ext4: re-inline ext4_rec_len_(to|from)_disk functions

commit 3d0518f, "ext4: New rec_len encoding for very
large blocksizes" made several changes to this path, but from
a perf perspective, un-inlining ext4_rec_len_from_disk() seems
most significant.  This function is called from ext4_check_dir_entry(),
which on a file-creation workload is called extremely often.

I tested this with bonnie:

# bonnie++ -u root -s 0 -f -x 200 -d /mnt/test -n 32

(this does 200 iterations) and got this for the file creations:

ext4 stock:   Average =  21206.8 files/s
ext4 inlined: Average =  22346.7 files/s  (+5%)

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

Author: Eric Sandeen

fs/ext4/ext4.h

@@ -1411,6 +1411,43 @@ struct ext4_dir_entry_2 {
 					 ~EXT4_DIR_ROUND)
 #define EXT4_MAX_REC_LEN		((1<<16)-1)
 
+/*
+ * If we ever get support for fs block sizes > page_size, we'll need
+ * to remove the #if statements in the next two functions...
+ */
+static inline unsigned int
+ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
+{
+	unsigned len = le16_to_cpu(dlen);
+
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len == EXT4_MAX_REC_LEN || len == 0)
+		return blocksize;
+	return (len & 65532) | ((len & 3) << 16);
+#else
+	return len;
+#endif
+}
+
+static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
+{
+	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
+		BUG();
+#if (PAGE_CACHE_SIZE >= 65536)
+	if (len < 65536)
+		return cpu_to_le16(len);
+	if (len == blocksize) {
+		if (blocksize == 65536)
+			return cpu_to_le16(EXT4_MAX_REC_LEN);
+		else
+			return cpu_to_le16(0);
+	}
+	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
+#else
+	return cpu_to_le16(len);
+#endif
+}
+
 /*
  * Hash Tree Directory indexing
  * (c) Daniel Phillips, 2001
@@ -1636,8 +1673,6 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
 extern int ext4_ext_migrate(struct inode *);
 
 /* namei.c */
-extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize);
-extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize);
 extern int ext4_orphan_add(handle_t *, struct inode *);
 extern int ext4_orphan_del(handle_t *, struct inode *);
 extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,

fs/ext4/namei.c

@@ -179,30 +179,6 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode);
 
-unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
-{
-	unsigned len = le16_to_cpu(dlen);
-
-	if (len == EXT4_MAX_REC_LEN || len == 0)
-		return blocksize;
-	return (len & 65532) | ((len & 3) << 16);
-}
-
-__le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
-{
-	if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
-		BUG();
-	if (len < 65536)
-		return cpu_to_le16(len);
-	if (len == blocksize) {
-		if (blocksize == 65536)
-			return cpu_to_le16(EXT4_MAX_REC_LEN);
-		else
-			return cpu_to_le16(0);
-	}
-	return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
-}
-
 /*
  * p is at least 6 bytes before the end of page
  */