aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/base/dd.c
blob: 92428e55b0c210a8c00cf8e656a934fa9e21f2d3 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
/*
 *	drivers/base/dd.c - The core device/driver interactions.
 *
 * 	This file contains the (sometimes tricky) code that controls the
 *	interactions between devices and drivers, which primarily includes
 *	driver binding and unbinding.
 *
 *	All of this code used to exist in drivers/base/bus.c, but was
 *	relocated to here in the name of compartmentalization (since it wasn't
 *	strictly code just for the 'struct bus_type'.
 *
 *	Copyright (c) 2002-5 Patrick Mochel
 *	Copyright (c) 2002-3 Open Source Development Labs
 *
 *	This file is released under the GPLv2
 */

#include <linux/device.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/wait.h>

#include "base.h"
#include "power/power.h"

#define to_drv(node) container_of(node, struct device_driver, kobj.entry)


static void driver_bound(struct device *dev)
{
	if (klist_node_attached(&dev->knode_driver)) {
		printk(KERN_WARNING "%s: device %s already bound\n",
			__FUNCTION__, kobject_name(&dev->kobj));
		return;
	}

	pr_debug("bound device '%s' to driver '%s'\n",
		 dev->bus_id, dev->driver->name);

	if (dev->bus)
		blocking_notifier_call_chain(&dev->bus->bus_notifier,
					     BUS_NOTIFY_BOUND_DRIVER, dev);

	klist_add_tail(&dev->knode_driver, &dev->driver->klist_devices);
}

static int driver_sysfs_add(struct device *dev)
{
	int ret;

	ret = sysfs_create_link(&dev->driver->kobj, &dev->kobj,
			  kobject_name(&dev->kobj));
	if (ret == 0) {
		ret = sysfs_create_link(&dev->kobj, &dev->driver->kobj,
					"driver");
		if (ret)
			sysfs_remove_link(&dev->driver->kobj,
					kobject_name(&dev->kobj));
	}
	return ret;
}

static void driver_sysfs_remove(struct device *dev)
{
	struct device_driver *drv = dev->driver;

	if (drv) {
		sysfs_remove_link(&drv->kobj, kobject_name(&dev->kobj));
		sysfs_remove_link(&dev->kobj, "driver");
	}
}

/**
 *	device_bind_driver - bind a driver to one device.
 *	@dev:	device.
 *
 *	Allow manual attachment of a driver to a device.
 *	Caller must have already set @dev->driver.
 *
 *	Note that this does not modify the bus reference count
 *	nor take the bus's rwsem. Please verify those are accounted
 *	for before calling this. (It is ok to call with no other effort
 *	from a driver's probe() method.)
 *
 *	This function must be called with @dev->sem held.
 */
int device_bind_driver(struct device *dev)
{
	int ret;

	ret = driver_sysfs_add(dev);
	if (!ret)
		driver_bound(dev);
	return ret;
}

static atomic_t probe_count = ATOMIC_INIT(0);
static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);

static int really_probe(struct device *dev, struct device_driver *drv)
{
	int ret = 0;

	atomic_inc(&probe_count);
	pr_debug("%s: Probing driver %s with device %s\n",
		 drv->bus->name, drv->name, dev->bus_id);
	WARN_ON(!list_empty(&dev->devres_head));

	dev->driver = drv;
	if (driver_sysfs_add(dev)) {
		printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
			__FUNCTION__, dev->bus_id);
		goto probe_failed;
	}

	if (dev->bus->probe) {
		ret = dev->bus->probe(dev);
		if (ret)
			goto probe_failed;
	} else if (drv->probe) {
		ret = drv->probe(dev);
		if (ret)
			goto probe_failed;
	}

	driver_bound(dev);
	ret = 1;
	pr_debug("%s: Bound Device %s to Driver %s\n",
		 drv->bus->name, dev->bus_id, drv->name);
	goto done;

probe_failed:
	devres_release_all(dev);
	driver_sysfs_remove(dev);
	dev->driver = NULL;

	if (ret != -ENODEV && ret != -ENXIO) {
		/* driver matched but the probe failed */
		printk(KERN_WARNING
		       "%s: probe of %s failed with error %d\n",
		       drv->name, dev->bus_id, ret);
	}
	/*
	 * Ignore errors returned by ->probe so that the next driver can try
	 * its luck.
	 */
	ret = 0;
done:
	atomic_dec(&probe_count);
	wake_up(&probe_waitqueue);
	return ret;
}

/**
 * driver_probe_done
 * Determine if the probe sequence is finished or not.
 *
 * Should somehow figure out how to use a semaphore, not an atomic variable...
 */
int driver_probe_done(void)
{
	pr_debug("%s: probe_count = %d\n", __FUNCTION__,
		 atomic_read(&probe_count));
	if (atomic_read(&probe_count))
		return -EBUSY;
	return 0;
}

/**
 * driver_probe_device - attempt to bind device & driver together
 * @drv: driver to bind a device to
 * @dev: device to try to bind to the driver
 *
 * First, we call the bus's match function, if one present, which should
 * compare the device IDs the driver supports with the device IDs of the
 * device. Note we don't do this ourselves because we don't know the
 * format of the ID structures, nor what is to be considered a match and
 * what is not.
 *
 * This function returns 1 if a match is found, -ENODEV if the device is
 * not registered, and 0 otherwise.
 *
 * This function must be called with @dev->sem held.  When called for a
 * USB interface, @dev->parent->sem must be held as well.
 */
int driver_probe_device(struct device_driver * drv, struct device * dev)
{
	int ret = 0;

	if (!device_is_registered(dev))
		return -ENODEV;
	if (drv->bus->match && !drv->bus->match(dev, drv))
		goto done;

	pr_debug("%s: Matched Device %s with Driver %s\n",
		 drv->bus->name, dev->bus_id, drv->name);

	ret = really_probe(dev, drv);

done:
	return ret;
}

static int __device_attach(struct device_driver * drv, void * data)
{
	struct device * dev = data;
	return driver_probe_device(drv, dev);
}

static int device_probe_drivers(void *data)
{
	struct device *dev = data;
	int ret = 0;

	if (dev->bus) {
		down(&dev->sem);
		ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
		up(&dev->sem);
	}
	return ret;
}

/**
 *	device_attach - try to attach device to a driver.
 *	@dev:	device.
 *
 *	Walk the list of drivers that the bus has and call
 *	driver_probe_device() for each pair. If a compatible
 *	pair is found, break out and return.
 *
 *	Returns 1 if the device was bound to a driver;
 *	0 if no matching device was found;
 *	-ENODEV if the device is not registered.
 *
 *	When called for a USB interface, @dev->parent->sem must be held.
 */
int device_attach(struct device * dev)
{
	int ret = 0;

	down(&dev->sem);
	if (dev->driver) {
		ret = device_bind_driver(dev);
		if (ret == 0)
			ret = 1;
		else {
			dev->driver = NULL;
			ret = 0;
		}
	} else {
		ret = bus_for_each_drv(dev->bus, NULL, dev, __device_attach);
	}
	up(&dev->sem);
	return ret;
}

static int __driver_attach(struct device * dev, void * data)
{
	struct device_driver * drv = data;

	/*
	 * Lock device and try to bind to it. We drop the error
	 * here and always return 0, because we need to keep trying
	 * to bind to devices and some drivers will return an error
	 * simply if it didn't support the device.
	 *
	 * driver_probe_device() will spit a warning if there
	 * is an error.
	 */

	if (dev->parent)	/* Needed for USB */
		down(&dev->parent->sem);
	down(&dev->sem);
	if (!dev->driver)
		driver_probe_device(drv, dev);
	up(&dev->sem);
	if (dev->parent)
		up(&dev->parent->sem);

	return 0;
}

/**
 *	driver_attach - try to bind driver to devices.
 *	@drv:	driver.
 *
 *	Walk the list of devices that the bus has on it and try to
 *	match the driver with each one.  If driver_probe_device()
 *	returns 0 and the @dev->driver is set, we've found a
 *	compatible pair.
 */
int driver_attach(struct device_driver * drv)
{
	return bus_for_each_dev(drv->bus, NULL, drv, __driver_attach);
}

