示例#1
0
文件: proto.c 项目: krzk/linux
void dccp_close(struct sock *sk, long timeout)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;
	u32 data_was_unread = 0;
	int state;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		/* Special case. */
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	sk_stop_timer(sk, &dp->dccps_xmit_timer);

	/*
	 * We need to flush the recv. buffs.  We do this only on the
	 * descriptor close, not protocol-sourced closes, because the
	  *reader process may not have drained the data yet!
	 */
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		data_was_unread += skb->len;
		__kfree_skb(skb);
	}

	/* If socket has been already reset kill it. */
	if (sk->sk_state == DCCP_CLOSED)
		goto adjudge_to_death;

	if (data_was_unread) {
		/* Unread data was tossed, send an appropriate Reset Code */
		DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		dccp_set_state(sk, DCCP_CLOSED);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		/* Check zero linger _after_ checking for unread data. */
		sk->sk_prot->disconnect(sk, 0);
	} else if (sk->sk_state != DCCP_CLOSED) {
		/*
		 * Normal connection termination. May need to wait if there are
		 * still packets in the TX queue that are delayed by the CCID.
		 */
		dccp_flush_write_queue(sk, &timeout);
		dccp_terminate_connection(sk);
	}

	/*
	 * Flush write queue. This may be necessary in several cases:
	 * - we have been closed by the peer but still have application data;
	 * - abortive termination (unread data or zero linger time),
	 * - normal termination but queue could not be flushed within time limit
	 */
	__skb_queue_purge(&sk->sk_write_queue);

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);

	/*
	 * It is the last release_sock in its life. It will remove backlog.
	 */
	release_sock(sk);
	/*
	 * Now socket is owned by kernel and we acquire BH lock
	 * to finish close. No need to check for user refs.
	 */
	local_bh_disable();
	bh_lock_sock(sk);
	WARN_ON(sock_owned_by_user(sk));

	percpu_counter_inc(sk->sk_prot->orphan_count);

	/* Have we already been destroyed by a softirq or backlog? */
	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
		goto out;

	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	/* Otherwise, socket is reprieved until protocol close. */

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}
示例#2
0
/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
{
	struct super_block *sb;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	int group;
	unsigned long ino = 0;
	struct inode * inode;
	struct ext3_group_desc * gdp = NULL;
	struct ext3_super_block * es;
	struct ext3_inode_info *ei;
	struct ext3_sb_info *sbi;
	int err = 0;
	struct inode *ret;
	int i;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	ei = EXT3_I(inode);

	sbi = EXT3_SB(sb);
	es = sbi->s_es;
	if (S_ISDIR(mode)) {
		if (test_opt (sb, OLDALLOC))
			group = find_group_dir(sb, dir);
		else
			group = find_group_orlov(sb, dir);
	} else
		group = find_group_other(sb, dir);

	err = -ENOSPC;
	if (group == -1)
		goto out;

	for (i = 0; i < sbi->s_groups_count; i++) {
		err = -EIO;

		gdp = ext3_get_group_desc(sb, group, &bh2);
		if (!gdp)
			goto fail;

		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, group);
		if (!bitmap_bh)
			goto fail;

		ino = 0;

repeat_in_this_group:
		ino = ext3_find_next_zero_bit((unsigned long *)
				bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
		if (ino < EXT3_INODES_PER_GROUP(sb)) {

			BUFFER_TRACE(bitmap_bh, "get_write_access");
			err = ext3_journal_get_write_access(handle, bitmap_bh);
			if (err)
				goto fail;

			if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
						ino, bitmap_bh->b_data)) {
				/* we won it */
				BUFFER_TRACE(bitmap_bh,
					"call ext3_journal_dirty_metadata");
				err = ext3_journal_dirty_metadata(handle,
								bitmap_bh);
				if (err)
					goto fail;
				goto got;
			}
			/* we lost it */
			journal_release_buffer(handle, bitmap_bh);

			if (++ino < EXT3_INODES_PER_GROUP(sb))
				goto repeat_in_this_group;
		}

		/*
		 * This case is possible in concurrent environment.  It is very
		 * rare.  We cannot repeat the find_group_xxx() call because
		 * that will simply return the same blockgroup, because the
		 * group descriptor metadata has not yet been updated.
		 * So we just go onto the next blockgroup.
		 */
		if (++group == sbi->s_groups_count)
			group = 0;
	}
	err = -ENOSPC;
	goto out;

