inode.c

linux 内核源代码

/*
 * Wait for the inode to get unlocked.
 */
static int nfs_wait_on_inode(struct inode *inode)
{
	struct rpc_clnt	*clnt = NFS_CLIENT(inode);
	struct nfs_inode *nfsi = NFS_I(inode);
	sigset_t oldmask;
	int error;

	rpc_clnt_sigmask(clnt, &oldmask);
	error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
					nfs_wait_schedule, TASK_INTERRUPTIBLE);
	rpc_clnt_sigunmask(clnt, &oldmask);

	return error;
}

static void nfs_wake_up_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
	smp_mb__after_clear_bit();
	wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
}

int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
	int err;

	/* Flush out writes to the server in order to update c/mtime */
	if (S_ISREG(inode->i_mode))
		nfs_wb_nocommit(inode);

	/*
	 * We may force a getattr if the user cares about atime.
	 *
	 * Note that we only have to check the vfsmount flags here:
	 *  - NFS always sets S_NOATIME by so checking it would give a
	 *    bogus result
	 *  - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
	 *    no point in checking those.
	 */
 	if ((mnt->mnt_flags & MNT_NOATIME) ||
 	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
		need_atime = 0;

	if (need_atime)
		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
	else
		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!err) {
		generic_fillattr(inode, stat);
		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
	}
	return err;
}

static struct nfs_open_context *alloc_nfs_open_context(struct vfsmount *mnt, struct dentry *dentry, struct rpc_cred *cred)
{
	struct nfs_open_context *ctx;

	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (ctx != NULL) {
		ctx->path.dentry = dget(dentry);
		ctx->path.mnt = mntget(mnt);
		ctx->cred = get_rpccred(cred);
		ctx->state = NULL;
		ctx->lockowner = current->files;
		ctx->error = 0;
		ctx->dir_cookie = 0;
		atomic_set(&ctx->count, 1);
	}
	return ctx;
}

struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
	if (ctx != NULL)
		atomic_inc(&ctx->count);
	return ctx;
}

static void __put_nfs_open_context(struct nfs_open_context *ctx, int wait)
{
	struct inode *inode = ctx->path.dentry->d_inode;

	if (!atomic_dec_and_lock(&ctx->count, &inode->i_lock))
		return;
	list_del(&ctx->list);
	spin_unlock(&inode->i_lock);
	if (ctx->state != NULL) {
		if (wait)
			nfs4_close_sync(&ctx->path, ctx->state, ctx->mode);
		else
			nfs4_close_state(&ctx->path, ctx->state, ctx->mode);
	}
	if (ctx->cred != NULL)
		put_rpccred(ctx->cred);
	dput(ctx->path.dentry);
	mntput(ctx->path.mnt);
	kfree(ctx);
}

void put_nfs_open_context(struct nfs_open_context *ctx)
{
	__put_nfs_open_context(ctx, 0);
}

static void put_nfs_open_context_sync(struct nfs_open_context *ctx)
{
	__put_nfs_open_context(ctx, 1);
}

/*
 * Ensure that mmap has a recent RPC credential for use when writing out
 * shared pages
 */
static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct nfs_inode *nfsi = NFS_I(inode);

	filp->private_data = get_nfs_open_context(ctx);
	spin_lock(&inode->i_lock);
	list_add(&ctx->list, &nfsi->open_files);
	spin_unlock(&inode->i_lock);
}

/*
 * Given an inode, search for an open context with the desired characteristics
 */
struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_context *pos, *ctx = NULL;

	spin_lock(&inode->i_lock);
	list_for_each_entry(pos, &nfsi->open_files, list) {
		if (cred != NULL && pos->cred != cred)
			continue;
		if ((pos->mode & mode) == mode) {
			ctx = get_nfs_open_context(pos);
			break;
		}
	}
	spin_unlock(&inode->i_lock);
	return ctx;
}

static void nfs_file_clear_open_context(struct file *filp)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	struct nfs_open_context *ctx = nfs_file_open_context(filp);

	if (ctx) {
		filp->private_data = NULL;
		spin_lock(&inode->i_lock);
		list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
		spin_unlock(&inode->i_lock);
		put_nfs_open_context_sync(ctx);
	}
}

/*
 * These allocate and release file read/write context information.
 */
int nfs_open(struct inode *inode, struct file *filp)
{
	struct nfs_open_context *ctx;
	struct rpc_cred *cred;

	cred = rpcauth_lookupcred(NFS_CLIENT(inode)->cl_auth, 0);
	if (IS_ERR(cred))
		return PTR_ERR(cred);
	ctx = alloc_nfs_open_context(filp->f_path.mnt, filp->f_path.dentry, cred);
	put_rpccred(cred);
	if (ctx == NULL)
		return -ENOMEM;
	ctx->mode = filp->f_mode;
	nfs_file_set_open_context(filp, ctx);
	put_nfs_open_context(ctx);
	return 0;
}

int nfs_release(struct inode *inode, struct file *filp)
{
	nfs_file_clear_open_context(filp);
	return 0;
}

