Revision 2a18da7a9c7886f1c7307f8d3f23f24318583f03 authored by George Spelvin on 23 May 2016, 11:43:58 UTC, committed by George Spelvin on 28 May 2016, 19:45:29 UTC
Patch 0fed3ac866 improved the hash mixing, but the function is slower than necessary; there's a 7-instruction dependency chain (10 on x86) each loop iteration. Word-at-a-time access is a very tight loop (which is good, because link_path_walk() is one of the hottest code paths in the entire kernel), and the hash mixing function must not have a longer latency to avoid slowing it down. There do not appear to be any published fast hash functions that: 1) Operate on the input a word at a time, and 2) Don't need to know the length of the input beforehand, and 3) Have a single iterated mixing function, not needing conditional branches or unrolling to distinguish different loop iterations. One of the algorithms which comes closest is Yann Collet's xxHash, but that's two dependent multiplies per word, which is too much. The key insights in this design are: 1) Barring expensive ops like multiplies, to diffuse one input bit across 64 bits of hash state takes at least log2(64) = 6 sequentially dependent instructions. That is more cycles than we'd like. 2) An operation like "hash ^= hash << 13" requires a second temporary register anyway, and on a 2-operand machine like x86, it's three instructions. 3) A better use of a second register is to hold a two-word hash state. With careful design, no temporaries are needed at all, so it doesn't increase register pressure. And this gets rid of register copying on 2-operand machines, so the code is smaller and faster. 4) Using two words of state weakens the requirement for one-round mixing; we now have two rounds of mixing before cancellation is possible. 5) A two-word hash state also allows operations on both halves to be done in parallel, so on a superscalar processor we get more mixing in fewer cycles. I ended up using a mixing function inspired by the ChaCha and Speck round functions. It is 6 simple instructions and 3 cycles per iteration (assuming multiply by 9 can be done by an "lea" instruction): x ^= *input++; y ^= x; x = ROL(x, K1); x += y; y = ROL(y, K2); y *= 9; Not only is this reversible, two consecutive rounds are reversible: if you are given the initial and final states, but not the intermediate state, it is possible to compute both input words. This means that at least 3 words of input are required to create a collision. (It also has the property, used by hash_name() to avoid a branch, that it hashes all-zero to all-zero.) The rotate constants K1 and K2 were found by experiment. The search took a sample of random initial states (I used 1023) and considered the effect of flipping each of the 64 input bits on each of the 128 output bits two rounds later. Each of the 8192 pairs can be considered a biased coin, and adding up the Shannon entropy of all of them produces a score. The best-scoring shifts also did well in other tests (flipping bits in y, trying 3 or 4 rounds of mixing, flipping all 64*63/2 pairs of input bits), so the choice was made with the additional constraint that the sum of the shifts is odd and not too close to the word size. The final state is then folded into a 32-bit hash value by a less carefully optimized multiply-based scheme. This also has to be fast, as pathname components tend to be short (the most common case is one iteration!), but there's some room for latency, as there is a fair bit of intervening logic before the hash value is used for anything. (Performance verified with "bonnie++ -s 0 -n 1536:-2" on tmpfs. I need a better benchmark; the numbers seem to show a slight dip in performance between 4.6.0 and this patch, but they're too noisy to quote.) Special thanks to Bruce fields for diligent testing which uncovered a nasty fencepost error in an earlier version of this patch. [checkpatch.pl formatting complaints noted and respectfully disagreed with.] Signed-off-by: George Spelvin <linux@sciencehorizons.net> Tested-by: J. Bruce Fields <bfields@redhat.com>
1 parent ef703f4
open.c
/*
* linux/fs/open.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
#include <linux/falloc.h>
#include <linux/fs_struct.h>
#include <linux/ima.h>
#include <linux/dnotify.h>
#include <linux/compat.h>
#include "internal.h"
int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
int ret;
struct iattr newattrs;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
if (length < 0)
return -EINVAL;
newattrs.ia_size = length;
newattrs.ia_valid = ATTR_SIZE | time_attrs;
if (filp) {
newattrs.ia_file = filp;
newattrs.ia_valid |= ATTR_FILE;
}
/* Remove suid, sgid, and file capabilities on truncate too */
ret = dentry_needs_remove_privs(dentry);
