C++ down_read函数代码示例

asmlinkage void
do_page_fault(unsigned long address, struct pt_regs *regs,
	      int protection, int writeaccess)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct * vma;
	siginfo_t info;

        D(printk("Page fault for %lX on %X at %lX, prot %d write %d\n",
                 address, smp_processor_id(), instruction_pointer(regs),
                 protection, writeaccess));

	tsk = current;

	/*
	 * We fault-in kernel-space virtual memory on-demand. The
	 * 'reference' page table is init_mm.pgd.
	 *
	 * NOTE! We MUST NOT take any locks for this case. We may
	 * be in an interrupt or a critical region, and should
	 * only copy the information from the master page table,
	 * nothing more.
	 *
	 * NOTE2: This is done so that, when updating the vmalloc
	 * mappings we don't have to walk all processes pgdirs and
	 * add the high mappings all at once. Instead we do it as they
	 * are used. However vmalloc'ed page entries have the PAGE_GLOBAL
	 * bit set so sometimes the TLB can use a lingering entry.
	 *
	 * This verifies that the fault happens in kernel space
	 * and that the fault was not a protection error (error_code & 1).
	 */

	if (address >= VMALLOC_START &&
	    !protection &&
	    !user_mode(regs))
		goto vmalloc_fault;

	/* When stack execution is not allowed we store the signal
	 * trampolines in the reserved cris_signal_return_page.
	 * Handle this in the exact same way as vmalloc (we know
	 * that the mapping is there and is valid so no need to
	 * call handle_mm_fault).
	 */
	if (cris_signal_return_page &&
	    address == cris_signal_return_page &&
	    !protection && user_mode(regs))
		goto vmalloc_fault;

	/* we can and should enable interrupts at this point */
	local_irq_enable();

	mm = tsk->mm;
	info.si_code = SEGV_MAPERR;

	/*
	 * If we're in an interrupt or have no user
	 * context, we must not take the fault..
	 */

	if (in_atomic() || !mm)
		goto no_context;

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;
	if (vma->vm_start <= address)
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (user_mode(regs)) {
		/*
		 * accessing the stack below usp is always a bug.
		 * we get page-aligned addresses so we can only check
		 * if we're within a page from usp, but that might be
		 * enough to catch brutal errors at least.
		 */
		if (address + PAGE_SIZE < rdusp())
			goto bad_area;
	}
	if (expand_stack(vma, address))
		goto bad_area;

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it..
	 */

 good_area:
	info.si_code = SEGV_ACCERR;

	/* first do some preliminary protection checks */

	if (writeaccess == 2){
		if (!(vma->vm_flags & VM_EXEC))
			goto bad_area;
	} else if (writeaccess == 1) {
		if (!(vma->vm_flags & VM_WRITE))
//.........这里部分代码省略.........

/*
 * Prepare the write for the inline data.
 * If the the data can be written into the inode, we just read
 * the page and make it uptodate, and start the journal.
 * Otherwise read the page, makes it dirty so that it can be
 * handle in writepages(the i_disksize update is left to the
 * normal ext4_da_write_end).
 */
int ext4_da_write_inline_data_begin(struct address_space *mapping,
				    struct inode *inode,
				    loff_t pos, unsigned len,
				    unsigned flags,
				    struct page **pagep,
				    void **fsdata)
{
	int ret, inline_size;
	handle_t *handle;
	struct page *page;
	struct ext4_iloc iloc;
	int retries;

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

retry_journal:
	handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		goto out;
	}

	inline_size = ext4_get_max_inline_size(inode);

	ret = -ENOSPC;
	if (inline_size >= pos + len) {
		ret = ext4_prepare_inline_data(handle, inode, pos + len);
		if (ret && ret != -ENOSPC)
			goto out_journal;
	}

	/*
	 * We cannot recurse into the filesystem as the transaction
	 * is already started.
	 */
	flags |= AOP_FLAG_NOFS;

	if (ret == -ENOSPC) {
		ret = ext4_da_convert_inline_data_to_extent(mapping,
							    inode,
							    flags,
							    fsdata);
		ext4_journal_stop(handle);
		if (ret == -ENOSPC &&
		    ext4_should_retry_alloc(inode->i_sb, &retries))
			goto retry_journal;
		goto out;
	}


	page = grab_cache_page_write_begin(mapping, 0, flags);
	if (!page) {
		ret = -ENOMEM;
		goto out_journal;
	}

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		ret = 0;
		goto out_release_page;
	}

	if (!PageUptodate(page)) {
		ret = ext4_read_inline_page(inode, page);
		if (ret < 0)
			goto out_release_page;
	}

	up_read(&EXT4_I(inode)->xattr_sem);
	*pagep = page;
	brelse(iloc.bh);
	return 1;
out_release_page:
	up_read(&EXT4_I(inode)->xattr_sem);
	unlock_page(page);
	page_cache_release(page);
out_journal:
	ext4_journal_stop(handle);
out:
	brelse(iloc.bh);
	return ret;
}

int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct f2fs_inode_info *fi = F2FS_I(inode);
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	nid_t ino = inode->i_ino;
	int ret = 0;
	bool need_cp = false;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.for_reclaim = 0,
	};

	if (unlikely(f2fs_readonly(inode->i_sb)))
		return 0;

	trace_f2fs_sync_file_enter(inode);

	/* if fdatasync is triggered, let's do in-place-update */
	if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
		set_inode_flag(fi, FI_NEED_IPU);
	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	clear_inode_flag(fi, FI_NEED_IPU);

	if (ret) {
		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
		return ret;
	}

	/* if the inode is dirty, let's recover all the time */
	if (!datasync) {
		f2fs_write_inode(inode, NULL);
		goto go_write;
	}

	/*
	 * if there is no written data, don't waste time to write recovery info.
	 */
	if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
			!exist_written_data(sbi, ino, APPEND_INO)) {

		/* it may call write_inode just prior to fsync */
		if (need_inode_page_update(sbi, ino))
			goto go_write;

		if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
				exist_written_data(sbi, ino, UPDATE_INO))
			goto flush_out;
		goto out;
	}
go_write:
	/* guarantee free sections for fsync */
	f2fs_balance_fs(sbi);

	/*
	 * Both of fdatasync() and fsync() are able to be recovered from
	 * sudden-power-off.
	 */
	down_read(&fi->i_sem);
	need_cp = need_do_checkpoint(inode);
	up_read(&fi->i_sem);

	if (need_cp) {
		/* all the dirty node pages should be flushed for POR */
		ret = f2fs_sync_fs(inode->i_sb, 1);

		/*
		 * We've secured consistency through sync_fs. Following pino
		 * will be used only for fsynced inodes after checkpoint.
		 */
		try_to_fix_pino(inode);
		clear_inode_flag(fi, FI_APPEND_WRITE);
		clear_inode_flag(fi, FI_UPDATE_WRITE);
		goto out;
	}
sync_nodes:
	sync_node_pages(sbi, ino, &wbc);

	/* if cp_error was enabled, we should avoid infinite loop */
	if (unlikely(f2fs_cp_error(sbi)))
		goto out;

	if (need_inode_block_update(sbi, ino)) {
		mark_inode_dirty_sync(inode);
		f2fs_write_inode(inode, NULL);
		goto sync_nodes;
	}

	ret = wait_on_node_pages_writeback(sbi, ino);
	if (ret)
		goto out;

	/* once recovery info is written, don't need to tack this */
	remove_dirty_inode(sbi, ino, APPEND_INO);
	clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
	remove_dirty_inode(sbi, ino, UPDATE_INO);
	clear_inode_flag(fi, FI_UPDATE_WRITE);
	ret = f2fs_issue_flush(sbi);
//.........这里部分代码省略.........

/*
 * So this function is called when the volume is mkfsed with
 * dir_index disabled. In order to keep f_pos persistent
 * after we convert from an inlined dir to a blocked based,
 * we just pretend that we are a normal dir and return the
 * offset as if '.' and '..' really take place.
 *
 */
int ext4_read_inline_dir(struct file *filp,
			 void *dirent, filldir_t filldir,
			 int *has_inline_data)
{
	int error = 0;
	unsigned int offset, parent_ino;
	int i, stored;
	struct ext4_dir_entry_2 *de;
	struct super_block *sb;
	struct inode *inode = file_inode(filp);
	int ret, inline_size = 0;
	struct ext4_iloc iloc;
	void *dir_buf = NULL;
	int dotdot_offset, dotdot_size, extra_offset, extra_size;

	ret = ext4_get_inode_loc(inode, &iloc);
	if (ret)
		return ret;

	down_read(&EXT4_I(inode)->xattr_sem);
	if (!ext4_has_inline_data(inode)) {
		up_read(&EXT4_I(inode)->xattr_sem);
		*has_inline_data = 0;
		goto out;
	}

	inline_size = ext4_get_inline_size(inode);
	dir_buf = kmalloc(inline_size, GFP_NOFS);
	if (!dir_buf) {
		ret = -ENOMEM;
		up_read(&EXT4_I(inode)->xattr_sem);
		goto out;
	}

	ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
	up_read(&EXT4_I(inode)->xattr_sem);
	if (ret < 0)
		goto out;

	ret = 0;
	sb = inode->i_sb;
	stored = 0;
	parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
	offset = filp->f_pos;

	/*
	 * dotdot_offset and dotdot_size is the real offset and
	 * size for ".." and "." if the dir is block based while
	 * the real size for them are only EXT4_INLINE_DOTDOT_SIZE.
	 * So we will use extra_offset and extra_size to indicate them
	 * during the inline dir iteration.
	 */
	dotdot_offset = EXT4_DIR_REC_LEN(1);
	dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
	extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
	extra_size = extra_offset + inline_size;

	while (!error && !stored && filp->f_pos < extra_size) {
revalidate:
		/*
		 * If the version has changed since the last call to
		 * readdir(2), then we might be pointing to an invalid
		 * dirent right now.  Scan from the start of the inline
		 * dir to make sure.
		 */
		if (filp->f_version != inode->i_version) {
			for (i = 0; i < extra_size && i < offset;) {
				/*
				 * "." is with offset 0 and
				 * ".." is dotdot_offset.
				 */
				if (!i) {
					i = dotdot_offset;
					continue;
				} else if (i == dotdot_offset) {
					i = dotdot_size;
					continue;
				}
				/* for other entry, the real offset in
				 * the buf has to be tuned accordingly.
				 */
				de = (struct ext4_dir_entry_2 *)
					(dir_buf + i - extra_offset);
				/* It's too expensive to do a full
				 * dirent test each time round this
				 * loop, but we do have to test at
				 * least that it is non-zero.  A
				 * failure will be detected in the
				 * dirent test below. */
				if (ext4_rec_len_from_disk(de->rec_len,
					extra_size) < EXT4_DIR_REC_LEN(1))
					break;
//.........这里部分代码省略.........

