linux/mm/memfd.c

/*
 * memfd_create system call and file sealing support
 *
 * Code was originally included in shmem.c, and broken out to facilitate
 * use by hugetlbfs as well as tmpfs.
 *
 * This file is released under the GPL.
 */

#include <linux/fs.h>
#include <linux/vfs.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/khugepaged.h>
#include <linux/syscalls.h>
#include <linux/hugetlb.h>
#include <linux/shmem_fs.h>
#include <linux/memfd.h>
#include <linux/pid_namespace.h>
#include <uapi/linux/memfd.h>

/*
 * We need a tag: a new tag would expand every xa_node by 8 bytes,
 * so reuse a tag which we firmly believe is never set or cleared on tmpfs
 * or hugetlbfs because they are memory only filesystems.
 */
#define MEMFD_TAG_PINNED …
#define LAST_SCAN …

static bool memfd_folio_has_extra_refs(struct folio *folio)
{ … }

static void memfd_tag_pins(struct xa_state *xas)
{ … }

/*
 * This is a helper function used by memfd_pin_user_pages() in GUP (gup.c).
 * It is mainly called to allocate a folio in a memfd when the caller
 * (memfd_pin_folios()) cannot find a folio in the page cache at a given
 * index in the mapping.
 */
struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
{ … }

/*
 * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
 * via get_user_pages(), drivers might have some pending I/O without any active
 * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all folios
 * and see whether it has an elevated ref-count. If so, we tag them and wait for
 * them to be dropped.
 * The caller must guarantee that no new user will acquire writable references
 * to those folios to avoid races.
 */
static int memfd_wait_for_pins(struct address_space *mapping)
{ … }

static unsigned int *memfd_file_seals_ptr(struct file *file)
{ … }

#define F_ALL_SEALS …

static int memfd_add_seals(struct file *file, unsigned int seals)
{ … }

static int memfd_get_seals(struct file *file)
{ … }

long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg)
{ … }

#define MFD_NAME_PREFIX …
#define MFD_NAME_PREFIX_LEN …
#define MFD_NAME_MAX_LEN …

#define MFD_ALL_FLAGS …

static int check_sysctl_memfd_noexec(unsigned int *flags)
{ … }

SYSCALL_DEFINE2(memfd_create,
		const char __user *, uname,
		unsigned int, flags)
{ … }