/**
 *	device_release_driver - manually detach device from driver.
 *	@dev:	device.
 *
 *	Manually detach device from driver.
 *
 *	__device_release_driver() must be called with @dev->sem held.
 *	When called for a USB interface, @dev->parent->sem must be held
 *	as well.
 */

static void __device_release_driver(struct device * dev)
{
	struct device_driver * drv;

	drv = dev->driver;
	if (drv) {
		get_driver(drv);
		driver_sysfs_remove(dev);
		sysfs_remove_link(&dev->kobj, "driver");
		klist_remove(&dev->knode_driver);

		if (dev->bus)
			blocking_notifier_call_chain(&dev->bus->bus_notifier,
						     BUS_NOTIFY_UNBIND_DRIVER,
						     dev);

		if (dev->bus && dev->bus->remove)
			dev->bus->remove(dev);
		else if (drv->remove)
			drv->remove(dev);
		devres_release_all(dev);
		dev->driver = NULL;
		put_driver(drv);
	}
}

void device_release_driver(struct device * dev)
{
	/*
	 * If anyone calls device_release_driver() recursively from
	 * within their ->remove callback for the same device, they
	 * will deadlock right here.
	 */
	down(&dev->sem);
	__device_release_driver(dev);
	up(&dev->sem);
}


/**
 * driver_detach - detach driver from all devices it controls.
 * @drv: driver.
 */
void driver_detach(struct device_driver * drv)
{
	struct device * dev;

	for (;;) {
		spin_lock(&drv->klist_devices.k_lock);
		if (list_empty(&drv->klist_devices.k_list)) {
			spin_unlock(&drv->klist_devices.k_lock);
			break;
		}
		dev = list_entry(drv->klist_devices.k_list.prev,
				struct device, knode_driver.n_node);
		get_device(dev);
		spin_unlock(&drv->klist_devices.k_lock);

		if (dev->parent)	/* Needed for USB */
			down(&dev->parent->sem);
		down(&dev->sem);
		if (dev->driver == drv)
			__device_release_driver(dev);
		up(&dev->sem);
		if (dev->parent)
			up(&dev->parent->sem);
		put_device(dev);
	}
}

EXPORT_SYMBOL_GPL(device_bind_driver);
EXPORT_SYMBOL_GPL(device_release_driver);
EXPORT_SYMBOL_GPL(device_attach);
EXPORT_SYMBOL_GPL(driver_attach);

