cpuset.c

linux 2.6.19 kernel source code before patching

/*
 *  kernel/cpuset.c
 *
 *  Processor and Memory placement constraints for sets of tasks.
 *
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpuset.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/kmod.h>
#include <linux/list.h>
#include <linux/mempolicy.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/time.h>
#include <linux/backing-dev.h>
#include <linux/sort.h>

#include <asm/uaccess.h>
#include <asm/atomic.h>
#include <linux/mutex.h>

#define CPUSET_SUPER_MAGIC		0x27e0eb

/*
 * Tracks how many cpusets are currently defined in system.
 * When there is only one cpuset (the root cpuset) we can
 * short circuit some hooks.
 */
int number_of_cpusets __read_mostly;

/* See "Frequency meter" comments, below. */

struct fmeter {
	int cnt;		/* unprocessed events count */
	int val;		/* most recent output value */
	time_t time;		/* clock (secs) when val computed */
	spinlock_t lock;	/* guards read or write of above */
};

struct cpuset {
	unsigned long flags;		/* "unsigned long" so bitops work */
	cpumask_t cpus_allowed;		/* CPUs allowed to tasks in cpuset */
	nodemask_t mems_allowed;	/* Memory Nodes allowed to tasks */

	/*
	 * Count is atomic so can incr (fork) or decr (exit) without a lock.
	 */
	atomic_t count;			/* count tasks using this cpuset */

	/*
	 * We link our 'sibling' struct into our parents 'children'.
	 * Our children link their 'sibling' into our 'children'.
	 */
	struct list_head sibling;	/* my parents children */
	struct list_head children;	/* my children */

	struct cpuset *parent;		/* my parent */
	struct dentry *dentry;		/* cpuset fs entry */

	/*
	 * Copy of global cpuset_mems_generation as of the most
	 * recent time this cpuset changed its mems_allowed.
	 */
	int mems_generation;

	struct fmeter fmeter;		/* memory_pressure filter */
};

/* bits in struct cpuset flags field */
typedef enum {
	CS_CPU_EXCLUSIVE,
	CS_MEM_EXCLUSIVE,
	CS_MEMORY_MIGRATE,
	CS_REMOVED,
	CS_NOTIFY_ON_RELEASE,
	CS_SPREAD_PAGE,
	CS_SPREAD_SLAB,
} cpuset_flagbits_t;

/* convenient tests for these bits */
static inline int is_cpu_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_CPU_EXCLUSIVE, &cs->flags);
}

static inline int is_mem_exclusive(const struct cpuset *cs)
{
	return test_bit(CS_MEM_EXCLUSIVE, &cs->flags);
}

static inline int is_removed(const struct cpuset *cs)
{
	return test_bit(CS_REMOVED, &cs->flags);
}

static inline int notify_on_release(const struct cpuset *cs)
{
	return test_bit(CS_NOTIFY_ON_RELEASE, &cs->flags);
}

static inline int is_memory_migrate(const struct cpuset *cs)
{
	return test_bit(CS_MEMORY_MIGRATE, &cs->flags);
}

static inline int is_spread_page(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_PAGE, &cs->flags);
}

static inline int is_spread_slab(const struct cpuset *cs)
{
	return test_bit(CS_SPREAD_SLAB, &cs->flags);
}

/*
 * Increment this integer everytime any cpuset changes its
 * mems_allowed value.  Users of cpusets can track this generation
 * number, and avoid having to lock and reload mems_allowed unless
 * the cpuset they're using changes generation.
 *
 * A single, global generation is needed because attach_task() could
 * reattach a task to a different cpuset, which must not have its
 * generation numbers aliased with those of that tasks previous cpuset.
 *
 * Generations are needed for mems_allowed because one task cannot
 * modify anothers memory placement.  So we must enable every task,
 * on every visit to __alloc_pages(), to efficiently check whether
 * its current->cpuset->mems_allowed has changed, requiring an update
 * of its current->mems_allowed.
 *
 * Since cpuset_mems_generation is guarded by manage_mutex,
 * there is no need to mark it atomic.
 */
static int cpuset_mems_generation;

static struct cpuset top_cpuset = {
	.flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
	.cpus_allowed = CPU_MASK_ALL,
	.mems_allowed = NODE_MASK_ALL,
	.count = ATOMIC_INIT(0),
	.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
	.children = LIST_HEAD_INIT(top_cpuset.children),
};

static struct vfsmount *cpuset_mount;
static struct super_block *cpuset_sb;

