fs/9p: Update zero-copy implementation in 9p

* remove lot of update to different data structure
* add a seperate callback for zero copy request.
* above makes non zero copy code path simpler
* remove conditionalizing TREAD/TREADDIR/TWRITE in the zero copy path
* Fix the dotu p9_check_errors with zero copy. Add sufficient doc around
* Add support for both in and output buffers in zero copy callback
* pin and unpin pages in the same context
* use helpers instead of defining page offset and rest of page ourself
* Fix mem leak in p9_check_errors
* Remove 'E' and 'F' in p9pdu_vwritef
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>

fs/9p/vfs_dir.c

@@ -231,7 +231,7 @@ static int v9fs_dir_readdir_dotl(struct file *filp, void *dirent,
 	while (err == 0) {
 		if (rdir->tail == rdir->head) {
 			err = p9_client_readdir(fid, rdir->buf, buflen,
-								filp->f_pos);
+						filp->f_pos);
 			if (err <= 0)
 				goto unlock_and_exit;
 

include/net/9p/9p.h

@@ -359,6 +359,9 @@ enum p9_qid_t {
 /* Room for readdir header */
 #define P9_READDIRHDRSZ	24
 
+/* size of header for zero copy read/write */
+#define P9_ZC_HDR_SZ 4096
+
 /**
  * struct p9_qid - file system entity information
  * @type: 8-bit type &p9_qid_t
@@ -555,10 +558,6 @@ struct p9_rstatfs {
  * @tag: transaction id of the request
  * @offset: used by marshalling routines to track current position in buffer
  * @capacity: used by marshalling routines to track total malloc'd capacity
- * @pubuf: Payload user buffer given by the caller
- * @pkbuf: Payload kernel buffer given by the caller
- * @pbuf_size: pubuf/pkbuf(only one will be !NULL) size to be read/write.
- * @private: For transport layer's use.
  * @sdata: payload
  *
  * &p9_fcall represents the structure for all 9P RPC
@@ -575,10 +574,6 @@ struct p9_fcall {
 
 	size_t offset;
 	size_t capacity;
-	char __user *pubuf;
-	char *pkbuf;
-	size_t pbuf_size;
-	void *private;
 
 	u8 *sdata;
 };

include/net/9p/transport.h

@@ -26,13 +26,6 @@
 #ifndef NET_9P_TRANSPORT_H
 #define NET_9P_TRANSPORT_H
 
-#define P9_TRANS_PREF_PAYLOAD_MASK 0x1
-
-/* Default. Add Payload to PDU before sending it down to transport layer */
-#define P9_TRANS_PREF_PAYLOAD_DEF  0x0
-/* Send pay load separately to transport layer along with PDU.*/
-#define P9_TRANS_PREF_PAYLOAD_SEP  0x1
-
 /**
  * struct p9_trans_module - transport module interface
  * @list: used to maintain a list of currently available transports
@@ -56,13 +49,14 @@ struct p9_trans_module {
 	struct list_head list;
 	char *name;		/* name of transport */
 	int maxsize;		/* max message size of transport */
-	int pref;               /* Preferences of this transport */
 	int def;		/* this transport should be default */
 	struct module *owner;
 	int (*create)(struct p9_client *, const char *, char *);
 	void (*close) (struct p9_client *);
 	int (*request) (struct p9_client *, struct p9_req_t *req);
 	int (*cancel) (struct p9_client *, struct p9_req_t *req);
+	int (*zc_request)(struct p9_client *, struct p9_req_t *,
+			  char *, char *, int , int, int, int);
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);

net/9p/protocol.c

@@ -81,7 +81,7 @@ void p9stat_free(struct p9_wstat *stbuf)
 }
 EXPORT_SYMBOL(p9stat_free);
 
-static size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
 {
 	size_t len = min(pdu->size - pdu->offset, size);
 	memcpy(data, &pdu->sdata[pdu->offset], len);
@@ -108,26 +108,6 @@ pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
 	return size - len;
 }
 
-static size_t
-pdu_write_urw(struct p9_fcall *pdu, const char *kdata, const char __user *udata,
-		size_t size)
-{
-	BUG_ON(pdu->size > P9_IOHDRSZ);
-	pdu->pubuf = (char __user *)udata;
-	pdu->pkbuf = (char *)kdata;
-	pdu->pbuf_size = size;
-	return 0;
-}
-
-static size_t
-pdu_write_readdir(struct p9_fcall *pdu, const char *kdata, size_t size)
-{
-	BUG_ON(pdu->size > P9_READDIRHDRSZ);
-	pdu->pkbuf = (char *)kdata;
-	pdu->pbuf_size = size;
-	return 0;
-}
-
 /*
 	b - int8_t
 	w - int16_t
@@ -459,26 +439,6 @@ p9pdu_vwritef(struct p9_fcall *pdu, int proto_version, const char *fmt,
 					errcode = -EFAULT;
 			}
 			break;
-		case 'E':{
-				 int32_t cnt = va_arg(ap, int32_t);
-				 const char *k = va_arg(ap, const void *);
-				 const char __user *u = va_arg(ap,
-							const void __user *);
-				 errcode = p9pdu_writef(pdu, proto_version, "d",
-						 cnt);
-				 if (!errcode && pdu_write_urw(pdu, k, u, cnt))
-					errcode = -EFAULT;
-			 }
-			 break;
-		case 'F':{
-				 int32_t cnt = va_arg(ap, int32_t);
-				 const char *k = va_arg(ap, const void *);
-				 errcode = p9pdu_writef(pdu, proto_version, "d",
-						 cnt);
-				 if (!errcode && pdu_write_readdir(pdu, k, cnt))
-					errcode = -EFAULT;
-			 }
-			 break;
 		case 'U':{
 				int32_t count = va_arg(ap, int32_t);
 				const char __user *udata =
@@ -637,10 +597,6 @@ void p9pdu_reset(struct p9_fcall *pdu)
 {
 	pdu->offset = 0;
 	pdu->size = 0;
-	pdu->private = NULL;
-	pdu->pubuf = NULL;
-	pdu->pkbuf = NULL;
-	pdu->pbuf_size = 0;
 }
 
