2005-04-16 16:20:36 -06:00
|
|
|
/*
|
|
|
|
* binfmt_misc.c
|
|
|
|
*
|
2007-10-19 15:21:04 -06:00
|
|
|
* Copyright (C) 1997 Richard Günther
|
2005-04-16 16:20:36 -06:00
|
|
|
*
|
|
|
|
* 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 15:22:52 -06:00
|
|
|
#include <linux/sched.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
#include <linux/binfmts.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/ctype.h>
|
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/pagemap.h>
|
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/syscalls.h>
|
2008-07-23 22:29:15 -06:00
|
|
|
#include <linux/fs.h>
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
#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 07:34:16 -06:00
|
|
|
static struct file_system_type bm_fs_type;
|
2005-04-16 16:20:36 -06:00
|
|
|
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
|
|
|
|
*/
|
|
|
|
static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
Node *fmt;
|
|
|
|
struct file * interp_file = NULL;
|
|
|
|
char iname[BINPRM_BUF_SIZE];
|
|
|
|
char *iname_addr = iname;
|
|
|
|
int retval;
|
|
|
|
int fd_binary = -1;
|
|
|
|
|
|
|
|
retval = -ENOEXEC;
|
|
|
|
if (!enabled)
|
|
|
|
goto _ret;
|
|
|
|
|
2008-04-29 01:59:24 -06:00
|
|
|
retval = -ENOEXEC;
|
|
|
|
if (bprm->misc_bang)
|
|
|
|
goto _ret;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
/* 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 02:48:16 -06:00
|
|
|
retval = remove_arg_zero(bprm);
|
|
|
|
if (retval)
|
|
|
|
goto _ret;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
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 03:11:59 -06:00
|
|
|
goto _ret;
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
fd_install(fd_binary, bprm->file);
|
|
|
|
|
|
|
|
/* if the binary is not readable than enforce mm->dumpable=0
|
|
|
|
regardless of the interpreter's permissions */
|
2005-11-08 22:35:04 -07:00
|
|
|
if (file_permission(bprm->file, MAY_READ))
|
2005-04-16 16:20:36 -06:00
|
|
|
bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP;
|
|
|
|
|
|
|
|
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 ++;
|
|
|
|
|
|
|
|
bprm->interp = iname; /* for binfmt_script */
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
2008-08-20 15:09:10 -06:00
|
|
|
bprm->misc_bang = 1;
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
retval = search_binary_handler (bprm, regs);
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int unquote(char *from)
|
|
|
|
{
|
|
|
|
char c = 0, *s = from, *p = from;
|
|
|
|
|
|
|
|
while ((c = *s++) != '\0') {
|
|
|
|
if (c == '\\' && *s == 'x') {
|
|
|
|
s++;
|
|
|
|
c = toupper(*s++);
|
|
|
|
*p = (c - (isdigit(c) ? '0' : 'A' - 10)) << 4;
|
|
|
|
c = toupper(*s++);
|
|
|
|
*p++ |= c - (isdigit(c) ? '0' : 'A' - 10);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
*p++ = c;
|
|
|
|
}
|
|
|
|
return p - from;
|
|
|
|
}
|
|
|
|
|
2006-01-14 14:20:43 -07:00
|
|
|
static char * check_special_flags (char * sfs, Node * e)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
|
|
|
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 01:35:56 -07:00
|
|
|
e = kmalloc(memsize, GFP_USER);
|
2005-04-16 16:20:36 -06:00
|
|
|
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;
|
|
|
|
e->size = unquote(e->magic);
|
|
|
|
if (e->mask && unquote(e->mask) != e->size)
|
|
|
|
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) {
|
|
|
|
inode->i_mode = mode;
|
|
|
|
inode->i_uid = 0;
|
|
|
|
inode->i_gid = 0;
|
|
|
|
inode->i_blocks = 0;
|
|
|
|
inode->i_atime = inode->i_mtime = inode->i_ctime =
|
|
|
|
current_fs_time(inode->i_sb);
|
|
|
|
}
|
|
|
|
return inode;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bm_clear_inode(struct inode *inode)
|
|
|
|
{
|
2006-09-27 02:50:46 -06:00
|
|
|
kfree(inode->i_private);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
