2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* binfmt_misc.c
|
|
|
|
*
|
2007-10-19 23:21:04 +02:00
|
|
|
* Copyright (C) 1997 Richard Günther
|
2005-04-17 00:20:36 +02:00
|
|
|
*
|
|
|
|
* binfmt_misc detects binaries via a magic or filename extension and invokes
|
|
|
|
* a specified wrapper. This should obsolete binfmt_java, binfmt_em86 and
|
|
|
|
* binfmt_mz.
|
|
|
|
*
|
|
|
|
* 1997-04-25 first version
|
|
|
|
* [...]
|
|
|
|
* 1997-05-19 cleanup
|
|
|
|
* 1997-06-26 hpa: pass the real filename rather than argv[0]
|
|
|
|
* 1997-06-30 minor cleanup
|
|
|
|
* 1997-08-09 removed extension stripping, locking cleanup
|
|
|
|
* 2001-02-28 AV: rewritten into something that resembles C. Original didn't.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/init.h>
|
Detach sched.h from mm.h
First thing mm.h does is including sched.h solely for can_do_mlock() inline
function which has "current" dereference inside. By dealing with can_do_mlock()
mm.h can be detached from sched.h which is good. See below, why.
This patch
a) removes unconditional inclusion of sched.h from mm.h
b) makes can_do_mlock() normal function in mm/mlock.c
c) exports can_do_mlock() to not break compilation
d) adds sched.h inclusions back to files that were getting it indirectly.
e) adds less bloated headers to some files (asm/signal.h, jiffies.h) that were
getting them indirectly
Net result is:
a) mm.h users would get less code to open, read, preprocess, parse, ... if
they don't need sched.h
b) sched.h stops being dependency for significant number of files:
on x86_64 allmodconfig touching sched.h results in recompile of 4083 files,
after patch it's only 3744 (-8.3%).
Cross-compile tested on
all arm defconfigs, all mips defconfigs, all powerpc defconfigs,
alpha alpha-up
arm
i386 i386-up i386-defconfig i386-allnoconfig
ia64 ia64-up
m68k
mips
parisc parisc-up
powerpc powerpc-up
s390 s390-up
sparc sparc-up
sparc64 sparc64-up
um-x86_64
x86_64 x86_64-up x86_64-defconfig x86_64-allnoconfig
as well as my two usual configs.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-20 23:22:52 +02:00
|
|
|
#include <linux/sched.h>
|
2012-03-23 23:01:50 +01:00
|
|
|
#include <linux/magic.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <linux/binfmts.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/ctype.h>
|
2013-05-01 00:27:33 +02:00
|
|
|
#include <linux/string_helpers.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/syscalls.h>
|
2008-07-24 06:29:15 +02:00
|
|
|
#include <linux/fs.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
|
|
|
enum {
|
|
|
|
VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
|
|
|
|
};
|
|
|
|
|
|
|
|
static LIST_HEAD(entries);
|
|
|
|
static int enabled = 1;
|
|
|
|
|
|
|
|
enum {Enabled, Magic};
|
|
|
|
#define MISC_FMT_PRESERVE_ARGV0 (1<<31)
|
|
|
|
#define MISC_FMT_OPEN_BINARY (1<<30)
|
|
|
|
#define MISC_FMT_CREDENTIALS (1<<29)
|
|
|
|
|
|
|
|
typedef struct {
|
|
|
|
struct list_head list;
|
|
|
|
unsigned long flags; /* type, status, etc. */
|
|
|
|
int offset; /* offset of magic */
|
|
|
|
int size; /* size of magic/mask */
|
|
|
|
char *magic; /* magic or filename extension */
|
|
|
|
char *mask; /* mask, NULL for exact match */
|
|
|
|
char *interpreter; /* filename of interpreter */
|
|
|
|
char *name;
|
|
|
|
struct dentry *dentry;
|
|
|
|
} Node;
|
|
|
|
|
|
|
|
static DEFINE_RWLOCK(entries_lock);
|
2006-06-09 15:34:16 +02:00
|
|
|
static struct file_system_type bm_fs_type;
|
2005-04-17 00:20:36 +02:00
|
|
|
static struct vfsmount *bm_mnt;
|
|
|
|
static int entry_count;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check if we support the binfmt
