the reserved area. > > (4) Because the reserved area is now used by Xen hypervisor, it > should not be accessible by Dom0 any more. Therefore, if a host > pmem device is recorded by Xen hypervisor, Xen will unmap its > reserved area from Dom0. Our design also needs to extend Linux > NVDIMM driver to "balloon out" the reserved area after it > successfully reports a pmem device to Xen hypervisor. > > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > Before a pmem file is assigned to a domain, we need to know the host > SPA ranges that are allocated to this file. We do this work in xl. > > If a pmem device /dev/pmem0 is given, xl will read > /sys/block/pmem0/device/{resource,size} respectively for the start > SPA and size of the pmem device. > > If a pre-allocated file /mnt/dax/file is given, > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > it uses the method above to get the start SPA of the host pmem > device. > (2) xl then uses fiemap ioctl to get the extend mappings of > /mnt/dax/file, and adds the corresponding physical offsets and > lengths in each mapping entries to above start SPA to get the SPA > ranges pre-allocated for this file. > Looks like PMEM can't be passed through to driver domain directly like e.g PCI devices. So if created a driver domain by: vnvdimm = [ 'file=/dev/pmem0' ], and make a DAX file system on the driver domain. Then creating new guests with vnvdimm = [ 'file=dax file in driver domain', backend = 'driver domain' ]. Is this going to work? In my understanding, fiemap can only get the GPFN instead of the really SPA of PMEM in this case. > The resulting host SPA ranges will be passed to QEMU which allocates > guest address space for vNVDIMM devices and calls Xen hypervisor to > map the guest address to the host SPA ranges. > Can Dom0 still access the same SPA range when Xen decides to assign it to new domU? I assume the range will be unmapped automatically from dom0 in the hypercall? Thanks, -Bob _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-19 1:57 ` Bob Liu @ 2016-07-19 2:40 ` Haozhong Zhang 0 siblings, 0 replies; 24+ messages in thread From: Haozhong Zhang @ 2016-07-19 2:40 UTC (permalink / raw) To: Bob Liu Cc: Juergen Gross, Tian, Kevin, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong On 07/19/16 09:57, Bob Liu wrote: > Hey Haozhong, > > On 07/18/2016 08:29 AM, Haozhong Zhang wrote: > > Hi, > > > > Following is version 2 of the design doc for supporting vNVDIMM in > > This version is really good, very clear and included almost everything I'd like to know. > > > Xen. It's basically the summary of discussion on previous v1 design > > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > > Any comments are welcome. The corresponding patches are WIP. > > > > So are you(or Intel) going to write all the patches? Is there any task the community to take part in? > For the first version I think so. Currently there are some dependencies among multiple parts in my patches (Xen/Linux/Qemu), and I have to adjust them from time to time in the development. Once after I can provide a working first version, I'm very glad to work with the community for the further development. > [..snip..] > > 3. Usage Example of vNVDIMM in Xen > > > > Our design is to provide virtual pmem devices to HVM domains. The > > virtual pmem devices are backed by host pmem devices. > > > > Dom0 Linux kernel can detect the host pmem devices and create > > /dev/pmemXX for each detected devices. Users in Dom0 can then create > > DAX file system on /dev/pmemXX and create several pre-allocate files > > in the DAX file system. > > > > After setup the file system on the host pmem, users can add the > > following lines in the xl configuration files to assign the host pmem > > regions to domains: > > vnvdimm = [ 'file=/dev/pmem0' ] > > or > > vnvdimm = [ 'file=/mnt/dax/pre_allocated_file' ] > > > > Could you please also consider the case when driver domain gets involved? > E.g vnvdimm = [ 'file=/dev/pmem0', backend='xxx' ]? > Will consider the design, but for the first version patches I would like to make things simple. > > The first type of configuration assigns the entire pmem device > > (/dev/pmem0) to the domain, while the second assigns the space > > allocated to /mnt/dax/pre_allocated_file on the host pmem device to > > the domain. > > > ..[snip..] > > > > 4.2.2 Detection of Host pmem Devices > > > > The detection and initialize host pmem devices require a non-trivial > > driver to interact with the corresponding ACPI namespace devices, > > parse namespace labels and make necessary recovery actions. Instead > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > detected host pmem devices to Xen hypervisor. > > > > Our design takes following steps to detect host pmem devices when Xen > > boots. > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > Linux NVDIMM driver. > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > of the pmem devices and reserved areas to Xen hypervisor via a > > new hypercall. > > > > (3) Xen hypervisor then checks > > - whether SPA and size of the newly reported pmem device is overlap > > with any previously reported pmem devices; > > - whether the reserved area can fit in the pmem device and is > > large enough to hold page_info structs for itself. > > > > If any checks fail, the reported pmem device will be ignored by > > Xen hypervisor and hence will not be used by any > > guests. Otherwise, Xen hypervisor will recorded the reported > > parameters and create page_info structs in the reserved area. > > > > (4) Because the reserved area is now used by Xen hypervisor, it > > should not be accessible by Dom0 any more. Therefore, if a host > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > reserved area from Dom0. Our design also needs to extend Linux > > NVDIMM driver to "balloon out" the reserved area after it > > successfully reports a pmem device to Xen hypervisor. > > > > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > > > Before a pmem file is assigned to a domain, we need to know the host > > SPA ranges that are allocated to this file. We do this work in xl. > > > > If a pmem device /dev/pmem0 is given, xl will read > > /sys/block/pmem0/device/{resource,size} respectively for the start > > SPA and size of the pmem device. > > > > If a pre-allocated file /mnt/dax/file is given, > > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > > it uses the method above to get the start SPA of the host pmem > > device. > > (2) xl then uses fiemap ioctl to get the extend mappings of > > /mnt/dax/file, and adds the corresponding physical offsets and > > lengths in each mapping entries to above start SPA to get the SPA > > ranges pre-allocated for this file. > > > > Looks like PMEM can't be passed through to driver domain directly like e.g PCI devices. > pmem is not a PCI device. I'm not familiar with the driver domain. If only PCI devices can be passed through to driver domain, it may not be able to passthrough a pmem device to driver domain. > So if created a driver domain by: vnvdimm = [ 'file=/dev/pmem0' ], and make a DAX file system on the driver domain. > > Then creating new guests with vnvdimm = [ 'file=dax file in driver domain', backend = 'driver domain' ]. > Is this going to work? In my understanding, fiemap can only get the GPFN instead of the really SPA of PMEM in this case. > fiemap returns the offsets of extents. They will be added to the start SPA of the corresponding /dev/pmem0 (got via /sys/block/pmem0/device/resource). For Dom0, we can get the host physical address in this way. I'm not sure whether a pmem device can be passed to a driver domain, and (if it can) whether the host SPA would be seen by the driver domain. If answer to either one is no, pmem would not work with driver domain in above way. > > > The resulting host SPA ranges will be passed to QEMU which allocates > > guest address space for vNVDIMM devices and calls Xen hypervisor to > > map the guest address to the host SPA ranges. > > > > Can Dom0 still access the same SPA range when Xen decides to assign it to new domU? > I assume the range will be unmapped automatically from dom0 in the hypercall? > Yes, they will be unmaaped from dom0. Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 0:29 [RFC Design Doc v2] Add vNVDIMM support for Xen Haozhong Zhang 2016-07-18 8:36 ` Tian, Kevin 2016-07-19 1:57 ` Bob Liu @ 2016-08-02 14:46 ` Jan Beulich 2016-08-03 6:54 ` Haozhong Zhang 2016-08-03 21:25 ` Konrad Rzeszutek Wilk 3 siblings, 1 reply; 24+ messages in thread From: Jan Beulich @ 2016-08-02 14:46 UTC (permalink / raw) To: Haozhong Zhang Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: > 4.2.2 Detection of Host pmem Devices > > The detection and initialize host pmem devices require a non-trivial > driver to interact with the corresponding ACPI namespace devices, > parse namespace labels and make necessary recovery actions. Instead > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > our designs leaves it to Dom0 Linux and let Dom0 Linux report > detected host pmem devices to Xen hypervisor. > > Our design takes following steps to detect host pmem devices when Xen > boots. > (1) As booting on bare metal, host pmem devices are detected by Dom0 > Linux NVDIMM driver. > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > of the pmem devices and reserved areas to Xen hypervisor via a > new hypercall. > > (3) Xen hypervisor then checks > - whether SPA and size of the newly reported pmem device is overlap > with any previously reported pmem devices; ... or with system RAM. > - whether the reserved area can fit in the pmem device and is > large enough to hold page_info structs for itself. So "reserved" here means available for Xen's use, but not for more general purposes? How would the area Linux uses for its own purposes get represented? > (4) Because the reserved area is now used by Xen hypervisor, it > should not be accessible by Dom0 any more. Therefore, if a host > pmem device is recorded by Xen hypervisor, Xen will unmap its > reserved area from Dom0. Our design also needs to extend Linux > NVDIMM driver to "balloon out" the reserved area after it > successfully reports a pmem device to Xen hypervisor. ... "balloon out" ... _after_? That'd be unsafe. > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > Before a pmem file is assigned to a domain, we need to know the host > SPA ranges that are allocated to this file. We do this work in xl. > > If a pmem device /dev/pmem0 is given, xl will read > /sys/block/pmem0/device/{resource,size} respectively for the start > SPA and size of the pmem device. > > If a pre-allocated file /mnt/dax/file is given, > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > it uses the method above to get the start SPA of the host pmem > device. > (2) xl then uses fiemap ioctl to get the extend mappings of > /mnt/dax/file, and adds the corresponding physical offsets and > lengths in each mapping entries to above start SPA to get the SPA > ranges pre-allocated for this file. Remind me again: These extents never change, not even across reboot? I think this would be good to be written down here explicitly. Hadn't there been talk of using labels to be able to allow a guest to own the exact same physical range again after reboot or guest or host? > 3) When hvmloader loads a type 0 entry, it extracts the signature > from the data blob and search for it in builtin_table_sigs[]. If > found anyone, hvmloader will report an error and stop. Otherwise, > it will append it to the end of loaded guest ACPI. Duplicate table names aren't generally collisions: There can, for example, be many tables named "SSDT". > 4) When hvmloader loads a type 1 entry, it extracts the device name > from the data blob and search for it in builtin_nd_names[]. If > found anyone, hvmloader will report and error and stop. Otherwise, > it will wrap the AML code snippet by "Device (name[4]) {...}" and > include it in a new SSDT which is then appended to the end of > loaded guest ACPI. But all of these could go into a single SSDT, instead of (as it sounds) each into its own one? Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-02 14:46 ` Jan Beulich @ 2016-08-03 6:54 ` Haozhong Zhang 2016-08-03 8:45 ` Jan Beulich 0 siblings, 1 reply; 24+ messages in thread From: Haozhong Zhang @ 2016-08-03 6:54 UTC (permalink / raw) To: Jan Beulich Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong On 08/02/16 08:46, Jan Beulich wrote: > >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: > > 4.2.2 Detection of Host pmem Devices > > > > The detection and initialize host pmem devices require a non-trivial > > driver to interact with the corresponding ACPI namespace devices, > > parse namespace labels and make necessary recovery actions. Instead > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > detected host pmem devices to Xen hypervisor. > > > > Our design takes following steps to detect host pmem devices when Xen > > boots. > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > Linux NVDIMM driver. > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > of the pmem devices and reserved areas to Xen hypervisor via a > > new hypercall. > > > > (3) Xen hypervisor then checks > > - whether SPA and size of the newly reported pmem device is overlap > > with any previously reported pmem devices; > > ... or with system RAM. > > > - whether the reserved area can fit in the pmem device and is > > large enough to hold page_info structs for itself. > > So "reserved" here means available for Xen's use, but not for more > general purposes? How would the area Linux uses for its own > purposes get represented? > Reserved for xen only. I was going to reuse the existing reservation mechanism in linux pmem driver to allow reserving two areas - one for xen and another for linux itself. However, I later realized the existing mechanism depends on huge page support, so it does not work in dom0. For the first implementation, I'm implementing in a different way to reserve only for xen, and letting dom0 linux put page struct for pmem in the normal ram. Afterwards, I'll look for a way to allow both. > > (4) Because the reserved area is now used by Xen hypervisor, it > > should not be accessible by Dom0 any more. Therefore, if a host > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > reserved area from Dom0. Our design also needs to extend Linux > > NVDIMM driver to "balloon out" the reserved area after it > > successfully reports a pmem device to Xen hypervisor. > > ... "balloon out" ... _after_? That'd be unsafe. > Before ballooning is accomplished, the pmem driver does not create any device node under /dev/ and hence no one except the pmem drive can access the reserved area on pmem, so I think it's okey to balloon after reporting. > > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > > > Before a pmem file is assigned to a domain, we need to know the host > > SPA ranges that are allocated to this file. We do this work in xl. > > > > If a pmem device /dev/pmem0 is given, xl will read > > /sys/block/pmem0/device/{resource,size} respectively for the start > > SPA and size of the pmem device. > > > > If a pre-allocated file /mnt/dax/file is given, > > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > > it uses the method above to get the start SPA of the host pmem > > device. > > (2) xl then uses fiemap ioctl to get the extend mappings of > > /mnt/dax/file, and adds the corresponding physical offsets and > > lengths in each mapping entries to above start SPA to get the SPA > > ranges pre-allocated for this file. > > Remind me again: These extents never change, not even across > reboot? I think this would be good to be written down here explicitly. Yes > Hadn't there been talk of using labels to be able to allow a guest to > own the exact same physical range again after reboot or guest or > host? > You mean labels in NVDIMM label storage area? As defined in Intel NVDIMM Namespace Specification, labels are used to specify namespaces. For a pmem interleave set (possible cross several dimms), at most one pmem namespace (and hence at most one label) is allowed. Therefore, labels can not be used to partition pmem. > > 3) When hvmloader loads a type 0 entry, it extracts the signature > > from the data blob and search for it in builtin_table_sigs[]. If > > found anyone, hvmloader will report an error and stop. Otherwise, > > it will append it to the end of loaded guest ACPI. > > Duplicate table names aren't generally collisions: There can, for > example, be many tables named "SSDT". > I'll exclude SSDT from the duplication check. > > 4) When hvmloader loads a type 1 entry, it extracts the device name > > from the data blob and search for it in builtin_nd_names[]. If > > found anyone, hvmloader will report and error and stop. Otherwise, > > it will wrap the AML code snippet by "Device (name[4]) {...}" and > > include it in a new SSDT which is then appended to the end of > > loaded guest ACPI. > > But all of these could go into a single SSDT, instead of (as it sounds) > each into its own one? > Yes, I meant to put them in one SSDT. Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 6:54 ` Haozhong Zhang @ 2016-08-03 8:45 ` Jan Beulich 2016-08-03 9:37 ` Haozhong Zhang 0 siblings, 1 reply; 24+ messages in thread From: Jan Beulich @ 2016-08-03 8:45 UTC (permalink / raw) To: Haozhong Zhang Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong >>> On 03.08.16 at 08:54, <haozhong.zhang@intel.com> wrote: > On 08/02/16 08:46, Jan Beulich wrote: >> >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: >> > (4) Because the reserved area is now used by Xen hypervisor, it >> > should not be accessible by Dom0 any more. Therefore, if a host >> > pmem device is recorded by Xen hypervisor, Xen will unmap its >> > reserved area from Dom0. Our design also needs to extend Linux >> > NVDIMM driver to "balloon out" the reserved area after it >> > successfully reports a pmem device to Xen hypervisor. >> >> ... "balloon out" ... _after_? That'd be unsafe. >> > > Before ballooning is accomplished, the pmem driver does not create any > device node under /dev/ and hence no one except the pmem drive can > access the reserved area on pmem, so I think it's okey to balloon > after reporting. Right now Dom0 isn't allowed to access any memory in use by Xen (and not explicitly shared), and I don't think we should deviate from that model for pmem. >> > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files >> > >> > Before a pmem file is assigned to a domain, we need to know the host >> > SPA ranges that are allocated to this file. We do this work in xl. >> > >> > If a pmem device /dev/pmem0 is given, xl will read >> > /sys/block/pmem0/device/{resource,size} respectively for the start >> > SPA and size of the pmem device. >> > >> > If a pre-allocated file /mnt/dax/file is given, >> > (1) xl first finds the host pmem device where /mnt/dax/file is. Then >> > it uses the method above to get the start SPA of the host pmem >> > device. >> > (2) xl then uses fiemap ioctl to get the extend mappings of >> > /mnt/dax/file, and adds the corresponding physical offsets and >> > lengths in each mapping entries to above start SPA to get the SPA >> > ranges pre-allocated for this file. >> >> Remind me again: These extents never change, not even across >> reboot? I think this would be good to be written down here explicitly. > > Yes > >> Hadn't there been talk of using labels to be able to allow a guest to >> own the exact same physical range again after reboot or guest or >> host? > > You mean labels in NVDIMM label storage area? As defined in Intel > NVDIMM Namespace Specification, labels are used to specify > namespaces. For a pmem interleave set (possible cross several dimms), > at most one pmem namespace (and hence at most one label) is > allowed. Therefore, labels can not be used to partition pmem. Okay. But then how do particular ranges get associated with the owning guest(s)? Merely by SPA would seem rather fragile to me. Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 8:45 ` Jan Beulich @ 2016-08-03 9:37 ` Haozhong Zhang 2016-08-03 9:47 ` Jan Beulich 0 siblings, 1 reply; 24+ messages in thread From: Haozhong Zhang @ 2016-08-03 9:37 UTC (permalink / raw) To: Jan Beulich Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong On 08/03/16 02:45, Jan Beulich wrote: > >>> On 03.08.16 at 08:54, <haozhong.zhang@intel.com> wrote: > > On 08/02/16 08:46, Jan Beulich wrote: > >> >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: > >> > (4) Because the reserved area is now used by Xen hypervisor, it > >> > should not be accessible by Dom0 any more. Therefore, if a host > >> > pmem device is recorded by Xen hypervisor, Xen will unmap its > >> > reserved area from Dom0. Our design also needs to extend Linux > >> > NVDIMM driver to "balloon out" the reserved area after it > >> > successfully reports a pmem device to Xen hypervisor. > >> > >> ... "balloon out" ... _after_? That'd be unsafe. > >> > > > > Before ballooning is accomplished, the pmem driver does not create any > > device node under /dev/ and hence no one except the pmem drive can > > access the reserved area on pmem, so I think it's okey to balloon > > after reporting. > > Right now Dom0 isn't allowed to access any memory in use by Xen > (and not explicitly shared), and I don't think we should deviate > from that model for pmem. > In this design, Xen hypervisor unmaps the reserved area from Dom0 so that Dom0 cannot access the reserved area afterwards. And "balloon" is in fact not a memory ballooning, because Linux kernel never allocates from pmem like normal ram. In my current implementation, it's just to remove the reserved area from a resource struct covering pmem. > >> > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > >> > > >> > Before a pmem file is assigned to a domain, we need to know the host > >> > SPA ranges that are allocated to this file. We do this work in xl. > >> > > >> > If a pmem device /dev/pmem0 is given, xl will read > >> > /sys/block/pmem0/device/{resource,size} respectively for the start > >> > SPA and size of the pmem device. > >> > > >> > If a pre-allocated file /mnt/dax/file is given, > >> > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > >> > it uses the method above to get the start SPA of the host pmem > >> > device. > >> > (2) xl then uses fiemap ioctl to get the extend mappings of > >> > /mnt/dax/file, and adds the corresponding physical offsets and > >> > lengths in each mapping entries to above start SPA to get the SPA > >> > ranges pre-allocated for this file. > >> > >> Remind me again: These extents never change, not even across > >> reboot? I think this would be good to be written down here explicitly. > > > > Yes > > > >> Hadn't there been talk of using labels to be able to allow a guest to > >> own the exact same physical range again after reboot or guest or > >> host? > > > > You mean labels in NVDIMM label storage area? As defined in Intel > > NVDIMM Namespace Specification, labels are used to specify > > namespaces. For a pmem interleave set (possible cross several dimms), > > at most one pmem namespace (and hence at most one label) is > > allowed. Therefore, labels can not be used to partition pmem. > > Okay. But then how do particular ranges get associated with the > owning guest(s)? Merely by SPA would seem rather fragile to me. > By using the file name, e.g. if I specify vnvdimm = [ 'file=/mnt/dax/foo' ] in a domain config file, SPA occupied by /mnt/dax/foo are mapped to the domain. If the same file is used every time the domain is created, the same virtual device will be seen by that domain. Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 9:37 ` Haozhong Zhang @ 2016-08-03 9:47 ` Jan Beulich 2016-08-03 10:08 ` Haozhong Zhang 0 siblings, 1 reply; 24+ messages in thread From: Jan Beulich @ 2016-08-03 9:47 UTC (permalink / raw) To: Haozhong Zhang Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong >>> On 03.08.16 at 11:37, <haozhong.zhang@intel.com> wrote: > On 08/03/16 02:45, Jan Beulich wrote: >> >>> On 03.08.16 at 08:54, <haozhong.zhang@intel.com> wrote: >> > On 08/02/16 08:46, Jan Beulich wrote: >> >> >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: >> >> > (4) Because the reserved area is now used by Xen hypervisor, it >> >> > should not be accessible by Dom0 any more. Therefore, if a host >> >> > pmem device is recorded by Xen hypervisor, Xen will unmap its >> >> > reserved area from Dom0. Our design also needs to extend Linux >> >> > NVDIMM driver to "balloon out" the reserved area after it >> >> > successfully reports a pmem device to Xen hypervisor. >> >> >> >> ... "balloon out" ... _after_? That'd be unsafe. >> >> >> > >> > Before ballooning is accomplished, the pmem driver does not create any >> > device node under /dev/ and hence no one except the pmem drive can >> > access the reserved area on pmem, so I think it's okey to balloon >> > after reporting. >> >> Right now Dom0 isn't allowed to access any memory in use by Xen >> (and not explicitly shared), and I don't think we should deviate >> from that model for pmem. > > In this design, Xen hypervisor unmaps the reserved area from Dom0 so > that Dom0 cannot access the reserved area afterwards. And "balloon" is > in fact not a memory ballooning, because Linux kernel never allocates > from pmem like normal ram. In my current implementation, it's just to > remove the reserved area from a resource struct covering pmem. Ah, in that case please either use a different term, or explain what "balloon out" is meant to mean in this context. >> >> > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files >> >> > >> >> > Before a pmem file is assigned to a domain, we need to know the host >> >> > SPA ranges that are allocated to this file. We do this work in xl. >> >> > >> >> > If a pmem device /dev/pmem0 is given, xl will read >> >> > /sys/block/pmem0/device/{resource,size} respectively for the start >> >> > SPA and size of the pmem device. >> >> > >> >> > If a pre-allocated file /mnt/dax/file is given, >> >> > (1) xl first finds the host pmem device where /mnt/dax/file is. Then >> >> > it uses the method above to get the start SPA of the host pmem >> >> > device. >> >> > (2) xl then uses fiemap ioctl to get the extend mappings of >> >> > /mnt/dax/file, and adds the corresponding physical offsets and >> >> > lengths in each mapping entries to above start SPA to get the SPA >> >> > ranges pre-allocated for this file. >> >> >> >> Remind me again: These extents never change, not even across >> >> reboot? I think this would be good to be written down here explicitly. >> > >> > Yes >> > >> >> Hadn't there been talk of using labels to be able to allow a guest to >> >> own the exact same physical range again after reboot or guest or >> >> host? >> > >> > You mean labels in NVDIMM label storage area? As defined in Intel >> > NVDIMM Namespace Specification, labels are used to specify >> > namespaces. For a pmem interleave set (possible cross several dimms), >> > at most one pmem namespace (and hence at most one label) is >> > allowed. Therefore, labels can not be used to partition pmem. >> >> Okay. But then how do particular ranges get associated with the >> owning guest(s)? Merely by SPA would seem rather fragile to me. >> > > By using the file name, e.g. if I specify vnvdimm = [ 'file=/mnt/dax/foo' ] > in a domain config file, SPA occupied by /mnt/dax/foo are mapped to > the domain. If the same file is used every time the domain is created, > the same virtual device will be seen by that domain. So what if the file got deleted and re-created in between? Since I don't think you can specify the SPAs to use when creating such a file, such an operation would be quite different from removing and re-adding e.g. a specific PCI device (to be used by a guest) on a host (while the guest is not running). Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 9:47 ` Jan Beulich @ 2016-08-03 10:08 ` Haozhong Zhang 2016-08-03 10:18 ` Jan Beulich 0 siblings, 1 reply; 24+ messages in thread From: Haozhong Zhang @ 2016-08-03 10:08 UTC (permalink / raw) To: Jan Beulich Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong On 08/03/16 03:47, Jan Beulich wrote: > >>> On 03.08.16 at 11:37, <haozhong.zhang@intel.com> wrote: > > On 08/03/16 02:45, Jan Beulich wrote: > >> >>> On 03.08.16 at 08:54, <haozhong.zhang@intel.com> wrote: > >> > On 08/02/16 08:46, Jan Beulich wrote: > >> >> >>> On 18.07.16 at 02:29, <haozhong.zhang@intel.com> wrote: > >> >> > (4) Because the reserved area is now used by Xen hypervisor, it > >> >> > should not be accessible by Dom0 any more. Therefore, if a host > >> >> > pmem device is recorded by Xen hypervisor, Xen will unmap its > >> >> > reserved area from Dom0. Our design also needs to extend Linux > >> >> > NVDIMM driver to "balloon out" the reserved area after it > >> >> > successfully reports a pmem device to Xen hypervisor. > >> >> > >> >> ... "balloon out" ... _after_? That'd be unsafe. > >> >> > >> > > >> > Before ballooning is accomplished, the pmem driver does not create any > >> > device node under /dev/ and hence no one except the pmem drive can > >> > access the reserved area on pmem, so I think it's okey to balloon > >> > after reporting. > >> > >> Right now Dom0 isn't allowed to access any memory in use by Xen > >> (and not explicitly shared), and I don't think we should deviate > >> from that model for pmem. > > > > In this design, Xen hypervisor unmaps the reserved area from Dom0 so > > that Dom0 cannot access the reserved area afterwards. And "balloon" is > > in fact not a memory ballooning, because Linux kernel never allocates > > from pmem like normal ram. In my current implementation, it's just to > > remove the reserved area from a resource struct covering pmem. > > Ah, in that case please either use a different term, or explain what > "balloon out" is meant to mean in this context. > > >> >> > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > >> >> > > >> >> > Before a pmem file is assigned to a domain, we need to know the host > >> >> > SPA ranges that are allocated to this file. We do this work in xl. > >> >> > > >> >> > If a pmem device /dev/pmem0 is given, xl will read > >> >> > /sys/block/pmem0/device/{resource,size} respectively for the start > >> >> > SPA and size of the pmem device. > >> >> > > >> >> > If a pre-allocated file /mnt/dax/file is given, > >> >> > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > >> >> > it uses the method above to get the start SPA of the host pmem > >> >> > device. > >> >> > (2) xl then uses fiemap ioctl to get the extend mappings of > >> >> > /mnt/dax/file, and adds the corresponding physical offsets and > >> >> > lengths in each mapping entries to above start SPA to get the SPA > >> >> > ranges pre-allocated for this file. > >> >> > >> >> Remind me again: These extents never change, not even across > >> >> reboot? I think this would be good to be written down here explicitly. > >> > > >> > Yes > >> > > >> >> Hadn't there been talk of using labels to be able to allow a guest to > >> >> own the exact same physical range again after reboot or guest or > >> >> host? > >> > > >> > You mean labels in NVDIMM label storage area? As defined in Intel > >> > NVDIMM Namespace Specification, labels are used to specify > >> > namespaces. For a pmem interleave set (possible cross several dimms), > >> > at most one pmem namespace (and hence at most one label) is > >> > allowed. Therefore, labels can not be used to partition pmem. > >> > >> Okay. But then how do particular ranges get associated with the > >> owning guest(s)? Merely by SPA would seem rather fragile to me. > >> > > > > By using the file name, e.g. if I specify vnvdimm = [ 'file=/mnt/dax/foo' ] > > in a domain config file, SPA occupied by /mnt/dax/foo are mapped to > > the domain. If the same file is used every time the domain is created, > > the same virtual device will be seen by that domain. > > So what if the file got deleted and re-created in between? Since > I don't think you can specify the SPAs to use when creating such > a file, such an operation would be quite different from removing > and re-adding e.g. a specific PCI device (to be used by a guest) > on a host (while the guest is not running). > If modified in between, guest will see a virtual pmem device of different data. But the usage of pmem is similar to disk: if a file of the same content is given every time, the guest can get a virtual pmem/disk of the same data as last reboot/shutdown; keeping the data unchanged between multiple boots is out of the scope of Xen. Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 10:08 ` Haozhong Zhang @ 2016-08-03 10:18 ` Jan Beulich 0 siblings, 0 replies; 24+ messages in thread From: Jan Beulich @ 2016-08-03 10:18 UTC (permalink / raw) To: Haozhong Zhang Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong >>> On 03.08.16 at 12:08, <haozhong.zhang@intel.com> wrote: > On 08/03/16 03:47, Jan Beulich wrote: >> >>> On 03.08.16 at 11:37, <haozhong.zhang@intel.com> wrote: >> > By using the file name, e.g. if I specify vnvdimm = [ 'file=/mnt/dax/foo' ] >> > in a domain config file, SPA occupied by /mnt/dax/foo are mapped to >> > the domain. If the same file is used every time the domain is created, >> > the same virtual device will be seen by that domain. >> >> So what if the file got deleted and re-created in between? Since >> I don't think you can specify the SPAs to use when creating such >> a file, such an operation would be quite different from removing >> and re-adding e.g. a specific PCI device (to be used by a guest) >> on a host (while the guest is not running). > > If modified in between, guest will see a virtual pmem device of > different data. But the usage of pmem is similar to disk: if a file of > the same content is given every time, the guest can get a virtual > pmem/disk of the same data as last reboot/shutdown; keeping the data > unchanged between multiple boots is out of the scope of Xen. Except that here we're talking of handing a piece of hardware to a guest, which to me is more like a PCI device than a (virtual) disk. But anyway ... Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-07-18 0:29 [RFC Design Doc v2] Add vNVDIMM support for Xen Haozhong Zhang ` (2 preceding siblings ...) 