int ext4_ext_migrate(struct inode *inode)
{
	handle_t *handle;
	int retval = 0, i;
	__le32 *i_data;
	struct ext4_inode_info *ei;
	struct inode *tmp_inode = NULL;
	struct migrate_struct lb;
	unsigned long max_entries;
	__u32 goal;
	uid_t owner[2];

	/*
	 * If the filesystem does not support extents, or the inode
	 * already is extent-based, error out.
	 */
	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
	    (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
		return -EINVAL;

	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
		/*
		 * don't migrate fast symlink
		 */
		return retval;

	/*
	 * Worst case we can touch the allocation bitmaps, a bgd
	 * block, and a block to link in the orphan list.  We do need
	 * need to worry about credits for modifying the quota inode.
	 */
	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE,
		4 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb));

	if (IS_ERR(handle)) {
		retval = PTR_ERR(handle);
		return retval;
	}
	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
	owner[0] = i_uid_read(inode);
	owner[1] = i_gid_read(inode);
	tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
				   S_IFREG, NULL, goal, owner);
	if (IS_ERR(tmp_inode)) {
		retval = PTR_ERR(tmp_inode);
		ext4_journal_stop(handle);
		return retval;
	}
	i_size_write(tmp_inode, i_size_read(inode));
	/*
	 * Set the i_nlink to zero so it will be deleted later
	 * when we drop inode reference.
	 */
	clear_nlink(tmp_inode);

	ext4_ext_tree_init(handle, tmp_inode);
	ext4_orphan_add(handle, tmp_inode);
	ext4_journal_stop(handle);

	/*
	 * start with one credit accounted for
	 * superblock modification.
	 *
	 * For the tmp_inode we already have committed the
	 * transaction that created the inode. Later as and
	 * when we add extents we extent the journal
	 */
	/*
	 * Even though we take i_mutex we can still cause block
	 * allocation via mmap write to holes. If we have allocated
	 * new blocks we fail migrate.  New block allocation will
	 * clear EXT4_STATE_EXT_MIGRATE flag.  The flag is updated
	 * with i_data_sem held to prevent racing with block
	 * allocation.
	 */
	down_read(&EXT4_I(inode)->i_data_sem);
	ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
	up_read((&EXT4_I(inode)->i_data_sem));

	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
	if (IS_ERR(handle)) {
		/*
		 * It is impossible to update on-disk structures without
		 * a handle, so just rollback in-core changes and live other
		 * work to orphan_list_cleanup()
		 */
		ext4_orphan_del(NULL, tmp_inode);
		retval = PTR_ERR(handle);
		goto out;
	}

	ei = EXT4_I(inode);
	i_data = ei->i_data;
	memset(&lb, 0, sizeof(lb));

	/* 32 bit block address 4 bytes */
	max_entries = inode->i_sb->s_blocksize >> 2;
	for (i = 0; i < EXT4_NDIR_BLOCKS; i++) {
//.........这里部分代码省略.........

/*
 * Get the appropriate destination keyring for the request.
 *
 * The keyring selected is returned with an extra reference upon it which the
 * caller must release.
 */
static void construct_get_dest_keyring(struct key **_dest_keyring)
{
	struct request_key_auth *rka;
	const struct cred *cred = current_cred();
	struct key *dest_keyring = *_dest_keyring, *authkey;

	kenter("%p", dest_keyring);

	/* find the appropriate keyring */
	if (dest_keyring) {
		/* the caller supplied one */
		key_get(dest_keyring);
	} else {
		/* use a default keyring; falling through the cases until we
		 * find one that we actually have */
		switch (cred->jit_keyring) {
		case KEY_REQKEY_DEFL_DEFAULT:
		case KEY_REQKEY_DEFL_REQUESTOR_KEYRING:
			if (cred->request_key_auth) {
				authkey = cred->request_key_auth;
				down_read(&authkey->sem);
				rka = authkey->payload.data;
				if (!test_bit(KEY_FLAG_REVOKED,
					      &authkey->flags))
					dest_keyring =
						key_get(rka->dest_keyring);
				up_read(&authkey->sem);
				if (dest_keyring)
					break;
			}

		case KEY_REQKEY_DEFL_THREAD_KEYRING:
			dest_keyring = key_get(cred->thread_keyring);
			if (dest_keyring)
				break;

		case KEY_REQKEY_DEFL_PROCESS_KEYRING:
			dest_keyring = key_get(cred->tgcred->process_keyring);
			if (dest_keyring)
				break;

		case KEY_REQKEY_DEFL_SESSION_KEYRING:
			rcu_read_lock();
			dest_keyring = key_get(
				rcu_dereference(cred->tgcred->session_keyring));
			rcu_read_unlock();

			if (dest_keyring)
				break;

		case KEY_REQKEY_DEFL_USER_SESSION_KEYRING:
			dest_keyring =
				key_get(cred->user->session_keyring);
			break;

		case KEY_REQKEY_DEFL_USER_KEYRING:
			dest_keyring = key_get(cred->user->uid_keyring);
			break;

		case KEY_REQKEY_DEFL_GROUP_KEYRING:
		default:
			BUG();
		}
	}

	*_dest_keyring = dest_keyring;
	kleave(" [dk %d]", key_serial(dest_keyring));
	return;
}