|
|
|
|
* if we do, return the node, else NULL
|
|
|
|
* locking is done in load_misc_binary
|
|
|
|
*/
|
|
|
|
static Node *check_file(struct linux_binprm *bprm)
|
|
|
|
{
|
|
|
|
char *p = strrchr(bprm->interp, '.');
|
|
|
|
struct list_head *l;
|
|
|
|
|
|
|
|
list_for_each(l, &entries) {
|
|
|
|
Node *e = list_entry(l, Node, list);
|
|
|
|
char *s;
|
|
|
|
int j;
|
|
|
|
|
|
|
|
if (!test_bit(Enabled, &e->flags))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (!test_bit(Magic, &e->flags)) {
|
|
|
|
if (p && !strcmp(e->magic, p + 1))
|
|
|
|
return e;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
s = bprm->buf + e->offset;
|
|
|
|
if (e->mask) {
|
|
|
|
for (j = 0; j < e->size; j++)
|
|
|
|
if ((*s++ ^ e->magic[j]) & e->mask[j])
|
|
|
|
break;
|
|
|
|
} else {
|
|
|
|
for (j = 0; j < e->size; j++)
|
|
|
|
if ((*s++ ^ e->magic[j]))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (j == e->size)
|
|
|
|
return e;
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* the loader itself
|
|
|
|
*/
|
2012-10-21 04:00:48 +02:00
|
|
|
static int load_misc_binary(struct linux_binprm *bprm)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
Node *fmt;
|
|
|
|
struct file * interp_file = NULL;
|
|
|
|
char iname[BINPRM_BUF_SIZE];
|
2010-08-18 00:52:56 +02:00
|
|
|
const char *iname_addr = iname;
|
2005-04-17 00:20:36 +02:00
|
|
|
int retval;
|
|
|
|
int fd_binary = -1;
|
|
|
|
|
|
|
|
retval = -ENOEXEC;
|
|
|
|
if (!enabled)
|
|
|
|
goto _ret;
|
|
|
|
|
|
|
|
/* to keep locking time low, we copy the interpreter string */
|
|
|
|
read_lock(&entries_lock);
|
|
|
|
fmt = check_file(bprm);
|
|
|
|
if (fmt)
|
|
|
|
strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
|
|
|
|
read_unlock(&entries_lock);
|
|
|
|
if (!fmt)
|
|
|
|
goto _ret;
|
|
|
|
|
|
|
|
if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
|
2007-07-19 10:48:16 +02:00
|
|
|
retval = remove_arg_zero(bprm);
|
|
|
|
if (retval)
|
|
|
|
goto _ret;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
if (fmt->flags & MISC_FMT_OPEN_BINARY) {
|
|
|
|
|
|
|
|
/* if the binary should be opened on behalf of the
|
|
|
|
* interpreter than keep it open and assign descriptor
|
|
|
|
* to it */
|
|
|
|
fd_binary = get_unused_fd();
|
|
|
|
if (fd_binary < 0) {
|
|
|
|
retval = fd_binary;
|
2008-04-22 11:11:59 +02:00
|
|
|
goto _ret;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
fd_install(fd_binary, bprm->file);
|
|
|
|
|
|
|
|
/* if the binary is not readable than enforce mm->dumpable=0
|
|
|
|
regardless of the interpreter's permissions */
|
2011-06-19 18:49:47 +02:00
|
|
|
would_dump(bprm, bprm->file);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
allow_write_access(bprm->file);
|
|
|
|
bprm->file = NULL;
|
|
|
|
|
|
|
|
/* mark the bprm that fd should be passed to interp */
|
|
|
|
bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
|
|
|
|
bprm->interp_data = fd_binary;
|
|
|
|
|
|
|
|
} else {
|
|
|
|
allow_write_access(bprm->file);
|
|
|
|
fput(bprm->file);
|
|
|
|
bprm->file = NULL;
|
|
|
|
}
|
|
|
|
/* make argv[1] be the path to the binary */
|
|
|
|
retval = copy_strings_kernel (1, &bprm->interp, bprm);
|
|
|
|
if (retval < 0)
|
|
|
|
goto _error;
|
|
|
|
bprm->argc++;
|
|
|
|
|
|
|
|
/* add the interp as argv[0] */
|
|
|
|
retval = copy_strings_kernel (1, &iname_addr, bprm);
|
|
|
|
if (retval < 0)
|
|
|
|
goto _error;
|
|
|
|
bprm->argc ++;
|
|
|
|
|
exec: do not leave bprm->interp on stack
If a series of scripts are executed, each triggering module loading via
unprintable bytes in the script header, kernel stack contents can leak
into the command line.