2016-08-02 14:46 ` Jan Beulich @ 2016-08-03 21:25 ` Konrad Rzeszutek Wilk 2016-08-03 23:16 ` Konrad Rzeszutek Wilk 2016-08-04 8:52 ` Haozhong Zhang 3 siblings, 2 replies; 24+ messages in thread From: Konrad Rzeszutek Wilk @ 2016-08-03 21:25 UTC (permalink / raw) To: xen-devel, Jan Beulich, George Dunlap, Andrew Cooper, Ian Jackson, Stefano Stabellini, Juergen Gross, Wei Liu, Tian, Kevin, Xiao Guangrong, Nakajima, Jun On Mon, Jul 18, 2016 at 08:29:12AM +0800, Haozhong Zhang wrote: > Hi, > Hey! Thanks for posting! Sorry for the late review. Below are some of my comment. > Following is version 2 of the design doc for supporting vNVDIMM in > Xen. It's basically the summary of discussion on previous v1 design > (https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html). > Any comments are welcome. The corresponding patches are WIP. > > Thanks, > Haozhong > > > > vNVDIMM Design v2 > > Changes in v2: > - Rewrite the the design details based on previous discussion [7]. > - Add Section 3 Usage Example of vNVDIMM in Xen. > - Remove content about pcommit instruction which has been deprecated [8]. > > Content > ======= > 1. Background > 1.1 Access Mechanisms: Persistent Memory and Block Window > 1.2 ACPI Support > 1.2.1 NFIT > 1.2.2 _DSM and _FIT > 1.3 Namespace > 1.4 clwb/clflushopt > 2. NVDIMM/vNVDIMM Support in Linux Kernel/KVM/QEMU > 2.1 NVDIMM Driver in Linux Kernel > 2.2 vNVDIMM Implementation in KVM/QEMU > 3. Usage Example of vNVDIMM in Xen > 4. Design of vNVDIMM in Xen > 4.1 Guest clwb/clflushopt Enabling > 4.2 pmem Address Management > 4.2.1 Reserve Storage for Management Structures > 4.2.2 Detection of Host pmem Devices > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > 4.2.4 Map Host pmem to Guests > 4.2.5 Misc 1: RAS > 4.2.6 Misc 2: hotplug > 4.3 Guest ACPI Emulation > 4.3.1 Building Guest ACPI Tables > 4.3.2 Emulating Guest _DSM > References > > > Non-Volatile DIMM or NVDIMM is a type of RAM device that provides > persistent storage and retains data across reboot and even power > failures. This document describes the design to provide virtual NVDIMM > devices or vNVDIMM in Xen. > > The rest of this document is organized as below. > - Section 1 introduces the background knowledge of NVDIMM hardware, > which is used by other parts of this document. > > - Section 2 briefly introduces the current/future NVDIMM/vNVDIMM > support in Linux kernel/KVM/QEMU. They will affect the vNVDIMM > design in Xen. > > - Section 3 shows the basic usage example of vNVDIMM in Xen. > > - Section 4 proposes design details of vNVDIMM in Xen. > > > > 1. Background > > 1.1 Access Mechanisms: Persistent Memory and Block Window > > NVDIMM provides two access mechanisms: byte-addressable persistent > memory (pmem) and block window (pblk). An NVDIMM can contain multiple > ranges and each range can be accessed through either pmem or pblk > (but not both). > > Byte-addressable persistent memory mechanism (pmem) maps NVDIMM or > ranges of NVDIMM into the system physical address (SPA) space, so > that software can access NVDIMM via normal memory loads and > stores. If the virtual address is used, then MMU will translate it to > the physical address. > > In the virtualization circumstance, we can pass through a pmem range > or partial of it to a guest by mapping it in EPT (i.e. mapping guest > vNVDIMM physical address to host NVDIMM physical address), so that > guest accesses are applied directly to the host NVDIMM device without > hypervisor's interceptions. > > Block window mechanism (pblk) provides one or multiple block windows > (BW). Each BW is composed of a command register, a status register > and a 8 Kbytes aperture register. Software fills the direction of the > transfer (read/write), the start address (LBA) and size on NVDIMM it > is going to transfer. If nothing goes wrong, the transferred data can > be read/write via the aperture register. The status and errors of the > transfer can be got from the status register. Other vendor-specific > commands and status can be implemented for BW as well. Details of the > block window access mechanism can be found in [3]. > > In the virtualization circumstance, different pblk regions on a > single NVDIMM device may be accessed by different guests, so the > hypervisor needs to emulate BW, which would introduce a high overhead > for I/O intensive workload. > > Therefore, we are going to only implement pmem for vNVDIMM. The rest > of this document will mostly concentrate on pmem. > > > 1.2 ACPI Support > > ACPI provides two factors of support for NVDIMM. First, NVDIMM > devices are described by firmware (BIOS/EFI) to OS via ACPI-defined > NVDIMM Firmware Interface Table (NFIT). Second, several functions of > NVDIMM, including operations on namespace labels, S.M.A.R.T and > hotplug, are provided by ACPI methods (_DSM and _FIT). > > 1.2.1 NFIT > > NFIT is a new system description table added in ACPI v6 with > signature "NFIT". It contains a set of structures. > > - System Physical Address Range Structure > (SPA Range Structure) > > SPA range structure describes system physical address ranges > occupied by NVDIMMs and types of regions. > > If Address Range Type GUID field of a SPA range structure is "Byte > Addressable Persistent Memory (PM) Region", then the structure > describes a NVDIMM region that is accessed via pmem. The System > Physical Address Range Base and Length fields describe the start > system physical address and the length that is occupied by that > NVDIMM region. > > A SPA range structure is identified by a non-zero SPA range > structure index. > > Note: [1] reserves E820 type 7: OSPM must comprehend this memory as > having non-volatile attributes and handle distinct from > conventional volatile memory (in Table 15-312 of [1]). The > memory region supports byte-addressable non-volatility. E820 > type 12 (OEM defined) may be also used for legacy NVDIMM > prior to ACPI v6. > > Note: Besides OS, EFI firmware may also parse NFIT for booting > drives (Section 9.3.6.9 of [5]). > > - Memory Device to System Physical Address Range Mapping Structure > (Range Mapping Structure) > > An NVDIMM region described by a SPA range structure can be > interleaved across multiple NVDIMM devices. A range mapping > structure is used to describe the single mapping on each NVDIMM > device. It describes the size and the offset in a SPA range that an > NVDIMM device occupies. It may refer to an Interleave Structure > that contains details of the entire interleave set. Those > information is used in pblk by the NVDIMM driver for address > translation. > > The NVDIMM device described by the range mapping structure is > identified by an unique NFIT Device Handle. > > Details of NFIT and other structures can be found in Section 5.25 in [1]. > > 1.2.2 _DSM and _FIT > > The ACPI namespace device uses _HID of ACPI0012 to identify the root > NVDIMM interface device. An ACPI namespace device is also present > under the root device For each NVDIMM device. Above ACPI namespace s/For/for/ > devices are defined in SSDT. > > _DSM methods are present under the root device and each NVDIMM > device. _DSM methods are used by drivers to access the label storage > area, get health information, perform vendor-specific commands, > etc. Details of all _DSM methods can be found in [4]. > > _FIT method is under the root device and evaluated by OSPM to get > NFIT of hotplugged NVDIMM. The hotplugged NVDIMM is indicated to OS > using ACPI Namespace device with PNPID of PNP0C80 and the device > object notification value is 0x80. Details of NVDIMM hotplug can be > found in Section 9.20 of [1]. > > > 1.3 Namespace > > [2] describes a mechanism to sub-divide NVDIMMs into namespaces, > which are logic units of storage similar to SCSI LUNs and NVM Express > namespaces. > > The namespace information is describes by namespace labels stored in > the persistent label storage area on each NVDIMM device. The label > storage area is excluded from the the range mapped by the SPA range s/the the/the > structure and can only be accessed via _DSM methods. > > There are two types of namespaces defined in [2]: the persistent > memory namespace and the block namespaces. Persistent memory > namespaces is built for only pmem NVDIMM regions, while block > namespaces only for pblk. Only one persistent memory namespace is > allowed for a pmem NVDIMM region. > > Besides being accessed via _DSM, namespaces are managed and > interpreted by software. OS vendors may decide to not follow [2] and > store other types of information in the label storage area. > > > 1.4 clwb/clflushopt > > Writes to NVDIMM may be cached by caches, so certain flushing > operations should be performed to make them persistent on > NVDIMM. clwb is used in favor of clflushopt and clflush to flush > writes from caches to memory. > > Details of clwb/clflushopt can be found in Chapter 10 of [6]. Didn't that opcode get dropped in favour of poking in some register? > > > > 2. NVDIMM/vNVDIMM Support in Linux Kernel/KVM/QEMU > > 2.1 NVDIMM Driver in Linux Kernel > > Linux kernel since 4.2 has added support for ACPI-defined NVDIMM > devices. > > NVDIMM driver in Linux probes NVDIMM devices through ACPI (i.e. NFIT > and _FIT). It is also responsible to parse the namsepace labels on s/namspace/namespace/ > each NVDIMM devices, recover namespace after power failure (as > described in [2]) and handle NVDIMM hotplug. There are also some > vendor drivers to perform vendor-specific operations on NVDIMMs > (e.g. via _DSM). > > Compared to the ordinary ram, NVDIMM is used more like a persistent s/ram/RAM/ > storage drive for its persistent aspect. For each persistent memory > namespace, or a label-less pmem NVDIMM range, NVDIMM driver > implements a block device interface (/dev/pmemX) for it. > > Userspace applications can mmap(2) the whole pmem into its own > virtual address space. Linux kernel maps the system physical address > space range occupied by pmem into the virtual address space, so that every > normal memory loads/writes with proper flushing instructions are > applied to the underlying pmem NVDIMM regions. > > Alternatively, a DAX file system can be made on /dev/pmemX. Files on > that file system can be used in the same way as above. As Linux > kernel maps the system address space range occupied by those files on > NVDIMM to the virtual address space, reads/writes on those files are > applied to the underlying NVDIMM regions as well. > > 2.2 vNVDIMM Implementation in KVM/QEMU > > An overview of vNVDIMM implementation in KVM (Linux kernel v4.2) / QEMU (commit > 70d1fb9 and patches in-review/future) is showed by the following figure. > > > +---------------------------------+ > Guest GPA | | /dev/pmem0 | > +---------------------------------+ > parse evaluate ^ ^ > ACPI _DSM | | > | | | | > -------------|------------|--------------------------------|------------|---- > V V | | > +-------+ +-------+ | | > QEMU | vACPI | | v_DSM | | | > +-------+ +-------+ | | > ^ | | > | Read/Write | | > V | | > +...+--------------------+...+-----------+ | | > VA | | Label Storage Area | | buf | KVM_SET_USER_MEMORY_REGION(buf) > +...+--------------------+...+-----------+ | | > ^ mmap(2) ^ | | > --------------------------------------|-----------|--------|------------|---- > | +--------~------------+ > | | | > Linux/KVM +--------------------+ | > | | > +....+------------+ > SPA | | /dev/pmem0 | > +....+------------+ > ^ > | > Host NVDIMM Driver > -------------------------------------------------------------------|--------- > | > HW +------------+ > | NVDIMM | > +------------+ > > Nice picture! > A part not put in above figure is enabling guest clwb/clflushopt > which exposes those instructions to guest via guest cpuid. And aren't those deprecated? > > Besides instruction enabling, there are two primary parts of vNVDIMM > implementation in KVM/QEMU. > > (1) Address Mapping > > As described before, the host Linux NVDIMM driver provides a block > device interface (/dev/pmem0 at the bottom) for a pmem NVDIMM > region. QEMU can than mmap(2) that device into its virtual address > space (buf). QEMU is responsible to find a proper guest physical > address space range that is large enough to hold /dev/pmem0. Then > QEMU passes the virtual address of mmapped buf to a KVM API > KVM_SET_USER_MEMORY_REGION that maps in EPT the host physical > address range of buf to the guest physical address space range where > the virtual pmem device will be. > > In this way, all guest writes/reads on the virtual pmem device is > applied directly to the host one. > > Besides, above implementation also allows to back a virtual pmem > device by a mmapped regular file or a piece of ordinary ram. > > (2) Guest ACPI Emulation > > As guest system physical address and the size of the virtual pmem > device are determined by QEMU, QEMU is responsible to emulate the > guest NFIT and SSDT. Basically, it builds the guest NFIT and its > sub-structures that describes the virtual NVDIMM topology, and a > guest SSDT that defines ACPI namespace devices of virtual NVDIMM in > guest SSDT. > > As a portion of host pmem device or a regular file/ordinary file can > be used to back the guest pmem device, the label storage area on > host pmem cannot always be passed through to guest. Therefore, the > guest reads/writes on the label storage area is emulated by QEMU. As > described before, _DSM method is utilized by OSPM to access the > label storage area, and therefore it is emulated by QEMU. The _DSM > buffer is registered as MMIO, and its guest physical address and > size are described in the guest ACPI. Every command/status > read/write from guest is trapped and emulated by QEMU. > And is there any need for the E820 type 7 to be exposed? I presume not as the ACPI NFIT is sufficient? > Guest _FIT method will be implemented similarly in the future. > > > > 3. Usage Example of vNVDIMM in Xen > > Our design is to provide virtual pmem devices to HVM domains. The > virtual pmem devices are backed by host pmem devices. > > Dom0 Linux kernel can detect the host pmem devices and create > /dev/pmemXX for each detected devices. Users in Dom0 can then create > DAX file system on /dev/pmemXX and create several pre-allocate files > in the DAX file system. > > After setup the file system on the host pmem, users can add the > following lines in the xl configuration files to assign the host pmem > regions to domains: > vnvdimm = [ 'file=/dev/pmem0' ] > or > vnvdimm = [ 'file=/mnt/dax/pre_allocated_file' ] > > The first type of configuration assigns the entire pmem device > (/dev/pmem0) to the domain, while the second assigns the space > allocated to /mnt/dax/pre_allocated_file on the host pmem device to > the domain. > > When the domain starts, guest can detect the (virtual) pmem devices > via ACPI and guest read/write on the virtual pmem devices are > directly applied on their host backends. Would guest namespace (128kb) be written at offset 0 of said file (or block)? And of course the guest can only manipulate this using ACPI _DSM methods? > > > > 4. Design of vNVDIMM in Xen > > As KVM/QEMU, our design currently only provides pmem vNVDIMM. > > Similarly to that in KVM/QEMU, enabling vNVDIMM in Xen is composed of > three parts: > (1) Guest clwb/clflushopt enabling, > (2) pmem address management, and > (3) Guest ACPI emulation. > > The rest of this section present the design of each part > respectively. The basic design principle to reuse existing code in > Linux NVDIMM driver, QEMU and Xen as much as possible. > > > 4.1 Guest clwb/clflushopt Enabling > > The instruction enabling is simple and we do the same work as in KVM/QEMU: > - clwb/clflushopt are exposed to guest via guest cpuid. > Again, isn't that deprecated and the new mechanism (pokng at some register) has to be used? > > 4.2 pmem Address Management > > pmem address management is primarily composed of three parts: > (1) detection of pmem devices and their address ranges, which is > accomplished by Dom0 Linux pmem driver and Xen hypervisor; > (2) get SPA ranges of an pmem area that will be mapped to domain > which is accomplished by xl; > (3) map the pmem area to a domain, which is accomplished by qemu and s/qemu/QEMU/ > Xen hypervisor. > > Our design intends to reuse the current memory management for normal > RAM in Xen to manage the mapping of pmem. Then we will come across a > problem: where we store the memory management data structs for pmem. s/we store/where to/ > > The rest of this section addresses above aspects respectively. Wait. What about alternatives? Why treat it as a RAM region instead of as an MMIO region? > > 4.2.1 Reserve Storage for Management Structures > > A core data struct in Xen memory management is 'struct page_info'. > For normal ram, Xen creates a page_info struct for each page. For > pmem, we are going to do the same. However, for large capacity pmem > devices (e.g. several terabytes or even larger), a large amount of > page_info structs will occupy too much storage space that cannot > fit in the normal ram. > > Our solution, as used by Linux kernel, is to reserve an area on pmem > and place pmem's page_info structs in that reserved area. Therefore, > we can always ensure there is enough space for pmem page_info > structs, though the access to them is slower than directly from the > normal ram. > > Such a pmem namespace can be created via a userspace tool ndctl and > then recognized by Linux NVDIMM