linux_dsm_epyc7002/drivers/base/devtmpfs.c
Heiko Carstens f776c5ec46 driver-core: fix devtmpfs crash on s390
On Mon, Jan 18, 2010 at 05:26:20PM +0530, Sachin Sant wrote:
> Hello Heiko,
>
> Today while trying to boot next-20100118 i came across
> the following Oops :
>
> Brought up 4 CPUs
> Unable to handle kernel pointer dereference at virtual kernel address 0000000000
> 543000
> Oops: 0004 #1 SMP
> Modules linked in:
> CPU: 0 Not tainted 2.6.33-rc4-autotest-next-20100118-5-default #1
> Process swapper (pid: 1, task: 00000000fd792038, ksp: 00000000fd797a30)
> Krnl PSW : 0704200180000000 00000000001eb0b8 (shmem_parse_options+0xc0/0x328)
>           R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:2 PM:0 EA:3
> Krnl GPRS: 000000000054388a 000000000000003d 0000000000543836 000000000000003d
>           0000000000000000 0000000000483f28 0000000000536112 00000000fd797d00
>           00000000fd4ba100 0000000000000100 0000000000483978 0000000000543832
>           0000000000000000 0000000000465958 00000000001eb0b0 00000000fd797c58
> Krnl Code: 00000000001eb0aa: c0e5000994f1       brasl   %r14,31da8c
>           00000000001eb0b0: b9020022           ltgr    %r2,%r2
>           00000000001eb0b4: a784010b           brc     8,1eb2ca
>          >00000000001eb0b8: 92002000           mvi     0(%r2),0
>           00000000001eb0bc: a7080000           lhi     %r0,0
>           00000000001eb0c0: 41902001           la      %r9,1(%r2)
>           00000000001eb0c4: b9040016           lgr     %r1,%r6
>           00000000001eb0c8: b904002b           lgr     %r2,%r11
> Call Trace:
> (<00000000fd797c50> 0xfd797c50)
> <00000000001eb5da> shmem_fill_super+0x13a/0x25c
> <0000000000228cfa> get_sb_single+0xbe/0xdc
> <000000000034ffc0> dev_get_sb+0x2c/0x38
> <000000000066c602> devtmpfs_init+0x46/0xc0
> <000000000066c53e> driver_init+0x22/0x60
> <000000000064d40a> kernel_init+0x24e/0x3d0
> <000000000010a7ea> kernel_thread_starter+0x6/0xc
> <000000000010a7e4> kernel_thread_starter+0x0/0xc
>
> I never tried to boot a kernel with DEVTMPFS enabled on a s390 box.
> So am wondering if this is supported or not ? If you think this
> is supported i will send a mail to community on this.

There is nothing arch specific to devtmpfs. This part crashes because the
kernel tries to modify the data read-only section which is write protected
on s390.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2010-01-20 15:02:05 -08:00

