litmus-rt.git - The LITMUS^RT kernel.

diff options

author	Tejun Heo <tj@kernel.org>	2013-09-05 12:30:04 -0400
committer	Tejun Heo <tj@kernel.org>	2013-11-22 18:14:02 -0500
commit	8a2b75384444488fc4f2cbb9f0921b6a0794838f (patch)
tree	c4b39daad8de264be08beec77621048e9b9fb9ed /include/linux/platform_data
parent	91151228065354a050fd0d190aefdd662a0580aa (diff)

workqueue: fix ordered workqueues in NUMA setups

An ordered workqueue implements execution ordering by using single pool_workqueue with max_active == 1. On a given pool_workqueue, work items are processed in FIFO order and limiting max_active to 1 enforces the queued work items to be processed one by one. Unfortunately, 4c16bd327c ("workqueue: implement NUMA affinity for unbound workqueues") accidentally broke this guarantee by applying NUMA affinity to ordered workqueues too. On NUMA setups, an ordered workqueue would end up with separate pool_workqueues for different nodes. Each pool_workqueue still limits max_active to 1 but multiple work items may be executed concurrently and out of order depending on which node they are queued to. Fix it by using dedicated ordered_wq_attrs[] when creating ordered workqueues. The new attrs match the unbound ones except that no_numa is always set thus forcing all NUMA nodes to share the default pool_workqueue. While at it, add sanity check in workqueue creation path which verifies that an ordered workqueues has only the default pool_workqueue. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Libin <huawei.libin@huawei.com> Cc: stable@vger.kernel.org Cc: Lai Jiangshan <laijs@cn.fujitsu.com>

Diffstat (limited to 'include/linux/platform_data')

