vfs: Add page_cache_seek_hole_data helper

Both ext4 and xfs implement seeking for the next hole or piece of data
in unwritten extents by scanning the page cache, and both versions share
the same bug when iterating the buffers of a page: the start offset into
the page isn't taken into account, so when a page fits more than two
filesystem blocks, things will go wrong.  For example, on a filesystem
with a block size of 1k, the following command will fail:

  xfs_io -f -c "falloc 0 4k" \
            -c "pwrite 1k 1k" \
            -c "pwrite 3k 1k" \
            -c "seek -a -r 0" foo

In this example, neither lseek(fd, 1024, SEEK_HOLE) nor lseek(fd, 2048,
SEEK_DATA) will return the correct result.

Introduce a generic vfs helper for seeking in the page cache that gets
this right.  The next commits will replace the filesystem specific
implementations.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: dropped the export]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

1 files changed, 124 insertions, 0 deletions

diff --git a/fs/buffer.c b/fs/buffer.c
index 161be58c5cb0..b3674eb7c9c0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3492,6 +3492,130 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ *
+ * Returns the offset within the file on success, and -ENOENT otherwise.
+ */
+static loff_t
+page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
+{
+        loff_t offset = page_offset(page);
+        struct buffer_head *bh, *head;
+        bool seek_data = whence == SEEK_DATA;
+
+        if (lastoff < offset)
+                lastoff = offset;
+
+        bh = head = page_buffers(page);
+        do {
+                offset += bh->b_size;
+                if (lastoff >= offset)
+                        continue;
+
+                /*
+                 * Unwritten extents that have data in the page cache covering
+                 * them can be identified by the BH_Unwritten state flag.
+                 * Pages with multiple buffers might have a mix of holes, data
+                 * and unwritten extents - any buffer with valid data in it
+                 * should have BH_Uptodate flag set on it.
+                 */
+
+                if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
+                        return lastoff;
+
+                lastoff = offset;
+        } while ((bh = bh->b_this_page) != head);
+        return -ENOENT;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: unwritten and uptodate buffer heads count as data;
+ * everything else counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+                          int whence)
+{
+        pgoff_t index = offset >> PAGE_SHIFT;
+        pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+        loff_t lastoff = offset;
+        struct pagevec pvec;
+
+        if (length <= 0)
+                return -ENOENT;
+
+        pagevec_init(&pvec, 0);
+
+        do {
+                unsigned want, nr_pages, i;
+
+                want = min_t(unsigned, end - index, PAGEVEC_SIZE);
+                nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+                if (nr_pages == 0)
+                        break;
+
+                for (i = 0; i < nr_pages; i++) {
+                        struct page *page = pvec.pages[i];
+
+                        /*
+                         * At this point, the page may be truncated or
+                         * invalidated (changing page->mapping to NULL), or
+                         * even swizzled back from swapper_space to tmpfs file
+                         * mapping.  However, page->index will not change
+                         * because we have a reference on the page.
+                         *
+                         * If current page offset is beyond where we've ended,
+                         * we've found a hole.
+                         */
+                        if (whence == SEEK_HOLE &&
+                            lastoff < page_offset(page))
+                                goto check_range;
+
+                        /* Searching done if the page index is out of range. */
+                        if (page->index >= end)
+                                goto not_found;
+
+                        lock_page(page);
+                        if (likely(page->mapping == inode->i_mapping) &&
+                            page_has_buffers(page)) {
+                                lastoff = page_seek_hole_data(page, lastoff, whence);
+                                if (lastoff >= 0) {
+                                        unlock_page(page);
+                                        goto check_range;
+                                }
+                        }
+                        unlock_page(page);
+                        lastoff = page_offset(page) + PAGE_SIZE;
+                }
+
+                /* Searching done if fewer pages returned than wanted. */
+                if (nr_pages < want)
+                        break;
+
+                index = pvec.pages[i - 1]->index + 1;
+                pagevec_release(&pvec);
+        } while (index < end);
+
+        /* When no page at lastoff and we are not done, we found a hole. */
+        if (whence != SEEK_HOLE)
+                goto not_found;
+
+check_range:
+        if (lastoff < offset + length)
+                goto out;
+not_found:
+        lastoff = -ENOENT;
+out:
+        pagevec_release(&pvec);
+        return lastoff;
+}
+
 void __init buffer_init(void)
 {
         unsigned long nrpages;