tmpfs: support SEEK_DATA and SEEK_HOLE

It's quite easy for tmpfs to scan the radix_tree to support llseek's new
SEEK_DATA and SEEK_HOLE options: so add them while the minutiae are still
on my mind (in particular, the !PageUptodate-ness of pages fallocated but
still unwritten).

But I don't know who actually uses SEEK_DATA or SEEK_HOLE, and whether it
would be of any use to them on tmpfs.  This code adds 92 lines and 752
bytes on x86_64 - is that bloat or worthwhile?

[akpm@linux-foundation.org: fix warning with CONFIG_TMPFS=n]
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Josef Bacik <josef@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Andreas Dilger <adilger@dilger.ca>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Marco Stornelli <marco.stornelli@gmail.com>
Cc: Jeff liu <jeff.liu@oracle.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Sunil Mushran <sunil.mushran@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/shmem.c

@@ -1674,6 +1674,98 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	return error;
 }
 
+/*
+ * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
+ */
+static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
+				    pgoff_t index, pgoff_t end, int origin)
+{
+	struct page *page;
+	struct pagevec pvec;
+	pgoff_t indices[PAGEVEC_SIZE];
+	bool done = false;
+	int i;
+
+	pagevec_init(&pvec, 0);
+	pvec.nr = 1;		/* start small: we may be there already */
+	while (!done) {
+		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+					pvec.nr, pvec.pages, indices);
+		if (!pvec.nr) {
+			if (origin == SEEK_DATA)
+				index = end;
+			break;
+		}
+		for (i = 0; i < pvec.nr; i++, index++) {
+			if (index < indices[i]) {
+				if (origin == SEEK_HOLE) {
+					done = true;
+					break;
+				}
+				index = indices[i];
+			}
+			page = pvec.pages[i];
+			if (page && !radix_tree_exceptional_entry(page)) {
+				if (!PageUptodate(page))
+					page = NULL;
+			}
+			if (index >= end ||
+			    (page && origin == SEEK_DATA) ||
+			    (!page && origin == SEEK_HOLE)) {
+				done = true;
+				break;
+			}
+		}
+		shmem_deswap_pagevec(&pvec);
+		pagevec_release(&pvec);
+		pvec.nr = PAGEVEC_SIZE;
+		cond_resched();
+	}
+	return index;
+}
+
+static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct address_space *mapping;
+	struct inode *inode;
+	pgoff_t start, end;
+	loff_t new_offset;
+
+	if (origin != SEEK_DATA && origin != SEEK_HOLE)
+		return generic_file_llseek_size(file, offset, origin,
+							MAX_LFS_FILESIZE);
+	mapping = file->f_mapping;
+	inode = mapping->host;
+	mutex_lock(&inode->i_mutex);
+	/* We're holding i_mutex so we can access i_size directly */
+
+	if (offset < 0)
+		offset = -EINVAL;
+	else if (offset >= inode->i_size)
+		offset = -ENXIO;
+	else {
+		start = offset >> PAGE_CACHE_SHIFT;
+		end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+		new_offset = shmem_seek_hole_data(mapping, start, end, origin);
+		new_offset <<= PAGE_CACHE_SHIFT;
+		if (new_offset > offset) {
+			if (new_offset < inode->i_size)
+				offset = new_offset;
+			else if (origin == SEEK_DATA)
+				offset = -ENXIO;
+			else
+				offset = inode->i_size;
+		}
+	}
+
+	if (offset >= 0 && offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	mutex_unlock(&inode->i_mutex);
+	return offset;
+}
+
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
@@ -2679,7 +2771,7 @@ static const struct address_space_operations shmem_aops = {
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
-	.llseek		= generic_file_llseek,
+	.llseek		= shmem_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= shmem_file_aio_read,