X-Git-Url: https://git.camperquake.de/gitweb.cgi?a=blobdiff_plain;f=module%2Fzfs%2Fzpl_file.c;h=6598c177971d46abbe6e3299f698249e70853582;hb=refs%2Fheads%2Frertzinger%2Ffeature-zpool-get--p;hp=585f971e8dc23abe2dea38d23077cc51d9234798;hpb=c0d35759c5ab1abaa6b72062cc4ecd0d86628de8;p=zfs.git

diff --git a/module/zfs/zpl_file.c b/module/zfs/zpl_file.c
index 585f971..6598c17 100644
--- a/module/zfs/zpl_file.c
+++ b/module/zfs/zpl_file.c
@@ -30,35 +30,141 @@
 
 
 static int
-zpl_readdir(struct file *filp, void *dirent, filldir_t filldir)
+zpl_open(struct inode *ip, struct file *filp)
+{
+	cred_t *cr = CRED();
+	int error;
+
+	crhold(cr);
+	error = -zfs_open(ip, filp->f_mode, filp->f_flags, cr);
+	crfree(cr);
+	ASSERT3S(error, <=, 0);
+
+	if (error)
+		return (error);
+
+	return generic_file_open(ip, filp);
+}
+
+static int
+zpl_release(struct inode *ip, struct file *filp)
+{
+	cred_t *cr = CRED();
+	int error;
+
+	if (ITOZ(ip)->z_atime_dirty)
+		mark_inode_dirty(ip);
+
+	crhold(cr);
+	error = -zfs_close(ip, filp->f_flags, cr);
+	crfree(cr);
+	ASSERT3S(error, <=, 0);
+
+	return (error);
+}
+
+static int
+zpl_iterate(struct file *filp, struct dir_context *ctx)
 {
 	struct dentry *dentry = filp->f_path.dentry;
-	cred_t *cr;
+	cred_t *cr = CRED();
 	int error;
 
-	cr = (cred_t *)get_current_cred();
-	error = -zfs_readdir(dentry->d_inode, dirent, filldir,
-	    &filp->f_pos, cr);
-	put_cred(cr);
+	crhold(cr);
+	error = -zfs_readdir(dentry->d_inode, ctx, cr);
+	crfree(cr);
 	ASSERT3S(error, <=, 0);
 
 	return (error);
 }
 
+#if !defined(HAVE_VFS_ITERATE)
+static int
+zpl_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	struct dir_context ctx = DIR_CONTEXT_INIT(dirent, filldir, filp->f_pos);
+	int error;
+
+	error = zpl_iterate(filp, &ctx);
+	filp->f_pos = ctx.pos;
+
+	return (error);
+}
+#endif /* HAVE_VFS_ITERATE */
+
+#if defined(HAVE_FSYNC_WITH_DENTRY)
+/*
+ * Linux 2.6.x - 2.6.34 API,
+ * Through 2.6.34 the nfsd kernel server would pass a NULL 'file struct *'
+ * to the fops->fsync() hook.  For this reason, we must be careful not to
+ * use filp unconditionally.
+ */
 static int
 zpl_fsync(struct file *filp, struct dentry *dentry, int datasync)
 {
-	cred_t *cr;
+	cred_t *cr = CRED();
 	int error;
 
-	cr = (cred_t *)get_current_cred();
-	error = -zfs_fsync(filp->f_path.dentry->d_inode, datasync, cr);
-	put_cred(cr);
+	crhold(cr);
+	error = -zfs_fsync(dentry->d_inode, datasync, cr);
+	crfree(cr);
 	ASSERT3S(error, <=, 0);
 