0 files changed, 0 insertions, 0 deletions

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

/* * linux/fs/file_table.c * * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) */ #include <linux/string.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/init.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/eventpoll.h> #include <linux/rcupdate.h> #include <linux/mount.h> #include <linux/capability.h> #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> #include <linux/percpu_counter.h> #include <asm/atomic.h> /* sysctl tunables... */ struct files_stat_struct files_stat = { .max_files = NR_FILE }; /* public. Not pretty! */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock); static struct percpu_counter nr_files __cacheline_aligned_in_smp; static inline void file_free_rcu(struct rcu_head *head) { struct file *f = container_of(head, struct file, f_u.fu_rcuhead); kmem_cache_free(filp_cachep, f); } static inline void file_free(struct file *f) { percpu_counter_dec(&nr_files); file_check_state(f); call_rcu(&f->f_u.fu_rcuhead, file_free_rcu); } /* * Return the total number of open files in the system */ static int get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } /* * Return the maximum number of open files in the system */ int get_max_files(void) { return files_stat.max_files; } EXPORT_SYMBOL_GPL(get_max_files); /* * Handle nr_files sysctl */ #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) int proc_nr_files(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_dointvec(table, write, filp, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; } #endif /* Find an unused file structure and return a pointer to it. * Returns NULL, if there are no more free file structures or * we run out of memory. * * Be very careful using this. You are responsible for * getting write access to any mount that you might assign * to this filp, if it is opened for write. If this is not * done, you will imbalance int the mount's writer count * and a warning at __fput() time. */ struct file *get_empty_filp(void) { struct task_struct *tsk; static int old_max; struct file * f; /* * Privileged users can go above max_files */ if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) { /* * percpu_counters are inaccurate. Do an expensive check before * we go and fail. */ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files) goto over; } f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL); if (f == NULL) goto fail; percpu_counter_inc(&nr_files); if (security_file_alloc(f)) goto fail_sec; tsk = current; INIT_LIST_HEAD(&f->f_u.fu_list); atomic_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); f->f_uid = tsk->fsuid; f->f_gid = tsk->fsgid; eventpoll_init_file(f); /* f->f_version: 0 */ return f; over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { printk(KERN_INFO "VFS: file-max limit %d reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; fail_sec: file_free(f); fail: return NULL; } EXPORT_SYMBOL(get_empty_filp); /** * alloc_file - allocate and initialize a 'struct file' * @mnt: the vfsmount on which the file will reside * @dentry: the dentry representing the new file * @mode: the mode with which the new file will be opened * @fop: the 'struct file_operations' for the new file * * Use this instead of get_empty_filp() to get a new * 'struct file'. Do so because of the same initialization * pitfalls reasons listed for init_file(). This is a * preferred interface to using init_file(). * * If all the callers of init_file() are eliminated, its * code should be moved into this function. */ struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry, mode_t mode, const struct file_operations *fop) { struct file *file; struct path; file = get_empty_filp(); if (!file) return NULL; init_file(file, mnt, dentry, mode, fop); return file; } EXPORT_SYMBOL(alloc_file); /** * init_file - initialize a 'struct file' * @file: the already allocated 'struct file' to initialized * @mnt: the vfsmount on which the file resides * @dentry: the dentry representing this file * @mode: the mode the file is opened with * @fop: the 'struct file_operations' for this file * * Use this instead of setting the members directly. Doing so * avoids making mistakes like forgetting the mntget() or * forgetting to take a write on the mnt. * * Note: This is a crappy interface. It is here to make * merging with the existing users of get_empty_filp() * who have complex failure logic easier. All users * of this should be moving to alloc_file(). */ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry, mode_t mode, const struct file_operations *fop) { int error = 0; file->f_path.dentry = dentry; file->f_path.mnt = mntget(mnt); file->f_mapping = dentry->d_inode->i_mapping; file->f_mode = mode; file->f_op = fop; /* * These mounts don't really matter in practice * for r/o bind mounts. They aren't userspace- * visible. We do this for consistency, and so * that we can do debugging checks at __fput() */ if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) { file_take_write(file); error = mnt_want_write(mnt); WARN_ON(error); } return error; } EXPORT_SYMBOL(init_file); void fput(struct file *file) { if (atomic_dec_and_test(&file->f_count)) __fput(file); } EXPORT_SYMBOL(fput); /** * drop_file_write_access - give up ability to write to a file * @file: the file to which we will stop writing * * This is a central place which will give up the ability * to write to @file, along with access to write through * its vfsmount. */ void drop_file_write_access(struct file *file) { struct vfsmount *mnt = file->f_path.mnt; struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; put_write_access(inode); if (special_file(inode->i_mode)) return; if (file_check_writeable(file) != 0) return; mnt_drop_write(mnt); file_release_write(file); } EXPORT_SYMBOL_GPL(drop_file_write_access); /* __fput is called from task context when aio completion releases the last * last use of a struct file *. Do not use otherwise. */ void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; struct inode *inode = dentry->d_inode; might_sleep(); fsnotify_close(file); /* * The function eventpoll_release() should be the first called * in the file cleanup chain. */ eventpoll_release(file); locks_remove_flock(file); if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); put_pid(file->f_owner.pid); file_kill(file); if (file->f_mode & FMODE_WRITE) drop_file_write_access(file); file->f_path.dentry = NULL; file->f_path.mnt = NULL; file_free(file); dput(dentry); mntput(mnt); } struct file *fget(unsigned int fd) { struct file *file; struct files_struct *files = current->files; rcu_read_lock(); file = fcheck_files(files, fd); if (file) { if (!atomic_inc_not_zero(&file->f_count)) { /* File object ref couldn't be taken */ rcu_read_unlock(); return NULL; } } rcu_read_unlock(); return file; } EXPORT_SYMBOL(fget); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * You can use this only if it is guranteed that the current task already * holds a refcnt to that file. That check has to be done at fget() only * and a flag is returned to be passed to the corresponding fput_light(). * There must not be a cloning between an fget_light/fput_light pair. */ struct file *fget_light(unsigned int fd, int *fput_needed) { struct file *file; struct files_struct *files = current->files; *fput_needed = 0; if (likely((atomic_read(&files->count) == 1))) { file = fcheck_files(files, fd); } else { rcu_read_lock(); file = fcheck_files(files, fd); if (file) { if (atomic_inc_not_zero(&file->f_count)) *fput_needed = 1; else /* Didn't get the reference, someone's freed */ file = NULL; } rcu_read_unlock(); } return file; } void put_filp(struct file *file) { if (atomic_dec_and_test(&file->f_count)) { security_file_free(file); file_kill(file); file_free(file); } } void file_move(struct file *file, struct list_head *list) { if (!list) return; file_list_lock(); list_move(&file->f_u.fu_list, list); file_list_unlock(); } void file_kill(struct file *file) { if (!list_empty(&file->f_u.fu_list)) { file_list_lock(); list_del_init(&file->f_u.fu_list); file_list_unlock(); } } int fs_may_remount_ro(struct super_block *sb) { struct file *file; /* Check that no files are currently opened for writing. */ file_list_lock(); list_for_each_entry(file, &sb->s_files, f_u.fu_list) { struct inode *inode = file->f_path.dentry->d_inode; /* File with pending delete? */ if (inode->i_nlink == 0) goto too_bad; /* Writeable file? */ if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE)) goto too_bad; } file_list_unlock(); return 1; /* Tis' cool bro. */ too_bad: file_list_unlock(); return 0; } void __init files_init(unsigned long mempages) { int n; /* One file with associated inode and dcache is very roughly 1K. * Per default don't use more than 10% of our memory for files. */ n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; if (files_stat.max_files < NR_FILE) files_stat.max_files = NR_FILE; files_defer_init(); percpu_counter_init(&nr_files, 0); }


context:
space:
mode: