Revision a7ba4bf5e7ff6bfe83e41c748b77b49297c1b5d9 authored by Linus Torvalds on 02 July 2015, 18:21:26 UTC, committed by Linus Torvalds on 02 July 2015, 18:21:26 UTC
Pull fuse updates from Miklos Szeredi:
 "This is the start of improving fuse scalability.

  An input queue and a processing queue is split out from the monolithic
  fuse connection, each of those having their own spinlock.  The end of
  the patchset adds the ability to clone a fuse connection.  This means,
  that instead of having to read/write requests/answers on a single fuse
  device fd, the fuse daemon can have multiple distinct file descriptors
  open.  Each of those can be used to receive requests and send answers,
  currently the only constraint is that a request must be answered on
  the same fd as it was read from.

  This can be extended further to allow binding a device clone to a
  specific CPU or NUMA node.

  Based on a patchset by Srinivas Eeda and Ashish Samant.  Thanks to
  Ashish for the review of this series"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse: (40 commits)
  fuse: update MAINTAINERS entry
  fuse: separate pqueue for clones
  fuse: introduce per-instance fuse_dev structure
  fuse: device fd clone
  fuse: abort: no fc->lock needed for request ending
  fuse: no fc->lock for pqueue parts
  fuse: no fc->lock in request_end()
  fuse: cleanup request_end()
  fuse: request_end(): do once
  fuse: add req flag for private list
  fuse: pqueue locking
  fuse: abort: group pqueue accesses
  fuse: cleanup fuse_dev_do_read()
  fuse: move list_del_init() from request_end() into callers
  fuse: duplicate ->connected in pqueue
  fuse: separate out processing queue
  fuse: simplify request_wait()
  fuse: no fc->lock for iqueue parts
  fuse: allow interrupt queuing without fc->lock
  fuse: iqueue locking
  ...
2 parent s a611fb7 + 0a30f61
Raw File
char_dev.c
/*
 *  linux/fs/char_dev.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/slab.h>
#include <linux/string.h>

#include <linux/major.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/seq_file.h>

#include <linux/kobject.h>
#include <linux/kobj_map.h>
#include <linux/cdev.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/tty.h>

#include "internal.h"

static struct kobj_map *cdev_map;

static DEFINE_MUTEX(chrdevs_lock);

static struct char_device_struct {
	struct char_device_struct *next;
	unsigned int major;
	unsigned int baseminor;
	int minorct;
	char name[64];
	struct cdev *cdev;		/* will die */
} *chrdevs[CHRDEV_MAJOR_HASH_SIZE];

/* index in the above */
static inline int major_to_index(unsigned major)
{
	return major % CHRDEV_MAJOR_HASH_SIZE;
}

#ifdef CONFIG_PROC_FS

void chrdev_show(struct seq_file *f, off_t offset)
{
	struct char_device_struct *cd;

	if (offset < CHRDEV_MAJOR_HASH_SIZE) {
		mutex_lock(&chrdevs_lock);
		for (cd = chrdevs[offset]; cd; cd = cd->next)
			seq_printf(f, "%3d %s\n", cd->major, cd->name);
		mutex_unlock(&chrdevs_lock);
	}
}

#endif /* CONFIG_PROC_FS */

/*
 * Register a single major with a specified minor range.
 *
 * If major == 0 this functions will dynamically allocate a major and return
 * its number.
 *
 * If major > 0 this function will attempt to reserve the passed range of
 * minors and will return zero on success.
 *
 * Returns a -ve errno on failure.
 */
static struct char_device_struct *
__register_chrdev_region(unsigned int major, unsigned int baseminor,
			   int minorct, const char *name)
{
	struct char_device_struct *cd, **cp;
	int ret = 0;
	int i;

	cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL);
	if (cd == NULL)
		return ERR_PTR(-ENOMEM);

	mutex_lock(&chrdevs_lock);

	/* temporary */
	if (major == 0) {
		for (i = ARRAY_SIZE(chrdevs)-1; i > 0; i--) {
			if (chrdevs[i] == NULL)
				break;
		}

		if (i == 0) {
			ret = -EBUSY;
			goto out;
		}
		major = i;
	}

	cd->major = major;
	cd->baseminor = baseminor;
	cd->minorct = minorct;
	strlcpy(cd->name, name, sizeof(cd->name));

	i = major_to_index(major);

	for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next)
		if ((*cp)->major > major ||
		    ((*cp)->major == major &&
		     (((*cp)->baseminor >= baseminor) ||
		      ((*cp)->baseminor + (*cp)->minorct > baseminor))))
			break;

