Merge tag '9p-for-4.20' of git://github.com/martinetd/linux

Pull 9p updates from Dominique Martinet:
 "Highlights this time around are the end of Matthew's work to remove
  the custom 9p request cache and use a slab directly for requests, with
  some extra patches on my end to not degrade performance, but it's a
  very good cleanup.

  Tomas and I fixed a few more syzkaller bugs (refcount is the big one),
  and I had a go at the coverity bugs and at some of the bugzilla
  reports we had open for a while.

  I'm a bit disappointed that I couldn't get much reviews for a few of
  my own patches, but the big ones got some and it's all been soaking in
  linux-next for quite a while so I think it should be OK.

  Summary:

   - Finish removing the custom 9p request cache mechanism

   - Embed part of the fcall in the request to have better slab
     performance (msize usually is power of two aligned)

   - syzkaller fixes:
      * add a refcount to 9p requests to avoid use after free
      * a few double free issues

   - A few coverity fixes

   - Some old patches that were in the bugzilla:
      * do not trust pdu content for size header
      * mount option for lock retry interval"

* tag '9p-for-4.20' of git://github.com/martinetd/linux: (21 commits)
  9p/trans_fd: put worker reqs on destroy
  9p/trans_fd: abort p9_read_work if req status changed
  9p: potential NULL dereference
  9p locks: fix glock.client_id leak in do_lock
  9p: p9dirent_read: check network-provided name length
  9p/rdma: remove useless check in cm_event_handler
  9p: acl: fix uninitialized iattr access
  9p locks: add mount option for lock retry interval
  9p: do not trust pdu content for stat item size
  9p: Rename req to rreq in trans_fd
  9p: fix spelling mistake in fall-through annotation
  9p/rdma: do not disconnect on down_interruptible EAGAIN
  9p: Add refcount to p9_req_t
  9p: rename p9_free_req() function
  9p: add a per-client fcall kmem_cache
  9p: embed fcall in req to round down buffer allocs
  9p: Remove p9_idpool
  9p: Use a slab for allocating requests
  9p: clear dangling pointers in p9stat_free
  v9fs_dir_readdir: fix double-free on p9stat_read error
  ...

fs/9p/acl.c

@@ -276,7 +276,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
 	switch (handler->flags) {
 	case ACL_TYPE_ACCESS:
 		if (acl) {
-			struct iattr iattr;
+			struct iattr iattr = { 0 };
 			struct posix_acl *old_acl = acl;
 
 			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);

fs/9p/v9fs.c

@@ -61,6 +61,8 @@ enum {
 	Opt_cache_loose, Opt_fscache, Opt_mmap,
 	/* Access options */
 	Opt_access, Opt_posixacl,
+	/* Lock timeout option */
+	Opt_locktimeout,
 	/* Error token */
 	Opt_err
 };
@@ -80,6 +82,7 @@ static const match_table_t tokens = {
 	{Opt_cachetag, "cachetag=%s"},
 	{Opt_access, "access=%s"},
 	{Opt_posixacl, "posixacl"},
+	{Opt_locktimeout, "locktimeout=%u"},
 	{Opt_err, NULL}
 };
 
@@ -187,6 +190,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 #ifdef CONFIG_9P_FSCACHE
 	v9ses->cachetag = NULL;
 #endif
+	v9ses->session_lock_timeout = P9_LOCK_TIMEOUT;
 
 	if (!opts)
 		return 0;
@@ -359,6 +363,23 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 #endif
 			break;
 
+		case Opt_locktimeout:
+			r = match_int(&args[0], &option);
+			if (r < 0) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "integer field, but no integer?\n");
+				ret = r;
+				continue;
+			}
+			if (option < 1) {
+				p9_debug(P9_DEBUG_ERROR,
+					 "locktimeout must be a greater than zero integer.\n");
+				ret = -EINVAL;
+				continue;
+			}
+			v9ses->session_lock_timeout = (long)option * HZ;
+			break;
+
 		default:
 			continue;
 		}

fs/9p/v9fs.h

@@ -116,6 +116,7 @@ struct v9fs_session_info {
 	struct p9_client *clnt;	/* 9p client */
 	struct list_head slist; /* list of sessions registered with v9fs */
 	struct rw_semaphore rename_sem;
+	long session_lock_timeout; /* retry interval for blocking locks */
 };
 
 /* cache_validity flags */

fs/9p/vfs_dir.c

@@ -76,15 +76,6 @@ static inline int dt_type(struct p9_wstat *mistat)
 	return rettype;
 }
 
