erofs: hold read context in iomap_iter if needed

Introduce `struct erofs_iomap_iter_ctx` to hold both `struct page *`
and `void *base`, avoiding bogus use of `kmap_to_page()` in
`erofs_iomap_end()`.

With this change, fiemap and bmap no longer need to read inline data.

Additionally, the upcoming page cache sharing mechanism requires
passing the backing inode pointer to `erofs_iomap_{begin,end}()`, as
I/O accesses must apply to backing inodes rather than anon inodes.

Signed-off-by: Hongbo Li <lihongbo22@huawei.com>
Link: https://patch.msgid.link/20260109102856.598531-3-lihongbo22@huawei.com
Reviewed-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index bb13c4cb845563492a616fc000910112b92df555..71e23d91123dc5ea8b79fdc36e16ab425e580928 100644 (file)
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -266,13 +266,20 @@ void erofs_onlinefolio_end(struct folio *folio, int err, bool dirty)
        folio_end_read(folio, !(v & BIT(EROFS_ONLINEFOLIO_EIO)));
 }
 
+struct erofs_iomap_iter_ctx {
+       struct page *page;
+       void *base;
+};
+
 static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
                unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
 {
-       int ret;
+       struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+       struct erofs_iomap_iter_ctx *ctx = iter->private;
        struct super_block *sb = inode->i_sb;
        struct erofs_map_blocks map;
        struct erofs_map_dev mdev;
+       int ret;
 
        map.m_la = offset;
        map.m_llen = length;
@@ -283,7 +290,6 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
        iomap->offset = map.m_la;
        iomap->length = map.m_llen;
        iomap->flags = 0;
-       iomap->private = NULL;
        iomap->addr = IOMAP_NULL_ADDR;
        if (!(map.m_flags & EROFS_MAP_MAPPED)) {
                iomap->type = IOMAP_HOLE;
@@ -309,16 +315,20 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
        }
 
        if (map.m_flags & EROFS_MAP_META) {
-               void *ptr;
-               struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
-
                iomap->type = IOMAP_INLINE;
-               ptr = erofs_read_metabuf(&buf, sb, map.m_pa,
-                                        erofs_inode_in_metabox(inode));
-               if (IS_ERR(ptr))
-                       return PTR_ERR(ptr);
-               iomap->inline_data = ptr;
-               iomap->private = buf.base;
+               /* read context should read the inlined data */
+               if (ctx) {
+                       struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
+                       void *ptr;
+
+                       ptr = erofs_read_metabuf(&buf, sb, map.m_pa,
+                                                erofs_inode_in_metabox(inode));
+                       if (IS_ERR(ptr))
+                               return PTR_ERR(ptr);
+                       iomap->inline_data = ptr;
+                       ctx->page = buf.page;
+                       ctx->base = buf.base;
+               }
        } else {
                iomap->type = IOMAP_MAPPED;
        }
@@ -328,18 +338,18 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 static int erofs_iomap_end(struct inode *inode, loff_t pos, loff_t length,
                ssize_t written, unsigned int flags, struct iomap *iomap)
 {
-       void *ptr = iomap->private;
+       struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
+       struct erofs_iomap_iter_ctx *ctx = iter->private;
 
-       if (ptr) {
+       if (ctx && ctx->base) {
                struct erofs_buf buf = {
-                       .page = kmap_to_page(ptr),
-                       .base = ptr,
+                       .page = ctx->page,
+                       .base = ctx->base,
                };
 
                DBG_BUGON(iomap->type != IOMAP_INLINE);
                erofs_put_metabuf(&buf);
-       } else {
-               DBG_BUGON(iomap->type == IOMAP_INLINE);
+               ctx->base = NULL;
        }
        return written;
 }
@@ -369,18 +379,30 @@ int erofs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  */
 static int erofs_read_folio(struct file *file, struct folio *folio)
 {
+       struct iomap_read_folio_ctx read_ctx = {
+               .ops            = &iomap_bio_read_ops,
+               .cur_folio      = folio,
+       };
+       struct erofs_iomap_iter_ctx iter_ctx = {};
+
        trace_erofs_read_folio(folio, true);
 
-       iomap_bio_read_folio(folio, &erofs_iomap_ops);
+       iomap_read_folio(&erofs_iomap_ops, &read_ctx, &iter_ctx);
        return 0;
 }
 
 static void erofs_readahead(struct readahead_control *rac)
 {
+       struct iomap_read_folio_ctx read_ctx = {
+               .ops            = &iomap_bio_read_ops,
+               .rac            = rac,
+       };
+       struct erofs_iomap_iter_ctx iter_ctx = {};
+
        trace_erofs_readahead(rac->mapping->host, readahead_index(rac),
                                        readahead_count(rac), true);
 
-       iomap_bio_readahead(rac, &erofs_iomap_ops);
+       iomap_readahead(&erofs_iomap_ops, &read_ctx, &iter_ctx);
 }
 
 static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
@@ -400,9 +422,12 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
        if (IS_DAX(inode))
                return dax_iomap_rw(iocb, to, &erofs_iomap_ops);
 #endif
-       if ((iocb->ki_flags & IOCB_DIRECT) && inode->i_sb->s_bdev)
+       if ((iocb->ki_flags & IOCB_DIRECT) && inode->i_sb->s_bdev) {
+               struct erofs_iomap_iter_ctx iter_ctx = {};
+
                return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-                                   NULL, 0, NULL, 0);
+                                   NULL, 0, &iter_ctx, 0);
+       }
        return filemap_read(iocb, to, 0);
 }