[PATCH] enhance ->sendfile(), allowing kNFSd to use it

I enhanced the sendfile method so that we could pass a proper actor to
it (which exposes the full power of the internal implementation).

Now knfsd calls the sendfile vector rather than depending on a
readpage() that hasn't been set up fully.

fs/nfsd/vfs.c

@@ -572,7 +572,6 @@ nfsd_get_raparms(dev_t dev, ino_t ino)
 	return ra;
 }
 
-#if 0 /* don't poke into fs code directly */
 /*
  * Grab and keep cached pages assosiated with a file in the svc_rqst
  * so that they can be passed to the netowork sendmsg/sendpage routines
@@ -605,30 +604,6 @@ nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset
 	return size;
 }
 
-static inline ssize_t
-nfsd_getpages(struct file *filp, struct svc_rqst *rqstp, unsigned long count)
-{
-	read_descriptor_t desc;
-	ssize_t	retval;
-
-	if (!count)
-		return 0;
-
-	svc_pushback_unused_pages(rqstp);
-
-	desc.written = 0;
-	desc.count = count;
-	desc.buf = (char *)rqstp;
-	desc.error = 0;
-	do_generic_file_read(filp, &filp->f_pos, &desc, nfsd_read_actor);
-
-	retval = desc.written;
-	if (!retval)
-		retval = desc.error;
-	return retval;
-}
-#endif
-
 /*
  * Read data from a file. count must contain the requested read count
  * on entry. On return, *count contains the number of bytes actually read.
@@ -660,13 +635,11 @@ nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
 	if (ra)
 		file.f_ra = ra->p_ra;
 
-#if 0 /* don't poke into fs code directly */
-	if (inode->i_mapping->a_ops->readpage) {
-		file.f_pos = offset;
-		err = nfsd_getpages(&file, rqstp, *count);
-	} else
-#endif
-	{
+	if (file.f_op->sendfile) {
+		svc_pushback_unused_pages(rqstp);
+		err = file.f_op->sendfile(&file, &offset, *count,
+						 nfsd_read_actor, rqstp);
+	} else {
 		oldfs = get_fs();
 		set_fs(KERNEL_DS);
 		err = vfs_readv(&file, vec, vlen, &offset);

fs/read_write.c

@@ -565,7 +565,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		count = max - pos;
 	}
 
-	retval = in_file->f_op->sendfile(out_file, in_file, ppos, count);
+	retval = in_file->f_op->sendfile(in_file, ppos, count, file_send_actor, out_file);
 
 	if (*ppos > max)
 		retval = -EOVERFLOW;

include/linux/fs.h

@@ -735,6 +735,24 @@ struct block_device_operations {
 	struct module *owner;
 };
 
+/*
+ * "descriptor" for what we're up to with a read for sendfile().
+ * This allows us to use the same read code yet
+ * have multiple different users of the data that
+ * we read from a file.
+ *
+ * The simplest case just copies the data to user
+ * mode.
+ */
+typedef struct {
+	size_t written;
+	size_t count;
+	char * buf;
+	int error;
+} read_descriptor_t;
+
+typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);
+
 /*
  * NOTE:
  * read, write, poll, fsync, readv, writev can be called
@@ -761,7 +779,7 @@ struct file_operations {
 	int (*lock) (struct file *, int, struct file_lock *);
 	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *);
 	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *);
-	ssize_t (*sendfile) (struct file *, struct file *, loff_t *, size_t);
+	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *);
 	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 };
@@ -1176,24 +1194,6 @@ extern ino_t find_inode_number(struct dentry *, struct qstr *);
 
 #include <linux/err.h>
 
-/*
- * "descriptor" for what we're up to with a read for sendfile().
- * This allows us to use the same read code yet
- * have multiple different users of the data that
- * we read from a file.
- *
- * The simplest case just copies the data to user
- * mode.
- */
-typedef struct {
-	size_t written;
-	size_t count;
-	char * buf;
-	int error;
-} read_descriptor_t;
-
-typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);
-
 /* needed for stackable file system support */
 extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
 
@@ -1256,7 +1256,7 @@ extern ssize_t do_sync_read(struct file *filp, char *buf, size_t len, loff_t *pp
 extern ssize_t do_sync_write(struct file *filp, const char *buf, size_t len, loff_t *ppos);
 ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov,
 				unsigned long nr_segs, loff_t *ppos);
-extern ssize_t generic_file_sendfile(struct file *, struct file *, loff_t *, size_t);
+extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
 extern void do_generic_mapping_read(struct address_space *, struct file_ra_state *, struct file *,
 				    loff_t *, read_descriptor_t *, read_actor_t);
 extern void

mm/filemap.c

@@ -888,8 +888,8 @@ int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long o
 	return written;
 }
 
-ssize_t generic_file_sendfile(struct file *out_file, struct file *in_file,
-			      loff_t *ppos, size_t count)
+ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
+			 size_t count, read_actor_t actor, void *target)
 {
 	read_descriptor_t desc;
 
@@ -898,10 +898,10 @@ ssize_t generic_file_sendfile(struct file *out_file, struct file *in_file,
 
 	desc.written = 0;
 	desc.count = count;
-	desc.buf = (char *)out_file;
+	desc.buf = target;
 	desc.error = 0;
 
-	do_generic_file_read(in_file, ppos, &desc, file_send_actor);
+	do_generic_file_read(in_file, ppos, &desc, actor);
 	if (desc.written)
 		return desc.written;
 	return desc.error;

mm/shmem.c

@@ -1387,8 +1387,8 @@ static ssize_t shmem_file_read(struct file *filp, char *buf, size_t count, loff_
 	return desc.error;
 }
 
-static ssize_t shmem_file_sendfile(struct file *out_file,
-	struct file *in_file, loff_t *ppos, size_t count)
+static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos,
+			 size_t count, read_actor_t actor, void *target)
 {
 	read_descriptor_t desc;
 
@@ -1397,10 +1397,10 @@ static ssize_t shmem_file_sendfile(struct file *out_file,
 
 	desc.written = 0;
 	desc.count = count;
-	desc.buf = (char *)out_file;
+	desc.buf = target;
 	desc.error = 0;
 
-	do_shmem_file_read(in_file, ppos, &desc, file_send_actor);
+	do_shmem_file_read(in_file, ppos, &desc, actor);
 	if (desc.written)
 		return desc.written;
 	return desc.error;