X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Ffile_table.c;h=32d12b78bac8e2c05a80dc53386b355bdc10ef73;hb=64fc35de60da3b1fe970168d10914bf1cf34a3e3;hp=7a0a9b8722513faae34fc0f145c06f241f2630f7;hpb=ad775f5a8faa5845377f093ca11caf577404add9;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/file_table.c b/fs/file_table.c index 7a0a9b8..32d12b7 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -20,9 +21,12 @@ #include #include #include +#include #include +#include "internal.h" + /* sysctl tunables... */ struct files_stat_struct files_stat = { .max_files = NR_FILE @@ -31,11 +35,16 @@ struct files_stat_struct files_stat = { /* public. Not pretty! */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock); +/* SLAB cache for file structures */ +static struct kmem_cache *filp_cachep __read_mostly; + 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); + struct file *f = container_of(head, struct file, f_u.fu_rcuhead); + + put_cred(f->f_cred); kmem_cache_free(filp_cachep, f); } @@ -67,14 +76,14 @@ 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, +int proc_nr_files(ctl_table *table, int write, 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); + return proc_dointvec(table, write, buffer, lenp, ppos); } #else -int proc_nr_files(ctl_table *table, int write, struct file *filp, +int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return -ENOSYS; @@ -93,7 +102,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *filp, */ struct file *get_empty_filp(void) { - struct task_struct *tsk; + const struct cred *cred = current_cred(); static int old_max; struct file * f; @@ -117,12 +126,11 @@ struct file *get_empty_filp(void) if (security_file_alloc(f)) goto fail_sec; - tsk = current; INIT_LIST_HEAD(&f->f_u.fu_list); - atomic_set(&f->f_count, 1); + atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); - f->f_uid = tsk->fsuid; - f->f_gid = tsk->fsgid; + f->f_cred = get_cred(cred); + spin_lock_init(&f->f_lock); eventpoll_init_file(f); /* f->f_version: 0 */ return f; @@ -142,8 +150,6 @@ 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 @@ -159,45 +165,17 @@ EXPORT_SYMBOL(get_empty_filp); * 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 *alloc_file(struct path *path, fmode_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_path = *path; + file->f_mapping = path->dentry->d_inode->i_mapping; file->f_mode = mode; file->f_op = fop; @@ -207,18 +185,18 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry, * 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)) { + if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) { file_take_write(file); - error = mnt_want_write(mnt); - WARN_ON(error); + WARN_ON(mnt_clone_write(path->mnt)); } - return error; + ima_counts_get(file); + return file; } -EXPORT_SYMBOL(init_file); +EXPORT_SYMBOL(alloc_file); void fput(struct file *file) { - if (atomic_dec_and_test(&file->f_count)) + if (atomic_long_dec_and_test(&file->f_count)) __fput(file); } @@ -268,9 +246,14 @@ void __fput(struct file *file) eventpoll_release(file); locks_remove_flock(file); + if (unlikely(file->f_flags & FASYNC)) { + if (file->f_op && file->f_op->fasync) + file->f_op->fasync(-1, file, 0); + } if (file->f_op && file->f_op->release) file->f_op->release(inode, file); security_file_free(file); + ima_file_free(file); if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL)) cdev_put(inode->i_cdev); fops_put(file->f_op); @@ -293,7 +276,7 @@ struct file *fget(unsigned int fd) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (!atomic_inc_not_zero(&file->f_count)) { + if (!atomic_long_inc_not_zero(&file->f_count)) { /* File object ref couldn't be taken */ rcu_read_unlock(); return NULL; @@ -325,7 +308,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed) rcu_read_lock(); file = fcheck_files(files, fd); if (file) { - if (atomic_inc_not_zero(&file->f_count)) + if (atomic_long_inc_not_zero(&file->f_count)) *fput_needed = 1; else /* Didn't get the reference, someone's freed */ @@ -340,7 +323,7 @@ struct file *fget_light(unsigned int fd, int *fput_needed) void put_filp(struct file *file) { - if (atomic_dec_and_test(&file->f_count)) { + if (atomic_long_dec_and_test(&file->f_count)) { security_file_free(file); file_kill(file); file_free(file); @@ -389,10 +372,55 @@ too_bad: return 0; } +/** + * mark_files_ro - mark all files read-only + * @sb: superblock in question + * + * All files are marked read-only. We don't care about pending + * delete files so this should be used in 'force' mode only. + */ +void mark_files_ro(struct super_block *sb) +{ + struct file *f; + +retry: + file_list_lock(); + list_for_each_entry(f, &sb->s_files, f_u.fu_list) { + struct vfsmount *mnt; + if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) + continue; + if (!file_count(f)) + continue; + if (!(f->f_mode & FMODE_WRITE)) + continue; + spin_lock(&f->f_lock); + f->f_mode &= ~FMODE_WRITE; + spin_unlock(&f->f_lock); + if (file_check_writeable(f) != 0) + continue; + file_release_write(f); + mnt = mntget(f->f_path.mnt); + file_list_unlock(); + /* + * This can sleep, so we can't hold + * the file_list_lock() spinlock. + */ + mnt_drop_write(mnt); + mntput(mnt); + goto retry; + } + file_list_unlock(); +} + void __init files_init(unsigned long mempages) { int n; - /* One file with associated inode and dcache is very roughly 1K. + + filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + + /* + * One file with associated inode and dcache is very roughly 1K. * Per default don't use more than 10% of our memory for files. */