Normally execution of binfmt_script and binfmt_misc happens recursively.
However, when modules are enabled, and unprintable bytes exist in the
bprm->buf, execution will restart after attempting to load matching
binfmt modules. Unfortunately, the logic in binfmt_script and
binfmt_misc does not expect to get restarted. They leave bprm->interp
pointing to their local stack. This means on restart bprm->interp is
left pointing into unused stack memory which can then be copied into the
userspace argv areas.
After additional study, it seems that both recursion and restart remains
the desirable way to handle exec with scripts, misc, and modules. As
such, we need to protect the changes to interp.
This changes the logic to require allocation for any changes to the
bprm->interp. To avoid adding a new kmalloc to every exec, the default
value is left as-is. Only when passing through binfmt_script or
binfmt_misc does an allocation take place.
For a proof of concept, see DoTest.sh from:
http://www.halfdog.net/Security/2012/LinuxKernelBinfmtScriptStackDataDisclosure/
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: halfdog <me@halfdog.net>
Cc: P J P <ppandit@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-21 00:05:16 +01:00
|
|
|
/* Update interp in case binfmt_script needs it. */
|
|
|
|
retval = bprm_change_interp(iname, bprm);
|
|
|
|
if (retval < 0)
|
|
|
|
goto _error;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
interp_file = open_exec (iname);
|
|
|
|
retval = PTR_ERR (interp_file);
|
|
|
|
if (IS_ERR (interp_file))
|
|
|
|
goto _error;
|
|
|
|
|
|
|
|
bprm->file = interp_file;
|
|
|
|
if (fmt->flags & MISC_FMT_CREDENTIALS) {
|
|
|
|
/*
|
|
|
|
* No need to call prepare_binprm(), it's already been
|
|
|
|
* done. bprm->buf is stale, update from interp_file.
|
|
|
|
*/
|
|
|
|
memset(bprm->buf, 0, BINPRM_BUF_SIZE);
|
|
|
|
retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
|
|
|
|
} else
|
|
|
|
retval = prepare_binprm (bprm);
|
|
|
|
|
|
|
|
if (retval < 0)
|
|
|
|
goto _error;
|
|
|
|
|
2012-10-21 03:53:31 +02:00
|
|
|
retval = search_binary_handler(bprm);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (retval < 0)
|
|
|
|
goto _error;
|
|
|
|
|
|
|
|
_ret:
|
|
|
|
return retval;
|
|
|
|
_error:
|
|
|
|
if (fd_binary > 0)
|
|
|
|
sys_close(fd_binary);
|
|
|
|
bprm->interp_flags = 0;
|
|
|
|
bprm->interp_data = 0;
|
|
|
|
goto _ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Command parsers */
|
|
|
|
|
|
|
|
/*
|
|
|
|
* parses and copies one argument enclosed in del from *sp to *dp,
|
|
|
|
* recognising the \x special.
|
|
|
|
* returns pointer to the copied argument or NULL in case of an
|
|
|
|
* error (and sets err) or null argument length.