driver. However, they currently only > reserve space for Linux kernel's page structs. Therefore, our design > need to extend both Linux NVDIMM driver and ndctl to reserve > arbitrary size. That seems .. fragile? What if Windows or FreeBSD want to use it too? Would this 'struct page' on on NVDIMM be generalized enough to work with Linux,Xen, FreeBSD and what not? And this ndctl is https://github.com/pmem/ndctl I presume? And how is this structure reserved? Is it a seperate namespace entry? And QEMU knows not to access it? Or Xen needs to make sure _nobody_ except it can access it? Which means Xen may need to know the format of the ndctl structures that are laid out in the NVDIMM region? > > 4.2.2 Detection of Host pmem Devices > > The detection and initialize host pmem devices require a non-trivial > driver to interact with the corresponding ACPI namespace devices, > parse namespace labels and make necessary recovery actions. Instead > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > our designs leaves it to Dom0 Linux and let Dom0 Linux report > detected host pmem devices to Xen hypervisor. So Xen would ignore at bootup ACPI NFIT structures? > > Our design takes following steps to detect host pmem devices when Xen > boots. > (1) As booting on bare metal, host pmem devices are detected by Dom0 > Linux NVDIMM driver. > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > of the pmem devices and reserved areas to Xen hypervisor via a > new hypercall. reserved areas? That is the namespace region and the SPA <start,end> for the ndctl areas? Are the ndctl areas guarnateed to be contingous? Is there some spec on the ndctl and how/where they are stuck in the NVDIMM? > > (3) Xen hypervisor then checks > - whether SPA and size of the newly reported pmem device is overlap > with any previously reported pmem devices; Or normal RAM? > - whether the reserved area can fit in the pmem device and is > large enough to hold page_info structs for itself. I think I know what you mean but it sounds odd. Perhaps: large enough to hold page_info struct's for it's entire range? Native speaker, like Ian, would know how to say this right I think. Anyhow, wouldn't this 'sizeof(struct page_info)' depend on the ndctl tool and what version was used to create this? What if one version used 32-bytes for a PAGE, while another used 64-bytes for a PAGE too? It would be a bit of catching up .. wait, this same problem MUST be with Linux? How does it deal with this? > > If any checks fail, the reported pmem device will be ignored by > Xen hypervisor and hence will not be used by any I hope this hypercall returns an error code too? > guests. Otherwise, Xen hypervisor will recorded the reported s/recorded/record/ > parameters and create page_info structs in the reserved area. Ohh. You just blast it away? I guess it makes sense. Then what is the purpose of the ndctl? Just to carve out an namespace region for this? And what if there is something there from previous OS (say Linux)? Just blast it away? But could Linux depend on this containing some persistent information? Or does it also blast it away? But those regions may be non-contingous (or maybe not? I need to check the spec to double-check) so how do you figure out this 'reserved area' as it may be an N SPA's of the <start>,<end> type? > > (4) Because the reserved area is now used by Xen hypervisor, it > should not be accessible by Dom0 any more. Therefore, if a host > pmem device is recorded by Xen hypervisor, Xen will unmap its s/recorded/usurped/? Maybe monopolized? Owned? Ah, possesed! s/its/this/ > reserved area from Dom0. Our design also needs to extend Linux > NVDIMM driver to "balloon out" the reserved area after it > successfully reports a pmem device to Xen hypervisor. This "balloon out" is interesting. You are effectively telling Linux to ignore a certain range of 'struct page_info', so that if somebody uses /sys/debug/kernel/page_walk it won't blow up? (As the kerne can't read the struct page_info anymore). How would you do this? Simulate an NVDIMM unplug? But if you do that how will SMART tools work anymore? And who would do the _DSM checks on the health of the NVDIMM? /me scratches his head. Perhaps the answers are later in this design.. > > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > Before a pmem file is assigned to a domain, we need to know the host > SPA ranges that are allocated to this file. We do this work in xl. > > If a pmem device /dev/pmem0 is given, xl will read > /sys/block/pmem0/device/{resource,size} respectively for the start > SPA and size of the pmem device. Oh! How convient! > > If a pre-allocated file /mnt/dax/file is given, > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > it uses the method above to get the start SPA of the host pmem > device. > (2) xl then uses fiemap ioctl to get the extend mappings of > /mnt/dax/file, and adds the corresponding physical offsets and > lengths in each mapping entries to above start SPA to get the SPA > ranges pre-allocated for this file. Nice ! > > The resulting host SPA ranges will be passed to QEMU which allocates > guest address space for vNVDIMM devices and calls Xen hypervisor to > map the guest address to the host SPA ranges. > > 4.2.4 Map Host pmem to Guests > > Our design reuses the existing address mapping in Xen for the normal > ram to map pmem. We will still initiate the mapping for pmem from > QEMU, and there is one difference from the mapping of normal ram: > - For the normal ram, QEMU only needs to provide gpfn, and the actual > host memory where gpfn is mapped is allocated by Xen hypervisor. > - For pmem, QEMU provides both gpfn and mfn where gpfn is expected to > be mapped to. mfn is provided by xl as described in Section 4.2.3. > > Our design introduce a new XENMEM op for the pmem mapping, which > finally calls guest_physmap_add_page() to add the host pmem page to a > domain's address space. > > 4.2.5 Misc 1: RAS > > Machine check can occur from NVDIMM as normal ram, so that we follow > the current machine check handling in Xen for MC# from NVDIMM. OK, so that is mc_memerr_dhandler. OK, Is there enought telemtry information for the guest to know it is NVDIMM and handle it via the NVDIMM #MCE error handling which is different than normal #MCE? I presume this means a certain Linux guest dependency as well for this to work? > > 4.2.6 Misc 2: hotplug > > The hotplugged host NVDIMM devices is detected via _FIT method under > the root ACPI namespace device for NVDIMM. We rely on Dom0 Linux > kernel to discover the hotplugged NVDIMM devices and follow steps in > Section 4.2.2 to report the hotplugged devices to Xen hypervisor. > > > 4.3 Guest ACPI Emulation > > Guest ACPI emulation is composed of two parts: building guest NFIT > and SSDT that defines ACPI namespace devices for NVDIMM, and > emulating guest _DSM. As QEMU has already implemented ACPI support > for vNVDIMM on KVM, our design intends to reuse its implementation. > > 4.3.1 Building Guest ACPI Tables > > Two tables for vNVDIMM need to be built: > - NFIT, which defines the basic parameters of vNVDIMM devices and > does not contain any AML code. > - SSDT, which defines ACPI namespace devices for vNVDIMM in AML code. > > The contents of both tables are affected by some parameters > (e.g. address and size of vNVDIMM devices) that cannot be determined > until a guest configuration is given. However, all AML code in guest > ACPI are currently generated at compile time fro pre-crafted .asl s/fro/for/ > files, which is not feasible for ACPI namespace devices for vNVDIMM. > > We could either introduce an AML builder to generate AML code at > runtime like what QEMU is currently doing, or pass vNVDIMM ACPI > tables from QEMU to Xen. In order to reduce the duplicated code (to s/to Xen/to hvmloader/ I think? > AML builder in QEMU), our design takes the latter approach. Basically, > our design takes the following steps: > 1) The current QEMU does not build any ACPI stuffs when it runs as > the Xen device model, so we need to patch it to generate NFIT and > AML code of ACPI namespace devices for vNVDIMM. > > 2) QEMU then copies above NFIT and ACPI namespace devices to an area > at the end of guest memory below 4G. The guest physical address > and size of this area are written to xenstore keys > (/local/domain/domid/hvmloader/dm-acpi/{address,length}) The > detailed format of data in this area is explained later. > > 3) hvmloader reads above xenstore keys to probe the passed-in ACPI > tables and ACPI namespace devices, and detects the potential > collisions as explained later. > > 4) If no collisions are found, hvmloader will > (1) append the passed-in ACPI tables to the end of existing guest > ACPI tables, like what current construct_passthrough_tables() > does. > (2) construct a SSDT for each passed-in ACPI namespace devices and > append to the end of existing guest ACPI tables. > > Passing arbitrary ACPI tables and AML code from QEMU could > introduce at least two types of collisions: > 1) a passed-in table and a Xen-built table have the same signature > 2) a passed-in ACPI namespace device and a Xen-built ACPI namespace > device have the same device name. > > Our design takes the following method to avoid and detect collisions. > 1) The data layout of area where QEMU copies its NFIT and ACPI > namespace devices is organized as below: Why can't this be expressed in XenStore? You could have /local/domain/domid/hvmloader/dm-acpi/<name>/{address,length, type} ? > > 1 byte 4 bytes length bytes > +------+--------+-----------+------+--------+-----------+----- > | type | length | data blob | type | length | data blob | ... > +------+--------+-----------+------+--------+-----------+----- > > type: 0 - data blob contains a complete ACPI table > 1 - data blob contains AML code for an ACPI namespace device > > length: the number of bytes of data blob > > data blob: type 0 - a complete ACPI table > type 1 - composed as below: > > 4 bytes (length - 4) bytes > +---------+------------------+ > | name[4] | AML code snippet | > +---------+------------------+ > > name[4] : name of ACPI namespace device > AML code snippet: AML code inside "Device(name[4])" > > e.g. for an ACPI namespace device defined by > Device(NVDR) > { > Name (_HID, "ACPI0012") > ... > } > QEMU builds a data blob like > +--------------------+-----------------------------+ > | 'N', 'V', 'D', 'R' | Name (_HID, "ACPI0012") ... | > +--------------------+-----------------------------+ > > 2) hvmloader stores signatures of its own guest ACPI tables in an > array builtin_table_sigs[], and names of its own guest ACPI > namespace devices in an array builtin_nd_names[]. Because there > are only a few guest ACPI tables and namespace devices built by > Xen, we can hardcode their signatures or names in hvmloader. > > 3) When hvmloader loads a type 0 entry, it extracts the signature s/type 0/data blob->type 0/ ? > from the data blob and search for it in builtin_table_sigs[]. If > found anyone, hvmloader will report an error and stop. Otherwise, > it will append it to the end of loaded guest ACPI. > > 4) When hvmloader loads a type 1 entry, it extracts the device name > from the data blob and search for it in builtin_nd_names[]. If > found anyone, hvmloader will report and error and stop. Otherwise, > it will wrap the AML code snippet by "Device (name[4]) {...}" and > include it in a new SSDT which is then appended to the end of > loaded guest ACPI. > > 4.3.2 Emulating Guest _DSM > > Our design leaves the emulation of guest _DSM to QEMU. Just as what > it does with KVM, QEMU registers the _DSM buffer as MMIO region with > Xen and then all guest evaluations of _DSM are trapped and emulated > by QEMU. Sweet! So one question that I am not if it has been answered, with the 'struct page_info' being removed from the dom0 how will OEM _DSM method operation? For example some of the AML code may asking to poke at specific SPAs, but how will Linux do this properly without 'struct page_info' be available? Thanks! > > > References: > [1] ACPI Specification v6, > http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf > [2] NVDIMM Namespace Specification, > http://pmem.io/documents/NVDIMM_Namespace_Spec.pdf > [3] NVDIMM Block Window Driver Writer's Guide, > http://pmem.io/documents/NVDIMM_Driver_Writers_Guide.pdf > [4] NVDIMM DSM Interface Example, > http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf > [5] UEFI Specification v2.6, > http://www.uefi.org/sites/default/files/resources/UEFI%20Spec%202_6.pdf > [6] Intel Architecture Instruction Set Extensions Programming Reference, > https://software.intel.com/sites/default/files/managed/07/b7/319433-023.pdf > [7] https://lists.xenproject.org/archives/html/xen-devel/2016-02/msg00006.html > [8] https://lists.xen.org/archives/html/xen-devel/2016-06/msg00606.html _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 21:25 ` Konrad Rzeszutek Wilk @ 2016-08-03 23:16 ` Konrad Rzeszutek Wilk 2016-08-04 1:51 ` Haozhong Zhang 2016-08-04 8:52 ` Haozhong Zhang 1 sibling, 1 reply; 24+ messages in thread From: Konrad Rzeszutek Wilk @ 2016-08-03 23:16 UTC (permalink / raw) To: Konrad Rzeszutek Wilk Cc: Juergen Gross, Tian, Kevin, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong > > 1.4 clwb/clflushopt > > > > Writes to NVDIMM may be cached by caches, so certain flushing > > operations should be performed to make them persistent on > > NVDIMM. clwb is used in favor of clflushopt and clflush to flush > > writes from caches to memory. > > > > Details of clwb/clflushopt can be found in Chapter 10 of [6]. > > Didn't that opcode get dropped in favour of poking in some register? Nevermind. I got this confused with pcommit which was deprecated. But looking at chapter 10.2.2 it mentions that to commit to persistent memory you need to use pcommit. So what is the story here? .. snip... > > A part not put in above figure is enabling guest clwb/clflushopt > > which exposes those instructions to guest via guest cpuid. > > And aren't those deprecated? And again. Ignore that comment. .. snip.. > > 4. Design of vNVDIMM in Xen > > > > As KVM/QEMU, our design currently only provides pmem vNVDIMM. > > > > Similarly to that in KVM/QEMU, enabling vNVDIMM in Xen is composed of > > three parts: > > (1) Guest clwb/clflushopt enabling, > > (2) pmem address management, and > > (3) Guest ACPI emulation. > > > > The rest of this section present the design of each part > > respectively. The basic design principle to reuse existing code in > > Linux NVDIMM driver, QEMU and Xen as much as possible. > > > > > > 4.1 Guest clwb/clflushopt Enabling > > > > The instruction enabling is simple and we do the same work as in KVM/QEMU: > > - clwb/clflushopt are exposed to guest via guest cpuid. > > > > Again, isn't that deprecated and the new mechanism (pokng at some register) > has to be used? So clflushopt can be used for flushing out a cacheline. But what to do about store in the non-volatile memory? I recall that you could do an sfence and then pcommit, which would be aking to an SCSI SYNC command. But with pcommit being deprecated (albeit the URL you pointed too still lists pcommit) - at least in Xen and Linux - how do you enforce this wholesale flush? Thanks! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 23:16 ` Konrad Rzeszutek Wilk @ 2016-08-04 1:51 ` Haozhong Zhang 0 siblings, 0 replies; 24+ messages in thread From: Haozhong Zhang @ 2016-08-04 1:51 UTC (permalink / raw) To: Konrad Rzeszutek Wilk Cc: Juergen Gross, Tian, Kevin, Stefano Stabellini, Wei Liu, Jan Beulich, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Nakajima, Jun, Xiao Guangrong On 08/03/16 19:16, Konrad Rzeszutek Wilk wrote: > > > 1.4 clwb/clflushopt > > > > > > Writes to NVDIMM may be cached by caches, so certain flushing > > > operations should be performed to make them persistent on > > > NVDIMM. clwb is used in favor of clflushopt and clflush to flush > > > writes from caches to memory. > > > > > > Details of clwb/clflushopt can be found in Chapter 10 of [6]. > > > > Didn't that opcode get dropped in favour of poking in some register? > > Nevermind. I got this confused with pcommit which was deprecated. > > But looking at chapter 10.2.2 it mentions that to commit to > persistent memory you need to use pcommit. So what is the story here? The document has not been updated yet, though patches to revert pcommit support for both Linux and Xen had been merged. > .. snip... > > > A part not put in above figure is enabling guest clwb/clflushopt > > > which exposes those instructions to guest via guest cpuid. > > > > And aren't those deprecated? > > And again. Ignore that comment. > .. snip.. > > > 4. Design of vNVDIMM in Xen > > > > > > As KVM/QEMU, our design currently only provides pmem vNVDIMM. > > > > > > Similarly to that in KVM/QEMU, enabling vNVDIMM in Xen is composed of > > > three parts: > > > (1) Guest clwb/clflushopt enabling, > > > (2) pmem address management, and > > > (3) Guest ACPI emulation. > > > > > > The rest of this section present the design of each part > > > respectively. The basic design principle to reuse existing code in > > > Linux NVDIMM driver, QEMU and Xen as much as possible. > > > > > > > > > 4.1 Guest clwb/clflushopt Enabling > > > > > > The instruction enabling is simple and we do the same work as in KVM/QEMU: > > > - clwb/clflushopt are exposed to guest via guest cpuid. > > > > > > > Again, isn't that deprecated and the new mechanism (pokng at some register) > > has to be used? > > So clflushopt can be used for flushing out a cacheline. But what > to do about store in the non-volatile memory? I recall that you could > do an sfence and then pcommit, which would be aking to an SCSI SYNC > command. > > But with pcommit being deprecated (albeit the URL you pointed too > still lists pcommit) - at least in Xen and Linux - how do you > enforce this wholesale flush? > After deprecating pcommit, at least one of following two approaches should be provided by HW to guarantee persistent: 1) Asynchronous DRAM refresh (ADR) If the platform supports ADR, flush CPU cache lines (e.g. by clwb/clflushopt/clflush) will result result in flush write pending queues in memory controller to NVDIMM. 