	/* Check for overlapping minor ranges.  */
	if (*cp && (*cp)->major == major) {
		int old_min = (*cp)->baseminor;
		int old_max = (*cp)->baseminor + (*cp)->minorct - 1;
		int new_min = baseminor;
		int new_max = baseminor + minorct - 1;

		/* New driver overlaps from the left.  */
		if (new_max >= old_min && new_max <= old_max) {
			ret = -EBUSY;
			goto out;
		}

		/* New driver overlaps from the right.  */
		if (new_min <= old_max && new_min >= old_min) {
			ret = -EBUSY;
			goto out;
		}
	}

	cd->next = *cp;
	*cp = cd;
	mutex_unlock(&chrdevs_lock);
	return cd;
out:
	mutex_unlock(&chrdevs_lock);
	kfree(cd);
	return ERR_PTR(ret);
}

static struct char_device_struct *
__unregister_chrdev_region(unsigned major, unsigned baseminor, int minorct)
{
	struct char_device_struct *cd = NULL, **cp;
	int i = major_to_index(major);

	mutex_lock(&chrdevs_lock);
	for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next)
		if ((*cp)->major == major &&
		    (*cp)->baseminor == baseminor &&
		    (*cp)->minorct == minorct)
			break;
	if (*cp) {
		cd = *cp;
		*cp = cd->next;
	}
	mutex_unlock(&chrdevs_lock);
	return cd;
}

/**
 * register_chrdev_region() - register a range of device numbers
 * @from: the first in the desired range of device numbers; must include
 *        the major number.
 * @count: the number of consecutive device numbers required
 * @name: the name of the device or driver.
 *
 * Return value is zero on success, a negative error code on failure.
 */
int register_chrdev_region(dev_t from, unsigned count, const char *name)
{
	struct char_device_struct *cd;
	dev_t to = from + count;
	dev_t n, next;

	for (n = from; n < to; n = next) {
		next = MKDEV(MAJOR(n)+1, 0);
		if (next > to)
			next = to;
		cd = __register_chrdev_region(MAJOR(n), MINOR(n),
			       next - n, name);
		if (IS_ERR(cd))
			goto fail;
	}
	return 0;
fail:
	to = n;
	for (n = from; n < to; n = next) {
		next = MKDEV(MAJOR(n)+1, 0);
		kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
	}
	return PTR_ERR(cd);
}

/**
 * alloc_chrdev_region() - register a range of char device numbers
 * @dev: output parameter for first assigned number
 * @baseminor: first of the requested range of minor numbers
 * @count: the number of minor numbers required
 * @name: the name of the associated device or driver
 *
 * Allocates a range of char device numbers.  The major number will be
 * chosen dynamically, and returned (along with the first minor number)
 * in @dev.  Returns zero or a negative error code.
 */
int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count,
			const char *name)
{
	struct char_device_struct *cd;
	cd = __register_chrdev_region(0, baseminor, count, name);
	if (IS_ERR(cd))
		return PTR_ERR(cd);
	*dev = MKDEV(cd->major, cd->baseminor);
	return 0;
}

/**
 * __register_chrdev() - create and register a cdev occupying a range of minors
 * @major: major device number or 0 for dynamic allocation
 * @baseminor: first of the requested range of minor numbers
 * @count: the number of minor numbers required
 * @name: name of this range of devices
 * @fops: file operations associated with this devices
 *
 * If @major == 0 this functions will dynamically allocate a major and return
 * its number.
 *
 * If @major > 0 this function will attempt to reserve a device with the given
 * major number and will return zero on success.
 *
 * Returns a -ve errno on failure.
 *
 * The name of this device has nothing to do with the name of the device in
 * /dev. It only helps to keep track of the different owners of devices. If
 * your module name has only one type of devices it's ok to use e.g. the name
 * of the module here.
 */
int __register_chrdev(unsigned int major, unsigned int baseminor,
		      unsigned int count, const char *name,
		      const struct file_operations *fops)
{
	struct char_device_struct *cd;
	struct cdev *cdev;
	int err = -ENOMEM;