|
|
|
|
*/
|
|
|
|
static char *scanarg(char *s, char del)
|
|
|
|
{
|
|
|
|
char c;
|
|
|
|
|
|
|
|
while ((c = *s++) != del) {
|
|
|
|
if (c == '\\' && *s == 'x') {
|
|
|
|
s++;
|
|
|
|
if (!isxdigit(*s++))
|
|
|
|
return NULL;
|
|
|
|
if (!isxdigit(*s++))
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
2006-01-14 22:20:43 +01:00
|
|
|
static char * check_special_flags (char * sfs, Node * e)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
|
|
|
char * p = sfs;
|
|
|
|
int cont = 1;
|
|
|
|
|
|
|
|
/* special flags */
|
|
|
|
while (cont) {
|
|
|
|
switch (*p) {
|
|
|
|
case 'P':
|
|
|
|
p++;
|
|
|
|
e->flags |= MISC_FMT_PRESERVE_ARGV0;
|
|
|
|
break;
|
|
|
|
case 'O':
|
|
|
|
p++;
|
|
|
|
e->flags |= MISC_FMT_OPEN_BINARY;
|
|
|
|
break;
|
|
|
|
case 'C':
|
|
|
|
p++;
|
|
|
|
/* this flags also implies the
|
|
|
|
open-binary flag */
|
|
|
|
e->flags |= (MISC_FMT_CREDENTIALS |
|
|
|
|
MISC_FMT_OPEN_BINARY);
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
cont = 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return p;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* This registers a new binary format, it recognises the syntax
|
|
|
|
* ':name:type:offset:magic:mask:interpreter:flags'
|
|
|
|
* where the ':' is the IFS, that can be chosen with the first char
|
|
|
|
*/
|
|
|
|
static Node *create_entry(const char __user *buffer, size_t count)
|
|
|
|
{
|
|
|
|
Node *e;
|
|
|
|
int memsize, err;
|
|
|
|
char *buf, *p;
|
|
|
|
char del;
|
|
|
|
|
|
|
|
/* some sanity checks */
|
|
|
|
err = -EINVAL;
|
|
|
|
if ((count < 11) || (count > 256))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = -ENOMEM;
|
|
|
|
memsize = sizeof(Node) + count + 8;
|
2006-12-13 09:35:56 +01:00
|
|
|
e = kmalloc(memsize, GFP_USER);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (!e)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
p = buf = (char *)e + sizeof(Node);
|
|
|
|
|
|
|
|
memset(e, 0, sizeof(Node));
|
|
|
|
if (copy_from_user(buf, buffer, count))
|
|
|
|
goto Efault;
|
|
|
|
|
|
|
|
del = *p++; /* delimeter */
|
|
|
|
|
|
|
|
memset(buf+count, del, 8);
|
|
|
|
|
|
|
|
e->name = p;
|
|
|
|
p = strchr(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
*p++ = '\0';
|
|
|
|
if (!e->name[0] ||
|
|
|
|
!strcmp(e->name, ".") ||
|
|
|
|
!strcmp(e->name, "..") ||
|
|
|
|
strchr(e->name, '/'))
|
|
|
|
goto Einval;
|
|
|
|
switch (*p++) {
|
|
|
|
case 'E': e->flags = 1<<Enabled; break;
|
|
|
|
case 'M': e->flags = (1<<Enabled) | (1<<Magic); break;
|
|
|
|
default: goto Einval;
|
|
|
|
}
|
|
|
|
if (*p++ != del)
|
|
|
|
goto Einval;
|
|
|
|
if (test_bit(Magic, &e->flags)) {
|
|
|
|
char *s = strchr(p, del);
|
|
|
|
if (!s)
|
|
|
|
goto Einval;
|
|
|
|
*s++ = '\0';
|
|
|
|
e->offset = simple_strtoul(p, &p, 10);
|
|
|
|
if (*p++)
|
|
|
|
goto Einval;
|
|
|
|
e->magic = p;
|
|
|
|
p = scanarg(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
p[-1] = '\0';
|
|
|
|
if (!e->magic[0])
|
|
|
|
goto Einval;
|
|
|
|
e->mask = p;
|
|
|
|
p = scanarg(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
p[-1] = '\0';
|
|
|
|
if (!e->mask[0])
|
|
|
|
e->mask = NULL;
|
2013-05-01 00:27:33 +02:00
|
|
|