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) {
|
|
|
|
dentry->d_inode->i_nlink--;
|
|
|
|
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)
|
|
|
|
{
|
2006-12-08 03:36:35 -07:00
|
|
|
Node *e = file->f_path.dentry->d_inode->i_private;
|
2005-04-16 16:20:36 -06:00
|
|
|
ssize_t res;
|
|
|
|
char *page;
|
|
|
|
|
|
|
|
if (!(page = (char*) __get_free_page(GFP_KERNEL)))
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
entry_status(e, page);
|
|
|
|
|
2008-07-23 22:29:15 -06:00
|
|
|
res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));
|
|
|
|
|
2005-04-16 16:20:36 -06:00
|
|
|
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;
|
2006-12-08 03:36:35 -07:00
|
|
|
Node *e = file->f_path.dentry->d_inode->i_private;
|
2005-04-16 16:20:36 -06:00
|
|
|
int res = parse_command(buffer, count);
|
|
|
|
|
|
|
|
switch (res) {
|
|
|
|
case 1: clear_bit(Enabled, &e->flags);
|
|
|
|
break;
|
|
|
|
case 2: set_bit(Enabled, &e->flags);
|
|
|
|
break;
|
2006-12-08 03:36:35 -07:00
|
|
|
case 3: root = dget(file->f_path.mnt->mnt_sb->s_root);
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
kill_node(e);
|
|
|
|
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
dput(root);
|
|
|
|
break;
|
|
|
|
default: return res;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 02:56:42 -07:00
|
|
|
static const struct file_operations bm_entry_operations = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.read = bm_entry_read,
|
|
|
|
.write = bm_entry_write,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* /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;
|
2006-12-08 03:36:35 -07:00
|
|
|
struct super_block *sb = file->f_path.mnt->mnt_sb;
|
2005-04-16 16:20:36 -06:00
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
e = create_entry(buffer, count);
|
|
|
|
|
|
|
|
if (IS_ERR(e))
|
|
|
|
return PTR_ERR(e);
|
|
|
|
|
|
|
|
root = dget(sb->s_root);
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
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 07:34:16 -06:00
|
|
|
err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
|
2005-04-16 16:20:36 -06:00
|
|
|
if (err) {
|
|
|
|
iput(inode);
|
|
|
|
inode = NULL;
|
|
|
|
goto out2;
|
|
|
|
}
|
|
|
|
|
|
|
|
e->dentry = dget(dentry);
|
2006-09-27 02:50:46 -06:00
|
|
|
inode->i_private = e;
|
2005-04-16 16:20:36 -06:00
|
|
|
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:
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
dput(root);
|
|
|
|
|
|
|
|
if (err) {
|
|
|
|
kfree(e);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 02:56:42 -07:00
|
|
|
static const struct file_operations bm_register_operations = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.write = bm_register_write,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* /status */
|
|
|
|
|
|
|
|
static ssize_t
|
|
|
|
bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
|
|
|
|
{
|
|
|
|
char *s = enabled ? "enabled" : "disabled";
|
|
|
|
|
2007-05-09 03:33:32 -06:00
|
|
|
return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
2006-12-08 03:36:35 -07:00
|
|
|
case 3: root = dget(file->f_path.mnt->mnt_sb->s_root);
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_lock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
|
|
|
|
while (!list_empty(&entries))
|
|
|
|
kill_node(list_entry(entries.next, Node, list));
|
|
|
|
|
2006-01-09 16:59:24 -07:00
|
|
|
mutex_unlock(&root->d_inode->i_mutex);
|
2005-04-16 16:20:36 -06:00
|
|
|
dput(root);
|
|
|
|
default: return res;
|
|
|
|
}
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 02:56:42 -07:00
|
|
|
static const struct file_operations bm_status_operations = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.read = bm_status_read,
|
|
|
|
.write = bm_status_write,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* Superblock handling */
|
|
|
|
|
2007-02-12 01:55:41 -07:00
|
|
|
