new file mode 100644
@@ -0,0 +1,107 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================================
+msharefs - a filesystem to support shared page tables
+=====================================================
+
+msharefs is a ram-based filesystem that allows multiple processes to
+share page table entries for shared pages.
+
+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. ioctls are used to initialize or retrieve the start address
+and size of a shared region and to map objects in the shared
+region. It is important to note that an msharefs file is a control
+file for the shared region and does not contain the contents
+of the region itself.
+
+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:
+
+.. code-block:: c
+
+ fd = open("/sys/fs/mshare/shareme",
+ O_RDWR|O_CREAT|O_EXCL, 0600);
+
+b. Establish the starting address and size of the region:
+
+.. code-block:: c
+
+ struct mshare_info minfo;
+
+ minfo.start = TB(2);
+ minfo.size = BUFFER_SIZE;
+ ioctl(fd, MSHAREFS_SET_SIZE, &minfo);
+
+c. Map some memory in the region:
+
+.. code-block:: c
+
+ struct mshare_create mcreate;
+
+ mcreate.addr = TB(2);
+ mcreate.size = BUFFER_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:
+
+.. code-block:: c
+
+ mmap((void *)TB(2), 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 file on msharefs, for example:
+
+.. code-block:: c
+
+ fd = open("/sys/fs/mshare/shareme", O_RDWR);
+
+b. Get information about mshare'd region from the file:
+
+.. code-block:: c
+
+ struct mshare_info minfo;
+
+ ioctl(fd, MSHAREFS_GET_SIZE, &minfo);
+
+c. Map the mshare'd region into the process:
+
+.. code-block:: c
+
+ mmap(minfo.start, minfo.size,
+ PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+
+5. To delete the mshare region:
+
+.. code-block:: c
+
+ unlink("/sys/fs/mshare/shareme");
+
@@ -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__ */
@@ -45,7 +45,7 @@ mmu-$(CONFIG_MMU) += process_vm_access.o
endif
ifdef CONFIG_64BIT
-mmu-$(CONFIG_MMU) += mseal.o
+mmu-$(CONFIG_MMU) += mseal.o mshare.o
endif
obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
new file mode 100644
@@ -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@kernel.org>
+ *
+ */
+
+#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,
+ .llseek = no_llseek,
+};
+
+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_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;
+
+ 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);