e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
|
|
|
|
if (e->mask &&
|
|
|
|
string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
|
2005-04-17 00:20:36 +02:00
|
|
|
goto Einval;
|
|
|
|
if (e->size + e->offset > BINPRM_BUF_SIZE)
|
|
|
|
goto Einval;
|
|
|
|
} else {
|
|
|
|
p = strchr(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
*p++ = '\0';
|
|
|
|
e->magic = p;
|
|
|
|
p = strchr(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
*p++ = '\0';
|
|
|
|
if (!e->magic[0] || strchr(e->magic, '/'))
|
|
|
|
goto Einval;
|
|
|
|
p = strchr(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
*p++ = '\0';
|
|
|
|
}
|
|
|
|
e->interpreter = p;
|
|
|
|
p = strchr(p, del);
|
|
|
|
if (!p)
|
|
|
|
goto Einval;
|
|
|
|
*p++ = '\0';
|
|
|
|
if (!e->interpreter[0])
|
|
|
|
goto Einval;
|
|
|
|
|
|
|
|
|
|
|
|
p = check_special_flags (p, e);
|
|
|
|
|
|
|
|
if (*p == '\n')
|
|
|
|
p++;
|
|
|
|
if (p != buf + count)
|
|
|
|
goto Einval;
|
|
|
|
return e;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ERR_PTR(err);
|
|
|
|
|
|
|
|
Efault:
|
|
|
|
kfree(e);
|
|
|
|
return ERR_PTR(-EFAULT);
|
|
|
|
Einval:
|
|
|
|
kfree(e);
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set status of entry/binfmt_misc:
|
|
|
|
* '1' enables, '0' disables and '-1' clears entry/binfmt_misc
|
|
|
|
*/
|
|
|
|
static int parse_command(const char __user *buffer, size_t count)
|
|
|
|
{
|
|
|
|
char s[4];
|
|
|
|
|
|
|
|
if (!count)
|
|
|
|
return 0;
|
|
|
|
if (count > 3)
|
|
|
|
return -EINVAL;
|
|
|
|
if (copy_from_user(s, buffer, count))
|
|
|
|
return -EFAULT;
|
|
|
|
if (s[count-1] == '\n')
|
|
|
|
count--;
|
|
|
|
if (count == 1 && s[0] == '0')
|
|
|
|
return 1;
|
|
|
|
if (count == 1 && s[0] == '1')
|
|
|
|
return 2;
|
|
|
|
if (count == 2 && s[0] == '-' && s[1] == '1')
|
|
|
|
return 3;
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* generic stuff */
|
|
|
|
|
|
|
|
static void entry_status(Node *e, char *page)
|
|
|
|
{
|
|
|
|
char *dp;
|
|
|
|
char *status = "disabled";
|
|
|
|
const char * flags = "flags: ";
|
|
|
|
|
|
|
|
if (test_bit(Enabled, &e->flags))
|
|
|
|
status = "enabled";
|
|
|
|
|
|
|
|
if (!VERBOSE_STATUS) {
|
|
|
|
sprintf(page, "%s\n", status);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
sprintf(page, "%s\ninterpreter %s\n", status, e->interpreter);
|
|
|
|
dp = page + strlen(page);
|
|
|
|
|
|
|
|
/* print the special flags */
|
|
|
|
sprintf (dp, "%s", flags);
|
|
|
|
dp += strlen (flags);
|
|
|
|
if (e->flags & MISC_FMT_PRESERVE_ARGV0) {
|
|
|
|
*dp ++ = 'P';
|
|
|
|
}
|
|
|
|
if (e->flags & MISC_FMT_OPEN_BINARY) {
|
|
|
|
*dp ++ = 'O';
|
|
|
|
}
|
|
|
|
if (e->flags & MISC_FMT_CREDENTIALS) {
|
|
|
|
*dp ++ = 'C';
|
|
|
|
}
|
|
|
|
*dp ++ = '\n';
|
|
|
|
|
|
|
|
|
|
|
|
if (!test_bit(Magic, &e->flags)) {
|
|
|
|
sprintf(dp, "extension .%s\n", e->magic);
|
|
|
|
} else {
|
|
|
|
int i;
|
|
|
|
|
|
|
|
sprintf(dp, "offset %i\nmagic ", e->offset);
|
|
|
|
dp = page + strlen(page);
|
|
|
|
for (i = 0; i < e->size; i++) {
|
|
|
|
sprintf(dp, "%02x", 0xff & (int) (e->magic[i]));
|
|
|
|
dp += 2;
|
|
|
|
}
|
|
|
|
if (e->mask) {
|
|
|
|
sprintf(dp, "\nmask ");
|
|
|
|
dp += 6;
|
|
|
|