 	return (error);
 }
 
+#elif defined(HAVE_FSYNC_WITHOUT_DENTRY)
+/*
+ * Linux 2.6.35 - 3.0 API,
+ * As of 2.6.35 the dentry argument to the fops->fsync() hook was deemed
+ * redundant.  The dentry is still accessible via filp->f_path.dentry,
+ * and we are guaranteed that filp will never be NULL.
+ */
+static int
+zpl_fsync(struct file *filp, int datasync)
+{
+	struct inode *inode = filp->f_mapping->host;
+	cred_t *cr = CRED();
+	int error;
+
+	crhold(cr);
+	error = -zfs_fsync(inode, datasync, cr);
+	crfree(cr);
+	ASSERT3S(error, <=, 0);
+
+	return (error);
+}
+
+#elif defined(HAVE_FSYNC_RANGE)
+/*
+ * Linux 3.1 - 3.x API,
+ * As of 3.1 the responsibility to call filemap_write_and_wait_range() has
+ * been pushed down in to the .fsync() vfs hook.  Additionally, the i_mutex
+ * lock is no longer held by the caller, for zfs we don't require the lock
+ * to be held so we don't acquire it.
+ */
+static int
+zpl_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
+{
+	struct inode *inode = filp->f_mapping->host;
+	cred_t *cr = CRED();
+	int error;
+
+	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	if (error)
+		return (error);
+
+	crhold(cr);
+	error = -zfs_fsync(inode, datasync, cr);
+	crfree(cr);
+	ASSERT3S(error, <=, 0);
+
+	return (error);
+}
+#else
+#error "Unsupported fops->fsync() implementation"
+#endif
+
 ssize_t
 zpl_read_common(struct inode *ip, const char *buf, size_t len, loff_t pos,
      uio_seg_t segment, int flags, cred_t *cr)
@@ -87,13 +193,13 @@ zpl_read_common(struct inode *ip, const char *buf, size_t len, loff_t pos,
 static ssize_t
 zpl_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
-	cred_t *cr;
+	cred_t *cr = CRED();
 	ssize_t read;
 
-	cr = (cred_t *)get_current_cred();
+	crhold(cr);
 	read = zpl_read_common(filp->f_mapping->host, buf, len, *ppos,
 	    UIO_USERSPACE, filp->f_flags, cr);
-	put_cred(cr);
+	crfree(cr);
 
 	if (read < 0)
 		return (read);
@@ -130,13 +236,13 @@ zpl_write_common(struct inode *ip, const char *buf, size_t len, loff_t pos,
 static ssize_t
 zpl_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 {
-	cred_t *cr;
+	cred_t *cr = CRED();
 	ssize_t wrote;
 
-	cr = (cred_t *)get_current_cred();
+	crhold(cr);
 	wrote = zpl_write_common(filp->f_mapping->host, buf, len, *ppos,
 	    UIO_USERSPACE, filp->f_flags, cr);
-	put_cred(cr);
+	crfree(cr);
 
 	if (wrote < 0)
 		return (wrote);
@@ -145,6 +251,28 @@ zpl_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 	return (wrote);
 }
 
+static loff_t
+zpl_llseek(struct file *filp, loff_t offset, int whence)
+{
+#if defined(SEEK_HOLE) && defined(SEEK_DATA)
+	if (whence == SEEK_DATA || whence == SEEK_HOLE) {
+		struct inode *ip = filp->f_mapping->host;
+		loff_t maxbytes = ip->i_sb->s_maxbytes;
+		loff_t error;
+
+		spl_inode_lock(ip);
+		error = -zfs_holey(ip, whence, &offset);
+		if (error == 0)
+			error = lseek_execute(filp, ip, offset, maxbytes);
+		spl_inode_unlock(ip);
+
+		return (error);
+	}
+#endif /* SEEK_HOLE && SEEK_DATA */
+
+	return generic_file_llseek(filp, offset, whence);
+}
+
 /*
  * It's worth taking a moment to describe how mmap is implemented
  * for zfs because it differs considerably from other Linux filesystems.
@@ -191,9 +319,15 @@ zpl_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 static int
 zpl_mmap(struct file *filp, struct vm_area_struct *vma)
 {
-	znode_t *zp = ITOZ(filp->f_mapping->host);
+	struct inode *ip = filp->f_mapping->host;
+	znode_t *zp = ITOZ(ip);
 	int error;
 
