iomap: introduce IOMAP_F_FSVERITY and teach writeback to handle fsverity

This flag indicates that I/O is for fsverity metadata.

In the write path skip i_size check and i_size updates as metadata is
past EOF. In writeback don't update i_size and continue writeback if
even folio is beyond EOF. In read path don't zero fsverity folios, again
they are past EOF.

The iomap_block_needs_zeroing() is also called from write path. For
folios of larger order we don't want to zero out pages in the folio as
these could contain other merkle tree blocks. For fsverity, filesystem
will request to read PAGE_SIZE memory regions. For data folios, iomap
will zero the rest of the folio for anything which is beyond EOF. We
don't want this for fsverity folios.

Christian Brauner <brauner@kernel.org> says:
Changed IOMAP_F_FSVERITY from (1U << 10) to (1U << 11) to avoid colliding
with IOMAP_F_ZERO_TAIL, which already uses (1U << 10).

Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Link: https://patch.msgid.link/20260520123722.405752-8-aalbersh@kernel.org
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner (Amutable) <brauner@kernel.org>

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index d6451c4208d499586c993574fceb678f3f8c9394..d9462f28afbd33d93131edb1deef0a92a7e40476 100644 (file)
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -353,9 +353,26 @@ static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
 {
        const struct iomap *srcmap = iomap_iter_srcmap(iter);
 
-       return srcmap->type != IOMAP_MAPPED ||
-               (srcmap->flags & IOMAP_F_NEW) ||
-               pos >= i_size_read(iter->inode);
+       /*
+        * If this block has not been written, there's nothing to read
+        */
+       if (srcmap->type != IOMAP_MAPPED)
+               return true;
+
+       /*
+        * Newly allocated blocks have not been written
+        */
+       if (srcmap->flags & IOMAP_F_NEW)
+               return true;
+
+       /*
+        * fsverity metadata is stored past i_size, we need to read it instead
+        * of zeroing
+        */
+       if (srcmap->flags & IOMAP_F_FSVERITY)
+               return false;
+
+       return pos >= i_size_read(iter->inode);
 }
 
 /**
@@ -1170,13 +1187,14 @@ retry:
                 * unlock and release the folio.
                 */
                old_size = iter->inode->i_size;
-               if (pos + written > old_size) {
+               if (pos + written > old_size &&
+                   !(iter->iomap.flags & IOMAP_F_FSVERITY)) {
                        i_size_write(iter->inode, pos + written);
                        iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
                }
                __iomap_put_folio(iter, write_ops, written, folio);
 
-               if (old_size < pos)
+               if (old_size < pos && !(iter->iomap.flags & IOMAP_F_FSVERITY))
                        pagecache_isize_extended(iter->inode, old_size, pos);
 
                cond_resched();
@@ -1802,13 +1820,20 @@ static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
  * Check interaction of the folio with the file end.
  *
  * If the folio is entirely beyond i_size, return false.  If it straddles
- * i_size, adjust end_pos and zero all data beyond i_size.
+ * i_size, adjust end_pos and zero all data beyond i_size. Don't skip fsverity
+ * folios as those are beyond i_size.
  */
-static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
-               u64 *end_pos)
+static bool iomap_writeback_handle_eof(struct folio *folio,
+               struct iomap_writepage_ctx *wpc, u64 *end_pos)
 {
+       struct inode *inode = wpc->inode;
        u64 isize = i_size_read(inode);
 
+       if (wpc->iomap.flags & IOMAP_F_FSVERITY) {
+               WARN_ON_ONCE(folio_pos(folio) < isize);
+               return true;
+       }
+
        if (*end_pos > isize) {
                size_t poff = offset_in_folio(folio, isize);
                pgoff_t end_index = isize >> PAGE_SHIFT;
@@ -1874,7 +1899,7 @@ int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
 
        trace_iomap_writeback_folio(inode, pos, folio_size(folio));
 
-       if (!iomap_writeback_handle_eof(folio, inode, &end_pos))
+       if (!iomap_writeback_handle_eof(folio, wpc, &end_pos))
                return 0;
        WARN_ON_ONCE(end_pos <= pos);
 

diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 097773c6db80e289bb488ef2af6e29f0d777b102..e4dd25b2765611b2e4a9bd76d0d59d49920d1581 100644 (file)
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -118,7 +118,8 @@ DEFINE_RANGE_EVENT(iomap_zero_iter);
        { IOMAP_F_ATOMIC_BIO,   "ATOMIC_BIO" }, \
        { IOMAP_F_PRIVATE,      "PRIVATE" }, \
        { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \
-       { IOMAP_F_STALE,        "STALE" }
+       { IOMAP_F_STALE,        "STALE" }, \
+       { IOMAP_F_FSVERITY,     "FSVERITY" }
 
 
 #define IOMAP_DIO_STRINGS \

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index cea6bbc97b6ef886f4aa57acbd5da6f0ec2cbff0..5b2b40e81b6116b1c0cde4ff27ede76d0d6caa46 100644 (file)
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -91,6 +91,14 @@ struct vm_fault;
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 #define IOMAP_F_ZERO_TAIL      (1U << 10)
 
+/*
+ * Indicates reads and writes of fsverity metadata.
+ *
+ * Fsverity metadata is stored after the regular file data and thus beyond
+ * i_size.
+ */
+#define IOMAP_F_FSVERITY       (1U << 11)
+
 /*
  * Flag reserved for file system specific usage
  */