for (i = 0; i < e->size; i++) {
|
|
|
|
sprintf(dp, "%02x", 0xff & (int) (e->mask[i]));
|
|
|
|
dp += 2;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
*dp++ = '\n';
|
|
|
|
*dp = '\0';
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct inode *bm_get_inode(struct super_block *sb, int mode)
|
|
|
|
{
|
|
|
|
struct inode * inode = new_inode(sb);
|
|
|
|
|
|
|
|
if (inode) {
|
2010-10-23 17:19:54 +02:00
|
|
|
inode->i_ino = get_next_ino();
|
2005-04-17 00:20:36 +02:00
|
|
|
inode->i_mode = mode;
|
|
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime =
|
|
|
|
current_fs_time(inode->i_sb);
|
|
|
|
}
|
|
|
|
return inode;
|
|
|
|
}
|
|
|
|
|
2010-06-07 20:34:48 +02:00
|
|
|
static void bm_evict_inode(struct inode *inode)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2012-05-03 14:48:02 +02:00
|
|
|
clear_inode(inode);
|
2006-09-27 10:50:46 +02:00
|
|
|
kfree(inode->i_private);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static void kill_node(Node *e)
|
|
|
|
{
|
|
|
|
struct dentry *dentry;
|
|
|
|
|
|
|
|
write_lock(&entries_lock);
|
|
|
|
dentry = e->dentry;
|
|
|
|
if (dentry) {
|
|
|
|
list_del_init(&e->list);
|
|
|
|
e->dentry = NULL;
|
|
|
|
}
|
|
|
|
write_unlock(&entries_lock);
|
|
|
|
|
|
|
|
if (dentry) {
|
2011-10-28 14:13:28 +02:00
|
|
|
drop_nlink(dentry->d_inode);
|
2005-04-17 00:20:36 +02:00
|
|
|
d_drop(dentry);
|
|
|
|
dput(dentry);
|
|
|
|
simple_release_fs(&bm_mnt, &entry_count);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* /<entry> */
|
|
|
|
|
|
|
|
static ssize_t
|
|
|
|
bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
|
|
|
|
{
|
2013-01-23 23:07:38 +01:00
|
|
|
Node *e = file_inode(file)->i_private;
|
2005-04-17 00:20:36 +02:00
|
|
|
ssize_t res;
|
|
|
|
char *page;
|
|
|
|
|
|
|
|
if (!(page = (char*) __get_free_page(GFP_KERNEL)))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
entry_status(e, page);
|
|
|
|
|
2008-07-24 06:29:15 +02:00
|
|
|
res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
free_page((unsigned long) page);
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
struct dentry *root;
|
2013-01-23 23:07:38 +01:00
|
|
|
Node *e = file_inode(file)->i_private;
|
2005-04-17 00:20:36 +02:00
|
|
|
int res = parse_command(buffer, count);
|
|
|
|
|
|
|
|
switch (res) {
|
|
|
|
case 1: clear_bit(Enabled, &e->flags);
|
|
|
|
break;
|
|
|
|
case 2: set_bit(Enabled, &e->flags);
|
|
|
|
break;
|
2011-12-08 00:16:57 +01:00
|
|
|
case 3: root = dget(file->f_path.dentry->d_sb->s_root);
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
kill_node(e);
|
|
|
|
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
dput(root);
|
|
|
|
break;
|
|
|
|
default: return res;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 11:56:42 +02:00
|
|
|
static const struct file_operations bm_entry_operations = {
|
2005-04-17 00:20:36 +02:00
|
|
|
.read = bm_entry_read,
|
|
|
|
.write = bm_entry_write,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
|
|
|
.llseek = default_llseek,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/* /register */
|
|
|
|
|
|
|
|
static ssize_t bm_register_write(struct file *file, const char __user *buffer,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