static const struct super_operations s_ops = {
|
2005-04-16 16:20:36 -06:00
|
|
|
.statfs = simple_statfs,
|
|
|
|
.clear_inode = bm_clear_inode,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int bm_fill_super(struct super_block * sb, void * data, int silent)
|
|
|
|
{
|
|
|
|
static struct tree_descr bm_files[] = {
|
2007-05-08 01:32:31 -06:00
|
|
|
[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
|
|
|
|
[3] = {"register", &bm_register_operations, S_IWUSR},
|
2005-04-16 16:20:36 -06:00
|
|
|
/* last one */ {""}
|
|
|
|
};
|
|
|
|
int err = simple_fill_super(sb, 0x42494e4d, bm_files);
|
|
|
|
if (!err)
|
|
|
|
sb->s_op = &s_ops;
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 03:02:57 -06:00
|
|
|
static int bm_get_sb(struct file_system_type *fs_type,
|
|
|
|
int flags, const char *dev_name, void *data, struct vfsmount *mnt)
|
2005-04-16 16:20:36 -06:00
|
|
|
{
|
[PATCH] VFS: Permit filesystem to override root dentry on mount
Extend the get_sb() filesystem operation to take an extra argument that
permits the VFS to pass in the target vfsmount that defines the mountpoint.
The filesystem is then required to manually set the superblock and root dentry
pointers. For most filesystems, this should be done with simple_set_mnt()
which will set the superblock pointer and then set the root dentry to the
superblock's s_root (as per the old default behaviour).
The get_sb() op now returns an integer as there's now no need to return the
superblock pointer.
This patch permits a superblock to be implicitly shared amongst several mount
points, such as can be done with NFS to avoid potential inode aliasing. In
such a case, simple_set_mnt() would not be called, and instead the mnt_root
and mnt_sb would be set directly.
The patch also makes the following changes:
(*) the get_sb_*() convenience functions in the core kernel now take a vfsmount
pointer argument and return an integer, so most filesystems have to change
very little.
(*) If one of the convenience function is not used, then get_sb() should
normally call simple_set_mnt() to instantiate the vfsmount. This will
always return 0, and so can be tail-called from get_sb().
(*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the
dcache upon superblock destruction rather than shrink_dcache_anon().
This is required because the superblock may now have multiple trees that
aren't actually bound to s_root, but that still need to be cleaned up. The
currently called functions assume that the whole tree is rooted at s_root,
and that anonymous dentries are not the roots of trees which results in
dentries being left unculled.
However, with the way NFS superblock sharing are currently set to be
implemented, these assumptions are violated: the root of the filesystem is
simply a dummy dentry and inode (the real inode for '/' may well be
inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries
with child trees.
[*] Anonymous until discovered from another tree.
(*) The documentation has been adjusted, including the additional bit of
changing ext2_* into foo_* in the documentation.
[akpm@osdl.org: convert ipath_fs, do other stuff]
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Nathan Scott <nathans@sgi.com>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 03:02:57 -06:00
|
|
|
return get_sb_single(fs_type, flags, data, bm_fill_super, mnt);
|
2005-04-16 16:20:36 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
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",
|
|
|
|
.get_sb = bm_get_sb,
|
|
|
|
.kill_sb = kill_litter_super,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init init_misc_binfmt(void)
|
|
|
|
{
|
|
|
|
int err = register_filesystem(&bm_fs_type);
|
|
|
|
if (!err) {
|
|
|
|
err = register_binfmt(&misc_format);
|
|
|
|
if (err)
|
|
|
|
unregister_filesystem(&bm_fs_type);
|
|
|
|
}
|
|
|
|
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");
|