/**
 * nilfs_fill_super() - initialize a super block instance
 * @sb: super_block
 * @data: mount options
 * @silent: silent mode flag
 * @nilfs: the_nilfs struct
 *
 * This function is called exclusively by nilfs->ns_mount_mutex.
 * So, the recovery process is protected from other simultaneous mounts.
 */
static int
nilfs_fill_super(struct super_block *sb, void *data, int silent,
		 struct the_nilfs *nilfs)
{
	struct nilfs_sb_info *sbi;
	struct inode *root;
	__u64 cno;
	int err;

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	sb->s_fs_info = sbi;

	get_nilfs(nilfs);
	sbi->s_nilfs = nilfs;
	sbi->s_super = sb;
	atomic_set(&sbi->s_count, 1);

	err = init_nilfs(nilfs, sbi, (char *)data);
	if (err)
		goto failed_sbi;

	spin_lock_init(&sbi->s_inode_lock);
	INIT_LIST_HEAD(&sbi->s_dirty_files);
	INIT_LIST_HEAD(&sbi->s_list);

	/*
	 * Following initialization is overlapped because
	 * nilfs_sb_info structure has been cleared at the beginning.
	 * But we reserve them to keep our interest and make ready
	 * for the future change.
	 */
	get_random_bytes(&sbi->s_next_generation,
			 sizeof(sbi->s_next_generation));
	spin_lock_init(&sbi->s_next_gen_lock);

	sb->s_op = &nilfs_sops;
	sb->s_export_op = &nilfs_export_ops;
	sb->s_root = NULL;
	sb->s_time_gran = 1;
	sb->s_bdi = nilfs->ns_bdi;

	err = load_nilfs(nilfs, sbi);
	if (err)
		goto failed_sbi;

	cno = nilfs_last_cno(nilfs);

	if (sb->s_flags & MS_RDONLY) {
		if (nilfs_test_opt(sbi, SNAPSHOT)) {
			down_read(&nilfs->ns_segctor_sem);
			err = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile,
						       sbi->s_snapshot_cno);
			up_read(&nilfs->ns_segctor_sem);
			if (err < 0) {
				if (err == -ENOENT)
					err = -EINVAL;
				goto failed_sbi;
			}
			if (!err) {
				printk(KERN_ERR
				       "NILFS: The specified checkpoint is "
				       "not a snapshot "
				       "(checkpoint number=%llu).\n",
				       (unsigned long long)sbi->s_snapshot_cno);
				err = -EINVAL;
				goto failed_sbi;
			}
			cno = sbi->s_snapshot_cno;
		}
	}

	err = nilfs_attach_checkpoint(sbi, cno);
	if (err) {
		printk(KERN_ERR "NILFS: error loading a checkpoint"
		       " (checkpoint number=%llu).\n", (unsigned long long)cno);
		goto failed_sbi;
	}

	if (!(sb->s_flags & MS_RDONLY)) {
		err = nilfs_attach_segment_constructor(sbi);
		if (err)
			goto failed_checkpoint;
	}

	root = nilfs_iget(sb, NILFS_ROOT_INO);
	if (IS_ERR(root)) {
		printk(KERN_ERR "NILFS: get root inode failed\n");
//.........这里部分代码省略.........

/*
 * Canonical page fault handler
 */
void do_page_fault(unsigned long address, long cause, struct pt_regs *regs)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	siginfo_t info;
	int si_code = SEGV_MAPERR;
	int fault;
	const struct exception_table_entry *fixup;

	/*
	 * If we're in an interrupt or have no user context,
	 * then must not take the fault.
	 */
	if (unlikely(in_interrupt() || !mm))
		goto no_context;

	local_irq_enable();

	down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;

	if (vma->vm_start <= address)
		goto good_area;

	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;

	if (expand_stack(vma, address))
		goto bad_area;

good_area:
	/* Address space is OK.  Now check access rights. */
	si_code = SEGV_ACCERR;

	switch (cause) {
	case FLT_IFETCH:
		if (!(vma->vm_flags & VM_EXEC))
			goto bad_area;
		break;
	case FLT_LOAD:
		if (!(vma->vm_flags & VM_READ))
			goto bad_area;
		break;
	case FLT_STORE:
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
		break;
	}

	fault = handle_mm_fault(mm, vma, address, (cause > 0));