+	error = -zfs_map(ip, vma->vm_pgoff, (caddr_t *)vma->vm_start,
+	    (size_t)(vma->vm_end - vma->vm_start), vma->vm_flags);
+	if (error)
+		return (error);
+
 	error = generic_file_mmap(filp, vma);
 	if (error)
 		return (error);
@@ -218,33 +352,14 @@ static int
 zpl_readpage(struct file *filp, struct page *pp)
 {
 	struct inode *ip;
-	loff_t off, i_size;
-	size_t len, wrote;
-	cred_t *cr;
-	void *pb;
+	struct page *pl[1];
 	int error = 0;
 
 	ASSERT(PageLocked(pp));
 	ip = pp->mapping->host;
-	off = page_offset(pp);
-	i_size = i_size_read(ip);
-	ASSERT3S(off, <, i_size);
-
-	cr = (cred_t *)get_current_cred();
-	len = MIN(PAGE_CACHE_SIZE, i_size - off);
-
-	pb = kmap(pp);
-
-	/* O_DIRECT is passed to bypass the page cache and avoid deadlock. */
-	wrote = zpl_read_common(ip, pb, len, off, UIO_SYSSPACE, O_DIRECT, cr);
-	if (wrote != len)
-		error = -EIO;
+	pl[0] = pp;
 
-	if (!error && (len < PAGE_CACHE_SIZE))
-		memset(pb + len, 0, PAGE_CACHE_SIZE - len);
-
-	kunmap(pp);
-	put_cred(cr);
+	error = -zfs_getpage(ip, pl, 1);
 
 	if (error) {
 		SetPageError(pp);
@@ -256,8 +371,48 @@ zpl_readpage(struct file *filp, struct page *pp)
 	}
 
 	unlock_page(pp);
+	return error;
+}
 
-	return (error);
+/*
+ * Populate a set of pages with data for the Linux page cache.  This
+ * function will only be called for read ahead and never for demand
+ * paging.  For simplicity, the code relies on read_cache_pages() to
+ * correctly lock each page for IO and call zpl_readpage().
+ */
+static int
+zpl_readpages(struct file *filp, struct address_space *mapping,
+	struct list_head *pages, unsigned nr_pages)
+{
+	return (read_cache_pages(mapping, pages,
+	    (filler_t *)zpl_readpage, filp));
+}
+
+int
+zpl_putpage(struct page *pp, struct writeback_control *wbc, void *data)
+{
+	struct address_space *mapping = data;
+
+	ASSERT(PageLocked(pp));
+	ASSERT(!PageWriteback(pp));
+	ASSERT(!(current->flags & PF_NOFS));
+
+	/*
+	 * Annotate this call path with a flag that indicates that it is
+	 * unsafe to use KM_SLEEP during memory allocations due to the
+	 * potential for a deadlock.  KM_PUSHPAGE should be used instead.
+	 */
+	current->flags |= PF_NOFS;
+	(void) zfs_putpage(mapping->host, pp, wbc);
+	current->flags &= ~PF_NOFS;
+
+	return (0);
+}
+
+static int
+zpl_writepages(struct address_space *mapping, struct writeback_control *wbc)
+{
+	return write_cache_pages(mapping, wbc, zpl_putpage, mapping);
 }
 
 /*
@@ -265,70 +420,113 @@ zpl_readpage(struct file *filp, struct page *pp)
  * support mmap(2).  Mapped pages may be dirtied by memory operations
  * which never call .write().  These dirty pages are kept in sync with
  * the ARC buffers via this hook.
- *
- * Currently this function relies on zpl_write_common() and the O_DIRECT
- * flag to push out the page.  This works but the more correct way is
- * to update zfs_putapage() to be Linux friendly and use that interface.
  */
 static int
 zpl_writepage(struct page *pp, struct writeback_control *wbc)
 {
-	struct inode *ip;
-	loff_t off, i_size;
-	size_t len, read;
-	cred_t *cr;
-	void *pb;
-	int error = 0;
+	return zpl_putpage(pp, wbc, pp->mapping);
+}
 