void xfs_cleanup_inode( struct inode *dir, struct inode *inode, struct dentry *dentry) { struct xfs_name teardown; /* Oh, the horror. * If we can't add the ACL or we fail in * xfs_init_security we must back out. * ENOSPC can hit here, among other things. */ xfs_dentry_to_name(&teardown, dentry, 0); xfs_remove(XFS_I(dir), &teardown, XFS_I(inode)); } STATIC int xfs_generic_create( struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev, bool tmpfile) /* unnamed file */ { struct inode *inode; struct xfs_inode *ip = NULL; struct posix_acl *default_acl, *acl; struct xfs_name name; int error; /* * Irix uses Missed'em'V split, but doesn't want to see * the upper 5 bits of (14bit) major. */ if (S_ISCHR(mode) || S_ISBLK(mode)) { if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff)) return -EINVAL; rdev = sysv_encode_dev(rdev); } else { rdev = 0; } error = posix_acl_create(dir, &mode, &default_acl, &acl); if (error) return error; if (!tmpfile) { xfs_dentry_to_name(&name, dentry, mode); error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip); } else { error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip); } if (unlikely(error)) goto out_free_acl; inode = VFS_I(ip); error = xfs_init_security(inode, dir, &dentry->d_name); if (unlikely(error)) goto out_cleanup_inode; #ifdef CONFIG_XFS_POSIX_ACL if (default_acl) { error = -xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) goto out_cleanup_inode; } if (acl) { error = -xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) goto out_cleanup_inode; } #endif if (tmpfile) d_tmpfile(dentry, inode); else d_instantiate(dentry, inode); out_free_acl: if (default_acl) posix_acl_release(default_acl); if (acl) posix_acl_release(acl); return -error; out_cleanup_inode: if (!tmpfile) xfs_cleanup_inode(dir, inode, dentry); iput(inode); goto out_free_acl; } STATIC int xfs_vn_mknod( struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { return xfs_generic_create(dir, dentry, mode, rdev, false); } STATIC int xfs_vn_create( struct inode *dir, struct dentry *dentry, umode_t mode, bool flags) { return xfs_vn_mknod(dir, dentry, mode, 0); } STATIC int xfs_vn_mkdir( struct inode *dir, struct dentry *dentry, umode_t mode) { return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0); } STATIC struct dentry * xfs_vn_lookup( struct inode *dir, struct dentry *dentry, unsigned int flags) { struct xfs_inode *cip; struct xfs_name name; int error; if (dentry->d_name.len >= MAXNAMELEN) return ERR_PTR(-ENAMETOOLONG); xfs_dentry_to_name(&name, dentry, 0); error = xfs_lookup(XFS_I(dir), &name, &cip, NULL); if (unlikely(error)) { if (unlikely(error != ENOENT)) return ERR_PTR(-error); d_add(dentry, NULL); return NULL; } return d_splice_alias(VFS_I(cip), dentry); } STATIC struct dentry * xfs_vn_ci_lookup( struct inode *dir, struct dentry *dentry, unsigned int flags) { struct xfs_inode *ip; struct xfs_name xname; struct xfs_name ci_name; struct qstr dname; int error; if (dentry->d_name.len >= MAXNAMELEN) return ERR_PTR(-ENAMETOOLONG); xfs_dentry_to_name(&xname, dentry, 0); error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name); if (unlikely(error)) { if (unlikely(error != ENOENT)) return ERR_PTR(-error); /* * call d_add(dentry, NULL) here when d_drop_negative_children * is called in xfs_vn_mknod (ie. allow negative dentries * with CI filesystems). */ return NULL; } /* if exact match, just splice and exit */ if (!ci_name.name) return d_splice_alias(VFS_I(ip), dentry); /* else case-insensitive match... */ dname.name = ci_name.name; dname.len = ci_name.len; dentry = d_add_ci(dentry, VFS_I(ip), &dname); kmem_free(ci_name.name); return dentry; } STATIC int xfs_vn_link( struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = old_dentry->d_inode; struct xfs_name name; int error; xfs_dentry_to_name(&name, dentry, inode->i_mode); error = xfs_link(XFS_I(dir), XFS_I(inode), &name); if (unlikely(error)) return -error; ihold(inode); d_instantiate(dentry, inode); return 0; } STATIC int xfs_vn_unlink( struct inode *dir, struct dentry *dentry) { struct xfs_name name; int error; xfs_dentry_to_name(&name, dentry, 0); error = -xfs_remove(XFS_I(dir), &name, XFS_I(dentry->d_inode)); if (error) return error; /* * With unlink, the VFS makes the dentry "negative": no inode, * but still hashed. This is incompatible with case-insensitive * mode, so invalidate (unhash) the dentry in CI-mode. */ if (xfs_sb_version_hasasciici(&XFS_M(dir->i_sb)->m_sb)) d_invalidate(dentry); return 0; } STATIC int xfs_vn_symlink( struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; struct xfs_inode *cip = NULL; struct xfs_name name; int error; umode_t mode; mode = S_IFLNK | (irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO); xfs_dentry_to_name(&name, dentry, mode); error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip); if (unlikely(error)) goto out; inode = VFS_I(cip); error = xfs_init_security(inode, dir, &dentry->d_name); if (unlikely(error)) goto out_cleanup_inode; d_instantiate(dentry, inode); return 0; out_cleanup_inode: xfs_cleanup_inode(dir, inode, dentry); iput(inode); out: return -error; } STATIC int xfs_vn_rename( struct inode *odir, struct dentry *odentry, struct inode *ndir, struct dentry *ndentry) { struct