if (ret < 0)
return ret;
if (ret)
newattrs.ia_valid |= ret | ATTR_FORCE;
inode_lock(dentry->d_inode);
/* Note any delegations or leases have already been broken: */
ret = notify_change(dentry, &newattrs, NULL);
inode_unlock(dentry->d_inode);
return ret;
}
long vfs_truncate(struct path *path, loff_t length)
{
struct inode *inode;
long error;
inode = path->dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
if (S_ISDIR(inode->i_mode))
return -EISDIR;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
error = mnt_want_write(path->mnt);
if (error)
goto out;
error = inode_permission(inode, MAY_WRITE);
if (error)
goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_APPEND(inode))
goto mnt_drop_write_and_out;
error = get_write_access(inode);
if (error)
goto mnt_drop_write_and_out;
/*
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
error = security_path_truncate(path);
if (!error)
error = do_truncate(path->dentry, length, 0, NULL);
put_write_and_out:
put_write_access(inode);
mnt_drop_write_and_out:
mnt_drop_write(path->mnt);
out:
return error;
}
EXPORT_SYMBOL_GPL(vfs_truncate);
static long do_sys_truncate(const char __user *pathname, loff_t length)
{
unsigned int lookup_flags = LOOKUP_FOLLOW;
struct path path;
int error;
if (length < 0) /* sorry, but loff_t says... */
return -EINVAL;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (!error) {
error = vfs_truncate(&path, length);
path_put(&path);
}
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
{
return do_sys_truncate(path, length);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(truncate, const char __user *, path, compat_off_t, length)
{
return do_sys_truncate(path, length);
}
#endif
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode *inode;
struct dentry *dentry;
struct fd f;
int error;
error = -EINVAL;
if (length < 0)
goto out;
error = -EBADF;
f = fdget(fd);
if (!f.file)
goto out;
/* explicitly opened as large or we are on 64-bit box */
if (f.file->f_flags & O_LARGEFILE)
small = 0;
dentry = f.file->f_path.dentry;
inode = dentry->d_inode;
error = -EINVAL;
if (!S_ISREG(inode->i_mode) || !(f.file->f_mode & FMODE_WRITE))
goto out_putf;
error = -EINVAL;
/* Cannot ftruncate over 2^31 bytes without large file support */
if (small && length > MAX_NON_LFS)
goto out_putf;
error = -EPERM;
if (IS_APPEND(inode))
goto out_putf;
sb_start_write(inode->i_sb);
error = locks_verify_truncate(inode, f.file, length);
if (!error)
error = security_path_truncate(&f.file->f_path);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, f.file);
sb_end_write(inode->i_sb);
out_putf:
fdput(f);
out:
return error;
}
SYSCALL_DEFINE2(ftruncate, unsigned int, fd, unsigned long, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#ifdef CONFIG_COMPAT
COMPAT_SYSCALL_DEFINE2(ftruncate, unsigned int, fd, compat_ulong_t, length)
{
return do_sys_ftruncate(fd, length, 1);
}
#endif
/* LFS versions of truncate are only needed on 32 bit machines */
#if BITS_PER_LONG == 32
SYSCALL_DEFINE2(truncate64, const char __user *, path, loff_t, length)
{
return do_sys_truncate(path, length);
}
SYSCALL_DEFINE2(ftruncate64, unsigned int, fd, loff_t, length)
{
return do_sys_ftruncate(fd, length, 0);
}
#endif /* BITS_PER_LONG == 32 */
int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
long ret;
if (offset < 0 || len <= 0)
return -EINVAL;
/* Return error if mode is not supported */
if (mode & ~FALLOC_FL_SUPPORTED_MASK)
return -EOPNOTSUPP;
/* Punch hole and zero range are mutually exclusive */
if ((mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) ==
(FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
/* Punch hole must have keep size set */
if ((mode & FALLOC_FL_PUNCH_HOLE) &&
!(mode & FALLOC_FL_KEEP_SIZE))
return -EOPNOTSUPP;
/* Collapse range should only be used exclusively. */
if ((mode & FALLOC_FL_COLLAPSE_RANGE) &&
(mode & ~FALLOC_FL_COLLAPSE_RANGE))
return -EINVAL;
/* Insert range should only be used exclusively. */
if ((mode & FALLOC_FL_INSERT_RANGE) &&
(mode & ~FALLOC_FL_INSERT_RANGE))
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
/*
* We can only allow pure fallocate on append only files
*/
if ((mode & ~FALLOC_FL_KEEP_SIZE) && IS_APPEND(inode))
return -EPERM;
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* We cannot allow any fallocate operation on an active swapfile
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
return ret;
if (S_ISFIFO(inode->i_mode))
return -ESPIPE;
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return -ENODEV;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
return -EFBIG;
if (!file->f_op->fallocate)
return -EOPNOTSUPP;
sb_start_write(inode->i_sb);
ret = file->f_op->fallocate(file, mode, offset, len);
/*
* Create inotify and fanotify events.