	/* The most common case -- we are done. */
	if (likely(!(fault & VM_FAULT_ERROR))) {
		if (fault & VM_FAULT_MAJOR)
			current->maj_flt++;
		else
			current->min_flt++;

		up_read(&mm->mmap_sem);
		return;
	}

	up_read(&mm->mmap_sem);

	/* Handle copyin/out exception cases */
	if (!user_mode(regs))
		goto no_context;

	if (fault & VM_FAULT_OOM) {
		pagefault_out_of_memory();
		return;
	}

	/* User-mode address is in the memory map, but we are
	 * unable to fix up the page fault.
	 */
	if (fault & VM_FAULT_SIGBUS) {
		info.si_signo = SIGBUS;
		info.si_code = BUS_ADRERR;
	}
	/* Address is not in the memory map */
	else {
		info.si_signo = SIGSEGV;
		info.si_code = SEGV_ACCERR;
	}
	info.si_errno = 0;
	info.si_addr = (void __user *)address;
	force_sig_info(info.si_code, &info, current);
	return;

bad_area:
	up_read(&mm->mmap_sem);

	if (user_mode(regs)) {
		info.si_signo = SIGSEGV;
//.........这里部分代码省略.........

/*
 * MS_SYNC syncs the entire file - including mappings.
 *
 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
 * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
 * Now it doesn't do anything, since dirty pages are properly tracked.
 *
 * The application may now run fsync() to
 * write out the dirty pages and wait on the writeout and check the result.
 * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
 * async writeout immediately.
 * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
 * applications.
 */
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
	unsigned long end;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int unmapped_error = 0;
	int error = -EINVAL;

	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
		goto out;
	if (start & ~PAGE_MASK)
		goto out;
	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
		goto out;
	error = -ENOMEM;
	len = (len + ~PAGE_MASK) & PAGE_MASK;
	end = start + len;
	if (end < start)
		goto out;
	error = 0;
	if (end == start)
		goto out;
	/*
	 * If the interval [start,end) covers some unmapped address ranges,
	 * just ignore them, but return -ENOMEM at the end.
	 */
	down_read(&mm->mmap_sem);
	vma = find_vma(mm, start);
	for (;;) {
		struct file *file;

		/* Still start < end. */
		error = -ENOMEM;
		if (!vma)
			goto out_unlock;
		/* Here start < vma->vm_end. */
		if (start < vma->vm_start) {
			start = vma->vm_start;
			if (start >= end)
				goto out_unlock;
			unmapped_error = -ENOMEM;
		}
		/* Here vma->vm_start <= start < vma->vm_end. */
		if ((flags & MS_INVALIDATE) &&
				(vma->vm_flags & VM_LOCKED)) {
			error = -EBUSY;
			goto out_unlock;
		}
		file = vma->vm_file;
		start = vma->vm_end;
		if ((flags & MS_SYNC) && file &&
				(vma->vm_flags & VM_SHARED)) {
			get_file(file);
			up_read(&mm->mmap_sem);
			error = do_fsync(file, 0);
			fput(file);
			if (error || start >= end)
				goto out;
			down_read(&mm->mmap_sem);
			vma = find_vma(mm, start);
		} else {
			if (start >= end) {
				error = 0;
				goto out_unlock;
			}
			vma = vma->vm_next;
		}
	}
out_unlock:
	up_read(&mm->mmap_sem);
out:
	return error ? : unmapped_error;
}

static int
nilfs_get_sb(struct file_system_type *fs_type, int flags,
	     const char *dev_name, void *data, struct vfsmount *mnt)
{
	struct nilfs_super_data sd;
	struct super_block *s;
	fmode_t mode = FMODE_READ;
	struct the_nilfs *nilfs;
	int err, need_to_close = 1;

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;

	sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type);
	if (IS_ERR(sd.bdev))
		return PTR_ERR(sd.bdev);

	/*
	 * To get mount instance using sget() vfs-routine, NILFS needs
	 * much more information than normal filesystems to identify mount
	 * instance.  For snapshot mounts, not only a mount type (ro-mount
	 * or rw-mount) but also a checkpoint number is required.
	 */
	sd.cno = 0;
	sd.flags = flags;
	if (nilfs_identify((char *)data, &sd)) {
		err = -EINVAL;
		goto failed;
	}

	nilfs = find_or_create_nilfs(sd.bdev);
	if (!nilfs) {
		err = -ENOMEM;
		goto failed;
	}

	mutex_lock(&nilfs->ns_mount_mutex);

	if (!sd.cno) {
		/*
		 * Check if an exclusive mount exists or not.
		 * Snapshot mounts coexist with a current mount
		 * (i.e. rw-mount or ro-mount), whereas rw-mount and
		 * ro-mount are mutually exclusive.
		 */
		down_read(&nilfs->ns_super_sem);
		if (nilfs->ns_current &&
		    ((nilfs->ns_current->s_super->s_flags ^ flags)
		     & MS_RDONLY)) {
			up_read(&nilfs->ns_super_sem);
			err = -EBUSY;
			goto failed_unlock;
		}
		up_read(&nilfs->ns_super_sem);
	}

	/*
	 * Find existing nilfs_sb_info struct
	 */
	sd.sbi = nilfs_find_sbinfo(nilfs, !(flags & MS_RDONLY), sd.cno);