inode *new_inode = ndentry->d_inode; struct xfs_name oname; struct xfs_name nname; xfs_dentry_to_name(&oname, odentry, 0); xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode); return -xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode), XFS_I(ndir), &nname, new_inode ? XFS_I(new_inode) : NULL); } /* * careful here - this function can get called recursively, so * we need to be very careful about how much stack we use. * uio is kmalloced for this reason... */ STATIC void * xfs_vn_follow_link( struct dentry *dentry, struct nameidata *nd) { char *link; int error = -ENOMEM; link = kmalloc(MAXPATHLEN+1, GFP_KERNEL); if (!link) goto out_err; error = -xfs_readlink(XFS_I(dentry->d_inode), link); if (unlikely(error)) goto out_kfree; nd_set_link(nd, link); return NULL; out_kfree: kfree(link); out_err: nd_set_link(nd, ERR_PTR(error)); return NULL; } STATIC int xfs_vn_getattr( struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; trace_xfs_getattr(ip); if (XFS_FORCED_SHUTDOWN(mp)) return -XFS_ERROR(EIO); stat->size = XFS_ISIZE(ip); stat->dev = inode->i_sb->s_dev; stat->mode = ip->i_d.di_mode; stat->nlink = ip->i_d.di_nlink; stat->uid = inode->i_uid; stat->gid = inode->i_gid; stat->ino = ip->i_ino; stat->atime = inode->i_atime; stat->mtime = inode->i_mtime; stat->ctime = inode->i_ctime; stat->blocks = XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks); switch (inode->i_mode & S_IFMT) { case S_IFBLK: case S_IFCHR: stat->blksize = BLKDEV_IOSIZE; stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff, sysv_minor(ip->i_df.if_u2.if_rdev)); break; default: if (XFS_IS_REALTIME_INODE(ip)) { /* * If the file blocks are being allocated from a * realtime volume, then return the inode's realtime * extent size or the realtime volume's extent size. */ stat->blksize = xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog; } else stat->blksize = xfs_preferred_iosize(mp); stat->rdev = 0; break; } return 0; } static void xfs_setattr_mode( struct xfs_inode *ip, struct iattr *iattr) { struct inode *inode = VFS_I(ip); umode_t mode = iattr->ia_mode; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ip->i_d.di_mode &= S_IFMT; ip->i_d.di_mode |= mode & ~S_IFMT; inode->i_mode &= S_IFMT; inode->i_mode |= mode & ~S_IFMT; } static void xfs_setattr_time( struct xfs_inode *ip, struct iattr *iattr) { struct inode *inode = VFS_I(ip); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); if (iattr->ia_valid & ATTR_ATIME) { inode->i_atime = iattr->ia_atime; ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec; ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec; } if (iattr->ia_valid & ATTR_CTIME) { inode->i_ctime = iattr->ia_ctime; ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec; ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec; } if (iattr->ia_valid & ATTR_MTIME) { inode->i_mtime = iattr->ia_mtime; ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec; ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec; } } int xfs_setattr_nonsize( struct xfs_inode *ip, struct iattr *iattr, int flags) { xfs_mount_t *mp = ip->i_mount; struct inode *inode = VFS_I(ip); int mask = iattr->ia_valid; xfs_trans_t *tp; int error; kuid_t uid = GLOBAL_ROOT_UID, iuid = GLOBAL_ROOT_UID; kgid_t gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID; struct xfs_dquot *udqp = NULL, *gdqp = NULL; struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL; trace_xfs_setattr(ip); /* If acls are being inherited, we already have this checked */ if (!(flags & XFS_ATTR_NOACL)) { if (mp->m_flags & XFS_MOUNT_RDONLY) return XFS_ERROR(EROFS); if (XFS_FORCED_SHUTDOWN(mp)) return XFS_ERROR(EIO); error = -inode_change_ok(inode, iattr); if (error) return XFS_ERROR(error); } ASSERT((mask & ATTR_SIZE) == 0); /* * If disk quotas is on, we make sure that the dquots do exist on disk, * before we start any other transactions. Trying to do this later * is messy. We don't care to take a readlock to look at the ids * in inode here, because we can't hold it across the trans_reserve. * If the IDs do change before we take the ilock, we're covered * because the i_*dquot fields will get updated anyway. */ if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) { uint qflags = 0; if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) { uid = iattr->ia_uid; qflags |= XFS_QMOPT_UQUOTA; } else { uid = inode->i_uid; } if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) { gid = iattr->ia_gid; qflags |= XFS_QMOPT_GQUOTA; } else { gid = inode->i_gid; } /* * We take a reference when we initialize udqp and gdqp, * so it is important that we never blindly double trip on * the same variable. See xfs_create() for an example. */ ASSERT(udqp == NULL); ASSERT(gdqp == NULL); error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid), xfs_kgid_to_gid(gid), xfs_get_projid(ip), qflags, &udqp, &gdqp, NULL); if (error) return error; } tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE); error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0); if (error) goto out_dqrele; xfs_ilock(ip, XFS_ILOCK_EXCL); /* * Change file ownership. Must be the owner or privileged. */ if (mask & (ATTR_UID|ATTR_GID)) { /* * These IDs could have changed since we last looked at them. * But, we're