	cd = __register_chrdev_region(major, baseminor, count, name);
	if (IS_ERR(cd))
		return PTR_ERR(cd);

	cdev = cdev_alloc();
	if (!cdev)
		goto out2;

	cdev->owner = fops->owner;
	cdev->ops = fops;
	kobject_set_name(&cdev->kobj, "%s", name);

	err = cdev_add(cdev, MKDEV(cd->major, baseminor), count);
	if (err)
		goto out;

	cd->cdev = cdev;

	return major ? 0 : cd->major;
out:
	kobject_put(&cdev->kobj);
out2:
	kfree(__unregister_chrdev_region(cd->major, baseminor, count));
	return err;
}

/**
 * unregister_chrdev_region() - return a range of device numbers
 * @from: the first in the range of numbers to unregister
 * @count: the number of device numbers to unregister
 *
 * This function will unregister a range of @count device numbers,
 * starting with @from.  The caller should normally be the one who
 * allocated those numbers in the first place...
 */
void unregister_chrdev_region(dev_t from, unsigned count)
{
	dev_t to = from + count;
	dev_t n, next;

	for (n = from; n < to; n = next) {
		next = MKDEV(MAJOR(n)+1, 0);
		if (next > to)
			next = to;
		kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
	}
}

/**
 * __unregister_chrdev - unregister and destroy a cdev
 * @major: major device number
 * @baseminor: first of the range of minor numbers
 * @count: the number of minor numbers this cdev is occupying
 * @name: name of this range of devices
 *
 * Unregister and destroy the cdev occupying the region described by
 * @major, @baseminor and @count.  This function undoes what
 * __register_chrdev() did.
 */
void __unregister_chrdev(unsigned int major, unsigned int baseminor,
			 unsigned int count, const char *name)
{
	struct char_device_struct *cd;

	cd = __unregister_chrdev_region(major, baseminor, count);
	if (cd && cd->cdev)
		cdev_del(cd->cdev);
	kfree(cd);
}

static DEFINE_SPINLOCK(cdev_lock);

static struct kobject *cdev_get(struct cdev *p)
{
	struct module *owner = p->owner;
	struct kobject *kobj;

	if (owner && !try_module_get(owner))
		return NULL;
	kobj = kobject_get(&p->kobj);
	if (!kobj)
		module_put(owner);
	return kobj;
}

void cdev_put(struct cdev *p)
{
	if (p) {
		struct module *owner = p->owner;
		kobject_put(&p->kobj);
		module_put(owner);
	}
}

/*
 * Called every time a character special file is opened
 */
static int chrdev_open(struct inode *inode, struct file *filp)
{
	const struct file_operations *fops;
	struct cdev *p;
	struct cdev *new = NULL;
	int ret = 0;

	spin_lock(&cdev_lock);
	p = inode->i_cdev;
	if (!p) {
		struct kobject *kobj;
		int idx;
		spin_unlock(&cdev_lock);
		kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
		if (!kobj)
			return -ENXIO;
		new = container_of(kobj, struct cdev, kobj);
		spin_lock(&cdev_lock);
		/* Check i_cdev again in case somebody beat us to it while
		   we dropped the lock. */
		p = inode->i_cdev;
		if (!p) {
			inode->i_cdev = p = new;
			list_add(&inode->i_devices, &p->list);
			new = NULL;
		} else if (!cdev_get(p))
			ret = -ENXIO;
	} else if (!cdev_get(p))
		ret = -ENXIO;
	spin_unlock(&cdev_lock);
	cdev_put(new);
	if (ret)
		return ret;

	ret = -ENXIO;
	fops = fops_get(p->ops);
	if (!fops)
		goto out_cdev_put;

	replace_fops(filp, fops);
	if (filp->f_op->open) {
		ret = filp->f_op->open(inode, filp);
		if (ret)
			goto out_cdev_put;
	}

	return 0;

 out_cdev_put:
	cdev_put(p);
	return ret;
}

void cd_forget(struct inode *inode)
{
	spin_lock(&cdev_lock);
	list_del_init(&inode->i_devices);
	inode->i_cdev = NULL;
	spin_unlock(&cdev_lock);
}

static void cdev_purge(struct cdev *cdev)
{
	spin_lock(&cdev_lock);
	while (!list_empty(&cdev->list)) {
		struct inode *inode;
		inode = container_of(cdev->list.next, struct inode, i_devices);
		list_del_init(&inode->i_devices);
		inode->i_cdev = NULL;
	}
	spin_unlock(&cdev_lock);
}