2) ACPI Flush Hint Address Structure If ACPI flush hint address structure is available for a NVDIMM region, software can write to that structure to flush any preceding stores to that NVDIMM region. (Section 5.2.25.8 of ACPI Spec 6.1) ADR is preferred, as guest clwb/clflushopt/clflush do not introduce VMEXITs. However, I'm also going to emulate ACPI flush hint address structure in case of the lack of ADR. Basically, guest writes to ACPI flush hint address structure will be trapped to QEMU which will submit them to the host ACPI flush hint address structure via Dom0 NVDIMM driver. If neither ADR nor ACPI flush hint address structure is available, persistent can not be guaranteed. Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-03 21:25 ` Konrad Rzeszutek Wilk 2016-08-03 23:16 ` Konrad Rzeszutek Wilk @ 2016-08-04 8:52 ` Haozhong Zhang 2016-08-04 9:25 ` Jan Beulich 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 1 sibling, 2 replies; 24+ messages in thread From: Haozhong Zhang @ 2016-08-04 8:52 UTC (permalink / raw) To: Konrad Rzeszutek Wilk Cc: Juergen Gross, Tian, Kevin, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong Hi Konrad, On 08/03/16 17:25, Konrad Rzeszutek Wilk wrote: > On Mon, Jul 18, 2016 at 08:29:12AM +0800, Haozhong Zhang wrote: > > Hi, > > > > Hey! > > Thanks for posting! Sorry for the late review. Below are some of my > comment. > Thank you for the review! [..] > And is there any need for the E820 type 7 to be exposed? I presume > not as the ACPI NFIT is sufficient? > No, NFIT is sufficient and provides more information than E820. > > > Guest _FIT method will be implemented similarly in the future. > > > > > > > > 3. Usage Example of vNVDIMM in Xen > > > > Our design is to provide virtual pmem devices to HVM domains. The > > virtual pmem devices are backed by host pmem devices. > > > > Dom0 Linux kernel can detect the host pmem devices and create > > /dev/pmemXX for each detected devices. Users in Dom0 can then create > > DAX file system on /dev/pmemXX and create several pre-allocate files > > in the DAX file system. > > > > After setup the file system on the host pmem, users can add the > > following lines in the xl configuration files to assign the host pmem > > regions to domains: > > vnvdimm = [ 'file=/dev/pmem0' ] > > or > > vnvdimm = [ 'file=/mnt/dax/pre_allocated_file' ] > > > > The first type of configuration assigns the entire pmem device > > (/dev/pmem0) to the domain, while the second assigns the space > > allocated to /mnt/dax/pre_allocated_file on the host pmem device to > > the domain. > > > > When the domain starts, guest can detect the (virtual) pmem devices > > via ACPI and guest read/write on the virtual pmem devices are > > directly applied on their host backends. > > Would guest namespace (128kb) be written at offset 0 of said file (or block)? > And of course the guest can only manipulate this using ACPI _DSM methods? > I guess you mean the label storage area which stores labels of namespaces. In the current QEMU implementation, the guest label storage area is at the end of the file or the block device. It's not mapped to the guest address space (which I missed to state here) and can be accessed only via guest _DSM. [..] > > 4.2 pmem Address Management > > > > pmem address management is primarily composed of three parts: > > (1) detection of pmem devices and their address ranges, which is > > accomplished by Dom0 Linux pmem driver and Xen hypervisor; > > (2) get SPA ranges of an pmem area that will be mapped to domain > > which is accomplished by xl; > > (3) map the pmem area to a domain, which is accomplished by qemu and > s/qemu/QEMU/ > > Xen hypervisor. > > > > Our design intends to reuse the current memory management for normal > > RAM in Xen to manage the mapping of pmem. Then we will come across a > > problem: where we store the memory management data structs for pmem. > > s/we store/where to/ > > > > The rest of this section addresses above aspects respectively. > > Wait. What about alternatives? Why treat it as a RAM region instead of > as an MMIO region? > The part used as the label storage area of vNVDIMM is treated as MMIO as described by a later section of this design. Other parts of vNVDIMM are directly accessed by guest, so I think we can treat them as normal RAM regions and map to guest, though we definitely need to mark them as pmem regions via virtual NFIT. > > > > 4.2.1 Reserve Storage for Management Structures > > > > A core data struct in Xen memory management is 'struct page_info'. > > For normal ram, Xen creates a page_info struct for each page. For > > pmem, we are going to do the same. However, for large capacity pmem > > devices (e.g. several terabytes or even larger), a large amount of > > page_info structs will occupy too much storage space that cannot > > fit in the normal ram. > > > > Our solution, as used by Linux kernel, is to reserve an area on pmem > > and place pmem's page_info structs in that reserved area. Therefore, > > we can always ensure there is enough space for pmem page_info > > structs, though the access to them is slower than directly from the > > normal ram. > > > > Such a pmem namespace can be created via a userspace tool ndctl and > > then recognized by Linux NVDIMM driver. However, they currently only > > reserve space for Linux kernel's page structs. Therefore, our design > > need to extend both Linux NVDIMM driver and ndctl to reserve > > arbitrary size. > > That seems .. fragile? What if Windows or FreeBSD want to use it > too? AFAIK, the way used by current Linux NVDIMM driver for reservation has not been documented in any public specifications yet. I'll consult driver developers for more information. > Would this 'struct page' on on NVDIMM be generalized enough > to work with Linux,Xen, FreeBSD and what not? > No. Different operating systems may choose different data structures to manage NVDIMM according to their own requirements and consideration, so it would be hard to reach an agreement on what to put in a generic data structure (and make it as part of ABI?). > And this ndctl is https://github.com/pmem/ndctl I presume? Yes. Sorry that I forgot to attach the URL. > > And how is this structure reserved? Is it a seperate namespace entry? No, it does not introduce any extra namespace entry. The current NVDIMM driver in Linux does the reservation in the way shown by the following diagram (I omit details about alignment and padding for simplicity): SPA SPA+4K | | V V +------+-----------+-- ... ---+-----...-----+ | | nd_pfn_sb | reserved | free to use | +------+-----------+-- ... ---+-----...-----+ |<-- nd_pfn_sb.dataoff -->| | | (+ necessary padding) | | | |<------------- pmem namespace ------------>| Given a pmem namespace which starts from SPA, 1) the driver stores a struct nd_pfn_sb at SPA+4K 2) the reserved area is after nd_pfn_sb 3) the free-to-use area is after the reserved area, and its location relative to SPA can be derived from nd_pfn_sb.dataoff 4) only the free-to-use area is exposed to a block device /dev/pmemX. Access to sector N of /dev/pmemX actually goes to (SPA + nd_pfn_sb.dataoff + N * SECT_SIZE) 5) nd_pfn_sb also contains a signature "NVDIMM_PFN_INFO" and a checksum. If the driver finds such signature and the checksum matches, then it knows this device contains reserved area. > And QEMU knows not to access it? QEMU as a userspace program can only access /dev/pmemX and hence has no way to touch the reserved area. > Or Xen needs to make sure _nobody_ > except it can access it? Which means Xen may need to know the format > of the ndctl structures that are laid out in the NVDIMM region? > Xen hypervisor relies on dom0 driver to parse the layout. At Dom0 boot, Dom0 NVDIMM driver reports address/size of area reserved for Xen to Xen hypervisor, which then unmaps the reserved area from Dom0. > > > > 4.2.2 Detection of Host pmem Devices > > > > The detection and initialize host pmem devices require a non-trivial > > driver to interact with the corresponding ACPI namespace devices, > > parse namespace labels and make necessary recovery actions. Instead > > of duplicating the comprehensive Linux pmem driver in Xen hypervisor, > > our designs leaves it to Dom0 Linux and let Dom0 Linux report > > detected host pmem devices to Xen hypervisor. > > So Xen would ignore at bootup ACPI NFIT structures? Yes, parsing NFIT is left to Dom0 which has the correct driver. > > > > Our design takes following steps to detect host pmem devices when Xen > > boots. > > (1) As booting on bare metal, host pmem devices are detected by Dom0 > > Linux NVDIMM driver. > > > > (2) Our design extends Linux NVDIMM driver to reports SPA's and sizes > > of the pmem devices and reserved areas to Xen hypervisor via a > > new hypercall. > > reserved areas? That is the namespace region and the SPA <start,end> > for the ndctl areas? Are the ndctl areas guarnateed to be contingous? > explained above. The reserved area on an individual pmem namespace is contiguous. > Is there some spec on the ndctl and how/where they are stuck in the NVDIMM? > No public spec so far, as mentioned above. > > > > (3) Xen hypervisor then checks > > - whether SPA and size of the newly reported pmem device is overlap > > with any previously reported pmem devices; > > Or normal RAM? > Yes, I missed normal RAM here. > > - whether the reserved area can fit in the pmem device and is > > large enough to hold page_info structs for itself. > > I think I know what you mean but it sounds odd. > > Perhaps: > > large enough to hold page_info struct's for it's entire range? > Yes, that is what I mean > Native speaker, like Ian, would know how to say this right I think. > > Anyhow, wouldn't this 'sizeof(struct page_info)' depend on the ndctl > tool and what version was used to create this? What if one version > used 32-bytes for a PAGE, while another used 64-bytes for a PAGE too? > It would be a bit of catching up .. wait, this same problem MUST > be with Linux? How does it deal with this? > Good question. Linux chooses a size (64 bytes) larger than its current sizeof(struct page) (40 bytes). We may also do in the same way, e.g. 32 bytes vs. 64 bytes? > > > > If any checks fail, the reported pmem device will be ignored by > > Xen hypervisor and hence will not be used by any > > I hope this hypercall returns an error code too? > Definitely yes > > guests. Otherwise, Xen hypervisor will recorded the reported > s/recorded/record/ > > parameters and create page_info structs in the reserved area. > > Ohh. You just blast it away? I guess it makes sense. Then what is the > purpose of the ndctl? Just to carve out an namespace region for this? > ndctl is used by, for example, a system admin to reserve space on a host pmem namespace. If there is already data in the namespace, ndctl will give a warning message and exit as long as --force option is not given. However, if --force is present, ndctl will break the existing data. > And what if there is something there from previous OS (say Linux)? > Just blast it away? But could Linux depend on this containing some > persistent information? Or does it also blast it away? > As above, if linux driver detects the signature "NVDIMM_PFN_INFO" and a matched checksum, it will know it's safe to write to the reserved area. Otherwise, it will treat the pmem namespace as a raw device and store page struct's in the normal RAM. > But those regions may be non-contingous (or maybe not? I need to check > the spec to double-check) so how do you figure out this 'reserved area' > as it may be an N SPA's of the <start>,<end> type? > the reserved area is per pmem namespace. > > > > (4) Because the reserved area is now used by Xen hypervisor, it > > should not be accessible by Dom0 any more. Therefore, if a host > > pmem device is recorded by Xen hypervisor, Xen will unmap its > > s/recorded/usurped/? Maybe monopolized? Owned? Ah, possesed! > > s/its/this/ > > reserved area from Dom0. Our design also needs to extend Linux > > NVDIMM driver to "balloon out" the reserved area after it > > successfully reports a pmem device to Xen hypervisor. > > This "balloon out" is interesting. You are effectively telling Linux > to ignore a certain range of 'struct page_info', so that if somebody > uses /sys/debug/kernel/page_walk it won't blow up? (As the kerne > can't read the struct page_info anymore). > > How would you do this? Simulate an NVDIMM unplug? s/page_info/page/ (struct page for linux, struct page_info for xen) As in Jan's comment, "balloon out" is a confusing name here. Basically, it's to remove the reserved area from some resource struct in nvdimm driver to avoid it's accessed out of the driver via the resource struct. And the nvdimm driver does not map the reserved area, so I think it cannot be touched via page_walk. > > But if you do that how will SMART tools work anymore? And > who would do the _DSM checks on the health of the NVDIMM? > A userspace SMART tool cannot access the reserved area, so I think it can still work. I haven't look at the implementation of any SMART tools for NVDIMM, but I guess they would finally call the driver to evaluate the ARS _DSM which reports the bad blocks. As long as the driver does not return the bad blocks in the reserved area to SMART tools (which I suppose to be handled by driver itself), SMART tools should work fine. > /me scratches his head. Perhaps the answers are later in this > design.. > > > > > 4.2.3 Get Host Machine Address (SPA) of Host pmem Files > > > > Before a pmem file is assigned to a domain, we need to know the host > > SPA ranges that are allocated to this file. We do this work in xl. > > > > If a pmem device /dev/pmem0 is given, xl will read > > /sys/block/pmem0/device/{resource,size} respectively for the start > > SPA and size of the pmem device. > > Oh! How convient! > > > > If a pre-allocated file /mnt/dax/file is given, > > (1) xl first finds the host pmem device where /mnt/dax/file is. Then > > it uses the method above to get the start SPA of the host pmem > > device. > > (2) xl then uses fiemap ioctl to get the extend mappings of > > /mnt/dax/file, and adds the corresponding physical offsets and > > lengths in each mapping entries to above start SPA to get the SPA > > ranges pre-allocated for this file. > > Nice ! > > > > The resulting host SPA ranges will be passed to QEMU which allocates > > guest address space for vNVDIMM devices and calls Xen hypervisor to > > map the guest address to the host SPA ranges. > > > > 4.2.4 Map Host pmem to Guests > > > > Our design reuses the existing address mapping in Xen for the normal > > ram to map pmem. We will still initiate the mapping for pmem from > > QEMU, and there is one difference from the mapping of normal ram: > > - For the normal ram, QEMU only needs to provide gpfn, and the actual > > host memory where gpfn is mapped is allocated by Xen hypervisor. > > - For pmem, QEMU provides both gpfn and mfn where gpfn is expected to > > be mapped to. mfn is provided by xl as described in Section 4.2.3. > > > > Our design introduce a new XENMEM op for the pmem mapping, which > > finally calls guest_physmap_add_page() to add the host pmem page to a > > domain's address space. > > > > 4.2.5 Misc 1: RAS > > > > Machine check can occur from NVDIMM as normal ram, so that we follow > > the current machine check handling in Xen for MC# from NVDIMM. > > OK, so that is mc_memerr_dhandler. OK, > > Is there enought telemtry information for the guest to know > it is NVDIMM and handle it via the NVDIMM #MCE error handling which > is different than normal #MCE? > > I presume this means a certain Linux guest dependency as well > for this to work? > Yes, the guest should at least know which address belongs to vNVDIMM. Then it can tell from the address of virtual #MC where the error comes from. Otherwise, the guest will see an #MC for an address it doesn't know. > > > > 4.2.6 Misc 2: hotplug > > > > The hotplugged host NVDIMM devices is detected via _FIT method under > > the root ACPI namespace device for NVDIMM. We rely on Dom0 Linux > > kernel to discover the hotplugged NVDIMM devices and follow steps in > > Section 4.2.2 to report the hotplugged devices to Xen hypervisor. > > > > > > 4.3 Guest ACPI Emulation > > > > Guest ACPI emulation is composed of two parts: building guest NFIT > > and SSDT that defines