Re: [PATCH v3 01/22] mm: Add msharefs filesystem

[Anthony Yznaga <anthony.yznaga@xxxxxxxxxx>]

On 9/8/25 11:29 AM, Liam R. Howlett wrote:
> * Anthony Yznaga <anthony.yznaga@xxxxxxxxxx> [250819 21:04]:
> > From: Khalid Aziz <khalid@xxxxxxxxxx>
> >
> > Add a pseudo filesystem that contains files and page table sharing
> > information that enables processes to share page table entries.
> > This patch adds the basic filesystem that can be mounted, a
> > CONFIG_MSHARE option to enable the feature, and documentation.
> >
> > Signed-off-by: Khalid Aziz <khalid@xxxxxxxxxx>
> > Signed-off-by: Anthony Yznaga <anthony.yznaga@xxxxxxxxxx>
> > ---
> >   Documentation/filesystems/index.rst    |  1 +
> >   Documentation/filesystems/msharefs.rst | 96 +++++++++++++++++++++++++
> >   include/uapi/linux/magic.h             |  1 +
> >   mm/Kconfig                             | 11 +++
> >   mm/Makefile                            |  4 ++
> >   mm/mshare.c                            | 97 ++++++++++++++++++++++++++
> >   6 files changed, 210 insertions(+)
> >   create mode 100644 Documentation/filesystems/msharefs.rst
> >   create mode 100644 mm/mshare.c
> >
> > diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
> > index 11a599387266..dcd6605eb228 100644
> > --- a/Documentation/filesystems/index.rst
> > +++ b/Documentation/filesystems/index.rst
> > @@ -102,6 +102,7 @@ Documentation for filesystem implementations.
> >      fuse-passthrough
> >      inotify
> >      isofs
> > +   msharefs
> >      nilfs2
> >      nfs/index
> >      ntfs3
> > diff --git a/Documentation/filesystems/msharefs.rst b/Documentation/filesystems/msharefs.rst
> > new file mode 100644
> > index 000000000000..3e5b7d531821
> > --- /dev/null
> > +++ b/Documentation/filesystems/msharefs.rst
> > @@ -0,0 +1,96 @@
> > +.. SPDX-License-Identifier: GPL-2.0
> > +
> > +=====================================================
> > +Msharefs - A filesystem to support shared page tables
> > +=====================================================
> > +
> > +What is msharefs?
> > +-----------------
> > +
> > +msharefs is a pseudo filesystem that allows multiple processes to
> > +share page table entries for shared pages. To enable support for
> > +msharefs the kernel must be compiled with CONFIG_MSHARE set.
> > +
> > +msharefs is typically mounted like this::
> > +
> > +	mount -t msharefs none /sys/fs/mshare
> > +
> > +A file created on msharefs creates a new shared region where all
> > +processes mapping that region will map it using shared page table
> > +entries. Once the size of the region has been established via
> > +ftruncate() or fallocate(), the region can be mapped into processes
> > +and ioctls used to map and unmap objects within it. Note that an
> > +msharefs file is a control file and accessing mapped objects within
> > +a shared region through read or write of the file is not permitted.
> > +
> > +How to use mshare
> > +-----------------
> > +
> > +Here are the basic steps for using mshare:
> > +
> > +  1. Mount msharefs on /sys/fs/mshare::
> > +
> > +	mount -t msharefs msharefs /sys/fs/mshare
> > +
> > +  2. mshare regions have alignment and size requirements. Start
> > +     address for the region must be aligned to an address boundary and
> > +     be a multiple of fixed size. This alignment and size requirement
> > +     can be obtained by reading the file ``/sys/fs/mshare/mshare_info``
> > +     which returns a number in text format. mshare regions must be
> > +     aligned to this boundary and be a multiple of this size.
> > +
> > +  3. For the process creating an mshare region:
> > +
> > +    a. Create a file on /sys/fs/mshare, for example::
> > +
> > +        fd = open("/sys/fs/mshare/shareme",
> > +                        O_RDWR|O_CREAT|O_EXCL, 0600);
> > +
> > +    b. Establish the size of the region::
> > +
> > +        fallocate(fd, 0, 0, BUF_SIZE);
> > +
> > +      or::
> > +
> > +        ftruncate(fd, BUF_SIZE);
> > +
> > +    c. Map some memory in the region::
> > +
> > +	struct mshare_create mcreate;
> > +
> > +	mcreate.region_offset = 0;
> > +	mcreate.size = BUF_SIZE;
> > +	mcreate.offset = 0;
> > +	mcreate.prot = PROT_READ | PROT_WRITE;
> > +	mcreate.flags = MAP_ANONYMOUS | MAP_SHARED | MAP_FIXED;
> > +	mcreate.fd = -1;
> > +
> > +	ioctl(fd, MSHAREFS_CREATE_MAPPING, &mcreate);
> > +
> > +    d. Map the mshare region into the process::
> > +
> > +	mmap(NULL, BUF_SIZE,
> > +		PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
> > +
> > +    e. Write and read to mshared region normally.
> > +
> > +
> > +  4. For processes attaching an mshare region:
> > +
> > +    a. Open the msharefs file, for example::
> > +
> > +	fd = open("/sys/fs/mshare/shareme", O_RDWR);
> > +
> > +    b. Get the size of the mshare region from the file::
> > +
> > +        fstat(fd, &sb);
> > +        mshare_size = sb.st_size;
> > +
> > +    c. Map the mshare region into the process::
> > +
> > +	mmap(NULL, mshare_size,
> > +		PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
> > +
> > +  5. To delete the mshare region::
> > +
> > +		unlink("/sys/fs/mshare/shareme");
> > diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
> > index bb575f3ab45e..e53dd6063cba 100644
> > --- a/include/uapi/linux/magic.h
> > +++ b/include/uapi/linux/magic.h
> > @@ -103,5 +103,6 @@
> >   #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
> >   #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
> >   #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
> > +#define MSHARE_MAGIC		0x4d534852	/* "MSHR" */
> >   
> >   #endif /* __LINUX_MAGIC_H__ */
> > diff --git a/mm/Kconfig b/mm/Kconfig
> > index 4108bcd96784..8b50e9785729 100644
> > --- a/mm/Kconfig
> > +++ b/mm/Kconfig
> > @@ -1400,6 +1400,17 @@ config PT_RECLAIM
> >   config FIND_NORMAL_PAGE
> >   	def_bool n
> >   
> > +config MSHARE
> > +	bool "Mshare"
> > +	depends on MMU
> > +	help
> > +	  Enable msharefs: A pseudo filesystem that allows multiple processes
> > +	  to share kernel resources for mapping shared pages. A file created on
> > +	  msharefs represents a shared region where all processes mapping that
> > +	  region will map objects within it with shared page table entries and
> > +	  VMAs. Ioctls are used to configure and map objects into the shared
> > +	  region.
> > +
> >   source "mm/damon/Kconfig"
> >   
> >   endmenu
> > diff --git a/mm/Makefile b/mm/Makefile
> > index ef54aa615d9d..4af111b29c68 100644
> > --- a/mm/Makefile
> > +++ b/mm/Makefile
> > @@ -48,6 +48,10 @@ ifdef CONFIG_64BIT
> >   mmu-$(CONFIG_MMU)	+= mseal.o
> >   endif
> >   
> > +ifdef CONFIG_MSHARE
> > +mmu-$(CONFIG_MMU)	+= mshare.o
> > +endif
> > +
> >   obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
> >   			   maccess.o page-writeback.o folio-compat.o \
> >   			   readahead.o swap.o truncate.o vmscan.o shrinker.o \
> > diff --git a/mm/mshare.c b/mm/mshare.c
> > new file mode 100644
> > index 000000000000..f703af49ec81
> > --- /dev/null
> > +++ b/mm/mshare.c
> > @@ -0,0 +1,97 @@
> > +// SPDX-License-Identifier: GPL-2.0-only
> > +/*
> > + * Enable cooperating processes to share page table between
> > + * them to reduce the extra memory consumed by multiple copies
> > + * of page tables.
> > + *
> > + * This code adds an in-memory filesystem - msharefs.
> > + * msharefs is used to manage page table sharing
> > + *
> > + *
> > + * Copyright (C) 2024 Oracle Corp. All rights reserved.
> > + * Author:	Khalid Aziz <khalid@xxxxxxxxxx>
>
> Probably needs a new year or year range and another author?