*
* To keep the logic simple always create events if fallocate succeeds.
* This implies that events are even created if the file size remains
* unchanged, e.g. when using flag FALLOC_FL_KEEP_SIZE.
*/
if (ret == 0)
fsnotify_modify(file);
sb_end_write(inode->i_sb);
return ret;
}
EXPORT_SYMBOL_GPL(vfs_fallocate);
SYSCALL_DEFINE4(fallocate, int, fd, int, mode, loff_t, offset, loff_t, len)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (f.file) {
error = vfs_fallocate(f.file, mode, offset, len);
fdput(f);
}
return error;
}
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
const struct cred *old_cred;
struct cred *override_cred;
struct path path;
struct inode *inode;
int res;
unsigned int lookup_flags = LOOKUP_FOLLOW;
if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */
return -EINVAL;
override_cred = prepare_creds();
if (!override_cred)
return -ENOMEM;
override_cred->fsuid = override_cred->uid;
override_cred->fsgid = override_cred->gid;
if (!issecure(SECURE_NO_SETUID_FIXUP)) {
/* Clear the capabilities if we switch to a non-root user */
kuid_t root_uid = make_kuid(override_cred->user_ns, 0);
if (!uid_eq(override_cred->uid, root_uid))
cap_clear(override_cred->cap_effective);
else
override_cred->cap_effective =
override_cred->cap_permitted;
}
old_cred = override_creds(override_cred);
retry:
res = user_path_at(dfd, filename, lookup_flags, &path);
if (res)
goto out;
inode = d_backing_inode(path.dentry);
if ((mode & MAY_EXEC) && S_ISREG(inode->i_mode)) {
/*
* MAY_EXEC on regular files is denied if the fs is mounted
* with the "noexec" flag.
*/
res = -EACCES;
if (path_noexec(&path))
goto out_path_release;
}
res = inode_permission(inode, mode | MAY_ACCESS);
/* SuS v2 requires we report a read only fs too */
if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
goto out_path_release;
/*
* This is a rare case where using __mnt_is_readonly()
* is OK without a mnt_want/drop_write() pair. Since
* no actual write to the fs is performed here, we do
* not need to telegraph to that to anyone.
*
* By doing this, we accept that this access is
* inherently racy and know that the fs may change
* state before we even see this result.
*/
if (__mnt_is_readonly(path.mnt))
res = -EROFS;
out_path_release:
path_put(&path);
if (retry_estale(res, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
revert_creds(old_cred);
put_cred(override_cred);
return res;
}
SYSCALL_DEFINE2(access, const char __user *, filename, int, mode)
{
return sys_faccessat(AT_FDCWD, filename, mode);
}
SYSCALL_DEFINE1(chdir, const char __user *, filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
set_fs_pwd(current->fs, &path);
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
struct fd f = fdget_raw(fd);
struct inode *inode;
int error = -EBADF;
error = -EBADF;
if (!f.file)
goto out;
inode = file_inode(f.file);
error = -ENOTDIR;
if (!S_ISDIR(inode->i_mode))
goto out_putf;
error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &f.file->f_path);
out_putf:
fdput(f);
out:
return error;
}
SYSCALL_DEFINE1(chroot, const char __user *, filename)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
retry:
error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
if (error)
goto out;
error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!ns_capable(current_user_ns(), CAP_SYS_CHROOT))
goto dput_and_out;
error = security_path_chroot(&path);
if (error)
goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
dput_and_out:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
static int chmod_common(struct path *path, umode_t mode)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
struct iattr newattrs;
int error;
error = mnt_want_write(path->mnt);
if (error)
return error;
retry_deleg:
inode_lock(inode);
error = security_path_chmod(path, mode);
if (error)
goto out_unlock;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(path->dentry, &newattrs, &delegated_inode);
out_unlock:
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
mnt_drop_write(path->mnt);
return error;
}
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
struct fd f = fdget(fd);
int err = -EBADF;
if (f.file) {
audit_file(f.file);
err = chmod_common(&f.file->f_path, mode);
fdput(f);
}
return err;
}
SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode)
{
struct path path;
int error;
unsigned int lookup_flags = LOOKUP_FOLLOW;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (!error) {
