linux_dsm_epyc7002/fs/readdir.c
Linus Torvalds 0e01df100b Fix a number of bugs, most notably a potential stale data exposure
after a crash and a potential BUG_ON crash if a file has the data
 journalling flag enabled while it has dirty delayed allocation blocks
 that haven't been written yet.  Also fix a potential crash in the new
 project quota code and a maliciously corrupted file system.
 
 In addition, fix some DAX-specific bugs, including when there is a
 transient ENOSPC situation and races between writes via direct I/O and
 an mmap'ed segment that could lead to lost I/O.
 
 Finally the usual set of miscellaneous cleanups.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQEcBAABCAAGBQJXQ40fAAoJEPL5WVaVDYGjnwMH+wXHASgPfzZgtRInsTG8W/2L
 jsmAcMlyMAYIATWMppNtPIq0td49z1dYO0YkKhtPVMwfzu230IFWhGWp93WqP9ve
 XYHMmaBorFlMAzWgMKn1K0ExWZlV+ammmcTKgU0kU4qyZp0G/NnMtlXIkSNv2amI
 9Mn6R+v97c20gn8e9HWP/IVWkgPr+WBtEXaSGjC7dL6yI8hL+rJMqN82D76oU5ea
 vtwzrna/ISijy+etYmQzqHNYNaBKf40+B5HxQZw/Ta3FSHofBwXAyLaeEAr260Mf
 V3Eg2NDcKQxiZ3adBzIUvrRnrJV381OmHoguo8Frs8YHTTRiZ0T/s7FGr2Q0NYE=
 =7yIM
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Fix a number of bugs, most notably a potential stale data exposure
  after a crash and a potential BUG_ON crash if a file has the data
  journalling flag enabled while it has dirty delayed allocation blocks
  that haven't been written yet.  Also fix a potential crash in the new
  project quota code and a maliciously corrupted file system.

  In addition, fix some DAX-specific bugs, including when there is a
  transient ENOSPC situation and races between writes via direct I/O and
  an mmap'ed segment that could lead to lost I/O.

  Finally the usual set of miscellaneous cleanups"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
  ext4: pre-zero allocated blocks for DAX IO
  ext4: refactor direct IO code
  ext4: fix race in transient ENOSPC detection
  ext4: handle transient ENOSPC properly for DAX
  dax: call get_blocks() with create == 1 for write faults to unwritten extents
  ext4: remove unmeetable inconsisteny check from ext4_find_extent()
  jbd2: remove excess descriptions for handle_s
  ext4: remove unnecessary bio get/put
  ext4: silence UBSAN in ext4_mb_init()
  ext4: address UBSAN warning in mb_find_order_for_block()
  ext4: fix oops on corrupted filesystem
  ext4: fix check of dqget() return value in ext4_ioctl_setproject()
  ext4: clean up error handling when orphan list is corrupted
  ext4: fix hang when processing corrupted orphaned inode list
  ext4: remove trailing \n from ext4_warning/ext4_error calls
  ext4: fix races between changing inode journal mode and ext4_writepages
  ext4: handle unwritten or delalloc buffers before enabling data journaling
  ext4: fix jbd2 handle extension in ext4_ext_truncate_extend_restart()
  ext4: do not ask jbd2 to write data for delalloc buffers
  jbd2: add support for avoiding data writes during transaction commits
  ...
2016-05-24 12:55:26 -07:00