Node *e;
|
|
|
|
struct inode *inode;
|
|
|
|
struct dentry *root, *dentry;
|
2011-12-08 00:16:57 +01:00
|
|
|
struct super_block *sb = file->f_path.dentry->d_sb;
|
2005-04-17 00:20:36 +02:00
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
e = create_entry(buffer, count);
|
|
|
|
|
|
|
|
if (IS_ERR(e))
|
|
|
|
return PTR_ERR(e);
|
|
|
|
|
|
|
|
root = dget(sb->s_root);
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
dentry = lookup_one_len(e->name, root, strlen(e->name));
|
|
|
|
err = PTR_ERR(dentry);
|
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
err = -EEXIST;
|
|
|
|
if (dentry->d_inode)
|
|
|
|
goto out2;
|
|
|
|
|
|
|
|
inode = bm_get_inode(sb, S_IFREG | 0644);
|
|
|
|
|
|
|
|
err = -ENOMEM;
|
|
|
|
if (!inode)
|
|
|
|
goto out2;
|
|
|
|
|
2006-06-09 15:34:16 +02:00
|
|
|
err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (err) {
|
|
|
|
iput(inode);
|
|
|
|
inode = NULL;
|
|
|
|
goto out2;
|
|
|
|
}
|
|
|
|
|
|
|
|
e->dentry = dget(dentry);
|
2006-09-27 10:50:46 +02:00
|
|
|
inode->i_private = e;
|
2005-04-17 00:20:36 +02:00
|
|
|
inode->i_fop = &bm_entry_operations;
|
|
|
|
|
|
|
|
d_instantiate(dentry, inode);
|
|
|
|
write_lock(&entries_lock);
|
|
|
|
list_add(&e->list, &entries);
|
|
|
|
write_unlock(&entries_lock);
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
out2:
|
|
|
|
dput(dentry);
|
|
|
|
out:
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
dput(root);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
kfree(e);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 11:56:42 +02:00
|
|
|
static const struct file_operations bm_register_operations = {
|
2005-04-17 00:20:36 +02:00
|
|
|
.write = bm_register_write,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
|
|
|
.llseek = noop_llseek,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/* /status */
|
|
|
|
|
|
|
|
static ssize_t
|
|
|
|
bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
|
|
|
|
{
|
2009-01-06 23:41:38 +01:00
|
|
|
char *s = enabled ? "enabled\n" : "disabled\n";
|
2005-04-17 00:20:36 +02:00
|
|
|
|
2007-05-09 11:33:32 +02:00
|
|
|
return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t bm_status_write(struct file * file, const char __user * buffer,
|
|
|
|
size_t count, loff_t *ppos)
|
|
|
|
{
|
|
|
|
int res = parse_command(buffer, count);
|
|
|
|
struct dentry *root;
|
|
|
|
|
|
|
|
switch (res) {
|
|
|
|
case 1: enabled = 0; break;
|
|
|
|
case 2: enabled = 1; break;
|
2011-12-08 00:16:57 +01:00
|
|
|
case 3: root = dget(file->f_path.dentry->d_sb->s_root);
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
while (!list_empty(&entries))
|
|
|
|
kill_node(list_entry(entries.next, Node, list));
|
|
|
|
|
2006-01-10 00:59:24 +01:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-17 00:20:36 +02:00
|
|
|
dput(root);
|
|
|
|
default: return res;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 11:56:42 +02:00
|
|
|
static const struct file_operations bm_status_operations = {
|
2005-04-17 00:20:36 +02:00
|
|
|
.read = bm_status_read,
|
|
|
|
.write = bm_status_write,
|
llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.