 int p9dirent_read(char *buf, int len, struct p9_dirent *dirent,

net/9p/protocol.h

@@ -32,3 +32,4 @@ int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
 int p9pdu_finalize(struct p9_fcall *pdu);
 void p9pdu_dump(int, struct p9_fcall *);
 void p9pdu_reset(struct p9_fcall *pdu);
+size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size);

net/9p/trans_common.c

@@ -21,30 +21,25 @@
 
 /**
  *  p9_release_req_pages - Release pages after the transaction.
- *  @*private: PDU's private page of struct trans_rpage_info
  */
-void
-p9_release_req_pages(struct trans_rpage_info *rpinfo)
+void p9_release_pages(struct page **pages, int nr_pages)
 {
 	int i = 0;
-
-	while (rpinfo->rp_data[i] && rpinfo->rp_nr_pages--) {
-		put_page(rpinfo->rp_data[i]);
+	while (pages[i] && nr_pages--) {
+		put_page(pages[i]);
 		i++;
 	}
 }
-EXPORT_SYMBOL(p9_release_req_pages);
+EXPORT_SYMBOL(p9_release_pages);
 
 /**
  * p9_nr_pages - Return number of pages needed to accommodate the payload.
  */
-int
-p9_nr_pages(struct p9_req_t *req)
+int p9_nr_pages(char *data, int len)
 {
 	unsigned long start_page, end_page;
-	start_page =  (unsigned long)req->tc->pubuf >> PAGE_SHIFT;
-	end_page = ((unsigned long)req->tc->pubuf + req->tc->pbuf_size +
-			PAGE_SIZE - 1) >> PAGE_SHIFT;
+	start_page =  (unsigned long)data >> PAGE_SHIFT;
+	end_page = ((unsigned long)data + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	return end_page - start_page;
 }
 EXPORT_SYMBOL(p9_nr_pages);
@@ -58,35 +53,17 @@ EXPORT_SYMBOL(p9_nr_pages);
  * @nr_pages: number of pages to accommodate the payload
  * @rw: Indicates if the pages are for read or write.
  */
-int
-p9_payload_gup(struct p9_req_t *req, size_t *pdata_off, int *pdata_len,
-		int nr_pages, u8 rw)
-{
-	uint32_t first_page_bytes = 0;
-	int32_t pdata_mapped_pages;
-	struct trans_rpage_info  *rpinfo;
-
-	*pdata_off = (__force size_t)req->tc->pubuf & (PAGE_SIZE-1);
 
-	if (*pdata_off)
-		first_page_bytes = min(((size_t)PAGE_SIZE - *pdata_off),
-				       req->tc->pbuf_size);
+int p9_payload_gup(char *data, int *nr_pages, struct page **pages, int write)
+{
+	int nr_mapped_pages;
 
-	rpinfo = req->tc->private;
-	pdata_mapped_pages = get_user_pages_fast((unsigned long)req->tc->pubuf,
-			nr_pages, rw, &rpinfo->rp_data[0]);
-	if (pdata_mapped_pages <= 0)
-		return pdata_mapped_pages;
+	nr_mapped_pages = get_user_pages_fast((unsigned long)data,
+					      *nr_pages, write, pages);
+	if (nr_mapped_pages <= 0)
+		return nr_mapped_pages;
 
-	rpinfo->rp_nr_pages = pdata_mapped_pages;
-	if (*pdata_off) {
-		*pdata_len = first_page_bytes;
-		*pdata_len += min((req->tc->pbuf_size - *pdata_len),
-				((size_t)pdata_mapped_pages - 1) << PAGE_SHIFT);
-	} else {
-		*pdata_len = min(req->tc->pbuf_size,
-				(size_t)pdata_mapped_pages << PAGE_SHIFT);
-	}
+	*nr_pages = nr_mapped_pages;
 	return 0;
 }
 EXPORT_SYMBOL(p9_payload_gup);

net/9p/trans_common.h

@@ -12,21 +12,6 @@
  *
  */
 
-/* TRUE if it is user context */
-#define P9_IS_USER_CONTEXT (!segment_eq(get_fs(), KERNEL_DS))
-
-/**
- * struct trans_rpage_info - To store mapped page information in PDU.
- * @rp_alloc:Set if this structure is allocd, not a reuse unused space in pdu.
- * @rp_nr_pages: Number of mapped pages
- * @rp_data: Array of page pointers
- */
-struct trans_rpage_info {
-	u8 rp_alloc;
-	int rp_nr_pages;
-	struct page *rp_data[0];
-};
-
-void p9_release_req_pages(struct trans_rpage_info *);
-int p9_payload_gup(struct p9_req_t *, size_t *, int *, int, u8);
-int p9_nr_pages(struct p9_req_t *);
+void p9_release_pages(struct page **, int);
+int p9_payload_gup(char *, int *, struct page **, int);
+int p9_nr_pages(char *, int);