cpuset.c

linux 2.6.19 kernel source code before patching

		break;
	case FILE_CPU_EXCLUSIVE:
		retval = update_flag(CS_CPU_EXCLUSIVE, cs, buffer);
		break;
	case FILE_MEM_EXCLUSIVE:
		retval = update_flag(CS_MEM_EXCLUSIVE, cs, buffer);
		break;
	case FILE_NOTIFY_ON_RELEASE:
		retval = update_flag(CS_NOTIFY_ON_RELEASE, cs, buffer);
		break;
	case FILE_MEMORY_MIGRATE:
		retval = update_flag(CS_MEMORY_MIGRATE, cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		retval = update_memory_pressure_enabled(cs, buffer);
		break;
	case FILE_MEMORY_PRESSURE:
		retval = -EACCES;
		break;
	case FILE_SPREAD_PAGE:
		retval = update_flag(CS_SPREAD_PAGE, cs, buffer);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	case FILE_SPREAD_SLAB:
		retval = update_flag(CS_SPREAD_SLAB, cs, buffer);
		cs->mems_generation = cpuset_mems_generation++;
		break;
	case FILE_TASKLIST:
		retval = attach_task(cs, buffer, &pathbuf);
		break;
	default:
		retval = -EINVAL;
		goto out2;
	}

	if (retval == 0)
		retval = nbytes;
out2:
	mutex_unlock(&manage_mutex);
	cpuset_release_agent(pathbuf);
out1:
	kfree(buffer);
	return retval;
}

static ssize_t cpuset_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	ssize_t retval = 0;
	struct cftype *cft = __d_cft(file->f_path.dentry);
	if (!cft)
		return -ENODEV;

	/* special function ? */
	if (cft->write)
		retval = cft->write(file, buf, nbytes, ppos);
	else
		retval = cpuset_common_file_write(file, buf, nbytes, ppos);

	return retval;
}

/*
 * These ascii lists should be read in a single call, by using a user
 * buffer large enough to hold the entire map.  If read in smaller
 * chunks, there is no guarantee of atomicity.  Since the display format
 * used, list of ranges of sequential numbers, is variable length,
 * and since these maps can change value dynamically, one could read
 * gibberish by doing partial reads while a list was changing.
 * A single large read to a buffer that crosses a page boundary is
 * ok, because the result being copied to user land is not recomputed
 * across a page fault.
 */

static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
{
	cpumask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->cpus_allowed;
	mutex_unlock(&callback_mutex);

	return cpulist_scnprintf(page, PAGE_SIZE, mask);
}

static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
{
	nodemask_t mask;

	mutex_lock(&callback_mutex);
	mask = cs->mems_allowed;
	mutex_unlock(&callback_mutex);

	return nodelist_scnprintf(page, PAGE_SIZE, mask);
}

static ssize_t cpuset_common_file_read(struct file *file, char __user *buf,
				size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_path.dentry);
	struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
	cpuset_filetype_t type = cft->private;
	char *page;
	ssize_t retval = 0;
	char *s;

	if (!(page = (char *)__get_free_page(GFP_KERNEL)))
		return -ENOMEM;

	s = page;

	switch (type) {
	case FILE_CPULIST:
		s += cpuset_sprintf_cpulist(s, cs);
		break;
	case FILE_MEMLIST:
		s += cpuset_sprintf_memlist(s, cs);
		break;
	case FILE_CPU_EXCLUSIVE:
		*s++ = is_cpu_exclusive(cs) ? '1' : '0';
		break;
	case FILE_MEM_EXCLUSIVE:
		*s++ = is_mem_exclusive(cs) ? '1' : '0';
		break;
	case FILE_NOTIFY_ON_RELEASE:
		*s++ = notify_on_release(cs) ? '1' : '0';
		break;
	case FILE_MEMORY_MIGRATE:
		*s++ = is_memory_migrate(cs) ? '1' : '0';
		break;
	case FILE_MEMORY_PRESSURE_ENABLED:
		*s++ = cpuset_memory_pressure_enabled ? '1' : '0';
		break;
	case FILE_MEMORY_PRESSURE:
		s += sprintf(s, "%d", fmeter_getrate(&cs->fmeter));
		break;
	case FILE_SPREAD_PAGE:
		*s++ = is_spread_page(cs) ? '1' : '0';
		break;
	case FILE_SPREAD_SLAB:
		*s++ = is_spread_slab(cs) ? '1' : '0';
		break;
	default:
		retval = -EINVAL;
		goto out;
	}
	*s++ = '\n';