error = chmod_common(&path, mode);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
}
return error;
}
SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
{
return sys_fchmodat(AT_FDCWD, filename, mode);
}
static int chown_common(struct path *path, uid_t user, gid_t group)
{
struct inode *inode = path->dentry->d_inode;
struct inode *delegated_inode = NULL;
int error;
struct iattr newattrs;
kuid_t uid;
kgid_t gid;
uid = make_kuid(current_user_ns(), user);
gid = make_kgid(current_user_ns(), group);
retry_deleg:
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
if (!uid_valid(uid))
return -EINVAL;
newattrs.ia_valid |= ATTR_UID;
newattrs.ia_uid = uid;
}
if (group != (gid_t) -1) {
if (!gid_valid(gid))
return -EINVAL;
newattrs.ia_valid |= ATTR_GID;
newattrs.ia_gid = gid;
}
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |=
ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
inode_lock(inode);
error = security_path_chown(path, uid, gid);
if (!error)
error = notify_change(path->dentry, &newattrs, &delegated_inode);
inode_unlock(inode);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
if (!error)
goto retry_deleg;
}
return error;
}
SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
gid_t, group, int, flag)
{
struct path path;
int error = -EINVAL;
int lookup_flags;
if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
goto out;
lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
if (flag & AT_EMPTY_PATH)
lookup_flags |= LOOKUP_EMPTY;
retry:
error = user_path_at(dfd, filename, lookup_flags, &path);
if (error)
goto out;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
out:
return error;
}
SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
{
return sys_fchownat(AT_FDCWD, filename, user, group, 0);
}
SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
{
return sys_fchownat(AT_FDCWD, filename, user, group,
AT_SYMLINK_NOFOLLOW);
}
SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
goto out;
error = mnt_want_write_file(f.file);
if (error)
goto out_fput;
audit_file(f.file);
error = chown_common(&f.file->f_path, user, group);
mnt_drop_write_file(f.file);
out_fput:
fdput(f);
out:
return error;
}
int open_check_o_direct(struct file *f)
{
/* NB: we're sure to have correct a_ops only after f_op->open */
if (f->f_flags & O_DIRECT) {
if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
return -EINVAL;
}
return 0;
}
static int do_dentry_open(struct file *f,
struct inode *inode,
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
static const struct file_operations empty_fops = {};
int error;
f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
path_get(&f->f_path);
f->f_inode = inode;
f->f_mapping = inode->i_mapping;
if (unlikely(f->f_flags & O_PATH)) {
f->f_mode = FMODE_PATH;
f->f_op = &empty_fops;
return 0;
}
if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
error = get_write_access(inode);
if (unlikely(error))
goto cleanup_file;
error = __mnt_want_write(f->f_path.mnt);
if (unlikely(error)) {
put_write_access(inode);
goto cleanup_file;
}
f->f_mode |= FMODE_WRITER;
}
/* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
if (S_ISREG(inode->i_mode))
f->f_mode |= FMODE_ATOMIC_POS;
f->f_op = fops_get(inode->i_fop);
if (unlikely(WARN_ON(!f->f_op))) {
error = -ENODEV;
goto cleanup_all;
}
error = security_file_open(f, cred);
if (error)
goto cleanup_all;
error = break_lease(inode, f->f_flags);
if (error)
goto cleanup_all;
if (!open)
open = f->f_op->open;
if (open) {
error = open(inode, f);
if (error)
goto cleanup_all;
}
if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(inode);
if ((f->f_mode & FMODE_READ) &&
likely(f->f_op->read || f->f_op->read_iter))
f->f_mode |= FMODE_CAN_READ;
if ((f->f_mode & FMODE_WRITE) &&
likely(f->f_op->write || f->f_op->write_iter))
f->f_mode |= FMODE_CAN_WRITE;
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
return 0;
cleanup_all:
fops_put(f->f_op);
if (f->f_mode & FMODE_WRITER) {
put_write_access(inode);
__mnt_drop_write(f->f_path.mnt);
}
cleanup_file:
path_put(&f->f_path);
f->f_path.mnt = NULL;
f->f_path.dentry = NULL;
f->f_inode = NULL;
return error;
}
/**
* finish_open - finish opening a file
* @file: file pointer
* @dentry: pointer to dentry
* @open: open callback
* @opened: state of open
*
* This can be used to finish opening a file passed to i_op->atomic_open().