-static void p9stat_init(struct p9_wstat *stbuf)
-{
-	stbuf->name  = NULL;
-	stbuf->uid   = NULL;
-	stbuf->gid   = NULL;
-	stbuf->muid  = NULL;
-	stbuf->extension = NULL;
-}
-
 /**
  * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir
  * @filp: opened file structure
@@ -114,7 +105,6 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 	int err = 0;
 	struct p9_fid *fid;
 	int buflen;
-	int reclen = 0;
 	struct p9_rdir *rdir;
 	struct kvec kvec;
 
@@ -145,15 +135,12 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 			rdir->tail = n;
 		}
 		while (rdir->head < rdir->tail) {
-			p9stat_init(&st);
 			err = p9stat_read(fid->clnt, rdir->buf + rdir->head,
 					  rdir->tail - rdir->head, &st);
-			if (err) {
+			if (err <= 0) {
 				p9_debug(P9_DEBUG_VFS, "returned %d\n", err);
-				p9stat_free(&st);
 				return -EIO;
 			}
-			reclen = st.size+2;
 
 			over = !dir_emit(ctx, st.name, strlen(st.name),
 					 v9fs_qid2ino(&st.qid), dt_type(&st));
@@ -161,8 +148,8 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx)
 			if (over)
 				return 0;
 
-			rdir->head += reclen;
-			ctx->pos += reclen;
+			rdir->head += err;
+			ctx->pos += err;
 		}
 	}
 }

fs/9p/vfs_file.c

@@ -154,6 +154,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	uint8_t status = P9_LOCK_ERROR;
 	int res = 0;
 	unsigned char fl_type;
+	struct v9fs_session_info *v9ses;
 
 	fid = filp->private_data;
 	BUG_ON(fid == NULL);
@@ -189,6 +190,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 	if (IS_SETLKW(cmd))
 		flock.flags = P9_LOCK_FLAGS_BLOCK;
 
+	v9ses = v9fs_inode2v9ses(file_inode(filp));
+
 	/*
 	 * if its a blocked request and we get P9_LOCK_BLOCKED as the status
 	 * for lock request, keep on trying
@@ -202,8 +205,17 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 			break;
 		if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
 			break;
-		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
+		if (schedule_timeout_interruptible(v9ses->session_lock_timeout)
+				!= 0)
 			break;
+		/*
+		 * p9_client_lock_dotl overwrites flock.client_id with the
+		 * server message, free and reuse the client name
+		 */
+		if (flock.client_id != fid->clnt->name) {
+			kfree(flock.client_id);
+			flock.client_id = fid->clnt->name;
+		}
 	}
 
 	/* map 9p status to VFS status */
@@ -216,7 +228,7 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		break;
 	default:
 		WARN_ONCE(1, "unknown lock status code: %d\n", status);
-		/* fallthough */
+		/* fall through */
 	case P9_LOCK_ERROR:
 	case P9_LOCK_GRACE:
 		res = -ENOLCK;
@@ -235,6 +247,8 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
 		locks_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
+	if (flock.client_id != fid->clnt->name)
+		kfree(flock.client_id);
 out:
 	return res;
 }
@@ -269,7 +283,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 
 	res = p9_client_getlock_dotl(fid, &glock);
 	if (res < 0)
-		return res;
+		goto out;
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:
@@ -290,7 +304,9 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
 			fl->fl_end = glock.start + glock.length - 1;
 		fl->fl_pid = -glock.proc_id;
 	}
-	kfree(glock.client_id);
+out:
+	if (glock.client_id != fid->clnt->name)
+		kfree(glock.client_id);
 	return res;
 }
 

include/net/9p/9p.h

@@ -336,6 +336,9 @@ enum p9_qid_t {
 #define P9_NOFID	(u32)(~0)
 #define P9_MAXWELEM	16
 
+/* Minimal header size: size[4] type[1] tag[2] */
+#define P9_HDRSZ	7
+
 /* ample room for Twrite/Rread header */
 #define P9_IOHDRSZ	24
 
@@ -558,19 +561,12 @@ struct p9_fcall {
 	size_t offset;
 	size_t capacity;
 
+	struct kmem_cache *cache;
 	u8 *sdata;
 };
 
-struct p9_idpool;
-
 int p9_errstr2errno(char *errstr, int len);
 