	retval = simple_read_from_buffer(buf, nbytes, ppos, page, s - page);
out:
	free_page((unsigned long)page);
	return retval;
}

static ssize_t cpuset_file_read(struct file *file, char __user *buf, size_t nbytes,
								loff_t *ppos)
{
	ssize_t retval = 0;
	struct cftype *cft = __d_cft(file->f_path.dentry);
	if (!cft)
		return -ENODEV;

	/* special function ? */
	if (cft->read)
		retval = cft->read(file, buf, nbytes, ppos);
	else
		retval = cpuset_common_file_read(file, buf, nbytes, ppos);

	return retval;
}

static int cpuset_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct cftype *cft;

	err = generic_file_open(inode, file);
	if (err)
		return err;

	cft = __d_cft(file->f_path.dentry);
	if (!cft)
		return -ENODEV;
	if (cft->open)
		err = cft->open(inode, file);
	else
		err = 0;

	return err;
}

static int cpuset_file_release(struct inode *inode, struct file *file)
{
	struct cftype *cft = __d_cft(file->f_path.dentry);
	if (cft->release)
		return cft->release(inode, file);
	return 0;
}

/*
 * cpuset_rename - Only allow simple rename of directories in place.
 */
static int cpuset_rename(struct inode *old_dir, struct dentry *old_dentry,
                  struct inode *new_dir, struct dentry *new_dentry)
{
	if (!S_ISDIR(old_dentry->d_inode->i_mode))
		return -ENOTDIR;
	if (new_dentry->d_inode)
		return -EEXIST;
	if (old_dir != new_dir)
		return -EIO;
	return simple_rename(old_dir, old_dentry, new_dir, new_dentry);
}

static const struct file_operations cpuset_file_operations = {
	.read = cpuset_file_read,
	.write = cpuset_file_write,
	.llseek = generic_file_llseek,
	.open = cpuset_file_open,
	.release = cpuset_file_release,
};

static const struct inode_operations cpuset_dir_inode_operations = {
	.lookup = simple_lookup,
	.mkdir = cpuset_mkdir,
	.rmdir = cpuset_rmdir,
	.rename = cpuset_rename,
};

static int cpuset_create_file(struct dentry *dentry, int mode)
{
	struct inode *inode;

	if (!dentry)
		return -ENOENT;
	if (dentry->d_inode)
		return -EEXIST;

	inode = cpuset_new_inode(mode);
	if (!inode)
		return -ENOMEM;

	if (S_ISDIR(mode)) {
		inode->i_op = &cpuset_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;

		/* start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);
	} else if (S_ISREG(mode)) {
		inode->i_size = 0;
		inode->i_fop = &cpuset_file_operations;
	}

	d_instantiate(dentry, inode);
	dget(dentry);	/* Extra count - pin the dentry in core */
	return 0;
}

/*
 *	cpuset_create_dir - create a directory for an object.
 *	cs:	the cpuset we create the directory for.
 *		It must have a valid ->parent field
 *		And we are going to fill its ->dentry field.
 *	name:	The name to give to the cpuset directory. Will be copied.
 *	mode:	mode to set on new directory.
 */

static int cpuset_create_dir(struct cpuset *cs, const char *name, int mode)
{
	struct dentry *dentry = NULL;
	struct dentry *parent;
	int error = 0;