/*
 * This function is called whenever some part of NFS notices that
 * the cached attributes have to be refreshed.
 */
int
__nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
	int		 status = -ESTALE;
	struct nfs_fattr fattr;
	struct nfs_inode *nfsi = NFS_I(inode);

	dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n",
		inode->i_sb->s_id, (long long)NFS_FILEID(inode));

	nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
	lock_kernel();
	if (is_bad_inode(inode))
 		goto out_nowait;
	if (NFS_STALE(inode))
 		goto out_nowait;

	status = nfs_wait_on_inode(inode);
	if (status < 0)
		goto out;

	status = -ESTALE;
	if (NFS_STALE(inode))
		goto out;

	status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), &fattr);
	if (status != 0) {
		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) getattr failed, error=%d\n",
			 inode->i_sb->s_id,
			 (long long)NFS_FILEID(inode), status);
		if (status == -ESTALE) {
			nfs_zap_caches(inode);
			if (!S_ISDIR(inode->i_mode))
				set_bit(NFS_INO_STALE, &NFS_FLAGS(inode));
		}
		goto out;
	}

	spin_lock(&inode->i_lock);
	status = nfs_update_inode(inode, &fattr);
	if (status) {
		spin_unlock(&inode->i_lock);
		dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Ld) refresh failed, error=%d\n",
			 inode->i_sb->s_id,
			 (long long)NFS_FILEID(inode), status);
		goto out;
	}
	spin_unlock(&inode->i_lock);

	if (nfsi->cache_validity & NFS_INO_INVALID_ACL)
		nfs_zap_acl_cache(inode);

	dfprintk(PAGECACHE, "NFS: (%s/%Ld) revalidation complete\n",
		inode->i_sb->s_id,
		(long long)NFS_FILEID(inode));

 out:
	nfs_wake_up_inode(inode);

 out_nowait:
	unlock_kernel();
	return status;
}

int nfs_attribute_timeout(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	if (nfs_have_delegation(inode, FMODE_READ))
		return 0;
	return !time_in_range(jiffies, nfsi->read_cache_jiffies, nfsi->read_cache_jiffies + nfsi->attrtimeo);
}

/**
 * nfs_revalidate_inode - Revalidate the inode attributes
 * @server - pointer to nfs_server struct
 * @inode - pointer to inode struct
 *
 * Updates inode attribute information by retrieving the data from the server.
 */
int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
{
	if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR)
			&& !nfs_attribute_timeout(inode))
		return NFS_STALE(inode) ? -ESTALE : 0;
	return __nfs_revalidate_inode(server, inode);
}

static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	
	if (mapping->nrpages != 0) {
		int ret = invalidate_inode_pages2(mapping);
		if (ret < 0)
			return ret;
	}
	spin_lock(&inode->i_lock);
	nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
	if (S_ISDIR(inode->i_mode))
		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
	spin_unlock(&inode->i_lock);
	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
	return 0;
}

static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
{
	int ret = 0;

	mutex_lock(&inode->i_mutex);
	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) {
		ret = nfs_sync_mapping(mapping);
		if (ret == 0)
			ret = nfs_invalidate_mapping_nolock(inode, mapping);
	}
	mutex_unlock(&inode->i_mutex);
	return ret;
}

/**
 * nfs_revalidate_mapping_nolock - Revalidate the pagecache
 * @inode - pointer to host inode
 * @mapping - pointer to mapping
 */
int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int ret = 0;

	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
			|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
		if (ret < 0)
			goto out;
	}
	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
		ret = nfs_invalidate_mapping_nolock(inode, mapping);
out:
	return ret;
}

/**
 * nfs_revalidate_mapping - Revalidate the pagecache
 * @inode - pointer to host inode
 * @mapping - pointer to mapping
 *
 * This version of the function will take the inode->i_mutex and attempt to
 * flush out all dirty data if it needs to invalidate the page cache.
 */
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int ret = 0;

	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
			|| nfs_attribute_timeout(inode) || NFS_STALE(inode)) {
		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
		if (ret < 0)
			goto out;
	}
	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
		ret = nfs_invalidate_mapping(inode, mapping);
out:
	return ret;
}

static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	if ((fattr->valid & NFS_ATTR_WCC_V4) != 0 &&
			nfsi->change_attr == fattr->pre_change_attr) {
		nfsi->change_attr = fattr->change_attr;
		if (S_ISDIR(inode->i_mode))
			nfsi->cache_validity |= NFS_INO_INVALID_DATA;
	}
	/* If we have atomic WCC data, we may update some attributes */
	if ((fattr->valid & NFS_ATTR_WCC) != 0) {
		if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
		if (timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
			if (S_ISDIR(inode->i_mode))
				nfsi->cache_validity |= NFS_INO_INVALID_DATA;
		}
		if (inode->i_size == fattr->pre_size && nfsi->npages == 0)
			inode->i_size = fattr->size;
	}
}

/**
 * nfs_check_inode_attributes - verify consistency of the inode attribute cache
 * @inode - pointer to inode
 * @fattr - updated attributes
 *
 * Verifies the attribute cache. If we have just changed the attributes,
 * so that fattr carries weak cache consistency data, then it may
 * also update the ctime/mtime/change_attribute.
 */
static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fattr)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	loff_t cur_size, new_isize;
	unsigned long invalid = 0;


	/* Has the inode gone and changed behind our back? */
	if (nfsi->fileid != fattr->fileid
			|| (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
		return -EIO;
	}

	/* Do atomic weak cache consistency updates */
	nfs_wcc_update_inode(inode, fattr);

	if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 &&
			nfsi->change_attr != fattr->change_attr)
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	/* Verify a few of the more important attributes */
	if (!timespec_equal(&inode->i_mtime, &fattr->mtime))
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;

	cur_size = i_size_read(inode);
 	new_isize = nfs_size_to_loff_t(fattr->size);
	if (cur_size != new_isize && nfsi->npages == 0)
		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;