-struct p9_idpool *p9_idpool_create(void);
-void p9_idpool_destroy(struct p9_idpool *);
-int p9_idpool_get(struct p9_idpool *p);
-void p9_idpool_put(int id, struct p9_idpool *p);
-int p9_idpool_check(int id, struct p9_idpool *p);
-
 int p9_error_init(void);
 int p9_trans_fd_init(void);
 void p9_trans_fd_exit(void);

include/net/9p/client.h

@@ -64,22 +64,15 @@ enum p9_trans_status {
 
 /**
  * enum p9_req_status_t - status of a request
- * @REQ_STATUS_IDLE: request slot unused
  * @REQ_STATUS_ALLOC: request has been allocated but not sent
  * @REQ_STATUS_UNSENT: request waiting to be sent
  * @REQ_STATUS_SENT: request sent to server
  * @REQ_STATUS_RCVD: response received from server
  * @REQ_STATUS_FLSHD: request has been flushed
  * @REQ_STATUS_ERROR: request encountered an error on the client side
- *
- * The @REQ_STATUS_IDLE state is used to mark a request slot as unused
- * but use is actually tracked by the idpool structure which handles tag
- * id allocation.
- *
  */
 
 enum p9_req_status_t {
-	REQ_STATUS_IDLE,
 	REQ_STATUS_ALLOC,
 	REQ_STATUS_UNSENT,
 	REQ_STATUS_SENT,
@@ -92,70 +85,46 @@ enum p9_req_status_t {
  * struct p9_req_t - request slots
  * @status: status of this request slot
  * @t_err: transport error
- * @flush_tag: tag of request being flushed (for flush requests)
  * @wq: wait_queue for the client to block on for this request
  * @tc: the request fcall structure
  * @rc: the response fcall structure
  * @aux: transport specific data (provided for trans_fd migration)
  * @req_list: link for higher level objects to chain requests
- *
- * Transport use an array to track outstanding requests
- * instead of a list.  While this may incurr overhead during initial
- * allocation or expansion, it makes request lookup much easier as the
- * tag id is a index into an array.  (We use tag+1 so that we can accommodate
- * the -1 tag for the T_VERSION request).
- * This also has the nice effect of only having to allocate wait_queues
- * once, instead of constantly allocating and freeing them.  Its possible
- * other resources could benefit from this scheme as well.
- *
  */
-
 struct p9_req_t {
 	int status;
 	int t_err;
+	struct kref refcount;
 	wait_queue_head_t wq;
-	struct p9_fcall *tc;
-	struct p9_fcall *rc;
+	struct p9_fcall tc;
+	struct p9_fcall rc;
 	void *aux;
-
 	struct list_head req_list;
 };
 
 /**
  * struct p9_client - per client instance state
- * @lock: protect @fidlist
+ * @lock: protect @fids and @reqs
  * @msize: maximum data size negotiated by protocol
- * @dotu: extension flags negotiated by protocol
  * @proto_version: 9P protocol version to use
  * @trans_mod: module API instantiated with this client
+ * @status: connection state
  * @trans: tranport instance state and API
  * @fids: All active FID handles
- * @tagpool - transaction id accounting for session
- * @reqs - 2D array of requests
- * @max_tag - current maximum tag id allocated
- * @name - node name used as client id
+ * @reqs: All active requests.
+ * @name: node name used as client id
  *
  * The client structure is used to keep track of various per-client
  * state that has been instantiated.
- * In order to minimize per-transaction overhead we use a
- * simple array to lookup requests instead of a hash table
- * or linked list.  In order to support larger number of
- * transactions, we make this a 2D array, allocating new rows
- * when we need to grow the total number of the transactions.
- *
- * Each row is 256 requests and we'll support up to 256 rows for
- * a total of 64k concurrent requests per session.
- *
- * Bugs: duplicated data and potentially unnecessary elements.
  */
-
 struct p9_client {
-	spinlock_t lock; /* protect client structure */
+	spinlock_t lock;
 	unsigned int msize;
 	unsigned char proto_version;
 	struct p9_trans_module *trans_mod;
 	enum p9_trans_status status;
 	void *trans;
+	struct kmem_cache *fcall_cache;
 
 	union {
 		struct {
@@ -170,10 +139,7 @@ struct p9_client {
 	} trans_opts;
 
 	struct idr fids;
-
-	struct p9_idpool *tagpool;
-	struct p9_req_t *reqs[P9_ROW_MAXTAG];
-	int max_tag;
+	struct idr reqs;
 
 	char name[__NEW_UTS_LEN + 1];
 };
@@ -266,7 +232,21 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 				kgid_t gid, struct p9_qid *);
 int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status);
 int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl);
+void p9_fcall_fini(struct p9_fcall *fc);
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
+
+static inline void p9_req_get(struct p9_req_t *r)
+{
+	kref_get(&r->refcount);
+}
+
+static inline int p9_req_try_get(struct p9_req_t *r)
+{
+	return kref_get_unless_zero(&r->refcount);
+}
+
+int p9_req_put(struct p9_req_t *r);
+
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status);
 
 int p9_parse_header(struct p9_fcall *, int32_t *, int8_t *, int16_t *, int);
@@ -279,4 +259,7 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *, const char *, u64 *);
 int p9_client_xattrcreate(struct p9_fid *, const char *, u64, int);
 int p9_client_readlink(struct p9_fid *fid, char **target);
 
