From ff0e03d3f467124b09c37bfb09e1a015cd700ddf Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Fri, 8 Aug 2014 14:25:29 -0700 Subject: [PATCH] shm: add memfd_create() syscall memfd_create() is similar to mmap(MAP_ANON), but returns a file-descriptor that you can pass to mmap(). It can support sealing and avoids any connection to user-visible mount-points. Thus, it's not subject to quotas on mounted file-systems, but can be used like malloc()'ed memory, but with a file-descriptor to it. memfd_create() returns the raw shmem file, so calls like ftruncate() can be used to modify the underlying inode. Also calls like fstat() will return proper information and mark the file as regular file. If you want sealing, you can specify MFD_ALLOW_SEALING. Otherwise, sealing is not supported (like on all other regular files). Compared to O_TMPFILE, it does not require a tmpfs mount-point and is not subject to a filesystem size limit. It is still properly accounted to memcg limits, though, and to the same overcommit or no-overcommit accounting as all user memory. Change-Id: Id7f5dc15f3dcca8e0e8e5d9aea4a9b53cad6a769 Signed-off-by: David Herrmann Acked-by: Hugh Dickins Cc: Michael Kerrisk Cc: Ryan Lortie Cc: Lennart Poettering Cc: Daniel Mack Cc: Andy Lutomirski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/syscalls/syscall_32.tbl | 1 + arch/x86/syscalls/syscall_64.tbl | 1 + include/linux/memfd.h | 8 ++++ include/linux/syscalls.h | 1 + kernel/sys_ni.c | 1 + mm/shmem.c | 73 ++++++++++++++++++++++++++++++++ 6 files changed, 85 insertions(+) create mode 100644 include/linux/memfd.h diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl index 06bb66b7e7c..03b8314a45e 100644 --- a/arch/x86/syscalls/syscall_32.tbl +++ b/arch/x86/syscalls/syscall_32.tbl @@ -356,3 +356,4 @@ 347 i386 process_vm_readv sys_process_vm_readv compat_sys_process_vm_readv 348 i386 process_vm_writev sys_process_vm_writev compat_sys_process_vm_writev 355 i386 getrandom sys_getrandom +356 i386 memfd_create sys_memfd_create diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 4a2d83cd082..184fdf12d87 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -319,6 +319,7 @@ 310 64 process_vm_readv sys_process_vm_readv 311 64 process_vm_writev sys_process_vm_writev 318 common getrandom sys_getrandom +319 common memfd_create sys_memfd_create # # x32-specific system call numbers start at 512 to avoid cache impact # for native 64-bit operation. diff --git a/include/linux/memfd.h b/include/linux/memfd.h new file mode 100644 index 00000000000..6632b15c461 --- /dev/null +++ b/include/linux/memfd.h @@ -0,0 +1,8 @@ +#ifndef _LINUX_MEMFD_H +#define _LINUX_MEMFD_H + +/* flags for memfd_create(2) (unsigned int) */ +#define MFD_CLOEXEC 0x0001U +#define MFD_ALLOW_SEALING 0x0002U + +#endif /* _LINUX_MEMFD_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index bd9ef27c22e..7d3db143a3d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -813,6 +813,7 @@ asmlinkage long sys_timerfd_settime(int ufd, int flags, asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr); asmlinkage long sys_eventfd(unsigned int count); asmlinkage long sys_eventfd2(unsigned int count, int flags); +asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len); asmlinkage long sys_old_readdir(unsigned int, struct old_linux_dirent __user *, unsigned int); asmlinkage long sys_pselect6(int, fd_set __user *, fd_set __user *, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 026f30a8985..b97ab3a6dc9 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -191,6 +191,7 @@ cond_syscall(compat_sys_timerfd_settime); cond_syscall(compat_sys_timerfd_gettime); cond_syscall(sys_eventfd); cond_syscall(sys_eventfd2); +cond_syscall(sys_memfd_create); /* performance counters: */ cond_syscall(sys_perf_event_open); diff --git a/mm/shmem.c b/mm/shmem.c index 4ca08f0578f..cc4ad1108ad 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -64,7 +64,9 @@ static struct vfsmount *shm_mnt; #include #include #include +#include #include +#include #include #include @@ -2784,6 +2786,77 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root) shmem_show_mpol(seq, sbinfo->mpol); return 0; } + +#define MFD_NAME_PREFIX "memfd:" +#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1) +#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN) + +#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING) + +SYSCALL_DEFINE2(memfd_create, + const char __user *, uname, + unsigned int, flags) +{ + struct shmem_inode_info *info; + struct file *file; + int fd, error; + char *name; + long len; + + if (flags & ~(unsigned int)MFD_ALL_FLAGS) + return -EINVAL; + + /* length includes terminating zero */ + len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1); + if (len <= 0) + return -EFAULT; + if (len > MFD_NAME_MAX_LEN + 1) + return -EINVAL; + + name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY); + if (!name) + return -ENOMEM; + + strcpy(name, MFD_NAME_PREFIX); + if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) { + error = -EFAULT; + goto err_name; + } + + /* terminating-zero may have changed after strnlen_user() returned */ + if (name[len + MFD_NAME_PREFIX_LEN - 1]) { + error = -EFAULT; + goto err_name; + } + + fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0); + if (fd < 0) { + error = fd; + goto err_name; + } + + file = shmem_file_setup(name, 0, VM_NORESERVE); + if (IS_ERR(file)) { + error = PTR_ERR(file); + goto err_fd; + } + info = SHMEM_I(file->f_path.dentry->d_inode); + file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE; + file->f_flags |= O_RDWR | O_LARGEFILE; + if (flags & MFD_ALLOW_SEALING) + info->seals &= ~F_SEAL_SEAL; + + fd_install(fd, file); + kfree(name); + return fd; + +err_fd: + put_unused_fd(fd); +err_name: + kfree(name); + return error; +} + #endif /* CONFIG_TMPFS */ static void shmem_put_super(struct super_block *sb)