327 lines
7.3 KiB
C

/*
* linux/fs/readdir.c
*
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/stddef.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/stat.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/dirent.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <asm/uaccess.h>
int iterate_dir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
bool shared = false;
int res = -ENOTDIR;
if (file->f_op->iterate_shared)
shared = true;
else if (!file->f_op->iterate)
goto out;
res = security_file_permission(file, MAY_READ);
if (res)
goto out;
if (shared)
inode_lock_shared(inode);
else
inode_lock(inode);
// res = mutex_lock_killable(&inode->i_mutex);
// if (res)
// goto out;
res = -ENOENT;
if (!IS_DEADDIR(inode)) {
ctx->pos = file->f_pos;
if (shared)
res = file->f_op->iterate_shared(file, ctx);
else
res = file->f_op->iterate(file, ctx);
file->f_pos = ctx->pos;
fsnotify_access(file);
file_accessed(file);
}
if (shared)
inode_unlock_shared(inode);
else
inode_unlock(inode);
out:
return res;
}
EXPORT_SYMBOL(iterate_dir);
/*
* Traditional linux readdir() handling..
*
* "count=1" is a special case, meaning that the buffer is one
* dirent-structure in size and that the code can't handle more
* anyway. Thus the special "fillonedir()" function for that
* case (the low-level handlers don't need to care about this).
*/
#ifdef __ARCH_WANT_OLD_READDIR
struct old_linux_dirent {
unsigned long d_ino;
unsigned long d_offset;
unsigned short d_namlen;
char d_name[1];
};
struct readdir_callback {
struct dir_context ctx;
struct old_linux_dirent __user * dirent;
int result;
};
static int fillonedir(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct readdir_callback *buf =
container_of(ctx, struct readdir_callback, ctx);
struct old_linux_dirent __user * dirent;
unsigned long d_ino;
if (buf->result)
return -EINVAL;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->result = -EOVERFLOW;
return -EOVERFLOW;
}
buf->result++;
dirent = buf->dirent;
if (!access_ok(VERIFY_WRITE, dirent,
(unsigned long)(dirent->d_name + namlen + 1) -
(unsigned long)dirent))
goto efault;
if ( __put_user(d_ino, &dirent->d_ino) ||
__put_user(offset, &dirent->d_offset) ||
__put_user(namlen, &dirent->d_namlen) ||
__copy_to_user(dirent->d_name, name, namlen) ||
__put_user(0, dirent->d_name + namlen))
goto efault;
return 0;
efault:
buf->result = -EFAULT;
return -EFAULT;
}
SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
struct old_linux_dirent __user *, dirent, unsigned int, count)
{
int error;
struct fd f = fdget_pos(fd);
struct readdir_callback buf = {
.ctx.actor = fillonedir,
.dirent = dirent
};
if (!f.file)
return -EBADF;
error = iterate_dir(f.file, &buf.ctx);
if (buf.result)
error = buf.result;
fdput_pos(f);
return error;
}
#endif /* __ARCH_WANT_OLD_READDIR */
/*
* New, all-improved, singing, dancing, iBCS2-compliant getdents()
* interface.
*/
struct linux_dirent {
unsigned long d_ino;
unsigned long d_off;
unsigned short d_reclen;
char d_name[1];
};
struct getdents_callback {
struct dir_context ctx;
struct linux_dirent __user * current_dir;
struct linux_dirent __user * previous;
int count;
int error;
};
static int filldir(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct linux_dirent __user * dirent;
struct getdents_callback *buf =
container_of(ctx, struct getdents_callback, ctx);
unsigned long d_ino;
int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2,
sizeof(long));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->error = -EOVERFLOW;
return -EOVERFLOW;
}
dirent = buf->previous;
if (dirent) {
if (signal_pending(current))
return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
dirent = buf->current_dir;
if (__put_user(d_ino, &dirent->d_ino))
goto efault;
if (__put_user(reclen, &dirent->d_reclen))
goto efault;
if (copy_to_user(dirent->d_name, name, namlen))
goto efault;
if (__put_user(0, dirent->d_name + namlen))
goto efault;
if (__put_user(d_type, (char __user *) dirent + reclen - 1))
goto efault;
buf->previous = dirent;
dirent = (void __user *)dirent + reclen;
buf->current_dir = dirent;
buf->count -= reclen;
return 0;
efault:
buf->error = -EFAULT;
return -EFAULT;
}
SYSCALL_DEFINE3(getdents, unsigned int, fd,
struct linux_dirent __user *, dirent, unsigned int, count)
{
struct fd f;
struct linux_dirent __user * lastdirent;
struct getdents_callback buf = {
.ctx.actor = filldir,
.count = count,
.current_dir = dirent
};
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
f = fdget_pos(fd);
if (!f.file)
return -EBADF;
error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
if (put_user(buf.ctx.pos, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
}
fdput_pos(f);
return error;
}
struct getdents_callback64 {
struct dir_context ctx;
struct linux_dirent64 __user * current_dir;
struct linux_dirent64 __user * previous;
int count;
int error;
};
static int filldir64(struct dir_context *ctx, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct linux_dirent64 __user *dirent;
struct getdents_callback64 *buf =
container_of(ctx, struct getdents_callback64, ctx);
int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
sizeof(u64));
buf->error = -EINVAL; /* only used if we fail.. */
if (reclen > buf->count)
return -EINVAL;
dirent = buf->previous;
if (dirent) {
if (signal_pending(current))
return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
dirent = buf->current_dir;
if (__put_user(ino, &dirent->d_ino))
goto efault;
if (__put_user(0, &dirent->d_off))
goto efault;
if (__put_user(reclen, &dirent->d_reclen))
goto efault;
if (__put_user(d_type, &dirent->d_type))
goto efault;
if (copy_to_user(dirent->d_name, name, namlen))
goto efault;
if (__put_user(0, dirent->d_name + namlen))
goto efault;
buf->previous = dirent;
dirent = (void __user *)dirent + reclen;
buf->current_dir = dirent;
buf->count -= reclen;
return 0;
efault:
buf->error = -EFAULT;
return -EFAULT;
}
SYSCALL_DEFINE3(getdents64, unsigned int, fd,
struct linux_dirent64 __user *, dirent, unsigned int, count)
{
struct fd f;
struct linux_dirent64 __user * lastdirent;
struct getdents_callback64 buf = {
.ctx.actor = filldir64,
.count = count,
.current_dir = dirent
};
int error;
if (!access_ok(VERIFY_WRITE, dirent, count))
return -EFAULT;
f = fdget_pos(fd);
if (!f.file)
return -EBADF;
error = iterate_dir(f.file, &buf.ctx);
if (error >= 0)
error = buf.error;
lastdirent = buf.previous;
if (lastdirent) {
typeof(lastdirent->d_off) d_off = buf.ctx.pos;
if (__put_user(d_off, &lastdirent->d_off))
error = -EFAULT;
else
error = count - buf.count;
}
fdput_pos(f);
return error;
}