+int p9_client_init(void);
+void p9_client_exit(void);
+
 #endif /* NET_9P_CLIENT_H */

net/9p/Makefile

@@ -8,7 +8,6 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 	mod.o \
 	client.o \
 	error.o \
-	util.o \
 	protocol.o \
 	trans_fd.o \
 	trans_common.o \

net/9p/client.c

@@ -231,144 +231,170 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	return ret;
 }
 
-static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc,
+			 int alloc_msize)
 {
-	struct p9_fcall *fc;
-	fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
-	if (!fc)
-		return NULL;
+	if (likely(c->fcall_cache) && alloc_msize == c->msize) {
+		fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS);
+		fc->cache = c->fcall_cache;
+	} else {
+		fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
+		fc->cache = NULL;
+	}
+	if (!fc->sdata)
+		return -ENOMEM;
 	fc->capacity = alloc_msize;
-	fc->sdata = (char *) fc + sizeof(struct p9_fcall);
-	return fc;
+	return 0;
+}
+
+void p9_fcall_fini(struct p9_fcall *fc)
+{
+	/* sdata can be NULL for interrupted requests in trans_rdma,
+	 * and kmem_cache_free does not do NULL-check for us
+	 */
+	if (unlikely(!fc->sdata))
+		return;
+
+	if (fc->cache)
+		kmem_cache_free(fc->cache, fc->sdata);
+	else
+		kfree(fc->sdata);
 }
+EXPORT_SYMBOL(p9_fcall_fini);
+
+static struct kmem_cache *p9_req_cache;
 
 /**
- * p9_tag_alloc - lookup/allocate a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
- *
- * this is a simple array lookup, but will grow the
- * request_slots as necessary to accommodate transaction
- * ids which did not previously have a slot.
- *
- * this code relies on the client spinlock to manage locks, its
- * possible we should switch to something else, but I'd rather
- * stick with something low-overhead for the common case.
+ * p9_req_alloc - Allocate a new request.
+ * @c: Client session.
+ * @type: Transaction type.
+ * @max_size: Maximum packet size for this request.
  *
+ * Context: Process context.
+ * Return: Pointer to new request.
  */
-
 static struct p9_req_t *
-p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size)
+p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
 {
-	unsigned long flags;
-	int row, col;
-	struct p9_req_t *req;
+	struct p9_req_t *req = kmem_cache_alloc(p9_req_cache, GFP_NOFS);
 	int alloc_msize = min(c->msize, max_size);
+	int tag;
 
-	/* This looks up the original request by tag so we know which
-	 * buffer to read the data into */
-	tag++;
-
-	if (tag >= c->max_tag) {
-		spin_lock_irqsave(&c->lock, flags);
-		/* check again since original check was outside of lock */
-		while (tag >= c->max_tag) {
-			row = (tag / P9_ROW_MAXTAG);
-			c->reqs[row] = kcalloc(P9_ROW_MAXTAG,
-					sizeof(struct p9_req_t), GFP_ATOMIC);
-
-			if (!c->reqs[row]) {
-				pr_err("Couldn't grow tag array\n");
-				spin_unlock_irqrestore(&c->lock, flags);
-				return ERR_PTR(-ENOMEM);
-			}
-			for (col = 0; col < P9_ROW_MAXTAG; col++) {
-				req = &c->reqs[row][col];
-				req->status = REQ_STATUS_IDLE;
-				init_waitqueue_head(&req->wq);
-			}
-			c->max_tag += P9_ROW_MAXTAG;
-		}
-		spin_unlock_irqrestore(&c->lock, flags);
-	}
-	row = tag / P9_ROW_MAXTAG;
-	col = tag % P9_ROW_MAXTAG;
-
-	req = &c->reqs[row][col];
-	if (!req->tc)
-		req->tc = p9_fcall_alloc(alloc_msize);
-	if (!req->rc)
-		req->rc = p9_fcall_alloc(alloc_msize);
-	if (!req->tc || !req->rc)
-		goto grow_failed;
+	if (!req)
+		return ERR_PTR(-ENOMEM);
 
-	p9pdu_reset(req->tc);
-	p9pdu_reset(req->rc);
+	if (p9_fcall_init(c, &req->tc, alloc_msize))
+		goto free_req;
+	if (p9_fcall_init(c, &req->rc, alloc_msize))
+		goto free;
 