/*
 * We have two global cpuset mutexes below.  They can nest.
 * It is ok to first take manage_mutex, then nest callback_mutex.  We also
 * require taking task_lock() when dereferencing a tasks cpuset pointer.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold both mutexes to modify cpusets.  If a task
 * holds manage_mutex, then it blocks others wanting that mutex,
 * ensuring that it is the only task able to also acquire callback_mutex
 * and be able to modify cpusets.  It can perform various checks on
 * the cpuset structure first, knowing nothing will change.  It can
 * also allocate memory while just holding manage_mutex.  While it is
 * performing these checks, various callback routines can briefly
 * acquire callback_mutex to query cpusets.  Once it is ready to make
 * the changes, it takes callback_mutex, blocking everyone else.
 *
 * Calls to the kernel memory allocator can not be made while holding
 * callback_mutex, as that would risk double tripping on callback_mutex
 * from one of the callbacks into the cpuset code from within
 * __alloc_pages().
 *
 * If a task is only holding callback_mutex, then it has read-only
 * access to cpusets.
 *
 * The task_struct fields mems_allowed and mems_generation may only
 * be accessed in the context of that task, so require no locks.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding manage_mutex or callback_mutex can't rely
 * on the count field not changing.  However, if the count goes to
 * zero, then only attach_task(), which holds both mutexes, can
 * increment it again.  Because a count of zero means that no tasks
 * are currently attached, therefore there is no way a task attached
 * to that cpuset can fork (the other way to increment the count).
 * So code holding manage_mutex or callback_mutex can safely assume that
 * if the count is zero, it will stay zero.  Similarly, if a task
 * holds manage_mutex or callback_mutex on a cpuset with zero count, it
 * knows that the cpuset won't be removed, as cpuset_rmdir() needs
 * both of those mutexes.
 *
 * The cpuset_common_file_write handler for operations that modify
 * the cpuset hierarchy holds manage_mutex across the entire operation,
 * single threading all such cpuset modifications across the system.
 *
 * The cpuset_common_file_read() handlers only hold callback_mutex across
 * small pieces of code, such as when reading out possibly multi-word
 * cpumasks and nodemasks.
 *
 * The fork and exit callbacks cpuset_fork() and cpuset_exit(), don't
 * (usually) take either mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cpuset_exit(),
 * when a task in a notify_on_release cpuset exits.  Then manage_mutex
 * is taken, and if the cpuset count is zero, a usermode call made
 * to /sbin/cpuset_release_agent with the name of the cpuset (path
 * relative to the root of cpuset file system) as the argument.
 *
 * A cpuset can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cpusets is empty.  Since all
 * tasks in the system use _some_ cpuset, and since there is always at
 * least one task in the system (init), therefore, top_cpuset
 * always has either children cpusets and/or using tasks.  So we don't
 * need a special hack to ensure that top_cpuset cannot be deleted.
 *
 * The above "Tale of Two Semaphores" would be complete, but for:
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of attach_task(),
 * which overwrites one tasks cpuset pointer with another.  It does
 * so using both mutexes, however there are several performance
 * critical places that need to reference task->cpuset without the
 * expense of grabbing a system global mutex.  Therefore except as
 * noted below, when dereferencing or, as in attach_task(), modifying
 * a tasks cpuset pointer we use task_lock(), which acts on a spinlock
 * (task->alloc_lock) already in the task_struct routinely used for
 * such matters.
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cpuset pointer by attach_task() and the
 * access of task->cpuset->mems_generation via that pointer in
 * the routine cpuset_update_task_memory_state().
 */

static DEFINE_MUTEX(manage_mutex);
static DEFINE_MUTEX(callback_mutex);

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 *  cpuset_mkdir -> cpuset_create -> cpuset_populate_dir -> cpuset_add_file
 *  -> cpuset_create_file -> cpuset_dir_inode_operations -> cpuset_mkdir.
 */

static int cpuset_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static int cpuset_rmdir(struct inode *unused_dir, struct dentry *dentry);

static struct backing_dev_info cpuset_backing_dev_info = {
	.ra_pages = 0,		/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};

static struct inode *cpuset_new_inode(mode_t mode)
{
	struct inode *inode = new_inode(cpuset_sb);

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cpuset_backing_dev_info;
	}
	return inode;
}

static void cpuset_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cpuset */
	if (S_ISDIR(inode->i_mode)) {
		struct cpuset *cs = dentry->d_fsdata;
		BUG_ON(!(is_removed(cs)));
		kfree(cs);
	}
	iput(inode);
}

static struct dentry_operations cpuset_dops = {
	.d_iput = cpuset_diput,
};

static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
{
	struct dentry *d = lookup_one_len(name, parent, strlen(name));
	if (!IS_ERR(d))
		d->d_op = &cpuset_dops;
	return d;
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cpuset_d_remove_dir(struct dentry *dentry)
{
	struct list_head *node;

	spin_lock(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
		list_del_init(node);
		if (d->d_inode) {
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

static struct super_operations cpuset_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
};

static int cpuset_fill_super(struct super_block *sb, void *unused_data,
							int unused_silent)
{
	struct inode *inode;
	struct dentry *root;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CPUSET_SUPER_MAGIC;
	sb->s_op = &cpuset_ops;
	cpuset_sb = sb;

	inode = cpuset_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR);
	if (inode) {
		inode->i_op = &simple_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;
		/* directories start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);
	} else {
		return -ENOMEM;
	}

	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = root;
	return 0;
}

static int cpuset_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	return get_sb_single(fs_type, flags, data, cpuset_fill_super, mnt);
}

static struct file_system_type cpuset_fs_type = {
	.name = "cpuset",
	.get_sb = cpuset_get_sb,
	.kill_sb = kill_litter_super,
};

/* struct cftype:
 *
 * The files in the cpuset filesystem mostly have a very simple read/write
 * handling, some common function will take care of it. Nevertheless some cases
 * (read tasks) are special and therefore I define this structure for every
 * kind of file.
 *
 *
 * When reading/writing to a file:
 *	- the cpuset to use in file->f_path.dentry->d_parent->d_fsdata
 *	- the 'cftype' of the file is file->f_path.dentry->d_fsdata
 */

struct cftype {
	char *name;
	int private;
	int (*open) (struct inode *inode, struct file *file);
	ssize_t (*read) (struct file *file, char __user *buf, size_t nbytes,
							loff_t *ppos);
	int (*write) (struct file *file, const char __user *buf, size_t nbytes,
							loff_t *ppos);
	int (*release) (struct inode *inode, struct file *file);
};

static inline struct cpuset *__d_cs(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/*
 * Call with manage_mutex held.  Writes path of cpuset into buf.
 * Returns 0 on success, -errno on error.
 */

static int cpuset_path(const struct cpuset *cs, char *buf, int buflen)
{
	char *start;