* Introduce Documentation/filesystems/famfs.rst into the Documentation tree and filesystems index * Add famfs famfs.rst to the filesystems doc index * Add famfs' ioctl opcodes to ioctl-number.rst * Update MAINTAINERS FILE Signed-off-by: John Groves <john@xxxxxxxxxx> --- Documentation/filesystems/famfs.rst | 135 ++++++++++++++++++ Documentation/filesystems/index.rst | 1 + .../userspace-api/ioctl/ioctl-number.rst | 1 + MAINTAINERS | 9 ++ 4 files changed, 146 insertions(+) create mode 100644 Documentation/filesystems/famfs.rst diff --git a/Documentation/filesystems/famfs.rst b/Documentation/filesystems/famfs.rst new file mode 100644 index 000000000000..792785598d6a --- /dev/null +++ b/Documentation/filesystems/famfs.rst @@ -0,0 +1,135 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _famfs_index: + +================================================================== +famfs: The kernel component of the famfs shared memory file system +================================================================== + +- Copyright (C) 2024 Micron Technology, Inc. + +Introduction +============ +Compute Express Link (CXL) provides a mechanism for disaggregated or +fabric-attached memory (FAM). This creates opportunities for data sharing; +clustered apps that would otherwise have to shard or replicate data can +share one copy in disaggregated memory. + +Famfs, which is not CXL-specific in any way, provides a mechanism for +multiple hosts to use data in shared memory, by giving it a file system +interface. With famfs, any app that understands files (which is almost +all apps) can access data sets in shared memory. Although famfs +supports read and write, the real point is to support mmap, which +provides direct (dax) access to the memory - either writable or read-only. + +Shared memory can pose complex coherency and synchronization issues, but +there are also simple cases. Two simple and eminently useful patterns that +occur frequently in data analytics and AI are: + +* Serial Sharing - Only one host or process at a time has access to a file +* Read-only Sharing - Multiple hosts or processes share read-only access + to a file + +The famfs kernel file system is part of the famfs framework; User space +components [1] handle metadata allocation and distribution, and direct the +famfs kernel module to instantiate files that map to specific memory. + +The famfs framework manages coherency of its own metadata and structures, +but does not attempt to manage coherency for applications. + +Famfs also provides data isolation between files. That is, even though +the host has access to an entire memory "device" (as a dax device), apps +cannot write to memory for which the file is read-only, and mapping one +file provides isolation from the memory of all other files. This is pretty +basic, but some experimental shared memory usage patterns provide no such +isolation. + +Principles of Operation +======================= + +Without its user space components, the famfs kernel module doesn't do +anything useful. The user space components maintain superblocks and +metadata logs, and use the famfs kernel component to provide a file system +view of shared memory across multiple hosts. + +Each host has an independent instance of the famfs kernel module. After +mount, files are not visible until the user space component instantiates +them (normally by playing the famfs metadata log). + +Once instantiated, files on each host can point to the same shared memory, +but in-memory metadata (inodes, etc.) is ephemeral on each host that has a +famfs instance mounted. Like ramfs, the famfs in-kernel file system has no +backing store for metadata modifications. If metadata mutations are ever +persisted, that must be done by the user space components. However, +mutations to file data are saved to the shared memory - subject to write +permission and processor cache behavior. + + +Famfs is Not a Conventional File System +--------------------------------------- + +Famfs files can be accessed by conventional means, but there are +limitations. The kernel component of famfs is not involved in the +allocation of backing memory for files at all; the famfs user space +creates files and passes the allocation extent lists into the kernel via +the per-file FAMFSIOC_MAP_CREATE ioctl. A file that lacks this metadata is +treated as invalid by the famfs kernel module. As a practical matter files +must be created via the famfs library or cli, but they can be consumed as +if they were conventional files. + +Famfs differs in some important ways from conventional file systems: + +* Files must be pre-allocated by the famfs framework; Allocation is never + performed on (or after) write. +* Any operation that changes a file's size is considered to put the file + in an invalid state, disabling access to the data. It may be possible to + revisit this in the future. (Typically the famfs user space can restore + files to a valid state by replaying the famfs metadata log.) + +Famfs exists to apply the existing file system abstractions to shared +memory so applications and workflows can more easily adapt to an +environment with disaggregated shared memory. + +Memory Error Handling +===================== + +Possible memory errors include timeouts, poison and unexpected +reconfiguration of an underlying dax device. In all of these cases, famfs +receives a call via its iomap_ops->notify_failure() function. If any +memory errors have been detected, Access to the affected famfs mount is +disabled to avoid further errors or corruption. Testing indicates that +a famfs instance that has encountered errors can be unmounted cleanly, but +Repairing memory errors or corruption is outside the scope of famfs. + +Key Requirements +================ + +The primary requirements for famfs are: + +1. Must support a file system abstraction backed by sharable dax memory +2. Files must efficiently handle VMA faults +3. Must support metadata distribution in a sharable way +4. Must handle clients with a stale copy of metadata + +The famfs kernel component takes care of 1-2 above by caching each file's +mapping metadata in the kernel. + +Requirements 3 and 4 are handled by the user space components, and are +largely orthogonal to the functionality of the famfs kernel module. + +Requirements 3 and 4 cannot be met by conventional fs-dax file systems +(e.g. xfs and ext4) because they use write-back metadata; it is not valid +to mount such a file system on two hosts from the same in-memory image. + + +Famfs Usage +=========== + +Famfs usage is documented at [1]. + + +References +========== + +- [1] Famfs user space repository and documentation + https://github.com/cxl-micron-reskit/famfs diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 1f9b4c905a6a..0fe2c70a106f 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -87,6 +87,7 @@ Documentation for filesystem implementations. ext3 ext4/index f2fs + famfs gfs2 gfs2-uevents gfs2-glocks diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index c472423412bf..ac407802cf10 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -289,6 +289,7 @@ Code Seq# Include File Comments 'u' 00-1F linux/smb_fs.h gone 'u' 20-3F linux/uvcvideo.h USB video class host driver 'u' 40-4f linux/udmabuf.h userspace dma-buf misc device +'u' 50-5F linux/famfs_ioctl.h famfs shared memory file system 'v' 00-1F linux/ext2_fs.h conflict! 'v' 00-1F linux/fs.h conflict! 'v' 00-0F linux/sonypi.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index ebf03f5f0619..3f2d847dcf01 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8180,6 +8180,15 @@ F: Documentation/networking/failover.rst F: include/net/failover.h F: net/core/failover.c +FAMFS +M: John Groves <jgroves@xxxxxxxxxx> +M: John Groves <John@xxxxxxxxxx> +M: John Groves <john@xxxxxxxxxxxxxx> +L: linux-cxl@xxxxxxxxxxxxxxx +L: linux-fsdevel@xxxxxxxxxxxxxxx +S: Supported +F: Documentation/filesystems/famfs.rst + FANOTIFY M: Jan Kara <jack@xxxxxxx> R: Amir Goldstein <amir73il@xxxxxxxxx> -- 2.43.0