-	ASSERT(PageLocked(pp));
-	ip = pp->mapping->host;
-	off = page_offset(pp);
-	i_size = i_size_read(ip);
+/*
+ * The only flag combination which matches the behavior of zfs_space()
+ * is FALLOC_FL_PUNCH_HOLE.  This flag was introduced in the 2.6.38 kernel.
+ */
+long
+zpl_fallocate_common(struct inode *ip, int mode, loff_t offset, loff_t len)
+{
+	cred_t *cr = CRED();
+	int error = -EOPNOTSUPP;
 
-	cr = (cred_t *)get_current_cred();
-	len = MIN(PAGE_CACHE_SIZE, i_size - off);
+	if (mode & FALLOC_FL_KEEP_SIZE)
+		return (-EOPNOTSUPP);
 
-	pb = kmap(pp);
+	crhold(cr);
 
-	/* O_DIRECT is passed to bypass the page cache and avoid deadlock. */
-	read = zpl_write_common(ip, pb, len, off, UIO_SYSSPACE, O_DIRECT, cr);
-	if (read != len)
-		error = -EIO;
+#ifdef FALLOC_FL_PUNCH_HOLE
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		flock64_t bf;
 
-	kunmap(pp);
-	put_cred(cr);
+		bf.l_type = F_WRLCK;
+		bf.l_whence = 0;
+		bf.l_start = offset;
+		bf.l_len = len;
+		bf.l_pid = 0;
 
-	if (error) {
-		SetPageError(pp);
-		ClearPageUptodate(pp);
-	} else {
-		ClearPageError(pp);
-		SetPageUptodate(pp);
+		error = -zfs_space(ip, F_FREESP, &bf, FWRITE, offset, cr);
 	}
+#endif /* FALLOC_FL_PUNCH_HOLE */
 
-	unlock_page(pp);
+	crfree(cr);
 
+	ASSERT3S(error, <=, 0);
 	return (error);
 }
 
+#ifdef HAVE_FILE_FALLOCATE
+static long
+zpl_fallocate(struct file *filp, int mode, loff_t offset, loff_t len)
+{
+	return zpl_fallocate_common(filp->f_path.dentry->d_inode,
+	    mode, offset, len);
+}
+#endif /* HAVE_FILE_FALLOCATE */
+
+static long
+zpl_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case ZFS_IOC_GETFLAGS:
+	case ZFS_IOC_SETFLAGS:
+		return (-EOPNOTSUPP);
+	default:
+		return (-ENOTTY);
+	}
+}
+
+#ifdef CONFIG_COMPAT
+static long
+zpl_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	return zpl_ioctl(filp, cmd, arg);
+}
+#endif /* CONFIG_COMPAT */
+
+
 const struct address_space_operations zpl_address_space_operations = {
+	.readpages	= zpl_readpages,
 	.readpage	= zpl_readpage,
 	.writepage	= zpl_writepage,
+	.writepages     = zpl_writepages,
 };
 
 const struct file_operations zpl_file_operations = {
-	.open		= generic_file_open,
-	.llseek		= generic_file_llseek,
+	.open		= zpl_open,
+	.release	= zpl_release,
+	.llseek		= zpl_llseek,
 	.read		= zpl_read,
 	.write		= zpl_write,
-	.readdir	= zpl_readdir,
 	.mmap		= zpl_mmap,
 	.fsync		= zpl_fsync,
+#ifdef HAVE_FILE_FALLOCATE
+	.fallocate      = zpl_fallocate,
+#endif /* HAVE_FILE_FALLOCATE */
+	.unlocked_ioctl = zpl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = zpl_compat_ioctl,
+#endif
 };
 
 const struct file_operations zpl_dir_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
+#ifdef HAVE_VFS_ITERATE
+	.iterate	= zpl_iterate,
+#else
 	.readdir	= zpl_readdir,
+#endif
 	.fsync		= zpl_fsync,
+	.unlocked_ioctl = zpl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl   = zpl_compat_ioctl,
+#endif
 };