got:
	ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
	if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext3_error (sb, "ext3_new_inode",
			    "reserved inode or inode > inodes count - "
			    "block_group = %d, inode=%lu", group, ino);
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
	err = ext3_journal_get_write_access(handle, bh2);
	if (err) goto fail;
	spin_lock(sb_bgl_lock(sbi, group));
	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
	if (S_ISDIR(mode)) {
		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
	}
	spin_unlock(sb_bgl_lock(sbi, group));
	BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, bh2);
	if (err) goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);

	inode->i_uid = current_fsuid();
	if (test_opt (sb, GRPID))
		inode->i_gid = dir->i_gid;
	else if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current_fsgid();
	inode->i_mode = mode;

	inode->i_ino = ino;
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

	ei->i_flags =
		ext3_mask_flags(mode, EXT3_I(dir)->i_flags & EXT3_FL_INHERITED);
#ifdef EXT3_FRAGMENTS
	ei->i_faddr = 0;
	ei->i_frag_no = 0;
	ei->i_frag_size = 0;
#endif
	ei->i_file_acl = 0;
	ei->i_dir_acl = 0;
	ei->i_dtime = 0;
	ei->i_block_alloc_info = NULL;
	ei->i_block_group = group;

	ext3_set_inode_flags(inode);
	if (IS_DIRSYNC(inode))
		handle->h_sync = 1;
	if (insert_inode_locked(inode) < 0) {
		err = -EINVAL;
		goto fail_drop;
	}
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

	ei->i_state = EXT3_STATE_NEW;
	ei->i_extra_isize =
		(EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE) ?
		sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE : 0;

	ret = inode;
	if (vfs_dq_alloc_inode(inode)) {
		err = -EDQUOT;
		goto fail_drop;
	}

	err = ext3_init_acl(handle, inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext3_init_security(handle,inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext3_mark_inode_dirty(handle, inode);
	if (err) {
		ext3_std_error(sb, err);
		goto fail_free_drop;
	}

	ext3_debug("allocating inode %lu\n", inode->i_ino);
	goto really_out;
fail:
	ext3_std_error(sb, err);
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(bitmap_bh);
	return ret;

fail_free_drop:
	vfs_dq_free_inode(inode);

fail_drop:
	vfs_dq_drop(inode);
	inode->i_flags |= S_NOQUOTA;
	inode->i_nlink = 0;
	unlock_new_inode(inode);
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}
示例#3
0
/*
 * NOTE! When we get the inode, we're the only people
 * that have access to it, and as such there are no
 * race conditions we have to worry about. The inode
 * is not on the hash-lists, and it cannot be reached
 * through the filesystem because the directory entry
 * has been deleted earlier.
 *
 * HOWEVER: we must make sure that we get no aliases,
 * which means that we have to call "clear_inode()"
 * _before_ we mark the inode not in use in the inode
 * bitmaps. Otherwise a newly created file might use
 * the same inode number (not actually the same pointer
 * though), and then we'd have two inodes sharing the
 * same inode number and space on the harddisk.
 */
void ext3_free_inode (handle_t *handle, struct inode * inode)
{
	struct super_block * sb = inode->i_sb;
	int is_directory;
	unsigned long ino;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	unsigned long block_group;
	unsigned long bit;
	struct ext3_group_desc * gdp;
	struct ext3_super_block * es;
	struct ext3_sb_info *sbi;
	int fatal = 0, err;

	if (atomic_read(&inode->i_count) > 1) {
		printk ("ext3_free_inode: inode has count=%d\n",
					atomic_read(&inode->i_count));
		return;
	}
	if (inode->i_nlink) {
		printk ("ext3_free_inode: inode has nlink=%d\n",
			inode->i_nlink);
		return;
	}
	if (!sb) {
		printk("ext3_free_inode: inode on nonexistent device\n");
		return;
	}
	sbi = EXT3_SB(sb);

	ino = inode->i_ino;
	ext3_debug ("freeing inode %lu\n", ino);