*
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
*
* NB: the dentry reference is _not_ consumed. If, for example, the dentry is
* the return value of d_splice_alias(), then the caller needs to perform dput()
* on it after finish_open().
*
* On successful return @file is a fully instantiated open file. After this, if
* an error occurs in ->atomic_open(), it needs to clean up with fput().
*
* Returns zero on success or -errno if the open failed.
*/
int finish_open(struct file *file, struct dentry *dentry,
int (*open)(struct inode *, struct file *),
int *opened)
{
int error;
BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
file->f_path.dentry = dentry;
error = do_dentry_open(file, d_backing_inode(dentry), open,
current_cred());
if (!error)
*opened |= FILE_OPENED;
return error;
}
EXPORT_SYMBOL(finish_open);
/**
* finish_no_open - finish ->atomic_open() without opening the file
*
* @file: file pointer
* @dentry: dentry or NULL (as returned from ->lookup())
*
* This can be used to set the result of a successful lookup in ->atomic_open().
*
* NB: unlike finish_open() this function does consume the dentry reference and
* the caller need not dput() it.
*
* Returns "1" which must be the return value of ->atomic_open() after having
* called this function.
*/
int finish_no_open(struct file *file, struct dentry *dentry)
{
file->f_path.dentry = dentry;
return 1;
}
EXPORT_SYMBOL(finish_no_open);
char *file_path(struct file *filp, char *buf, int buflen)
{
return d_path(&filp->f_path, buf, buflen);
}
EXPORT_SYMBOL(file_path);
/**
* vfs_open - open the file at the given path
* @path: path to open
* @file: newly allocated file with f_flag initialized
* @cred: credentials to use
*/
int vfs_open(const struct path *path, struct file *file,
const struct cred *cred)
{
struct inode *inode = vfs_select_inode(path->dentry, file->f_flags);
if (IS_ERR(inode))
return PTR_ERR(inode);
file->f_path = *path;
return do_dentry_open(file, inode, NULL, cred);
}
struct file *dentry_open(const struct path *path, int flags,
const struct cred *cred)
{
int error;
struct file *f;
validate_creds(cred);
/* We must always pass in a valid mount pointer. */
BUG_ON(!path->mnt);
f = get_empty_filp();
if (!IS_ERR(f)) {
f->f_flags = flags;
error = vfs_open(path, f, cred);
if (!error) {
/* from now on we need fput() to dispose of f */
error = open_check_o_direct(f);
if (error) {
fput(f);
f = ERR_PTR(error);
}
} else {
put_filp(f);
f = ERR_PTR(error);
}
}
return f;
}
EXPORT_SYMBOL(dentry_open);
static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
{
int lookup_flags = 0;
int acc_mode = ACC_MODE(flags);
if (flags & (O_CREAT | __O_TMPFILE))
op->mode = (mode & S_IALLUGO) | S_IFREG;
else
op->mode = 0;
/* Must never be set by userspace */
flags &= ~FMODE_NONOTIFY & ~O_CLOEXEC;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
* always set instead of having to deal with possibly weird behaviour
* for malicious applications setting only __O_SYNC.
