iomap: use mapping_seek_hole_data

Enhance mapping_seek_hole_data() to handle partially uptodate pages and
convert the iomap seek code to call it.

Link: https://lkml.kernel.org/r/20201112212641.27837-9-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <dchinner@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index 107ee80c356833936487d200fae5825eac90d976..dab1b02eba5b7f36b6ef5401b05177691f5b75dc 100644 (file)
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -10,122 +10,17 @@
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
 
-/*
- * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
- * Returns true if found and updates @lastoff to the offset in file.
- */
-static bool
-page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
-               int whence)
-{
-       const struct address_space_operations *ops = inode->i_mapping->a_ops;
-       unsigned int bsize = i_blocksize(inode), off;
-       bool seek_data = whence == SEEK_DATA;
-       loff_t poff = page_offset(page);
-
-       if (WARN_ON_ONCE(*lastoff >= poff + PAGE_SIZE))
-               return false;
-
-       if (*lastoff < poff) {
-               /*
-                * Last offset smaller than the start of the page means we found
-                * a hole:
-                */
-               if (whence == SEEK_HOLE)
-                       return true;
-               *lastoff = poff;
-       }
-
-       /*
-        * Just check the page unless we can and should check block ranges:
-        */
-       if (bsize == PAGE_SIZE || !ops->is_partially_uptodate)
-               return PageUptodate(page) == seek_data;
-
-       lock_page(page);
-       if (unlikely(page->mapping != inode->i_mapping))
-               goto out_unlock_not_found;
-
-       for (off = 0; off < PAGE_SIZE; off += bsize) {
-               if (offset_in_page(*lastoff) >= off + bsize)
-                       continue;
-               if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
-                       unlock_page(page);
-                       return true;
-               }
-               *lastoff = poff + off + bsize;
-       }
-
-out_unlock_not_found:
-       unlock_page(page);
-       return false;
-}
-
-/*
- * 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: uptodate buffer heads count as data; everything else
- * counts as a hole.
- *
- * Returns the resulting offset on successs, and -ENOENT otherwise.
- */
 static 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);
-
-       do {
-               unsigned nr_pages, i;
-
-               nr_pages = pagevec_lookup_range(&pvec, inode->i_mapping, &index,
-                                               end - 1);
-               if (nr_pages == 0)
-                       break;
-
-               for (i = 0; i < nr_pages; i++) {
-                       struct page *page = pvec.pages[i];
-
-                       if (page_seek_hole_data(inode, page, &lastoff, whence))
-                               goto check_range;
-                       lastoff = page_offset(page) + PAGE_SIZE;
-               }
-               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;
-}
-
-
-static loff_t
-iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
+iomap_seek_hole_actor(struct inode *inode, loff_t start, loff_t length,
                      void *data, struct iomap *iomap, struct iomap *srcmap)
 {
+       loff_t offset = start;
+
        switch (iomap->type) {
        case IOMAP_UNWRITTEN:
-               offset = page_cache_seek_hole_data(inode, offset, length,
-                                                  SEEK_HOLE);
-               if (offset < 0)
+               offset = mapping_seek_hole_data(inode->i_mapping, start,
+                               start + length, SEEK_HOLE);
+               if (offset == start + length)
                        return length;
                fallthrough;
        case IOMAP_HOLE:
@@ -164,15 +59,17 @@ iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
 EXPORT_SYMBOL_GPL(iomap_seek_hole);
 
 static loff_t
-iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
+iomap_seek_data_actor(struct inode *inode, loff_t start, loff_t length,
                      void *data, struct iomap *iomap, struct iomap *srcmap)
 {
+       loff_t offset = start;
+
        switch (iomap->type) {
        case IOMAP_HOLE:
                return length;
        case IOMAP_UNWRITTEN:
-               offset = page_cache_seek_hole_data(inode, offset, length,
-                                                  SEEK_DATA);
+               offset = mapping_seek_hole_data(inode->i_mapping, start,
+                               start + length, SEEK_DATA);
                if (offset < 0)
                        return length;
                fallthrough;

diff --git a/mm/filemap.c b/mm/filemap.c
index eff3006be12af16385053cebdcc8de2c1e9f8e4a..6a34f94adf3b29c858293149f6f4c67e8856fc75 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2553,11 +2553,36 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 }
 EXPORT_SYMBOL(generic_file_read_iter);
 
-static inline bool page_seek_match(struct page *page, bool seek_data)
+static inline loff_t page_seek_hole_data(struct xa_state *xas,
+               struct address_space *mapping, struct page *page,
+               loff_t start, loff_t end, bool seek_data)
 {
+       const struct address_space_operations *ops = mapping->a_ops;
+       size_t offset, bsz = i_blocksize(mapping->host);
+
        if (xa_is_value(page) || PageUptodate(page))
-               return seek_data;
-       return !seek_data;
+               return seek_data ? start : end;
+       if (!ops->is_partially_uptodate)
+               return seek_data ? end : start;
+
+       xas_pause(xas);
+       rcu_read_unlock();
+       lock_page(page);
+       if (unlikely(page->mapping != mapping))
+               goto unlock;
+
+       offset = offset_in_thp(page, start) & ~(bsz - 1);
+
+       do {
+               if (ops->is_partially_uptodate(page, offset, bsz) == seek_data)
+                       break;
+               start = (start + bsz) & ~(bsz - 1);
+               offset += bsz;
+       } while (offset < thp_size(page));
+unlock:
+       unlock_page(page);
+       rcu_read_lock();
+       return start;
 }
 
 static inline
@@ -2607,9 +2632,11 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
                        start = pos;
                }
 
-               if (page_seek_match(page, seek_data))
+               pos += seek_page_size(&xas, page);
+               start = page_seek_hole_data(&xas, mapping, page, start, pos,
+                               seek_data);
+               if (start < pos)
                        goto unlock;
-               start = pos + seek_page_size(&xas, page);
                if (!xa_is_value(page))
                        put_page(page);
        }