-	req->tc->tag = tag-1;
+	p9pdu_reset(&req->tc);
+	p9pdu_reset(&req->rc);
 	req->status = REQ_STATUS_ALLOC;
+	init_waitqueue_head(&req->wq);
+	INIT_LIST_HEAD(&req->req_list);
+
+	idr_preload(GFP_NOFS);
+	spin_lock_irq(&c->lock);
+	if (type == P9_TVERSION)
+		tag = idr_alloc(&c->reqs, req, P9_NOTAG, P9_NOTAG + 1,
+				GFP_NOWAIT);
+	else
+		tag = idr_alloc(&c->reqs, req, 0, P9_NOTAG, GFP_NOWAIT);
+	req->tc.tag = tag;
+	spin_unlock_irq(&c->lock);
+	idr_preload_end();
+	if (tag < 0)
+		goto free;
+
+	/* Init ref to two because in the general case there is one ref
+	 * that is put asynchronously by a writer thread, one ref
+	 * temporarily given by p9_tag_lookup and put by p9_client_cb
+	 * in the recv thread, and one ref put by p9_tag_remove in the
+	 * main thread. The only exception is virtio that does not use
+	 * p9_tag_lookup but does not have a writer thread either
+	 * (the write happens synchronously in the request/zc_request
+	 * callback), so p9_client_cb eats the second ref there
+	 * as the pointer is duplicated directly by virtqueue_add_sgs()
+	 */
+	refcount_set(&req->refcount.refcount, 2);
 
 	return req;
 
-grow_failed:
-	pr_err("Couldn't grow tag array\n");
-	kfree(req->tc);
-	kfree(req->rc);
-	req->tc = req->rc = NULL;
+free:
+	p9_fcall_fini(&req->tc);
+	p9_fcall_fini(&req->rc);
+free_req:
+	kmem_cache_free(p9_req_cache, req);
 	return ERR_PTR(-ENOMEM);
 }
 
 /**
- * p9_tag_lookup - lookup a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
+ * p9_tag_lookup - Look up a request by tag.
+ * @c: Client session.
+ * @tag: Transaction ID.
  *
+ * Context: Any context.
+ * Return: A request, or %NULL if there is no request with that tag.
  */
-
 struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
 {
-	int row, col;
-
-	/* This looks up the original request by tag so we know which
-	 * buffer to read the data into */
-	tag++;
-
-	if (tag >= c->max_tag)
-		return NULL;
+	struct p9_req_t *req;
 
-	row = tag / P9_ROW_MAXTAG;
-	col = tag % P9_ROW_MAXTAG;
+	rcu_read_lock();
+again:
+	req = idr_find(&c->reqs, tag);
+	if (req) {
+		/* We have to be careful with the req found under rcu_read_lock
+		 * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the
+		 * ref again without corrupting other data, then check again
+		 * that the tag matches once we have the ref
+		 */
+		if (!p9_req_try_get(req))
+			goto again;
+		if (req->tc.tag != tag) {
+			p9_req_put(req);
+			goto again;
+		}
+	}
+	rcu_read_unlock();
 
-	return &c->reqs[row][col];
+	return req;
 }
 EXPORT_SYMBOL(p9_tag_lookup);
 
 /**
- * p9_tag_init - setup tags structure and contents
- * @c:  v9fs client struct
- *
- * This initializes the tags structure for each client instance.
+ * p9_tag_remove - Remove a tag.
+ * @c: Client session.
+ * @r: Request of reference.
  *
+ * Context: Any context.
  */
+static int p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
+{
+	unsigned long flags;
+	u16 tag = r->tc.tag;
+
+	p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
+	spin_lock_irqsave(&c->lock, flags);
+	idr_remove(&c->reqs, tag);
+	spin_unlock_irqrestore(&c->lock, flags);
+	return p9_req_put(r);
+}
 
-static int p9_tag_init(struct p9_client *c)
+static void p9_req_free(struct kref *ref)
 {
-	int err = 0;
+	struct p9_req_t *r = container_of(ref, struct p9_req_t, refcount);
+	p9_fcall_fini(&r->tc);
+	p9_fcall_fini(&r->rc);
+	kmem_cache_free(p9_req_cache, r);
+}
 
-	c->tagpool = p9_idpool_create();
-	if (IS_ERR(c->tagpool)) {
-		err = PTR_ERR(c->tagpool);
-		goto error;
-	}
-	err = p9_idpool_get(c->tagpool); /* reserve tag 0 */
-	if (err < 0) {
-		p9_idpool_destroy(c->tagpool);
-		goto error;
-	}
-	c->max_tag = 0;
-error:
-	return err;
+int p9_req_put(struct p9_req_t *r)
+{
+	return kref_put(&r->refcount, p9_req_free);
 }
+EXPORT_SYMBOL(p9_req_put);
 