	/*
	 * Note: we must free any quota before locking the superblock,
	 * as writing the quota to disk may need the lock as well.
	 */
	vfs_dq_init(inode);
	ext3_xattr_delete_inode(handle, inode);
	vfs_dq_free_inode(inode);
	vfs_dq_drop(inode);

	is_directory = S_ISDIR(inode->i_mode);

	/* Do this BEFORE marking the inode not in use or returning an error */
	clear_inode (inode);

	es = EXT3_SB(sb)->s_es;
	if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext3_error (sb, "ext3_free_inode",
			    "reserved or nonexistent inode %lu", ino);
		goto error_return;
	}
	block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT3_INODES_PER_GROUP(sb);
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;

	BUFFER_TRACE(bitmap_bh, "get_write_access");
	fatal = ext3_journal_get_write_access(handle, bitmap_bh);
	if (fatal)
		goto error_return;

	/* Ok, now we can actually update the inode bitmaps.. */
	if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
					bit, bitmap_bh->b_data))
		ext3_error (sb, "ext3_free_inode",
			      "bit already cleared for inode %lu", ino);
	else {
		gdp = ext3_get_group_desc (sb, block_group, &bh2);

		BUFFER_TRACE(bh2, "get_write_access");
		fatal = ext3_journal_get_write_access(handle, bh2);
		if (fatal) goto error_return;

		if (gdp) {
			spin_lock(sb_bgl_lock(sbi, block_group));
			le16_add_cpu(&gdp->bg_free_inodes_count, 1);
			if (is_directory)
				le16_add_cpu(&gdp->bg_used_dirs_count, -1);
			spin_unlock(sb_bgl_lock(sbi, block_group));
			percpu_counter_inc(&sbi->s_freeinodes_counter);
			if (is_directory)
				percpu_counter_dec(&sbi->s_dirs_counter);

		}
		BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
		err = ext3_journal_dirty_metadata(handle, bh2);
		if (!fatal) fatal = err;
	}
	BUFFER_TRACE(bitmap_bh, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, bitmap_bh);
	if (!fatal)
		fatal = err;

error_return:
	brelse(bitmap_bh);
	ext3_std_error(sb, fatal);
}
示例#4
0
/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
struct inode *ext3_new_inode(handle_t *handle, struct inode * dir, int mode)
{
	struct super_block *sb;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	int group;
	unsigned long ino = 0;
	struct inode * inode;
	struct ext3_group_desc * gdp = NULL;
	struct ext3_super_block * es;
	struct ext3_inode_info *ei;
	struct ext3_sb_info *sbi;
	int err = 0;
	struct inode *ret;
	int i;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	ei = EXT3_I(inode);

	sbi = EXT3_SB(sb);
	es = sbi->s_es;
	if (S_ISDIR(mode)) {
		if (test_opt (sb, OLDALLOC))
			group = find_group_dir(sb, dir);
		else
			group = find_group_orlov(sb, dir);
	} else 
		group = find_group_other(sb, dir);

	err = -ENOSPC;
	if (group == -1)
		goto out;

	for (i = 0; i < sbi->s_groups_count; i++) {
		gdp = ext3_get_group_desc(sb, group, &bh2);

		err = -EIO;
		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, group);
		if (!bitmap_bh)
			goto fail;

		ino = 0;

repeat_in_this_group:
		ino = ext3_find_next_zero_bit((unsigned long *)
				bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
		if (ino < EXT3_INODES_PER_GROUP(sb)) {
			int credits = 0;

			BUFFER_TRACE(bitmap_bh, "get_write_access");
			err = ext3_journal_get_write_access_credits(handle,
							bitmap_bh, &credits);
			if (err)
				goto fail;

			if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
						ino, bitmap_bh->b_data)) {
				/* we won it */
				BUFFER_TRACE(bitmap_bh,
					"call ext3_journal_dirty_metadata");
				err = ext3_journal_dirty_metadata(handle,
								bitmap_bh);
				if (err)
					goto fail;
				goto got;
			}
			/* we lost it */
			journal_release_buffer(handle, bitmap_bh, credits);