	parent = cs->parent->dentry;
	dentry = cpuset_get_dentry(parent, name);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	error = cpuset_create_file(dentry, S_IFDIR | mode);
	if (!error) {
		dentry->d_fsdata = cs;
		inc_nlink(parent->d_inode);
		cs->dentry = dentry;
	}
	dput(dentry);

	return error;
}

static int cpuset_add_file(struct dentry *dir, const struct cftype *cft)
{
	struct dentry *dentry;
	int error;

	mutex_lock(&dir->d_inode->i_mutex);
	dentry = cpuset_get_dentry(dir, cft->name);
	if (!IS_ERR(dentry)) {
		error = cpuset_create_file(dentry, 0644 | S_IFREG);
		if (!error)
			dentry->d_fsdata = (void *)cft;
		dput(dentry);
	} else
		error = PTR_ERR(dentry);
	mutex_unlock(&dir->d_inode->i_mutex);
	return error;
}

/*
 * Stuff for reading the 'tasks' file.
 *
 * Reading this file can return large amounts of data if a cpuset has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 * Upon tasks file open(), a struct ctr_struct is allocated, that
 * will have a pointer to an array (also allocated here).  The struct
 * ctr_struct * is stored in file->private_data.  Its resources will
 * be freed by release() when the file is closed.  The array is used
 * to sprintf the PIDs and then used by read().
 */

/* cpusets_tasks_read array */

struct ctr_struct {
	char *buf;
	int bufsz;
};

/*
 * Load into 'pidarray' up to 'npids' of the tasks using cpuset 'cs'.
 * Return actual number of pids loaded.  No need to task_lock(p)
 * when reading out p->cpuset, as we don't really care if it changes
 * on the next cycle, and we are not going to try to dereference it.
 */
static int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
{
	int n = 0;
	struct task_struct *g, *p;

	read_lock(&tasklist_lock);

	do_each_thread(g, p) {
		if (p->cpuset == cs) {
			if (unlikely(n == npids))
				goto array_full;
			pidarray[n++] = p->pid;
		}
	} while_each_thread(g, p);

array_full:
	read_unlock(&tasklist_lock);
	return n;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}

/*
 * Convert array 'a' of 'npids' pid_t's to a string of newline separated
 * decimal pids in 'buf'.  Don't write more than 'sz' chars, but return
 * count 'cnt' of how many chars would be written if buf were large enough.
 */
static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
{
	int cnt = 0;
	int i;

	for (i = 0; i < npids; i++)
		cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
	return cnt;
}

/*
 * Handle an open on 'tasks' file.  Prepare a buffer listing the
 * process id's of tasks currently attached to the cpuset being opened.
 *
 * Does not require any specific cpuset mutexes, and does not take any.
 */
static int cpuset_tasks_open(struct inode *unused, struct file *file)
{
	struct cpuset *cs = __d_cs(file->f_path.dentry->d_parent);
	struct ctr_struct *ctr;
	pid_t *pidarray;
	int npids;
	char c;

	if (!(file->f_mode & FMODE_READ))
		return 0;

	ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
	if (!ctr)
		goto err0;

	/*
	 * If cpuset gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cpuset users didn't
	 * show up until sometime later on.
	 */
	npids = atomic_read(&cs->count);
	pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
	if (!pidarray)
		goto err1;

	npids = pid_array_load(pidarray, npids, cs);
	sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);

	/* Call pid_array_to_buf() twice, first just to get bufsz */
	ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
	ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
	if (!ctr->buf)
		goto err2;
	ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);

	kfree(pidarray);
	file->private_data = ctr;
	return 0;

err2:
	kfree(pidarray);
err1:
	kfree(ctr);
err0:
	return -ENOMEM;
}

static ssize_t cpuset_tasks_read(struct file *file, char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct ctr_struct *ctr = file->private_data;

	return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
}

static int cpuset_tasks_release(struct inode *unused_inode, struct file *file)
{
	struct ctr_struct *ctr;

	if (file->f_mode & FMODE_READ) {
		ctr = file->private_data;
		kfree(ctr->buf);
		kfree(ctr);
	}
	return 0;
}