ACPI namespace devices for NVDIMM, and > > emulating guest _DSM. As QEMU has already implemented ACPI support > > for vNVDIMM on KVM, our design intends to reuse its implementation. > > > > 4.3.1 Building Guest ACPI Tables > > > > Two tables for vNVDIMM need to be built: > > - NFIT, which defines the basic parameters of vNVDIMM devices and > > does not contain any AML code. > > - SSDT, which defines ACPI namespace devices for vNVDIMM in AML code. > > > > The contents of both tables are affected by some parameters > > (e.g. address and size of vNVDIMM devices) that cannot be determined > > until a guest configuration is given. However, all AML code in guest > > ACPI are currently generated at compile time fro pre-crafted .asl > > s/fro/for/ > > > files, which is not feasible for ACPI namespace devices for vNVDIMM. > > > > We could either introduce an AML builder to generate AML code at > > runtime like what QEMU is currently doing, or pass vNVDIMM ACPI > > tables from QEMU to Xen. In order to reduce the duplicated code (to > > s/to Xen/to hvmloader/ I think? > yes > > AML builder in QEMU), our design takes the latter approach. Basically, > > our design takes the following steps: > > 1) The current QEMU does not build any ACPI stuffs when it runs as > > the Xen device model, so we need to patch it to generate NFIT and > > AML code of ACPI namespace devices for vNVDIMM. > > > > 2) QEMU then copies above NFIT and ACPI namespace devices to an area > > at the end of guest memory below 4G. The guest physical address > > and size of this area are written to xenstore keys > > (/local/domain/domid/hvmloader/dm-acpi/{address,length}) The > > detailed format of data in this area is explained later. > > > > 3) hvmloader reads above xenstore keys to probe the passed-in ACPI > > tables and ACPI namespace devices, and detects the potential > > collisions as explained later. > > > > 4) If no collisions are found, hvmloader will > > (1) append the passed-in ACPI tables to the end of existing guest > > ACPI tables, like what current construct_passthrough_tables() > > does. > > (2) construct a SSDT for each passed-in ACPI namespace devices and > > append to the end of existing guest ACPI tables. > > > > Passing arbitrary ACPI tables and AML code from QEMU could > > introduce at least two types of collisions: > > 1) a passed-in table and a Xen-built table have the same signature > > 2) a passed-in ACPI namespace device and a Xen-built ACPI namespace > > device have the same device name. > > > > Our design takes the following method to avoid and detect collisions. > > 1) The data layout of area where QEMU copies its NFIT and ACPI > > namespace devices is organized as below: > > Why can't this be expressed in XenStore? > > You could have /local/domain/domid/hvmloader/dm-acpi/<name>/{address,length, type} > ? > If XenStore can be used, then it could save some guest memory. This is a general mechanism to pass ACPI which and is not limited to NVDIMM, so it means QEMU may pass a lot of entries. I'm not sure if XenStore is still a proper place when the number is large. Maybe we should put an upper limit for the number of entries. > > > > 1 byte 4 bytes length bytes > > +------+--------+-----------+------+--------+-----------+----- > > | type | length | data blob | type | length | data blob | ... > > +------+--------+-----------+------+--------+-----------+----- > > > > type: 0 - data blob contains a complete ACPI table > > 1 - data blob contains AML code for an ACPI namespace device > > > > length: the number of bytes of data blob > > > > data blob: type 0 - a complete ACPI table > > type 1 - composed as below: > > > > 4 bytes (length - 4) bytes > > +---------+------------------+ > > | name[4] | AML code snippet | > > +---------+------------------+ > > > > name[4] : name of ACPI namespace device > > AML code snippet: AML code inside "Device(name[4])" > > > > e.g. for an ACPI namespace device defined by > > Device(NVDR) > > { > > Name (_HID, "ACPI0012") > > ... > > } > > QEMU builds a data blob like > > +--------------------+-----------------------------+ > > | 'N', 'V', 'D', 'R' | Name (_HID, "ACPI0012") ... | > > +--------------------+-----------------------------+ > > > > 2) hvmloader stores signatures of its own guest ACPI tables in an > > array builtin_table_sigs[], and names of its own guest ACPI > > namespace devices in an array builtin_nd_names[]. Because there > > are only a few guest ACPI tables and namespace devices built by > > Xen, we can hardcode their signatures or names in hvmloader. > > > > 3) When hvmloader loads a type 0 entry, it extracts the signature > > s/type 0/data blob->type 0/ ? > no, type information is out of data blob ({type, length, data blob}) > > from the data blob and search for it in builtin_table_sigs[]. If > > found anyone, hvmloader will report an error and stop. Otherwise, > > it will append it to the end of loaded guest ACPI. > > > > 4) When hvmloader loads a type 1 entry, it extracts the device name > > from the data blob and search for it in builtin_nd_names[]. If > > found anyone, hvmloader will report and error and stop. Otherwise, > > it will wrap the AML code snippet by "Device (name[4]) {...}" and > > include it in a new SSDT which is then appended to the end of > > loaded guest ACPI. > > > > 4.3.2 Emulating Guest _DSM > > > > Our design leaves the emulation of guest _DSM to QEMU. Just as what > > it does with KVM, QEMU registers the _DSM buffer as MMIO region with > > Xen and then all guest evaluations of _DSM are trapped and emulated > > by QEMU. > > Sweet! > > So one question that I am not if it has been answered, with the > 'struct page_info' being removed from the dom0 how will OEM _DSM method > operation? For example some of the AML code may asking to poke > at specific SPAs, but how will Linux do this properly without > 'struct page_info' be available? > (s/page_info/page/) The current Intel NVDIMM driver in Linux does not evaluate any OEM _DSM method, so I'm not sure whether the kernel has to access a NVDIMM page during evaluating _DSM. The most close one in my mind, though not an OEM _DSM, is function 1 of ARS _DSM, which requires inputs of a start SPA and a length in bytes. After kernel gives the inputs, the scrubbing of the specified area is done by the hardware and does not requires any mappings in OS. Any example of such OEM _DSM methods? Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-04 8:52 ` Haozhong Zhang @ 2016-08-04 9:25 ` Jan Beulich 2016-08-04 9:35 ` Haozhong Zhang 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 1 sibling, 1 reply; 24+ messages in thread From: Jan Beulich @ 2016-08-04 9:25 UTC (permalink / raw) To: Haozhong Zhang, Konrad Rzeszutek Wilk Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong >>> On 04.08.16 at 10:52, <haozhong.zhang@intel.com> wrote: > On 08/03/16 17:25, Konrad Rzeszutek Wilk wrote: >> Anyhow, wouldn't this 'sizeof(struct page_info)' depend on the ndctl >> tool and what version was used to create this? What if one version >> used 32-bytes for a PAGE, while another used 64-bytes for a PAGE too? >> It would be a bit of catching up .. wait, this same problem MUST >> be with Linux? How does it deal with this? > > Good question. Linux chooses a size (64 bytes) larger than its current > sizeof(struct page) (40 bytes). We may also do in the same way, > e.g. 32 bytes vs. 64 bytes? I don't understand this: These structures aren't meant to be persistent, so their size shouldn't matter? Jan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-04 9:25 ` Jan Beulich @ 2016-08-04 9:35 ` Haozhong Zhang 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 0 siblings, 1 reply; 24+ messages in thread From: Haozhong Zhang @ 2016-08-04 9:35 UTC (permalink / raw) To: Jan Beulich Cc: Juergen Gross, Kevin Tian, Stefano Stabellini, Wei Liu, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jun Nakajima, Xiao Guangrong On 08/04/16 03:25, Jan Beulich wrote: > >>> On 04.08.16 at 10:52, <haozhong.zhang@intel.com> wrote: > > On 08/03/16 17:25, Konrad Rzeszutek Wilk wrote: > >> Anyhow, wouldn't this 'sizeof(struct page_info)' depend on the ndctl > >> tool and what version was used to create this? What if one version > >> used 32-bytes for a PAGE, while another used 64-bytes for a PAGE too? > >> It would be a bit of catching up .. wait, this same problem MUST > >> be with Linux? How does it deal with this? > > > > Good question. Linux chooses a size (64 bytes) larger than its current > > sizeof(struct page) (40 bytes). We may also do in the same way, > > e.g. 32 bytes vs. 64 bytes? > > I don't understand this: These structures aren't meant to be > persistent, so their size shouldn't matter? > But the size of the reserved area is persistent. If the size of struct page_info increases in future versions, the reserved area which is just enough for old version struct page_info would not be enough for the new version. Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-04 9:35 ` Haozhong Zhang @ 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 0 siblings, 0 replies; 24+ messages in thread From: Konrad Rzeszutek Wilk @ 2016-08-04 14:51 UTC (permalink / raw) To: Jan Beulich, Andrew Cooper, Wei Liu, George Dunlap, Ian Jackson, Jun Nakajima, Kevin Tian, Stefano Stabellini, Xiao Guangrong, xen-devel, Juergen Gross On Thu, Aug 04, 2016 at 05:35:12PM +0800, Haozhong Zhang wrote: > On 08/04/16 03:25, Jan Beulich wrote: > > >>> On 04.08.16 at 10:52, <haozhong.zhang@intel.com> wrote: > > > On 08/03/16 17:25, Konrad Rzeszutek Wilk wrote: > > >> Anyhow, wouldn't this 'sizeof(struct page_info)' depend on the ndctl > > >> tool and what version was used to create this? What if one version > > >> used 32-bytes for a PAGE, while another used 64-bytes for a PAGE too? > > >> It would be a bit of catching up .. wait, this same problem MUST > > >> be with Linux? How does it deal with this? > > > > > > Good question. Linux chooses a size (64 bytes) larger than its current > > > sizeof(struct page) (40 bytes). We may also do in the same way, > > > e.g. 32 bytes vs. 64 bytes? > > > > I don't understand this: These structures aren't meant to be > > persistent, so their size shouldn't matter? > > > > But the size of the reserved area is persistent. If the size of struct > page_info increases in future versions, the reserved area which is > just enough for old version struct page_info would not be enough for > the new version. Exactly!! Thanks! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-04 8:52 ` Haozhong Zhang 2016-08-04 9:25 ` Jan Beulich @ 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 2016-08-05 6:25 ` Haozhong Zhang 1 sibling, 1 reply; 24+ messages in thread From: Konrad Rzeszutek Wilk @ 2016-08-04 14:51 UTC (permalink / raw) To: xen-devel, Jan Beulich, George Dunlap, Andrew Cooper, Ian Jackson, Stefano Stabellini, Juergen Gross, Wei Liu, Tian, Kevin, Xiao Guangrong, Nakajima, Jun > > > Such a pmem namespace can be created via a userspace tool ndctl and > > > then recognized by Linux NVDIMM driver. However, they currently only > > > reserve space for Linux kernel's page structs. Therefore, our design > > > need to extend both Linux NVDIMM driver and ndctl to reserve > > > arbitrary size. > > > > That seems .. fragile? What if Windows or FreeBSD want to use it > > too? > > AFAIK, the way used by current Linux NVDIMM driver for reservation has > not been documented in any public specifications yet. I'll consult > driver developers for more information. > > > Would this 'struct page' on on NVDIMM be generalized enough > > to work with Linux,Xen, FreeBSD and what not? > > > > No. Different operating systems may choose different data structures > to manage NVDIMM according to their own requirements and > consideration, so it would be hard to reach an agreement on what to > put in a generic data structure (and make it as part of ABI?). Yes. As I can see different OSes having different sizes. And then this size of 'reserved region' ends up being too small and only some part of the NVDIMM can be used. > > > And this ndctl is https://github.com/pmem/ndctl I presume? > > Yes. Sorry that I forgot to attach the URL. > > > > > And how is this structure reserved? Is it a seperate namespace entry? > > No, it does not introduce any extra namespace entry. The current > NVDIMM driver in Linux does the reservation in the way shown by the > following diagram (I omit details about alignment and padding for > simplicity): > > SPA SPA+4K > | | > V V > +------+-----------+-- ... ---+-----...-----+ > | | nd_pfn_sb | reserved | free to use | > +------+-----------+-- ... ---+-----...-----+ > |<-- nd_pfn_sb.dataoff -->| | > | (+ necessary padding) | > | | > |<------------- pmem namespace ------------>| > > Given a pmem namespace which starts from SPA, AAAAh, so it is at start of the namespace! Thanks > 1) the driver stores a struct nd_pfn_sb at SPA+4K > 2) the reserved area is after nd_pfn_sb > 3) the free-to-use area is after the reserved area, and its location > relative to SPA can be derived from nd_pfn_sb.dataoff > 4) only the free-to-use area is exposed to a block device /dev/pmemX. > Access to sector N of /dev/pmemX actually goes to (SPA + > nd_pfn_sb.dataoff + N * SECT_SIZE) > 5) nd_pfn_sb also contains a signature "NVDIMM_PFN_INFO" and a > checksum. If the driver finds such signature and the checksum > matches, then it knows this device contains reserved area. /me nods. And of course this nice diagram and such is going to be in a public ABI document :-) > > > And QEMU knows not to access it? > > QEMU as a userspace program can only access /dev/pmemX and hence has > no way to touch the reserved area. Rightto. > > > Or Xen needs to make sure _nobody_ > > except it can access it? Which means Xen may need to know the format > > of the ndctl structures that are laid out in the NVDIMM region? > > > > Xen hypervisor relies on dom0 driver to parse the layout. At Dom0 > boot, Dom0 NVDIMM driver reports address/size of area reserved for Xen > to Xen hypervisor, which then unmaps the reserved area from Dom0. OK, so the /dev/pmem driver would consult this when somebody is mmaping the area. But since this would be removed from the driver (unregistered) it would report an zero size? Or would it "Otherwise, it will treat the pmem namespace as a raw device and store page struct's in the normal RAM." - which means dom0 can still access the SPA (except obviously the area that is for this reserved region)? ..snip.. > > > guests. Otherwise, Xen hypervisor will recorded the reported > > s/recorded/record/ > > > parameters and create page_info structs in the reserved area. > > > > Ohh. You just blast it away? I guess it makes sense. Then what is the > > purpose of the ndctl? Just to carve out an namespace region for this? > > > > ndctl is used by, for example, a system admin to reserve space on a > host pmem namespace. If there is already data in the namespace, ndctl > will give a warning message and exit as long as --force option is not > given. However, if --force is present, ndctl will break the existing > data. > > > And what if there is something there from previous OS (say Linux)? > > Just blast it away? But could Linux depend on this containing some > > persistent information? Or does it also blast it away? > > > > As above, if linux driver detects the signature "NVDIMM_PFN_INFO" and > a matched checksum, it will know it's safe to write to the reserved > area. Otherwise, it will treat the pmem namespace as a raw device and > store page struct's in the normal RAM. OK, so my worry is that we will have a divergence. Which is that the system admin creates this under ndctl v0, boots Xen uses it. Then moves the NVDIMM to another machine which has ndctl v1 and he/she boots in Linux. Linux gets all confused b/c the region has something it can't understand and the user is very angry. So it sounds like the size the ndctl reserves MUST be baked in an ABI and made sure to expand if needed. ..snip.. > > This "balloon out" is interesting. You are effectively telling Linux > > to ignore a certain range of 'struct page_info', so that if somebody > > uses /sys/debug/kernel/page_walk it won't blow up? (As the kerne > > can't read the struct page_info anymore). > > > > How would you do this? Simulate an NVDIMM unplug? > > s/page_info/page/ (struct page for linux, struct page_info for xen) > > As in Jan's comment, "balloon out" is a confusing name here. > Basically, it's to remove the reserved area from some resource struct > in nvdimm driver to avoid it's accessed out of the driver via the > resource struct. And the nvdimm driver does not map the reserved area, > so I think it cannot be touched via page_walk. OK, I need to read the Linux code more to make sure I am not missing something. Basically the question that keeps revolving in my head is: Why is this even neccessary? Let me expand - it feels like (and I think I am missing something here) that we are crippling the Linux driver so that it won't break - b/c if it tried to access the 'strut page_info' in this reserved region it would crash. So we eliminate that, and make the driver believe the region exists (is reserved), but it can't use it. And instead use the normal RAM pages to keep track of the NVDIMM SPAs. Or perhaps not keep track at all and just treat the whole NVDIMM as opaque MMIO that is inaccessible? But how will that work if there is a DAX filesystem on it? The ext4 needs some mechanism to access the files that are there. (Otherwise you couldn't use the fiemap ioctl to find the SPAs). [see below] > > > > > But if you do that how will SMART tools work anymore? And > > who would do the _DSM checks on the health of the NVDIMM? > > > > A userspace SMART tool cannot access the reserved area, so I think it > can still work. I haven't look at the implementation of any SMART > tools for NVDIMM, but I guess they would finally call the driver to > evaluate the ARS _DSM which reports the bad blocks. As long as the > driver does not return the bad blocks in the reserved area to SMART > tools (which I suppose to be handled by driver itself), SMART tools > should work fine. > > > /me scratches his head. Perhaps the answers are later in this > > design.. So I think I figured out the issue here!! You just want to have the Linux kernel driver to use normal RAM pages to keep track of the NVDIMM SPA ranges. As in treat the NVDIMM as if it is normal RAM? [Or is Linux treating this area as MMIO region (in wihch case it does not need struct page_info)??] And then Xen can use this reserved region for its own purpose! Perhaps then the section that explains this 'reserved region' could say something along: "We need to keep track of the SPAs. The guest NVDIMM 'file' on the NVDIMM may be in the worst case be randomly and in descending discontingous order (say from the end of the NVDIMM), we need to keep track of each of the SPAs. The reason is that we need the SPAs when we populate the guest EPT. As such we can store the guest SPA in memory (linear array?) or red-black tree, or any other - but all of them will consume "normal RAM". And with sufficient large enough NVDIMM we may not have enough 'normal RAM' to store this. Also we only need to know these SPAs during guest creation, destruction, ballooning, etc - hence we may store them on the NVDIMM itself. Fortunatly for us the ndctl and Linux are available which carve out right after the namespace region (128kb) and 'reserved region' which the OS can use to store its struct page_info to cover the full range of the NVDIMM. The complexity in this is that: - We MUST make sure Linux does not try to use it while we use it. - That the size of this 'reserved region' is sufficiently large for our 'struct page_info' structure. - The layout has an ABI baked. - Linux fs'es with DAX support MUST be able mlock these SPA regions (so that nobody tries to remove the 'file' while a guest is using it). - Linus fs'es with DAX support MUST be able to resize the 'file', hereby using more of the SPAs and rewritting the properties of the file on DAX (which should then cause an memory hotplug ACPI in the guest treating the new size of the file as new NFIT region?) " I think that covers it? ..snip.. > > > Our design takes the following method to avoid and detect collisions. > > > 1) The data layout of area where QEMU copies its NFIT and ACPI > > > namespace devices is organized as below: > > > > Why can't this be expressed in XenStore? > > > > You could have /local/domain/domid/hvmloader/dm-acpi/<name>/{address,length, type} > > ? > > > > If XenStore can be used, then it could save some guest memory. It is also easier than relaying on the format of a blob in memory. > > This is a general mechanism to pass ACPI which and is not limited to > NVDIMM, so it means QEMU may pass a lot of entries. I'm not sure if > XenStore is still a proper place when the number is large. Maybe we > should put an upper limit for the number of entries. Why put a limit on it? It should easily handle thousands of <name>. And the only attributes you have under <name> are just address, length and type. .. snip.. > > > 4.3.2 Emulating Guest _DSM > > > > > > Our design leaves the emulation of guest _DSM to QEMU. Just as what > > > it does with KVM, QEMU registers the _DSM buffer as MMIO region with > > > Xen and then all guest evaluations of _DSM are trapped and emulated > > > by QEMU. > > > > Sweet! > > > > So one question that I am not if it has been answered, with the > > 'struct page_info' being removed from the dom0 how will OEM _DSM method > > operation? For example some of the AML code may asking to poke > > at specific SPAs, but how will Linux do this properly without > > 'struct page_info' be available? > > > > (s/page_info/page/) > > The current Intel NVDIMM driver in Linux does not evaluate any OEM > _DSM method, so I'm not sure whether the kernel has to access a NVDIMM > page during evaluating _DSM. > > The most close one in my mind, though not an OEM _DSM, is function 1 > of ARS _DSM, which requires inputs of a start SPA and a length in > bytes. After kernel gives the inputs, the scrubbing of the specified > area is done by the hardware and does not requires any mappings in OS. <nods> > > Any example of such OEM _DSM methods? I can't think of any right now - but that is the danger of OEMs - they may decide to do something .. ill advisable. Hence having it work the same way as Linux is what we should strive for. > > Thanks, > Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-04 14:51 ` Konrad Rzeszutek Wilk @ 2016-08-05 6:25 ` Haozhong Zhang 2016-08-05 13:29 ` Konrad Rzeszutek Wilk 0 siblings, 1 reply; 24+ messages in thread From: Haozhong Zhang @ 2016-08-05 6:25 UTC (permalink / raw) To: Konrad Rzeszutek Wilk Cc: Juergen Gross, Tian, Kevin, Stefano Stabellini, Wei Liu, Nakajima, Jun, George Dunlap, Andrew Cooper, Ian Jackson, xen-devel, Jan Beulich, Xiao Guangrong On 08/04/16 10:51, Konrad Rzeszutek Wilk wrote: > > > > Such a pmem namespace can be created via a userspace tool ndctl and > > > > then recognized by Linux NVDIMM driver. However, they currently only > > > > reserve space for Linux kernel's page structs. Therefore, our design > > > > need to extend both Linux NVDIMM driver and ndctl to reserve > > > > arbitrary size. > > > > > > That seems .. fragile? What if Windows or FreeBSD want to use it > > > too? > > > > AFAIK, the way used by current Linux NVDIMM driver for reservation has > > not been documented in any public specifications yet. I'll consult > > driver developers for more information. > > > > > Would this 'struct page' on on NVDIMM be generalized enough > > > to work with Linux,Xen, FreeBSD and what not? > > > > > > > No. Different operating systems may choose different data structures > > to manage NVDIMM according to their own requirements and > > consideration, so it would be hard to reach an agreement on what to > > put in a generic data structure (and make it as part of ABI?). > > Yes. As I can see different OSes having different sizes. And then > this size of 'reserved region' ends up being too small and only > some part of the NVDIMM can be used. > If the reserved area is too small for some OS, those OS may choose to put management data structures in the normal RAM in order to map all NVDIMM. Possibly, a tool can be developed to adjust the reserved size w/o breaking existing data (e.g. by moving data towards the end to leave room for reserved area). > > > > > And this ndctl is https://github.com/pmem/ndctl I presume? > > > > Yes. Sorry that I forgot to attach the URL. > > > > > > > > And how is this structure reserved? Is it a seperate namespace entry? > > > > No, it does not introduce any extra namespace entry. The current > > NVDIMM driver in Linux does the reservation in the way shown by the > > following diagram (I omit details about alignment and padding for > > simplicity): > > > > SPA SPA+4K > > | | > > V V > > +------+-----------+-- ... ---+-----...-----+ > > | | nd_pfn_sb | reserved | free to use | > > +------+-----------+-- ... ---+-----...-----+ > > |<-- nd_pfn_sb.dataoff -->| | > > | (+ necessary padding) | > > | | > > |<------------- pmem namespace ------------>| > > > > Given a pmem namespace which starts from SPA, > > AAAAh, so it is at start of the namespace! Thanks > > > 1) the driver stores a struct nd_pfn_sb at SPA+4K > > 2) the reserved area is after nd_pfn_sb > > 3) the free-to-use area is after the reserved area, and its location > > relative to SPA can be derived from nd_pfn_sb.dataoff > > 4) only the free-to-use area is exposed to a block device /dev/pmemX. > > Access to sector N of /dev/pmemX actually goes to (SPA + > > nd_pfn_sb.dataoff + N * SECT_SIZE) > > 5) nd_pfn_sb also contains a signature "NVDIMM_PFN_INFO" and a > > checksum. If the driver finds such signature and the checksum > > matches, then it knows this device contains reserved area. > > /me nods. > > And of course this nice diagram and such is going to be in > a public ABI document :-) > > > > > And QEMU knows not to access it? > > > > QEMU as a userspace program can only access /dev/pmemX and hence has > > no way to touch the reserved area. > > Rightto. > > > > > Or Xen needs to make sure _nobody_ > > > except it can access it? Which means Xen may need to know the format > > > of the ndctl structures that are laid out in the NVDIMM region? > > > > > > > Xen hypervisor relies on dom0 driver to parse the layout. At Dom0 > > boot, Dom0 NVDIMM driver reports address/size of area reserved for Xen > > to Xen hypervisor, which then unmaps the reserved area from Dom0. > > OK, so the /dev/pmem driver would consult this when somebody is mmaping > the area. But since this would be removed from the driver (unregistered) > it would report an zero size? > The current pmem driver in Linux need be modified (which I'm doing) to understand the reserved area is unmapped and should never be accessed. > Or would it "Otherwise, it will treat the pmem namespace as a raw device and > store page struct's in the normal RAM." - which means dom0 can still > access the SPA (except obviously the area that is for this reserved region)? > Yes, a raw device means there is no reserved area and the entire pmem namespace can be used for free (i.e. the free-to-use are in above diagram covers the entire pmem namespace). > ..snip.. > > > > guests. Otherwise, Xen hypervisor will recorded the reported > > > s/recorded/record/ > > > > parameters and create page_info structs in the reserved area. > > > > > > Ohh. You just blast it away? I guess it makes sense. Then what is the > > > purpose of the ndctl? Just to carve out an namespace region for this? > > > > > > > ndctl is used by, for example, a system admin to reserve space on a > > host pmem namespace. If there is already data in the namespace, ndctl > > will give a warning message and exit as long as --force option is not > > given. However, if --force is present, ndctl will break the existing > > data. > > > > > And what if there is something there from previous OS (say Linux)? > > > Just blast it away? But could Linux depend on this containing some > > > persistent information? Or does it also blast it away? > > > > > > > As above, if linux driver detects the signature "NVDIMM_PFN_INFO" and > > a matched checksum, it will know it's safe to write to the reserved > > area. Otherwise, it will treat the pmem namespace as a raw device and > > store page struct's in the normal RAM. > > OK, so my worry is that we will have a divergence. Which is that > the system admin creates this under ndctl v0, boots Xen uses it. > Then moves the NVDIMM to another machine which has ndctl v1 and > he/she boots in Linux. > > Linux gets all confused b/c the region has something it can't understand > and the user is very angry. > > So it sounds like the size the ndctl reserves MUST be baked in an ABI > and made sure to expand if needed. > ndctl is a management tool which passes all its requests to the driver via sysfs, so the compatibility across different versions of Linux would actual be introduced by the different versions of drivers. All newer versions of drivers should provide backwards compatibility to previous versions (which is the current drivers' behavior). However, the forwards compatibility is hard to preserved, e.g. - an old version w/o reserved area support (e.g. the one in linux kernel 4.2) recognizes a pmem namespace w/ reserved area as a raw device and may write to the reserved area. If it's a xen reserved area and the driver is in dom0, the dom0 kernel will crash. - the same crash would happen if an old version driver w/ reserved area support but xen reserved area support (e.g. the one in linux kernel 4.7) is used for a pmem namespace w/ xen reserved area. For the cross-OS compatibility, there is an effort to standardize the reservation. In the meantime, only linux is capable to handle such pmem namespaces with reserved area. > ..snip.. > > > This "balloon out" is interesting. You are effectively telling Linux > > > to ignore a certain range of 'struct page_info', so that if somebody > > > uses /sys/debug/kernel/page_walk it won't blow up? (As the kerne > > > can't read the struct page_info anymore). > > > > > > How would you do this? Simulate an NVDIMM unplug? > > > > s/page_info/page/ (struct page for linux, struct page_info for xen) > > > > As in Jan's comment, "balloon out" is a confusing name here. > > Basically, it's to remove the reserved area from some resource struct > > in nvdimm driver to avoid it's accessed out of the driver via the > > resource struct. And the nvdimm driver does not map the reserved area, > > so I think it cannot be touched via page_walk. > > OK, I need to read the Linux code more to make sure I am > not missing something. > > Basically the question that keeps revolving in my head is: > > Why is this even neccessary? > > Let me expand - it feels like (and I think I am missing something > here) that we are crippling the Linux driver so that it won't > break - b/c if it tried to access the 'strut page_info' in this > reserved region it would crash. So we eliminate that, and make > the driver believe the region exists (is reserved), but it can't > use it. And instead use the normal RAM pages to keep track > of the NVDIMM SPAs. > > Or perhaps not keep track at all and just treat the whole > NVDIMM as opaque MMIO that is inaccessible? > If we trust the driver in dom0 kernel always does correct things (and we can trust it, right?), no crash will happen. However, as Jan comment (https://lists.xenproject.org/archives/html/xen-devel/2016-08/msg00433.html): | Right now Dom0 isn't allowed to access any memory in use by Xen | (and not explicitly shared), and I don't think we should deviate | from that model for pmem. xen hypervisor must explicitly disallow dom0 from accessing the reserved area. > But how will that work if there is a DAX filesystem on it? > The ext4 needs some mechanism to access the files that are there. > (Otherwise you couldn't use the fiemap ioctl to find the SPAs). > No, the file system does not touch the reserved area. If a reserved area exists, the start SPA of /dev/pmem0 reported via sysfs is the start SPA of the reserved area, so fiemap can still work. > [see below] > > > > > > > > But if you do that how will SMART tools work anymore? And > > > who would do the _DSM checks on the health of the NVDIMM? > > > > > > > A userspace SMART tool cannot access the reserved area, so I think it > > can still work. I haven't look at the implementation of any SMART > > tools for NVDIMM, but I guess they would finally call the driver to > > evaluate the ARS _DSM which reports the bad blocks. As long as the > > driver does not return the bad blocks in the reserved area to SMART > > tools (which I suppose to be handled by driver itself), SMART tools > > should work fine. > > > > > /me scratches his head. Perhaps the answers are later in this > > > design.. > > So I think I figured out the issue here!! > > You just want to have the Linux kernel driver to use normal RAM > pages to keep track of the NVDIMM SPA ranges. Yes, this is what the current driver does for a raw device. > As in treat the NVDIMM as if it is normal RAM? If you are talking about the location of page struct, then yes. The page struct's for NVDIMM is put in the normal RAM just like the page struct's for the normal RAM. But NVDIMM can never, for example, be allocated via the kernel memory allocator (buddy/slab/etc.). > > [Or is Linux treating this area as MMIO region (in wihch case it does not > need struct page_info)??] > > And then Xen can use this reserved region for its own > purpose! > > Perhaps then the section that explains this 'reserved region' could > say something along: > > "We need to keep track of the SPAs. The guest NVDIMM 'file' > on the NVDIMM may be in the worst case be randomly and in descending > discontingous order (say from the end of the NVDIMM), we need > to keep track of each of the SPAs. The reason is that we need > the SPAs when we populate the guest EPT. > > As such we can store the guest SPA in memory (linear array?) > or red-black tree, or any other - but all of them will consume > "normal RAM". And with sufficient large enough NVDIMM we may > not have enough 'normal RAM' to store this. > > Also we only need to know these SPAs during guest creation, > destruction, ballooning, etc - hence we may store them on the > NVDIMM itself. Fortunatly for us the ndctl and Linux are > available which carve out right after the namespace region (128kb) > and 'reserved region' which the OS can use to store its > struct page_info to cover the full range of the NVDIMM. > > The complexity in this is that: > - We MUST make sure Linux does not try to use it while > we use it. > - That the size of this 'reserved region' is sufficiently > large for our 'struct page_info' structure. > - The layout has an ABI baked. > - Linux fs'es with DAX support MUST be able mlock these SPA > regions (so that nobody tries to remove the 'file' while > a guest is using it). I need to check whether linux currently does this. > - Linus fs'es with DAX support MUST be able to resize the > 'file', hereby using more of the SPAs and rewritting the > properties of the file on DAX (which should then cause an > memory hotplug ACPI in the guest treating the new size of > the file as new NFIT region?) > Currently my plan is to disallow such resizing and possibly other changes out of guest if it's being used by guest (akin to disk) in the first implementation. It's mostly for simplicity and we can add it in future. For hotplug, we can pass another file as a new pmem namespace to guest. > " > > I think that covers it? > ..snip.. > > > > Our design takes the following method to avoid and detect collisions. > > > > 1) The data layout of area where QEMU copies its NFIT and ACPI > > > > namespace devices is organized as below: > > > > > > Why can't this be expressed in XenStore? > > > > > > You could have /local/domain/domid/hvmloader/dm-acpi/<name>/{address,length, type} > > > ? > > > > > > > If XenStore can be used, then it could save some guest memory. > > It is also easier than relaying on the format of a blob in memory. > > > > This is a general mechanism to pass ACPI which and is not limited to > > NVDIMM, so it means QEMU may pass a lot of entries. I'm not sure if > > XenStore is still a proper place when the number is large. Maybe we > > should put an upper limit for the number of entries. > > Why put a limit on it? It should easily handle thousands of <name>. > And the only attributes you have under <name> are just address, > length and type. > OK, if it's not a problem, I will use xenstore to pass those information. > .. snip.. > > > > 4.3.2 Emulating Guest _DSM > > > > > > > > Our design leaves the emulation of guest _DSM to QEMU. Just as what > > > > it does with KVM, QEMU registers the _DSM buffer as MMIO region with > > > > Xen and then all guest evaluations of _DSM are trapped and emulated > > > > by QEMU. > > > > > > Sweet! > > > > > > So one question that I am not if it has been answered, with the > > > 'struct page_info' being removed from the dom0 how will OEM _DSM method > > > operation? For example some of the AML code may asking to poke > > > at specific SPAs, but how will Linux do this properly without > > > 'struct page_info' be available? > > > > > > > (s/page_info/page/) > > > > The current Intel NVDIMM driver in Linux does not evaluate any OEM > > _DSM method, so I'm not sure whether the kernel has to access a NVDIMM > > page during evaluating _DSM. > > > > The most close one in my mind, though not an OEM _DSM, is function 1 > > of ARS _DSM, which requires inputs of a start SPA and a length in > > bytes. After kernel gives the inputs, the scrubbing of the specified > > area is done by the hardware and does not requires any mappings in OS. > > <nods> > > > > Any example of such OEM _DSM methods? > > I can't think of any right now - but that is the danger of OEMs - they > may decide to do something .. ill advisable. Hence having it work > the same way as Linux is what we should strive for. > I see: though the evaluation itself does not use any software maintained mappings, the driver may use when handling the result of evaluation, e.g. ARS _DSM reports bad blocks in the reserved area and the driver may then have to access the reserved area (though this could never happen in the current kernel because the driver does ARS before reservation). Currently there is no OEM _DSM support in linux kernel, so I cannot think of any solution. However, if such an OEM _DSM comes, we may add xen specific handling to the driver or introduce a way in nvdimm driver framework to avoid accessing the reserved area in certain circumstances (e.g. when used in xen dom0). Thanks, Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [RFC Design Doc v2] Add vNVDIMM support for Xen 2016-08-05 6:25 ` Haozhong Zhang @ 2016-08-05 13:29 ` Konrad Rzeszutek Wilk 0 siblings, 0 replies; 24+ messages in thread From: Konrad Rzeszutek Wilk @ 2016-08-05 13:29 UTC (permalink / raw) To: xen-devel, Jan Beulich, George Dunlap, Andrew Cooper, Ian Jackson, Stefano Stabellini, Juergen Gross, Wei Liu, Tian, Kevin, Xiao Guangrong, Nakajima, Jun > > > As above, if linux driver detects the signature "NVDIMM_PFN_INFO" and > > > a matched checksum, it will know it's safe to write to the reserved > > > area. Otherwise, it will treat the pmem namespace as a raw device and > > > store page struct's in the normal RAM. > > > > OK, so my worry is that we will have a divergence. Which is that > > the system admin creates this under ndctl v0, boots Xen uses it. > > Then moves the NVDIMM to another machine which has ndctl v1 and > > he/she boots in Linux. > > > > Linux gets all confused b/c the region has something it can't understand > > and the user is very angry. > > > > So it sounds like the size the ndctl reserves MUST be baked in an ABI > > and made sure to expand if needed. > > > > ndctl is a management tool which passes all its requests to the driver > via sysfs, so the compatibility across different versions of Linux > would actual be introduced by the different versions of drivers. > > All newer versions of drivers should provide backwards compatibility > to previous versions (which is the current drivers' > behavior). However, the forwards compatibility is hard to preserved, > e.g. > - an old version w/o reserved area support (e.g. the one in linux > kernel 4.2) recognizes a pmem namespace w/ reserved area as a raw > device and may write to the reserved area. If it's a xen reserved > area and the driver is in dom0, the dom0 kernel will crash. Yikes! > > - the same crash would happen if an old version driver w/ reserved > area support but xen reserved area support (e.g. the one in linux > kernel 4.7) is used for a pmem namespace w/ xen reserved area. > > For the cross-OS compatibility, there is an effort to standardize the > reservation. In the meantime, only linux is capable to handle such > pmem namespaces with reserved area. It may be good to mention these difficulties you enumerated in the design doc so if somebody does end up in this position and they search for it - they could find a reference. > > > ..snip.. > > > > This "balloon out" is interesting. You are effectively telling Linux > > > > to ignore a certain range of 'struct page_info', so that if somebody > > > > uses /sys/debug/kernel/page_walk it won't blow up? (As the kerne > > > > can't read the struct page_info anymore). > > > > > > > > How would you do this? Simulate an NVDIMM unplug? > > > > > > s/page_info/page/ (struct page for linux, struct page_info for xen) > > > > > > As in Jan's comment, "balloon out" is a confusing name here. > > > Basically, it's to remove the reserved area from some resource struct > > > in nvdimm driver to avoid it's accessed out of the driver via the > > > resource struct. And the nvdimm driver does not map the reserved area, > > > so I think it cannot be touched via page_walk. > > > > OK, I need to read the Linux code more to make sure I am > > not missing something. > > > > Basically the question that keeps revolving in my head is: > > > > Why is this even neccessary? > > > > Let me expand - it feels like (and I think I am missing something > > here) that we are crippling the Linux driver so that it won't > > break - b/c if it tried to access the 'strut page_info' in this > > reserved region it would crash. So we eliminate that, and make > > the driver believe the region exists (is reserved), but it can't > > use it. And instead use the normal RAM pages to keep track > > of the NVDIMM SPAs. > > > > Or perhaps not keep track at all and just treat the whole > > NVDIMM as opaque MMIO that is inaccessible? > > > > If we trust the driver in dom0 kernel always does correct things (and > we can trust it, right?), no crash will happen. However, as Jan > comment (https://lists.xenproject.org/archives/html/xen-devel/2016-08/msg00433.html): > > | Right now Dom0 isn't allowed to access any memory in use by Xen > | (and not explicitly shared), and I don't think we should deviate > | from that model for pmem. > > xen hypervisor must explicitly disallow dom0 from accessing the > reserved area. Right. > > > But how will that work if there is a DAX filesystem on it? > > The ext4 needs some mechanism to access the files that are there. > > (Otherwise you couldn't use the fiemap ioctl to find the SPAs). > > > > No, the file system does not touch the reserved area. If a reserved Ah, OK! > area exists, the start SPA of /dev/pmem0 reported via sysfs is the > start SPA of the reserved area, so fiemap can still work. > > > [see below] > > > > > > > > > > > But if you do that how will SMART tools work anymore? And > > > > who would do the _DSM checks on the health of the NVDIMM? > > > > > > > > > > A userspace SMART tool cannot access the reserved area, so I think it > > > can still work. I haven't look at the implementation of any SMART > > > tools for NVDIMM, but I guess they would finally call the driver to > > > evaluate the ARS _DSM which reports the bad blocks. As long as the > > > driver does not return the bad blocks in the reserved area to SMART > > > tools (which I suppose to be handled by driver itself), SMART tools > > > should work fine. > > > > > > > /me scratches his head. Perhaps the answers are later in this > > > > design.. > > > > So I think I figured out the issue here!! > > > > You just want to have the Linux kernel driver to use normal RAM > > pages to keep track of the NVDIMM SPA ranges. > > Yes, this is what the current driver does for a raw device. > > > As in treat the NVDIMM as if it is normal RAM? > > If you are talking about the location of page struct, then yes. The > page struct's for NVDIMM is put in the normal RAM just like the page > struct's for the normal RAM. But NVDIMM can never, for example, be > allocated via the kernel memory allocator (buddy/slab/etc.). Right. I was thinking of page struct location. > > > > > [Or is Linux treating this area as MMIO region (in wihch case it does not > > need struct page_info)??] > > > > And then Xen can use this reserved region for its own > > purpose! > > > > Perhaps then the section that explains this 'reserved region' could > > say something along: > > > > "We need to keep track of the SPAs. The guest NVDIMM 'file' > > on the NVDIMM may be in the worst case be randomly and in descending > > discontingous order (say from the end of the NVDIMM), we need > > to keep track of each of the SPAs. The reason is that we need > > the SPAs when we populate the guest EPT. > > > > As such we can store the guest SPA in memory (linear array?) > > or red-black tree, or any other - but all of them will consume > > "normal RAM". And with sufficient large enough NVDIMM we may > > not have enough 'normal RAM' to store this. > > > > Also we only need to know these SPAs during guest creation, > > destruction, ballooning, etc - hence we may store them on the > > NVDIMM itself. Fortunatly for us the ndctl and Linux are > > available which carve out right after the namespace region (128kb) > > and 'reserved region' which the OS can use to store its > > struct page_info to cover the full range of the NVDIMM. > > > > The complexity in this is that: > > - We MUST make sure Linux does not try to use it while > > we use it. > > - That the size of this 'reserved region' is sufficiently > > large for our 'struct page_info' structure. > > - The layout has an ABI baked. > > - Linux fs'es with DAX support MUST be able mlock these SPA > > regions (so that nobody tries to remove the 'file' while > > a guest is using it). > > I need to check whether linux currently does this. > > > - Linus fs'es with DAX support MUST be able to resize the > > 'file', hereby using more of the SPAs and rewritting the > > properties of the file on DAX (which should then cause an > > memory hotplug ACPI in the guest treating the new size of > > the file as new NFIT region?) > > > > Currently my plan is to disallow such resizing and possibly other > changes out of guest if it's being used by guest (akin to disk) in the > first implementation. It's mostly for simplicity and we can add it in > future. For hotplug, we can pass another file as a new pmem namespace > to guest. > > > " > > > > I think that covers it? > > ..snip.. > > > > > Our design takes the following method to avoid and detect collisions. > > > > > 1) The data layout of area where QEMU copies its NFIT and ACPI > > > > > namespace devices is organized as below: > > > > > > > > Why can't this be expressed in XenStore? > > > > > > > > You could have /local/domain/domid/hvmloader/dm-acpi/<name>/{address,length, type} > > > > ? > > > > > > > > > > If XenStore can be used, then it could save some guest memory. > > > > It is also easier than relaying on the format of a blob in memory. > > > > > > This is a general mechanism to pass ACPI which and is not limited to > > > NVDIMM, so it means QEMU may pass a lot of entries. I'm not sure if > > > XenStore is still a proper place when the number is large. Maybe we > > > should put an upper limit for the number of entries. > > > > Why put a limit on it? It should easily handle thousands of <name>. > > And the only attributes you have under <name> are just address, > > length and type. > > > > OK, if it's not a problem, I will use xenstore to pass those > information. > > > .. snip.. > > > > > 4.3.2 Emulating Guest _DSM > > > > > > > > > > Our design leaves the emulation of guest _DSM to QEMU. Just as what > > > > > it does with KVM, QEMU registers the _DSM buffer as MMIO region with > > > > > Xen and then all guest evaluations of _DSM are trapped and emulated > > > > > by QEMU. > > > > > > > > Sweet! > > > > > > > > So one question that I am not if it has been answered, with the > > > > 'struct page_info' being removed from the dom0 how will OEM _DSM method > > > > operation? For example some of the AML code may asking to poke > > > > at specific SPAs, but how will Linux do this properly without > > > > 'struct page_info' be available? > > > > > > > > > > (s/page_info/page/) > > > > > > The current Intel NVDIMM driver in Linux does not evaluate any OEM > > > _DSM method, so I'm not sure whether the kernel has to access a NVDIMM > > > page during evaluating _DSM. > > > > > > The most close one in my mind, though not an OEM _DSM, is function 1 > > > of ARS _DSM, which requires inputs of a start SPA and a length in > > > bytes. After kernel gives the inputs, the scrubbing of the specified > > > area is done by the hardware and does not requires any mappings in OS. > > > > <nods> > > > > > > Any example of such OEM _DSM methods? > > > > I can't think of any right now - but that is the danger of OEMs - they > > may decide to do something .. ill advisable. Hence having it work > > the same way as Linux is what we should strive for. > > > > I see: though the evaluation itself does not use any software > maintained mappings, the driver may use when handling the result of > evaluation, e.g. ARS _DSM reports bad blocks in the reserved area and > the driver may then have to access the reserved area (though this > could never happen in the current kernel because the driver does ARS > before reservation). > > Currently there is no OEM _DSM support in linux kernel, so I cannot > think of any solution. However, if such an OEM _DSM comes, we may add > xen specific handling to the driver or introduce a way in nvdimm > driver framework to avoid accessing the reserved area in certain > circumstances (e.g. when used in xen dom0). Thanks! > > Thanks, > Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel ^ permalink raw reply [flat|nested] 24+ messages in thread
end of thread, other threads:[~2016-08-05 13:29 UTC | newest] Thread overview: 24+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2016-07-18 0:29 [RFC Design Doc v2] Add vNVDIMM support for Xen Haozhong Zhang 2016-07-18 8:36 ` Tian, Kevin 2016-07-18 9:01 ` Zhang, Haozhong 2016-07-19 0:58 ` Tian, Kevin 2016-07-19 2:10 ` Zhang, Haozhong 2016-07-19 1:57 ` Bob Liu 2016-07-19 2:40 ` Haozhong Zhang 2016-08-02 14:46 ` Jan Beulich 2016-08-03 6:54 ` Haozhong Zhang 2016-08-03 8:45 ` Jan Beulich 2016-08-03 9:37 ` Haozhong Zhang 2016-08-03 9:47 ` Jan Beulich 2016-08-03 10:08 ` Haozhong Zhang 2016-08-03 10:18 ` Jan Beulich 2016-08-03 21:25 ` Konrad Rzeszutek Wilk 2016-08-03 23:16 ` Konrad Rzeszutek Wilk 2016-08-04 1:51 ` Haozhong Zhang 2016-08-04 8:52 ` Haozhong Zhang 2016-08-04 9:25 ` Jan Beulich 2016-08-04 9:35 ` Haozhong Zhang 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 2016-08-04 14:51 ` Konrad Rzeszutek Wilk 2016-08-05 6:25 ` Haozhong Zhang 2016-08-05 13:29 ` Konrad Rzeszutek Wilk
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).