			if (++ino < EXT3_INODES_PER_GROUP(sb))
				goto repeat_in_this_group;
		}

		/*
		 * This case is possible in concurrent environment.  It is very
		 * rare.  We cannot repeat the find_group_xxx() call because
		 * that will simply return the same blockgroup, because the
		 * group descriptor metadata has not yet been updated.
		 * So we just go onto the next blockgroup.
		 */
		if (++group == sbi->s_groups_count)
			group = 0;
	}
	err = -ENOSPC;
	goto out;

got:
	ino += group * EXT3_INODES_PER_GROUP(sb) + 1;
	if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext3_error (sb, "ext3_new_inode",
			    "reserved inode or inode > inodes count - "
			    "block_group = %d, inode=%lu", group, ino);
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
	err = ext3_journal_get_write_access(handle, bh2);
	if (err) goto fail;
	spin_lock(sb_bgl_lock(sbi, group));
	gdp->bg_free_inodes_count =
		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
	if (S_ISDIR(mode)) {
		gdp->bg_used_dirs_count =
			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
	}
	spin_unlock(sb_bgl_lock(sbi, group));
	BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
	err = ext3_journal_dirty_metadata(handle, bh2);
	if (err) goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);
	sb->s_dirt = 1;

	inode->i_uid = current->fsuid;
	if (test_opt (sb, GRPID))
		inode->i_gid = dir->i_gid;
	else if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current->fsgid;
	inode->i_mode = mode;

	inode->i_ino = ino;
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blksize = PAGE_SIZE;
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_next_alloc_block = 0;
	ei->i_next_alloc_goal = 0;
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

	ei->i_flags = EXT3_I(dir)->i_flags & ~EXT3_INDEX_FL;
	if (S_ISLNK(mode))
		ei->i_flags &= ~(EXT3_IMMUTABLE_FL|EXT3_APPEND_FL);
	/* dirsync only applies to directories */
	if (!S_ISDIR(mode))
		ei->i_flags &= ~EXT3_DIRSYNC_FL;
#ifdef EXT3_FRAGMENTS
	ei->i_faddr = 0;
	ei->i_frag_no = 0;
	ei->i_frag_size = 0;
#endif
	ei->i_file_acl = 0;
	ei->i_dir_acl = 0;
	ei->i_dtime = 0;
	ei->i_rsv_window.rsv_start = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	ei->i_rsv_window.rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	atomic_set(&ei->i_rsv_window.rsv_goal_size, EXT3_DEFAULT_RESERVE_BLOCKS);
	atomic_set(&ei->i_rsv_window.rsv_alloc_hit, 0);
	seqlock_init(&ei->i_rsv_window.rsv_seqlock);
	ei->i_block_group = group;

	ext3_set_inode_flags(inode);
	if (IS_DIRSYNC(inode))
		handle->h_sync = 1;
	insert_inode_hash(inode);
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

	ei->i_state = EXT3_STATE_NEW;

	ret = inode;
	if(DQUOT_ALLOC_INODE(inode)) {
		DQUOT_DROP(inode);
		err = -EDQUOT;
		goto fail2;
	}
	err = ext3_init_acl(handle, inode, dir);
	if (err) {
		DQUOT_FREE_INODE(inode);
		goto fail2;
  	}
	err = ext3_mark_inode_dirty(handle, inode);
	if (err) {
		ext3_std_error(sb, err);
		DQUOT_FREE_INODE(inode);
		goto fail2;
	}

	ext3_debug("allocating inode %lu\n", inode->i_ino);
	goto really_out;
fail:
	ext3_std_error(sb, err);
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(bitmap_bh);
	return ret;

fail2:
	inode->i_flags |= S_NOQUOTA;
	inode->i_nlink = 0;
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}
/* Find an unused file structure and return a pointer to it.
 * Returns an error pointer if some error happend e.g. we over file
 * structures limit, run out of memory or operation is not permitted.
 *
 * 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)
{
	const struct cred *cred = current_cred();
	static long old_max;
	struct file *f;
	int error;