 /**
  * p9_tag_cleanup - cleans up tags structure and reclaims resources
@@ -379,52 +405,17 @@ static int p9_tag_init(struct p9_client *c)
  */
 static void p9_tag_cleanup(struct p9_client *c)
 {
-	int row, col;
-
-	/* check to insure all requests are idle */
-	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
-		for (col = 0; col < P9_ROW_MAXTAG; col++) {
-			if (c->reqs[row][col].status != REQ_STATUS_IDLE) {
-				p9_debug(P9_DEBUG_MUX,
-					 "Attempting to cleanup non-free tag %d,%d\n",
-					 row, col);
-				/* TODO: delay execution of cleanup */
-				return;
-			}
-		}
-	}
-
-	if (c->tagpool) {
-		p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */
-		p9_idpool_destroy(c->tagpool);
-	}
+	struct p9_req_t *req;
+	int id;
 
-	/* free requests associated with tags */
-	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
-		for (col = 0; col < P9_ROW_MAXTAG; col++) {
-			kfree(c->reqs[row][col].tc);
-			kfree(c->reqs[row][col].rc);
-		}
-		kfree(c->reqs[row]);
+	rcu_read_lock();
+	idr_for_each_entry(&c->reqs, req, id) {
+		pr_info("Tag %d still in use\n", id);
+		if (p9_tag_remove(c, req) == 0)
+			pr_warn("Packet with tag %d has still references",
+				req->tc.tag);
 	}
-	c->max_tag = 0;
-}
-
-/**
- * p9_free_req - free a request and clean-up as necessary
- * c: client state
- * r: request to release
- *
- */
-
-static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
-{
-	int tag = r->tc->tag;
-	p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
-
-	r->status = REQ_STATUS_IDLE;
-	if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool))
-		p9_idpool_put(tag, c->tagpool);
+	rcu_read_unlock();
 }
 
 /**
@@ -435,7 +426,7 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
  */
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 {
-	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
+	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag);
 
 	/*
 	 * This barrier is needed to make sure any change made to req before
@@ -445,7 +436,8 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 	req->status = status;
 
 	wake_up(&req->wq);
-	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
+	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag);
+	p9_req_put(req);
 }
 EXPORT_SYMBOL(p9_client_cb);
 
@@ -516,18 +508,18 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 	int err;
 	int ecode;
 
-	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
-	if (req->rc->size >= c->msize) {
+	err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
+	if (req->rc.size >= c->msize) {
 		p9_debug(P9_DEBUG_ERROR,
 			 "requested packet size too big: %d\n",
-			 req->rc->size);
+			 req->rc.size);
 		return -EIO;
 	}
 	/*
 	 * dump the response from server
 	 * This should be after check errors which poplulate pdu_fcall.
 	 */
-	trace_9p_protocol_dump(c, req->rc);
+	trace_9p_protocol_dump(c, &req->rc);
 	if (err) {
 		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
 		return err;
@@ -537,7 +529,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 
 	if (!p9_is_proto_dotl(c)) {
 		char *ename;
-		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+		err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
 				  &ename, &ecode);
 		if (err)
 			goto out_err;
@@ -553,7 +545,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		}
 		kfree(ename);
 	} else {
-		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
 		err = -ecode;
 
 		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -587,12 +579,12 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 	int8_t type;
 	char *ename = NULL;
 
-	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+	err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
 	/*
 	 * dump the response from server
 	 * This should be after parse_header which poplulate pdu_fcall.
 	 */
-	trace_9p_protocol_dump(c, req->rc);
+	trace_9p_protocol_dump(c, &req->rc);
 	if (err) {
 		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
 		return err;
@@ -607,13 +599,13 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		/* 7 = header size for RERROR; */
 		int inline_len = in_hdrlen - 7;
 
-		len =  req->rc->size - req->rc->offset;
+		len = req->rc.size - req->rc.offset;
 		if (len > (P9_ZC_HDR_SZ - 7)) {
 			err = -EFAULT;
 			goto out_err;
 		}
 
-		ename = &req->rc->sdata[req->rc->offset];
+		ename = &req->rc.sdata[req->rc.offset];
 		if (len > inline_len) {
 			/* We have error in external buffer */
 			if (!copy_from_iter_full(ename + inline_len,
@@ -623,7 +615,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 			}
 		}
 		ename = NULL;
-		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+		err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
 				  &ename, &ecode);
 		if (err)
 			goto out_err;
@@ -639,7 +631,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		}
 		kfree(ename);
 	} else {
-		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
 		err = -ecode;
 
 		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -672,7 +664,7 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	int16_t oldtag;
 	int err;
 