	/*
	 * Get super block instance holding the nilfs_sb_info struct.
	 * A new instance is allocated if no existing mount is present or
	 * existing instance has been unmounted.
	 */
	s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, &sd);
	if (sd.sbi)
		nilfs_put_sbinfo(sd.sbi);

	if (IS_ERR(s)) {
		err = PTR_ERR(s);
		goto failed_unlock;
	}

	if (!s->s_root) {
		char b[BDEVNAME_SIZE];

		/* New superblock instance created */
		s->s_flags = flags;
		s->s_mode = mode;
		strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
		sb_set_blocksize(s, block_size(sd.bdev));

		err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0,
				       nilfs);
		if (err)
			goto cancel_new;

		s->s_flags |= MS_ACTIVE;
		need_to_close = 0;
	}

	mutex_unlock(&nilfs->ns_mount_mutex);
	put_nilfs(nilfs);
	if (need_to_close)
		close_bdev_exclusive(sd.bdev, mode);
	simple_set_mnt(mnt, s);
	return 0;

//.........这里部分代码省略.........

/*
 * inode->i_mutex: down
 */
int
reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
		   size_t buffer_size)
{
	ssize_t err = 0;
	struct dentry *dentry;
	size_t isize;
	size_t file_pos = 0;
	size_t buffer_pos = 0;
	struct page *page;
	__u32 hash = 0;

	if (name == NULL)
		return -EINVAL;

	/* We can't have xattrs attached to v1 items since they don't have
	 * generation numbers */
	if (get_inode_sd_version(inode) == STAT_DATA_V1)
		return -EOPNOTSUPP;

	dentry = xattr_lookup(inode, name, XATTR_REPLACE);
	if (IS_ERR(dentry)) {
		err = PTR_ERR(dentry);
		goto out;
	}

	down_read(&REISERFS_I(inode)->i_xattr_sem);

	isize = i_size_read(dentry->d_inode);

	/* Just return the size needed */
	if (buffer == NULL) {
		err = isize - sizeof(struct reiserfs_xattr_header);
		goto out_unlock;
	}

	if (buffer_size < isize - sizeof(struct reiserfs_xattr_header)) {
		err = -ERANGE;
		goto out_unlock;
	}

	while (file_pos < isize) {
		size_t chunk;
		char *data;
		size_t skip = 0;
		if (isize - file_pos > PAGE_CACHE_SIZE)
			chunk = PAGE_CACHE_SIZE;
		else
			chunk = isize - file_pos;

		page = reiserfs_get_page(dentry->d_inode, file_pos);
		if (IS_ERR(page)) {
			err = PTR_ERR(page);
			goto out_unlock;
		}

		lock_page(page);
		data = page_address(page);
		if (file_pos == 0) {
			struct reiserfs_xattr_header *rxh =
			    (struct reiserfs_xattr_header *)data;
			skip = file_pos = sizeof(struct reiserfs_xattr_header);
			chunk -= skip;
			/* Magic doesn't match up.. */
			if (rxh->h_magic != cpu_to_le32(REISERFS_XATTR_MAGIC)) {
				unlock_page(page);
				reiserfs_put_page(page);
				reiserfs_warning(inode->i_sb, "jdm-20001",
						 "Invalid magic for xattr (%s) "
						 "associated with %k", name,
						 INODE_PKEY(inode));
				err = -EIO;
				goto out_unlock;
			}
			hash = le32_to_cpu(rxh->h_hash);
		}
		memcpy(buffer + buffer_pos, data + skip, chunk);
		unlock_page(page);
		reiserfs_put_page(page);
		file_pos += chunk;
		buffer_pos += chunk;
		skip = 0;
	}
	err = isize - sizeof(struct reiserfs_xattr_header);

	if (xattr_hash(buffer, isize - sizeof(struct reiserfs_xattr_header)) !=
	    hash) {
		reiserfs_warning(inode->i_sb, "jdm-20002",
				 "Invalid hash for xattr (%s) associated "
				 "with %k", name, INODE_PKEY(inode));
		err = -EIO;
	}

out_unlock:
	up_read(&REISERFS_I(inode)->i_xattr_sem);
	dput(dentry);

//.........这里部分代码省略.........

asmlinkage long sys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
{
    struct msg_queue *msq;
    int err, version;
    struct ipc_namespace *ns;

    if (msqid < 0 || cmd < 0)
        return -EINVAL;

    version = ipc_parse_version(&cmd);
    ns = current->nsproxy->ipc_ns;

    switch (cmd) {
    case IPC_INFO:
    case MSG_INFO:
    {
        struct msginfo msginfo;
        int max_id;

        if (!buf)
            return -EFAULT;
        /*
         * We must not return kernel stack data.
         * due to padding, it's not enough
         * to set all member fields.
         */
        err = security_msg_queue_msgctl(NULL, cmd);
        if (err)
            return err;