*/
if (flags & __O_SYNC)
flags |= O_DSYNC;
if (flags & __O_TMPFILE) {
if ((flags & O_TMPFILE_MASK) != O_TMPFILE)
return -EINVAL;
if (!(acc_mode & MAY_WRITE))
return -EINVAL;
} else if (flags & O_PATH) {
/*
* If we have O_PATH in the open flag. Then we
* cannot have anything other than the below set of flags
*/
flags &= O_DIRECTORY | O_NOFOLLOW | O_PATH;
acc_mode = 0;
}
op->open_flag = flags;
/* O_TRUNC implies we need access checks for write permissions */
if (flags & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if (flags & O_APPEND)
acc_mode |= MAY_APPEND;
op->acc_mode = acc_mode;
op->intent = flags & O_PATH ? 0 : LOOKUP_OPEN;
if (flags & O_CREAT) {
op->intent |= LOOKUP_CREATE;
if (flags & O_EXCL)
op->intent |= LOOKUP_EXCL;
}
if (flags & O_DIRECTORY)
lookup_flags |= LOOKUP_DIRECTORY;
if (!(flags & O_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
op->lookup_flags = lookup_flags;
return 0;
}
/**
* file_open_name - open file and return file pointer
*
* @name: struct filename containing path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *file_open_name(struct filename *name, int flags, umode_t mode)
{
struct open_flags op;
int err = build_open_flags(flags, mode, &op);
return err ? ERR_PTR(err) : do_filp_open(AT_FDCWD, name, &op);
}
/**
* filp_open - open file and return file pointer
*
* @filename: path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *filp_open(const char *filename, int flags, umode_t mode)
{
struct filename *name = getname_kernel(filename);
struct file *file = ERR_CAST(name);
if (!IS_ERR(name)) {
file = file_open_name(name, flags, mode);
putname(name);
}
return file;
}
EXPORT_SYMBOL(filp_open);
struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
const char *filename, int flags, umode_t mode)
{
struct open_flags op;
int err = build_open_flags(flags, mode, &op);
if (err)
return ERR_PTR(err);
return do_file_open_root(dentry, mnt, filename, &op);
}
EXPORT_SYMBOL(file_open_root);
long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
{
struct open_flags op;
int fd = build_open_flags(flags, mode, &op);
struct filename *tmp;
if (fd)
return fd;
tmp = getname(filename);
if (IS_ERR(tmp))
return PTR_ERR(tmp);
fd = get_unused_fd_flags(flags);
if (fd >= 0) {
struct file *f = do_filp_open(dfd, tmp, &op);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
fsnotify_open(f);
fd_install(fd, f);
}
}
putname(tmp);
return fd;
}
SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(AT_FDCWD, filename, flags, mode);
}
SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
umode_t, mode)
{
if (force_o_largefile())
flags |= O_LARGEFILE;
return do_sys_open(dfd, filename, flags, mode);
}
#ifndef __alpha__
/*
* For backward compatibility? Maybe this should be moved
* into arch/i386 instead?
*/
SYSCALL_DEFINE2(creat, const char __user *, pathname, umode_t, mode)
{
return sys_open(pathname, O_CREAT | O_WRONLY | O_TRUNC, mode);
}
#endif
/*
* "id" is the POSIX thread ID. We use the
* files pointer for this..
*/
int filp_close(struct file *filp, fl_owner_t id)
{
int retval = 0;
if (!file_count(filp)) {
printk(KERN_ERR "VFS: Close: file count is 0\n");
return 0;
}
if (filp->f_op->flush)
retval = filp->f_op->flush(filp, id);
if (likely(!(filp->f_mode & FMODE_PATH))) {
dnotify_flush(filp, id);
locks_remove_posix(filp, id);
}
fput(filp);
return retval;
}
EXPORT_SYMBOL(filp_close);
/*
* Careful here! We test whether the file pointer is NULL before
* releasing the fd. This ensures that one clone task can't release
* an fd while another clone is opening it.
*/
SYSCALL_DEFINE1(close, unsigned int, fd)
{
int retval = __close_fd(current->files, fd);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
retval == -ERESTARTNOINTR ||
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
return retval;
}
EXPORT_SYMBOL(sys_close);
/*
* This routine simulates a hangup on the tty, to arrange that users
* are given clean terminals at login time.
*/
SYSCALL_DEFINE0(vhangup)
{
if (capable(CAP_SYS_TTY_CONFIG)) {
tty_vhangup_self();
return 0;
}
return -EPERM;
}
/*
* Called when an inode is about to be open.
* We use this to disallow opening large files on 32bit systems if
* the caller didn't specify O_LARGEFILE. On 64bit systems we force
* on this flag in sys_open.
*/
int generic_file_open(struct inode * inode, struct file * filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
return 0;
}
EXPORT_SYMBOL(generic_file_open);
/*
* This is used by subsystems that don't want seekable
* file descriptors. The function is not supposed to ever fail, the only
* reason it returns an 'int' and not 'void' is so that it can be plugged
* directly into file_operations structure.
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
return 0;
}
EXPORT_SYMBOL(nonseekable_open);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...