-	err = p9_parse_header(oldreq->tc, NULL, NULL, &oldtag, 1);
+	err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1);
 	if (err)
 		return err;
 
@@ -686,11 +678,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	 * if we haven't received a response for oldreq,
 	 * remove it from the list
 	 */
-	if (oldreq->status == REQ_STATUS_SENT)
+	if (oldreq->status == REQ_STATUS_SENT) {
 		if (c->trans_mod->cancelled)
 			c->trans_mod->cancelled(c, oldreq);
+	}
 
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return 0;
 }
 
@@ -698,7 +691,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 					      int8_t type, int req_size,
 					      const char *fmt, va_list ap)
 {
-	int tag, err;
+	int err;
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type);
@@ -711,27 +704,22 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 	if ((c->status == BeginDisconnect) && (type != P9_TCLUNK))
 		return ERR_PTR(-EIO);
 
-	tag = P9_NOTAG;
-	if (type != P9_TVERSION) {
-		tag = p9_idpool_get(c->tagpool);
-		if (tag < 0)
-			return ERR_PTR(-ENOMEM);
-	}
-
-	req = p9_tag_alloc(c, tag, req_size);
+	req = p9_tag_alloc(c, type, req_size);
 	if (IS_ERR(req))
 		return req;
 
 	/* marshall the data */
-	p9pdu_prepare(req->tc, tag, type);
-	err = p9pdu_vwritef(req->tc, c->proto_version, fmt, ap);
+	p9pdu_prepare(&req->tc, req->tc.tag, type);
+	err = p9pdu_vwritef(&req->tc, c->proto_version, fmt, ap);
 	if (err)
 		goto reterr;
-	p9pdu_finalize(c, req->tc);
-	trace_9p_client_req(c, type, tag);
+	p9pdu_finalize(c, &req->tc);
+	trace_9p_client_req(c, type, req->tc.tag);
 	return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
+	/* We have to put also the 2nd reference as it won't be used */
+	p9_req_put(req);
 	return ERR_PTR(err);
 }
 
@@ -741,7 +729,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
  * @type: type of request
  * @fmt: protocol format string (see protocol.c)
  *
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
  */
 
 static struct p9_req_t *
@@ -766,6 +754,8 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 
 	err = c->trans_mod->request(c, req);
 	if (err < 0) {
+		/* write won't happen */
+		p9_req_put(req);
 		if (err != -ERESTARTSYS && err != -EFAULT)
 			c->status = Disconnected;
 		goto recalc_sigpending;
@@ -813,11 +803,11 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 		goto reterr;
 
 	err = p9_check_errors(c, req);
-	trace_9p_client_res(c, type, req->rc->tag, err);
+	trace_9p_client_res(c, type, req->rc.tag, err);
 	if (!err)
 		return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return ERR_PTR(safe_errno(err));
 }
 
@@ -832,7 +822,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
  * @hdrlen: reader header size, This is the size of response protocol data
  * @fmt: protocol format string (see protocol.c)
  *
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
  */
 static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 					 struct iov_iter *uidata,
@@ -895,11 +885,11 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 		goto reterr;
 
 	err = p9_check_zc_errors(c, req, uidata, in_hdrlen);
-	trace_9p_client_res(c, type, req->rc->tag, err);
+	trace_9p_client_res(c, type, req->rc.tag, err);
 	if (!err)
 		return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return ERR_PTR(safe_errno(err));
 }
 
@@ -978,10 +968,10 @@ static int p9_client_version(struct p9_client *c)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, c->proto_version, "ds", &msize, &version);
+	err = p9pdu_readf(&req->rc, c->proto_version, "ds", &msize, &version);
 	if (err) {
 		p9_debug(P9_DEBUG_9P, "version error %d\n", err);
-		trace_9p_protocol_dump(c, req->rc);
+		trace_9p_protocol_dump(c, &req->rc);
 		goto error;
 	}
 
@@ -1002,7 +992,7 @@ static int p9_client_version(struct p9_client *c)
 
 error:
 	kfree(version);
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 
 	return err;
 }
@@ -1020,20 +1010,18 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 
 	clnt->trans_mod = NULL;
 	clnt->trans = NULL;
+	clnt->fcall_cache = NULL;
 
 	client_id = utsname()->nodename;
 	memcpy(clnt->name, client_id, strlen(client_id) + 1);
 
 	spin_lock_init(&clnt->lock);
 	idr_init(&clnt->fids);
-
-	err = p9_tag_init(clnt);
-	if (err < 0)
-		goto free_client;
+	idr_init(&clnt->reqs);
 
 	err = parse_opts(options, clnt);
 	if (err < 0)
-		goto destroy_tagpool;
+		goto free_client;
 
 	if (!clnt->trans_mod)
 		clnt->trans_mod = v9fs_get_default_trans();
@@ -1042,7 +1030,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		err = -EPROTONOSUPPORT;
 		p9_debug(P9_DEBUG_ERROR,
 			 "No transport defined or default transport\n");
-		goto destroy_tagpool;
+		goto free_client;
 	}
 
 	p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n",
@@ -1059,14 +1047,21 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 	if (err)
 		goto close_trans;
 