        memset(&msginfo, 0, sizeof(msginfo));
        msginfo.msgmni = ns->msg_ctlmni;
        msginfo.msgmax = ns->msg_ctlmax;
        msginfo.msgmnb = ns->msg_ctlmnb;
        msginfo.msgssz = MSGSSZ;
        msginfo.msgseg = MSGSEG;
        down_read(&msg_ids(ns).rw_mutex);
        if (cmd == MSG_INFO) {
            msginfo.msgpool = msg_ids(ns).in_use;
            msginfo.msgmap = atomic_read(&ns->msg_hdrs);
            msginfo.msgtql = atomic_read(&ns->msg_bytes);
        } else {
            msginfo.msgmap = MSGMAP;
            msginfo.msgpool = MSGPOOL;
            msginfo.msgtql = MSGTQL;
        }
        max_id = ipc_get_maxid(&msg_ids(ns));
        up_read(&msg_ids(ns).rw_mutex);
        if (copy_to_user(buf, &msginfo, sizeof(struct msginfo)))
            return -EFAULT;
        return (max_id < 0) ? 0 : max_id;
    }
    case MSG_STAT:    /* msqid is an index rather than a msg queue id */
    case IPC_STAT:
    {
        struct msqid64_ds tbuf;
        int success_return;

        if (!buf)
            return -EFAULT;

        if (cmd == MSG_STAT) {
            msq = msg_lock(ns, msqid);
            if (IS_ERR(msq))
                return PTR_ERR(msq);
            success_return = msq->q_perm.id;
        } else {
            msq = msg_lock_check(ns, msqid);
            if (IS_ERR(msq))
                return PTR_ERR(msq);
            success_return = 0;
        }
        err = -EACCES;
        if (ipcperms(&msq->q_perm, S_IRUGO))
            goto out_unlock;

        err = security_msg_queue_msgctl(msq, cmd);
        if (err)
            goto out_unlock;

        memset(&tbuf, 0, sizeof(tbuf));

        kernel_to_ipc64_perm(&msq->q_perm, &tbuf.msg_perm);
        tbuf.msg_stime  = msq->q_stime;
        tbuf.msg_rtime  = msq->q_rtime;
        tbuf.msg_ctime  = msq->q_ctime;
        tbuf.msg_cbytes = msq->q_cbytes;
        tbuf.msg_qnum   = msq->q_qnum;
        tbuf.msg_qbytes = msq->q_qbytes;
        tbuf.msg_lspid  = msq->q_lspid;
        tbuf.msg_lrpid  = msq->q_lrpid;
        msg_unlock(msq);
        if (copy_msqid_to_user(buf, &tbuf, version))
            return -EFAULT;
        return success_return;
    }
    case IPC_SET:
    case IPC_RMID:
        err = msgctl_down(ns, msqid, cmd, buf, version);
        return err;
//.........这里部分代码省略.........

static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
{
	struct inode *inode = file_inode(filp);
	struct super_block *sb = inode->i_sb;
	struct ext4_inode_info *ei = EXT4_I(inode);
	int err, rc;
	handle_t *handle;
	kprojid_t kprojid;
	struct ext4_iloc iloc;
	struct ext4_inode *raw_inode;
	struct dquot *transfer_to[MAXQUOTAS] = { };

	if (!ext4_has_feature_project(sb)) {
		if (projid != EXT4_DEF_PROJID)
			return -EOPNOTSUPP;
		else
			return 0;
	}

	if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE)
		return -EOPNOTSUPP;

	kprojid = make_kprojid(&init_user_ns, (projid_t)projid);

	if (projid_eq(kprojid, EXT4_I(inode)->i_projid))
		return 0;

	err = -EPERM;
	/* Is it quota file? Do not allow user to mess with it */
	if (ext4_is_quota_file(inode))
		return err;

	err = ext4_get_inode_loc(inode, &iloc);
	if (err)
		return err;

	raw_inode = ext4_raw_inode(&iloc);
	if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
		err = ext4_expand_extra_isize(inode,
					      EXT4_SB(sb)->s_want_extra_isize,
					      &iloc);
		if (err)
			return err;
	} else {
		brelse(iloc.bh);
	}

	err = dquot_initialize(inode);
	if (err)
		return err;

	handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
		EXT4_QUOTA_INIT_BLOCKS(sb) +
		EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
	if (IS_ERR(handle))
		return PTR_ERR(handle);

	err = ext4_reserve_inode_write(handle, inode, &iloc);
	if (err)
		goto out_stop;

	transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
	if (!IS_ERR(transfer_to[PRJQUOTA])) {

		/* __dquot_transfer() calls back ext4_get_inode_usage() which
		 * counts xattr inode references.
		 */
		down_read(&EXT4_I(inode)->xattr_sem);
		err = __dquot_transfer(inode, transfer_to);
		up_read(&EXT4_I(inode)->xattr_sem);
		dqput(transfer_to[PRJQUOTA]);
		if (err)
			goto out_dirty;
	}

	EXT4_I(inode)->i_projid = kprojid;
	inode->i_ctime = current_time(inode);
out_dirty:
	rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
	if (!err)
		err = rc;
out_stop:
	ext4_journal_stop(handle);
	return err;
}

static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
	struct the_nilfs *nilfs = sb->s_fs_info;
	unsigned long old_sb_flags;
	unsigned long old_mount_opt;
	int err;

	old_sb_flags = sb->s_flags;
	old_mount_opt = nilfs->ns_mount_opt;

	if (!parse_options(data, sb, 1)) {
		err = -EINVAL;
		goto restore_opts;
	}
	sb->s_flags = (sb->s_flags & ~MS_POSIXACL);

	err = -EINVAL;

	if (!nilfs_valid_fs(nilfs)) {
		printk(KERN_WARNING "NILFS (device %s): couldn't "
		       "remount because the filesystem is in an "
		       "incomplete recovery state.\n", sb->s_id);
		goto restore_opts;
	}

