erofs: support dot-omitted directories

There's no need to record "." dirents in the directory data (while
they could be used for sanity checks, they aren't very useful.)
Omitting "." dirents also improves directory data deduplication.

Use a per-inode (instead of per-sb) flag to indicate if the "." dirent
is omitted or not, ensuring compatibility with incremental builds.  It
also reuses EROFS_I_NLINK_1_BIT, as it has very limited use cases for
directories with `nlink = 1`.

Emit the "." entry as the last virtual dirent in the directory because
it is _much_ less frequently used than the ".." dirent.  It also keeps
`f_pos` meaningful, as it strictly follows the directory data when it's
less than i_size.

Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Acked-by: Chao Yu <chao@kernel.org>
Link: https://lore.kernel.org/r/20250310095459.2620647-6-hsiangkao@linux.alibaba.com

diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
index fa3c2d380cc9bd602eae90712249b66b1f314922..2fae209d0274031d69ab15538fd7308c9ec6047b 100644 (file)
--- a/fs/erofs/dir.c
+++ b/fs/erofs/dir.c
@@ -90,6 +90,11 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
                ofs = 0;
        }
        erofs_put_metabuf(&buf);
+       if (EROFS_I(dir)->dot_omitted && ctx->pos == dir->i_size) {
+               if (!dir_emit_dot(f, ctx))
+                       return 0;
+               ++ctx->pos;
+       }
        return err < 0 ? err : 0;
 }
 

diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h
index 8330ca3b18d336e4633d157d1f59aa8d9fe635a7..791124b3f57c9065a279b5f490fb8261111d5da7 100644 (file)
--- a/fs/erofs/erofs_fs.h
+++ b/fs/erofs/erofs_fs.h
@@ -116,6 +116,7 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode)
 #define EROFS_I_VERSION_BIT    0
 #define EROFS_I_DATALAYOUT_BIT 1
 #define EROFS_I_NLINK_1_BIT    4       /* non-directory compact inodes only */
+#define EROFS_I_DOT_OMITTED_BIT        4       /* (directories) omit the `.` dirent */
 #define EROFS_I_ALL            ((1 << (EROFS_I_NLINK_1_BIT + 1)) - 1)
 
 /* indicate chunk blkbits, thus 'chunksize = blocksize << chunk blkbits' */

diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
index 6de281312ea7ebee3b088c192eb1a2d5ec4dd4f9..a0ae0b4f7b012a3481f39cd52a5418e79fb262e0 100644 (file)
--- a/fs/erofs/inode.c
+++ b/fs/erofs/inode.c
@@ -136,8 +136,10 @@ static int erofs_read_inode(struct inode *inode)
                goto err_out;
        }
        switch (inode->i_mode & S_IFMT) {
-       case S_IFREG:
        case S_IFDIR:
+               vi->dot_omitted = (ifmt >> EROFS_I_DOT_OMITTED_BIT) & 1;
+               fallthrough;
+       case S_IFREG:
        case S_IFLNK:
                vi->startblk = le32_to_cpu(copied.i_u.startblk_lo) |
                        ((u64)le16_to_cpu(copied.i_nb.startblk_hi) << 32);

diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 07515a6f2534a8fc8cef4a2a393d51432a31b3b4..91d0b400459cf9c8e2470e1212e492761514708d 100644 (file)
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -245,6 +245,7 @@ struct erofs_inode {
 
        unsigned char datalayout;
        unsigned char inode_isize;
+       bool dot_omitted;
        unsigned int xattr_isize;
 
        unsigned int xattr_name_filter;