assured that if the ownership did change * while we didn't have the inode locked, inode's dquot(s) * would have changed also. */ iuid = inode->i_uid; igid = inode->i_gid; gid = (mask & ATTR_GID) ? iattr->ia_gid : igid; uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid; /* * Do a quota reservation only if uid/gid is actually * going to change. */ if (XFS_IS_QUOTA_RUNNING(mp) && ((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) || (XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) { ASSERT(tp); error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp, NULL, capable(CAP_FOWNER) ? XFS_QMOPT_FORCE_RES : 0); if (error) /* out of quota */ goto out_trans_cancel; } } xfs_trans_ijoin(tp, ip, 0); /* * Change file ownership. Must be the owner or privileged. */ if (mask & (ATTR_UID|ATTR_GID)) { /* * CAP_FSETID overrides the following restrictions: * * The set-user-ID and set-group-ID bits of a file will be * cleared upon successful return from chown() */ if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) && !capable(CAP_FSETID)) ip->i_d.di_mode &= ~(S_ISUID|S_ISGID); /* * Change the ownerships and register quota modifications * in the transaction. */ if (!uid_eq(iuid, uid)) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) { ASSERT(mask & ATTR_UID); ASSERT(udqp); olddquot1 = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp); } ip->i_d.di_uid = xfs_kuid_to_uid(uid); inode->i_uid = uid; } if (!gid_eq(igid, gid)) { if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) { ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) || !XFS_IS_PQUOTA_ON(mp)); ASSERT(mask & ATTR_GID); ASSERT(gdqp); olddquot2 = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp); } ip->i_d.di_gid = xfs_kgid_to_gid(gid); inode->i_gid = gid; } } if (mask & ATTR_MODE) xfs_setattr_mode(ip, iattr); if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) xfs_setattr_time(ip, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); XFS_STATS_INC(xs_ig_attrchg); if (mp->m_flags & XFS_MOUNT_WSYNC) xfs_trans_set_sync(tp); error = xfs_trans_commit(tp, 0); xfs_iunlock(ip, XFS_ILOCK_EXCL); /* * Release any dquot(s) the inode had kept before chown. */ xfs_qm_dqrele(olddquot1); xfs_qm_dqrele(olddquot2); xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); if (error) return XFS_ERROR(error); /* * XXX(hch): Updating the ACL entries is not atomic vs the i_mode * update. We could avoid this with linked transactions * and passing down the transaction pointer all the way * to attr_set. No previous user of the generic * Posix ACL code seems to care about this issue either. */ if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) { error = -posix_acl_chmod(inode, inode->i_mode); if (error) return XFS_ERROR(error); } return 0; out_trans_cancel: xfs_trans_cancel(tp, 0); xfs_iunlock(ip, XFS_ILOCK_EXCL); out_dqrele: xfs_qm_dqrele(udqp); xfs_qm_dqrele(gdqp); return error; } /* * Truncate file. Must have write permission and not be a directory. */ int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) { struct xfs_mount *mp = ip->i_mount; struct inode *inode = VFS_I(ip); xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; uint lock_flags = 0; uint commit_flags = 0; trace_xfs_setattr(ip); if (mp->m_flags & XFS_MOUNT_RDONLY) return XFS_ERROR(EROFS); if (XFS_FORCED_SHUTDOWN(mp)) return XFS_ERROR(EIO); error = -inode_change_ok(inode, iattr); if (error) return XFS_ERROR(error); ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(S_ISREG(ip->i_d.di_mode)); ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET| ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); oldsize = inode->i_size; newsize = iattr->ia_size; /* * Short circuit the truncate case for zero length files. */ if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) { if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME))) return 0; /* * Use the regular setattr path to update the timestamps. */ iattr->ia_valid &= ~ATTR_SIZE; return xfs_setattr_nonsize(ip, iattr, 0); } /* * Make sure that the dquots are attached to the inode. */ error = xfs_qm_dqattach(ip, 0); if (error) return error; /* * Now we can make the changes. Before we join the inode to the * transaction, take care of the part of the truncation that must be * done without the inode lock. This needs to be done before joining * the inode to the transaction, because the inode cannot be unlocked * once it is a part of the transaction. */ if (newsize > oldsize) { /* * Do the first part of growing a file: zero any data in the * last block that is beyond the old EOF. We need to do this * before the inode is joined to the transaction to modify * i_size. */ error = xfs_zero_eof(ip, newsize, oldsize); if (error) return error; } /* * We are going to log the inode size change in this transaction so * any previous writes that are beyond the on disk EOF and the new * EOF that have not been written out need to be written here. If we * do not write the data out, we expose ourselves to the null files * problem. * * Only flush from the on disk size to the smaller of the in memory * file size or the new size as that's the range we really care about * here and prevents waiting for other data not within the range we * care about here.