378 lines
7.7 KiB
C

/*
* devtmpfs - kernel-maintained tmpfs-based /dev
*
* Copyright (C) 2009, Kay Sievers <kay.sievers@vrfy.org>
*
* During bootup, before any driver core device is registered,
* devtmpfs, a tmpfs-based filesystem is created. Every driver-core
* device which requests a device node, will add a node in this
* filesystem.
* By default, all devices are named after the the name of the
* device, owned by root and have a default mode of 0600. Subsystems
* can overwrite the default setting if needed.
*/
#include <linux/kernel.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/device.h>
#include <linux/genhd.h>
#include <linux/namei.h>
#include <linux/fs.h>
#include <linux/shmem_fs.h>
#include <linux/cred.h>
#include <linux/sched.h>
#include <linux/init_task.h>
static struct vfsmount *dev_mnt;
#if defined CONFIG_DEVTMPFS_MOUNT
static int dev_mount = 1;
#else
static int dev_mount;
#endif
static DEFINE_MUTEX(dirlock);
static int __init mount_param(char *str)
{
dev_mount = simple_strtoul(str, NULL, 0);
return 1;
}
__setup("devtmpfs.mount=", mount_param);
static int dev_get_sb(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data, struct vfsmount *mnt)
{
return get_sb_single(fs_type, flags, data, shmem_fill_super, mnt);
}
static struct file_system_type dev_fs_type = {
.name = "devtmpfs",
.get_sb = dev_get_sb,
.kill_sb = kill_litter_super,
};
#ifdef CONFIG_BLOCK
static inline int is_blockdev(struct device *dev)
{
return dev->class == &block_class;
}
#else
static inline int is_blockdev(struct device *dev) { return 0; }
#endif
static int dev_mkdir(const char *name, mode_t mode)
{
struct nameidata nd;
struct dentry *dentry;
int err;
err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
name, LOOKUP_PARENT, &nd);
if (err)
return err;
dentry = lookup_create(&nd, 1);
if (!IS_ERR(dentry)) {
err = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
if (!err)
/* mark as kernel-created inode */
dentry->d_inode->i_private = &dev_mnt;
dput(dentry);
} else {
err = PTR_ERR(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
return err;
}
static int create_path(const char *nodepath)
{
int err;
mutex_lock(&dirlock);
err = dev_mkdir(nodepath, 0755);
if (err == -ENOENT) {
char *path;
char *s;
/* parent directories do not exist, create them */
path = kstrdup(nodepath, GFP_KERNEL);
if (!path) {
err = -ENOMEM;
goto out;
}
s = path;
for (;;) {
s = strchr(s, '/');
if (!s)
break;
s[0] = '\0';
err = dev_mkdir(path, 0755);
if (err && err != -EEXIST)
break;
s[0] = '/';
s++;
}
kfree(path);
}
out:
mutex_unlock(&dirlock);
return err;
}
int devtmpfs_create_node(struct device *dev)
{
const char *tmp = NULL;
const char *nodename;
const struct cred *curr_cred;
mode_t mode = 0;
struct nameidata nd;
struct dentry *dentry;
int err;
if (!dev_mnt)
return 0;
nodename = device_get_devnode(dev, &mode, &tmp);
if (!nodename)
return -ENOMEM;
if (mode == 0)
mode = 0600;
if (is_blockdev(dev))
mode |= S_IFBLK;
else
mode |= S_IFCHR;
curr_cred = override_creds(&init_cred);
err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
nodename, LOOKUP_PARENT, &nd);
if (err == -ENOENT) {
create_path(nodename);
err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
nodename, LOOKUP_PARENT, &nd);
}
if (err)
goto out;
dentry = lookup_create(&nd, 0);
if (!IS_ERR(dentry)) {
err = vfs_mknod(nd.path.dentry->d_inode,
dentry, mode, dev->devt);
if (!err) {
struct iattr newattrs;
/* fixup possibly umasked mode */
newattrs.ia_mode = mode;
newattrs.ia_valid = ATTR_MODE;
mutex_lock(&dentry->d_inode->i_mutex);
notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
/* mark as kernel-created inode */
dentry->d_inode->i_private = &dev_mnt;
}
dput(dentry);
} else {
err = PTR_ERR(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
out:
kfree(tmp);
revert_creds(curr_cred);
return err;
}
static int dev_rmdir(const char *name)
{
struct nameidata nd;
struct dentry *dentry;
int err;
err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
name, LOOKUP_PARENT, &nd);
if (err)
return err;
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
if (!IS_ERR(dentry)) {
if (dentry->d_inode) {
if (dentry->d_inode->i_private == &dev_mnt)
err = vfs_rmdir(nd.path.dentry->d_inode,
dentry);
else
err = -EPERM;
} else {
err = -ENOENT;
}
dput(dentry);
} else {
err = PTR_ERR(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
return err;
}
static int delete_path(const char *nodepath)
{
const char *path;
int err = 0;
path = kstrdup(nodepath, GFP_KERNEL);
if (!path)
return -ENOMEM;
mutex_lock(&dirlock);
for (;;) {
char *base;
base = strrchr(path, '/');
if (!base)
break;
base[0] = '\0';
err = dev_rmdir(path);
if (err)
break;
}
mutex_unlock(&dirlock);
kfree(path);
return err;
}
static int dev_mynode(struct device *dev, struct inode *inode, struct kstat *stat)
{
/* did we create it */
if (inode->i_private != &dev_mnt)
return 0;
/* does the dev_t match */
if (is_blockdev(dev)) {
if (!S_ISBLK(stat->mode))
return 0;
} else {
if (!S_ISCHR(stat->mode))
return 0;
}
if (stat->rdev != dev->devt)
return 0;
/* ours */
return 1;
}
int devtmpfs_delete_node(struct device *dev)
{
const char *tmp = NULL;
const char *nodename;
const struct cred *curr_cred;
struct nameidata nd;
struct dentry *dentry;
struct kstat stat;
int deleted = 1;
int err;
if (!dev_mnt)
return 0;
nodename = device_get_devnode(dev, NULL, &tmp);
if (!nodename)
return -ENOMEM;
curr_cred = override_creds(&init_cred);
err = vfs_path_lookup(dev_mnt->mnt_root, dev_mnt,
nodename, LOOKUP_PARENT, &nd);
if (err)
goto out;
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
if (!IS_ERR(dentry)) {
if (dentry->d_inode) {
err = vfs_getattr(nd.path.mnt, dentry, &stat);
if (!err && dev_mynode(dev, dentry->d_inode, &stat)) {
err = vfs_unlink(nd.path.dentry->d_inode,
dentry);
if (!err || err == -ENOENT)
deleted = 1;
}
} else {
err = -ENOENT;
}
dput(dentry);
} else {
err = PTR_ERR(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
if (deleted && strchr(nodename, '/'))
delete_path(nodename);
out:
kfree(tmp);
revert_creds(curr_cred);
return err;
}
/*
* If configured, or requested by the commandline, devtmpfs will be
* auto-mounted after the kernel mounted the root filesystem.
*/
int devtmpfs_mount(const char *mntdir)
{
int err;
if (!dev_mount)
return 0;
if (!dev_mnt)
return 0;
err = sys_mount("devtmpfs", (char *)mntdir, "devtmpfs", MS_SILENT, NULL);
if (err)
printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
else
printk(KERN_INFO "devtmpfs: mounted\n");
return err;
}
/*
* Create devtmpfs instance, driver-core devices will add their device
* nodes here.
*/
int __init devtmpfs_init(void)
{
int err;
struct vfsmount *mnt;
char options[] = "mode=0755";
err = register_filesystem(&dev_fs_type);
if (err) {
printk(KERN_ERR "devtmpfs: unable to register devtmpfs "
"type %i\n", err);
return err;
}
mnt = kern_mount_data(&dev_fs_type, options);
if (IS_ERR(mnt)) {
err = PTR_ERR(mnt);
printk(KERN_ERR "devtmpfs: unable to create devtmpfs %i\n", err);
unregister_filesystem(&dev_fs_type);
return err;
}
dev_mnt = mnt;
printk(KERN_INFO "devtmpfs: initialized\n");
return 0;
}