Yes. I'll make sure the next series is updated.

> > + *
> > + */
> > +
> > +#include <linux/fs.h>
> > +#include <linux/fs_context.h>
> > +#include <uapi/linux/magic.h>
> > +
> > +static const struct file_operations msharefs_file_operations = {
> > +	.open			= simple_open,
> > +};
> > +
> > +static const struct super_operations mshare_s_ops = {
> > +	.statfs		= simple_statfs,
> > +};
> > +
> > +static int
> > +msharefs_fill_super(struct super_block *sb, struct fs_context *fc)
> > +{
> > +	struct inode *inode;
> > +
> > +	sb->s_blocksize		= PAGE_SIZE;
> > +	sb->s_blocksize_bits	= PAGE_SHIFT;
> > +	sb->s_maxbytes		= MAX_LFS_FILESIZE;
> > +	sb->s_magic		= MSHARE_MAGIC;
> > +	sb->s_op		= &mshare_s_ops;
> > +	sb->s_time_gran		= 1;
> > +
> > +	inode = new_inode(sb);
> > +	if (!inode)
> > +		return -ENOMEM;
> > +
> > +	inode->i_ino = 1;
> > +	inode->i_mode = S_IFDIR | 0777;
> > +	simple_inode_init_ts(inode);
> > +	inode->i_op = &simple_dir_inode_operations;
> > +	inode->i_fop = &simple_dir_operations;
> > +	set_nlink(inode, 2);
> > +
> > +	sb->s_root = d_make_root(inode);
> > +	if (!sb->s_root)
> > +		return -ENOMEM;
>
> I don't know the recovery here, but what about inode and inode link
> count?

If d_make_root() returns NULL it will have called iput_final(inode) 
which takes care of freeing the inode.

> > +
> > +	return 0;
> > +}
> > +
> > +static int
> > +msharefs_get_tree(struct fs_context *fc)
> > +{
> > +	return get_tree_nodev(fc, msharefs_fill_super);
> > +}
> > +
> > +static const struct fs_context_operations msharefs_context_ops = {
> > +	.get_tree	= msharefs_get_tree,
> > +};
> > +
> > +static int
> > +mshare_init_fs_context(struct fs_context *fc)
> > +{
> > +	fc->ops = &msharefs_context_ops;
> > +	return 0;
> > +}
> > +
> > +static struct file_system_type mshare_fs = {
> > +	.name			= "msharefs",
> > +	.init_fs_context	= mshare_init_fs_context,
> > +	.kill_sb		= kill_litter_super,
> > +};
> > +
> > +static int __init
> > +mshare_init(void)
> > +{
> > +	int ret;
> > +
> > +	ret = sysfs_create_mount_point(fs_kobj, "mshare");
> > +	if (ret)
> > +		return ret;
> > +
> > +	ret = register_filesystem(&mshare_fs);
> > +	if (ret)
> > +		sysfs_remove_mount_point(fs_kobj, "mshare");
> > +
> > +	return ret;
> > +}
> > +
> > +core_initcall(mshare_init);
> > --
> > 2.47.1