linux_dsm_epyc7002/include/uapi/linux/fcntl.h
Joel Fernandes (Google) ab3948f58f mm/memfd: add an F_SEAL_FUTURE_WRITE seal to memfd
Android uses ashmem for sharing memory regions.  We are looking forward
to migrating all usecases of ashmem to memfd so that we can possibly
remove the ashmem driver in the future from staging while also
benefiting from using memfd and contributing to it.  Note staging
drivers are also not ABI and generally can be removed at anytime.

One of the main usecases Android has is the ability to create a region
and mmap it as writeable, then add protection against making any
"future" writes while keeping the existing already mmap'ed
writeable-region active.  This allows us to implement a usecase where
receivers of the shared memory buffer can get a read-only view, while
the sender continues to write to the buffer.  See CursorWindow
documentation in Android for more details:

  https://developer.android.com/reference/android/database/CursorWindow

This usecase cannot be implemented with the existing F_SEAL_WRITE seal.
To support the usecase, this patch adds a new F_SEAL_FUTURE_WRITE seal
which prevents any future mmap and write syscalls from succeeding while
keeping the existing mmap active.

A better way to do F_SEAL_FUTURE_WRITE seal was discussed [1] last week
where we don't need to modify core VFS structures to get the same
behavior of the seal.  This solves several side-effects pointed by Andy.
self-tests are provided in later patch to verify the expected semantics.

[1] https://lore.kernel.org/lkml/20181111173650.GA256781@google.com/

Thanks a lot to Andy for suggestions to improve code.

Link: http://lkml.kernel.org/r/20190112203816.85534-2-joel@joelfernandes.org
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Acked-by: John Stultz <john.stultz@linaro.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: J. Bruce Fields <bfields@fieldses.org>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Marc-Andr Lureau <marcandre.lureau@redhat.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-05 21:07:19 -08:00

96 lines
3.3 KiB
C

/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _UAPI_LINUX_FCNTL_H
#define _UAPI_LINUX_FCNTL_H
#include <asm/fcntl.h>
#define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0)
#define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1)
/*
* Cancel a blocking posix lock; internal use only until we expose an
* asynchronous lock api to userspace:
*/
#define F_CANCELLK (F_LINUX_SPECIFIC_BASE + 5)
/* Create a file descriptor with FD_CLOEXEC set. */
#define F_DUPFD_CLOEXEC (F_LINUX_SPECIFIC_BASE + 6)
/*
* Request nofications on a directory.
* See below for events that may be notified.
*/
#define F_NOTIFY (F_LINUX_SPECIFIC_BASE+2)
/*
* Set and get of pipe page size array
*/
#define F_SETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 7)
#define F_GETPIPE_SZ (F_LINUX_SPECIFIC_BASE + 8)
/*
* Set/Get seals
*/
#define F_ADD_SEALS (F_LINUX_SPECIFIC_BASE + 9)
#define F_GET_SEALS (F_LINUX_SPECIFIC_BASE + 10)
/*
* Types of seals
*/
#define F_SEAL_SEAL 0x0001 /* prevent further seals from being set */
#define F_SEAL_SHRINK 0x0002 /* prevent file from shrinking */
#define F_SEAL_GROW 0x0004 /* prevent file from growing */
#define F_SEAL_WRITE 0x0008 /* prevent writes */
#define F_SEAL_FUTURE_WRITE 0x0010 /* prevent future writes while mapped */
/* (1U << 31) is reserved for signed error codes */
/*
* Set/Get write life time hints. {GET,SET}_RW_HINT operate on the
* underlying inode, while {GET,SET}_FILE_RW_HINT operate only on
* the specific file.
*/
#define F_GET_RW_HINT (F_LINUX_SPECIFIC_BASE + 11)
#define F_SET_RW_HINT (F_LINUX_SPECIFIC_BASE + 12)
#define F_GET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 13)
#define F_SET_FILE_RW_HINT (F_LINUX_SPECIFIC_BASE + 14)
/*
* Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
* used to clear any hints previously set.
*/
#define RWF_WRITE_LIFE_NOT_SET 0
#define RWH_WRITE_LIFE_NONE 1
#define RWH_WRITE_LIFE_SHORT 2
#define RWH_WRITE_LIFE_MEDIUM 3
#define RWH_WRITE_LIFE_LONG 4
#define RWH_WRITE_LIFE_EXTREME 5
/*
* Types of directory notifications that may be requested.
*/
#define DN_ACCESS 0x00000001 /* File accessed */
#define DN_MODIFY 0x00000002 /* File modified */
#define DN_CREATE 0x00000004 /* File created */
#define DN_DELETE 0x00000008 /* File removed */
#define DN_RENAME 0x00000010 /* File renamed */
#define DN_ATTRIB 0x00000020 /* File changed attibutes */
#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
#define AT_FDCWD -100 /* Special value used to indicate
openat should use the current
working directory. */
#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
#define AT_REMOVEDIR 0x200 /* Remove directory instead of
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
#define AT_NO_AUTOMOUNT 0x800 /* Suppress terminal automount traversal */
#define AT_EMPTY_PATH 0x1000 /* Allow empty relative pathname */
#define AT_STATX_SYNC_TYPE 0x6000 /* Type of synchronisation required from statx() */
#define AT_STATX_SYNC_AS_STAT 0x0000 /* - Do whatever stat() does */
#define AT_STATX_FORCE_SYNC 0x2000 /* - Force the attributes to be sync'd with the server */
#define AT_STATX_DONT_SYNC 0x4000 /* - Don't sync attributes with the server */
#endif /* _UAPI_LINUX_FCNTL_H */