	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		goto out;
	if (*flags & MS_RDONLY) {
		/* Shutting down log writer */
		nilfs_detach_log_writer(sb);
		sb->s_flags |= MS_RDONLY;

		/*
		 * Remounting a valid RW partition RDONLY, so set
		 * the RDONLY flag and then mark the partition as valid again.
		 */
		down_write(&nilfs->ns_sem);
		nilfs_cleanup_super(sb);
		up_write(&nilfs->ns_sem);
	} else {
		__u64 features;
		struct nilfs_root *root;

		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by fsck since we originally mounted the partition.)
		 */
		down_read(&nilfs->ns_sem);
		features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
			~NILFS_FEATURE_COMPAT_RO_SUPP;
		up_read(&nilfs->ns_sem);
		if (features) {
			printk(KERN_WARNING "NILFS (device %s): couldn't "
			       "remount RDWR because of unsupported optional "
			       "features (%llx)\n",
			       sb->s_id, (unsigned long long)features);
			err = -EROFS;
			goto restore_opts;
		}

		sb->s_flags &= ~MS_RDONLY;

		root = NILFS_I(sb->s_root->d_inode)->i_root;
		err = nilfs_attach_log_writer(sb, root);
		if (err)
			goto restore_opts;

		down_write(&nilfs->ns_sem);
		nilfs_setup_super(sb, true);
		up_write(&nilfs->ns_sem);
	}
 out:
	return 0;

 restore_opts:
	sb->s_flags = old_sb_flags;
	nilfs->ns_mount_opt = old_mount_opt;
	return err;
}

int ext4_ext_migrate(struct inode *inode)
{
	handle_t *handle;
	int retval = 0, i;
	__le32 *i_data;
	ext4_lblk_t blk_count = 0;
	struct ext4_inode_info *ei;
	struct inode *tmp_inode = NULL;
	struct list_blocks_struct lb;
	unsigned long max_entries;

	/*
	 * If the filesystem does not support extents, or the inode
	 * already is extent-based, error out.
	 */
	if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
				       EXT4_FEATURE_INCOMPAT_EXTENTS) ||
	    (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
		return -EINVAL;

	if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
		/*
		 * don't migrate fast symlink
		 */
		return retval;

	handle = ext4_journal_start(inode,
					EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
					2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
					+ 1);
	if (IS_ERR(handle)) {
		retval = PTR_ERR(handle);
		return retval;
	}
	tmp_inode = ext4_new_inode(handle,
				inode->i_sb->s_root->d_inode,
				S_IFREG);
	if (IS_ERR(tmp_inode)) {
		retval = -ENOMEM;
		ext4_journal_stop(handle);
		return retval;
	}
	i_size_write(tmp_inode, i_size_read(inode));
	/*
	 * We don't want the inode to be reclaimed
	 * if we got interrupted in between. We have
	 * this tmp inode carrying reference to the
	 * data blocks of the original file. We set
	 * the i_nlink to zero at the last stage after
	 * switching the original file to extent format
	 */
	tmp_inode->i_nlink = 1;

	ext4_ext_tree_init(handle, tmp_inode);
	ext4_orphan_add(handle, tmp_inode);
	ext4_journal_stop(handle);

	/*
	 * start with one credit accounted for
	 * superblock modification.
	 *
	 * For the tmp_inode we already have commited the
	 * trascation that created the inode. Later as and
	 * when we add extents we extent the journal
	 */
	/*
	 * Even though we take i_mutex we can still cause block allocation
	 * via mmap write to holes. If we have allocated new blocks we fail
	 * migrate.  New block allocation will clear EXT4_EXT_MIGRATE flag.
	 * The flag is updated with i_data_sem held to prevent racing with
	 * block allocation.
	 */
	down_read((&EXT4_I(inode)->i_data_sem));
	EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags | EXT4_EXT_MIGRATE;
	up_read((&EXT4_I(inode)->i_data_sem));

	handle = ext4_journal_start(inode, 1);

	ei = EXT4_I(inode);
	i_data = ei->i_data;
	memset(&lb, 0, sizeof(lb));

	/* 32 bit block address 4 bytes */
	max_entries = inode->i_sb->s_blocksize >> 2;
	for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
		if (i_data[i]) {
			retval = update_extent_range(handle, tmp_inode,
						le32_to_cpu(i_data[i]),
						blk_count, &lb);
			if (retval)
				goto err_out;
		}
	}
	if (i_data[EXT4_IND_BLOCK]) {
		retval = update_ind_extent_range(handle, tmp_inode,
					le32_to_cpu(i_data[EXT4_IND_BLOCK]),
					&blk_count, &lb);
			if (retval)
				goto err_out;
//.........这里部分代码省略.........