	/*
	 * 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 (unlikely(!f))
		return ERR_PTR(-ENOMEM);

	percpu_counter_inc(&nr_files);
	f->f_cred = get_cred(cred);
	error = security_file_alloc(f);
	if (unlikely(error)) {
		file_free(f);
		return ERR_PTR(error);
	}

	atomic_long_set(&f->f_count, 1);
	rwlock_init(&f->f_owner.lock);
	spin_lock_init(&f->f_lock);
	mutex_init(&f->f_pos_lock);
	eventpoll_init_file(f);
	/* f->f_version: 0 */
	return f;

over:
	/* Ran out of filps - report that */
	if (get_nr_files() > old_max) {
#ifdef FD_OVER_CHECK
		static int fd_dump_all_files;

		if (!fd_dump_all_files) {
			struct task_struct *p;
			struct files_struct *files;
			pid_t pid;

			fd_dump_all_files = 0x1;

			for_each_process(p) {
				if (p->flags & PF_KTHREAD)
					continue;

				files = p->files;
				if (files) {
					struct fdtable *fdt = files_fdtable(files);

					if (fdt) {
						pid = p->pid;
						pr_err("[FDLEAK]dump FDs for [%d:%s]\n", pid, p->comm);
						fd_show_open_files(pid, files, fdt);
					}
				}
			}
		}
#endif
		pr_info("VFS: file-max limit %lu reached\n", get_max_files());
		old_max = get_nr_files();
	}
	return ERR_PTR(-ENFILE);
}
/* 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)
{
	const struct cred *cred = current_cred();
	static long 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);
	f->f_cred = get_cred(cred);
	if (security_file_alloc(f))
		goto fail_sec;

	INIT_LIST_HEAD(&f->f_u.fu_list);
	atomic_long_set(&f->f_count, 1);
	rwlock_init(&f->f_owner.lock);
	spin_lock_init(&f->f_lock);
	eventpoll_init_file(f);
	/* f->f_version: 0 */
	return f;

over:
	/* Ran out of filps - report that */
	if (get_nr_files() > old_max) {
#ifdef FILE_OVER_MAX
        static int fd_dump_all_files = 0;        
        if(!fd_dump_all_files) { 
	        struct task_struct *p;
	        xlog_printk(ANDROID_LOG_INFO, FS_TAG, "(PID:%d)files %d over old_max:%d", current->pid, get_nr_files(), old_max);
	        for_each_process(p) {
	            pid_t pid = p->pid;
	            struct files_struct *files = p->files;
	            struct fdtable *fdt = files_fdtable(files);
#ifdef FD_OVER_CHECK
	            if(files && fdt) {
	                fd_show_open_files(pid, files, fdt);
	            }	        
#endif
	        }
	        fd_dump_all_files = 0x1;
        }
#endif	    
		pr_info("VFS: file-max limit %lu reached\n", get_max_files());
		old_max = get_nr_files();
	}
	goto fail;

fail_sec:
	file_free(f);
fail:
	return NULL;
}
示例#7
0
文件: dev-replace.c 项目: Abioy/kasan
void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
{
	percpu_counter_inc(&fs_info->bio_counter);
}
示例#8
0
void dccp_close(struct sock *sk, long timeout)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;
	u32 data_was_unread = 0;
	int state;

	lock_sock(sk);

	sk->sk_shutdown = SHUTDOWN_MASK;

	if (sk->sk_state == DCCP_LISTEN) {
		dccp_set_state(sk, DCCP_CLOSED);

		
		inet_csk_listen_stop(sk);

		goto adjudge_to_death;
	}

	sk_stop_timer(sk, &dp->dccps_xmit_timer);

	
	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		data_was_unread += skb->len;
		__kfree_skb(skb);
	}

	if (data_was_unread) {
		
		DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread);
		dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
		dccp_set_state(sk, DCCP_CLOSED);
	} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
		
		sk->sk_prot->disconnect(sk, 0);
	} else if (sk->sk_state != DCCP_CLOSED) {
		dccp_terminate_connection(sk);
	}

	sk_stream_wait_close(sk, timeout);

adjudge_to_death:
	state = sk->sk_state;
	sock_hold(sk);
	sock_orphan(sk);

	
	release_sock(sk);
	
	local_bh_disable();
	bh_lock_sock(sk);
	WARN_ON(sock_owned_by_user(sk));

	percpu_counter_inc(sk->sk_prot->orphan_count);

	
	if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
		goto out;

	if (sk->sk_state == DCCP_CLOSED)
		inet_csk_destroy_sock(sk);

	

out:
	bh_unlock_sock(sk);
	local_bh_enable();
	sock_put(sk);
}