/*
 * Dummy default file-operations: the only thing this does
 * is contain the open that then fills in the correct operations
 * depending on the special file...
 */
const struct file_operations def_chr_fops = {
	.open = chrdev_open,
	.llseek = noop_llseek,
};

static struct kobject *exact_match(dev_t dev, int *part, void *data)
{
	struct cdev *p = data;
	return &p->kobj;
}

static int exact_lock(dev_t dev, void *data)
{
	struct cdev *p = data;
	return cdev_get(p) ? 0 : -1;
}

/**
 * cdev_add() - add a char device to the system
 * @p: the cdev structure for the device
 * @dev: the first device number for which this device is responsible
 * @count: the number of consecutive minor numbers corresponding to this
 *         device
 *
 * cdev_add() adds the device represented by @p to the system, making it
 * live immediately.  A negative error code is returned on failure.
 */
int cdev_add(struct cdev *p, dev_t dev, unsigned count)
{
	int error;

	p->dev = dev;
	p->count = count;

	error = kobj_map(cdev_map, dev, count, NULL,
			 exact_match, exact_lock, p);
	if (error)
		return error;

	kobject_get(p->kobj.parent);

	return 0;
}

static void cdev_unmap(dev_t dev, unsigned count)
{
	kobj_unmap(cdev_map, dev, count);
}

/**
 * cdev_del() - remove a cdev from the system
 * @p: the cdev structure to be removed
 *
 * cdev_del() removes @p from the system, possibly freeing the structure
 * itself.
 */
void cdev_del(struct cdev *p)
{
	cdev_unmap(p->dev, p->count);
	kobject_put(&p->kobj);
}


static void cdev_default_release(struct kobject *kobj)
{
	struct cdev *p = container_of(kobj, struct cdev, kobj);
	struct kobject *parent = kobj->parent;

	cdev_purge(p);
	kobject_put(parent);
}

static void cdev_dynamic_release(struct kobject *kobj)
{
	struct cdev *p = container_of(kobj, struct cdev, kobj);
	struct kobject *parent = kobj->parent;

	cdev_purge(p);
	kfree(p);
	kobject_put(parent);
}

static struct kobj_type ktype_cdev_default = {
	.release	= cdev_default_release,
};

static struct kobj_type ktype_cdev_dynamic = {
	.release	= cdev_dynamic_release,
};

/**
 * cdev_alloc() - allocate a cdev structure
 *
 * Allocates and returns a cdev structure, or NULL on failure.
 */
struct cdev *cdev_alloc(void)
{
	struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL);
	if (p) {
		INIT_LIST_HEAD(&p->list);
		kobject_init(&p->kobj, &ktype_cdev_dynamic);
	}
	return p;
}

/**
 * cdev_init() - initialize a cdev structure
 * @cdev: the structure to initialize
 * @fops: the file_operations for this device
 *
 * Initializes @cdev, remembering @fops, making it ready to add to the
 * system with cdev_add().
 */
void cdev_init(struct cdev *cdev, const struct file_operations *fops)
{
	memset(cdev, 0, sizeof *cdev);
	INIT_LIST_HEAD(&cdev->list);
	kobject_init(&cdev->kobj, &ktype_cdev_default);
	cdev->ops = fops;
}

static struct kobject *base_probe(dev_t dev, int *part, void *data)
{
	if (request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
		/* Make old-style 2.4 aliases work */
		request_module("char-major-%d", MAJOR(dev));
	return NULL;
}

void __init chrdev_init(void)
{
	cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
}


/* Let modules do char dev stuff */
EXPORT_SYMBOL(register_chrdev_region);
EXPORT_SYMBOL(unregister_chrdev_region);
EXPORT_SYMBOL(alloc_chrdev_region);
EXPORT_SYMBOL(cdev_init);
EXPORT_SYMBOL(cdev_alloc);
EXPORT_SYMBOL(cdev_del);
EXPORT_SYMBOL(cdev_add);
EXPORT_SYMBOL(__register_chrdev);
EXPORT_SYMBOL(__unregister_chrdev);
back to top