The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.
New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time. Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.
The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.
Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.
Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.
===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
// but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}
@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}
@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}
@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
*off = E
|
*off += E
|
func(..., off, ...)
|
E = *off
)
...+>
}
@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}
@ fops0 @
identifier fops;
@@
struct file_operations fops = {
...
};
@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
.llseek = llseek_f,
...
};
@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
.read = read_f,
...
};
@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
.write = write_f,
...
};
@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
.open = open_f,
...
};
// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
... .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};
@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
... .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};
// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
... .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};
// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};
// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};
@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+ .llseek = default_llseek, /* write accesses f_pos */
};
// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////
@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
.write = write_f,
.read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};
@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};
@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};
@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
|
|
|
.llseek = default_llseek,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/* Superblock handling */
|
|
|
|
|
2007-02-12 09:55:41 +01:00
|
|
|
static const struct super_operations s_ops = {
|
2005-04-17 00:20:36 +02:00
|
|
|
.statfs = simple_statfs,
|
2010-06-07 20:34:48 +02:00
|
|
|
.evict_inode = bm_evict_inode,
|
2005-04-17 00:20:36 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
static int bm_fill_super(struct super_block * sb, void * data, int silent)
|
|
|
|
{
|
|
|
|
static struct tree_descr bm_files[] = {
|
2007-05-08 09:32:31 +02:00
|
|
|
[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
|
|
|
|
[3] = {"register", &bm_register_operations, S_IWUSR},
|
2005-04-17 00:20:36 +02:00
|
|
|
/* last one */ {""}
|
|
|
|
};
|
2012-03-23 23:01:50 +01:00
|
|
|
int err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
|
2005-04-17 00:20:36 +02:00
|
|
|
if (!err)
|
|
|
|
sb->s_op = &s_ops;
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2010-07-24 23:48:30 +02:00
|
|
|
static struct dentry *bm_mount(struct file_system_type *fs_type,
|
|
|
|
int flags, const char *dev_name, void *data)
|
2005-04-17 00:20:36 +02:00
|
|
|
{
|
2010-07-24 23:48:30 +02:00
|
|
|
return mount_single(fs_type, flags, data, bm_fill_super);
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
static struct linux_binfmt misc_format = {
|
|
|
|
.module = THIS_MODULE,
|
|
|
|
.load_binary = load_misc_binary,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct file_system_type bm_fs_type = {
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.name = "binfmt_misc",
|
2010-07-24 23:48:30 +02:00
|
|
|
.mount = bm_mount,
|
2005-04-17 00:20:36 +02:00
|
|
|
.kill_sb = kill_litter_super,
|
|
|
|
};
|
2013-03-03 04:39:14 +01:00
|
|
|
MODULE_ALIAS_FS("binfmt_misc");
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
static int __init init_misc_binfmt(void)
|
|
|
|
{
|
|
|
|
int err = register_filesystem(&bm_fs_type);
|
2012-03-17 08:05:16 +01:00
|
|
|
if (!err)
|
|
|
|
insert_binfmt(&misc_format);
|
2005-04-17 00:20:36 +02:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit exit_misc_binfmt(void)
|
|
|
|
{
|
|
|
|
unregister_binfmt(&misc_format);
|
|
|
|
unregister_filesystem(&bm_fs_type);
|
|
|
|
}
|
|
|
|
|
|
|
|
core_initcall(init_misc_binfmt);
|
|
|
|
module_exit(exit_misc_binfmt);
|
|
|
|
MODULE_LICENSE("GPL");
|