+	/* P9_HDRSZ + 4 is the smallest packet header we can have that is
+	 * followed by data accessed from userspace by read
+	 */
+	clnt->fcall_cache =
+		kmem_cache_create_usercopy("9p-fcall-cache", clnt->msize,
+					   0, 0, P9_HDRSZ + 4,
+					   clnt->msize - (P9_HDRSZ + 4),
+					   NULL);
+
 	return clnt;
 
 close_trans:
 	clnt->trans_mod->close(clnt);
 put_trans:
 	v9fs_put_trans(clnt->trans_mod);
-destroy_tagpool:
-	p9_idpool_destroy(clnt->tagpool);
 free_client:
 	kfree(clnt);
 	return ERR_PTR(err);
@@ -1092,6 +1087,7 @@ void p9_client_destroy(struct p9_client *clnt)
 
 	p9_tag_cleanup(clnt);
 
+	kmem_cache_destroy(clnt->fcall_cache);
 	kfree(clnt);
 }
 EXPORT_SYMBOL(p9_client_destroy);
@@ -1135,10 +1131,10 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", &qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1147,7 +1143,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 
 	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return fid;
 
 error:
@@ -1192,13 +1188,13 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "R", &nwqids, &wqids);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "R", &nwqids, &wqids);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto clunk_fid;
 	}
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 
 	p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
 
@@ -1259,9 +1255,9 @@ int p9_client_open(struct p9_fid *fid, int mode)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1273,7 +1269,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 	fid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1303,9 +1299,9 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1318,7 +1314,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 	ofid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1348,9 +1344,9 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1363,7 +1359,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 	fid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1387,9 +1383,9 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1397,7 +1393,7 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
 			qid->type, (unsigned long long)qid->path, qid->version);
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1417,7 +1413,7 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newna
 		return PTR_ERR(req);
 
 	p9_debug(P9_DEBUG_9P, "<<< RLINK\n");
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return 0;
 }
 EXPORT_SYMBOL(p9_client_link);
@@ -1441,7 +1437,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync)
 
 	p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 
 error:
 	return err;
@@ -1476,7 +1472,7 @@ int p9_client_clunk(struct p9_fid *fid)
 
 	p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	/*
 	 * Fid is not valid even after a failed clunk
@@ -1510,7 +1506,7 @@ int p9_client_remove(struct p9_fid *fid)
 
 	p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	if (err == -ERESTARTSYS)
 		p9_client_clunk(fid);
@@ -1537,7 +1533,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags)
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1585,11 +1581,11 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			break;
 		}
 
-		*err = p9pdu_readf(req->rc, clnt->proto_version,
+		*err = p9pdu_readf(&req->rc, clnt->proto_version,
 				   "D", &count, &dataptr);
 		if (*err) {
-			trace_9p_protocol_dump(clnt, req->rc);
-			p9_free_req(clnt, req);
+			trace_9p_protocol_dump(clnt, &req->rc);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 		if (rsize < count) {
@@ -1599,7 +1595,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 
 		p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 		if (!count) {
-			p9_free_req(clnt, req);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 
@@ -1609,7 +1605,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			offset += n;
 			if (n != count) {
 				*err = -EFAULT;
-				p9_free_req(clnt, req);
+				p9_tag_remove(clnt, req);
 				break;
 			}
 		} else {
@@ -1617,7 +1613,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			total += count;
 			offset += count;
 		}
-		p9_free_req(clnt, req);
+		p9_tag_remove(clnt, req);
 	}
 	return total;
 }
@@ -1658,10 +1654,10 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 			break;
 		}
 
-		*err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count);
+		*err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &count);
 		if (*err) {
-			trace_9p_protocol_dump(clnt, req->rc);
-			p9_free_req(clnt, req);
+			trace_9p_protocol_dump(clnt, &req->rc);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 		if (rsize < count) {
@@ -1671,7 +1667,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 
 		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
-		p9_free_req(clnt, req);
+		p9_tag_remove(clnt, req);
 		iov_iter_advance(from, count);
 		total += count;
 		offset += count;
@@ -1702,10 +1698,10 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "wS", &ignored, ret);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "wS", &ignored, ret);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1722,7 +1718,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 		from_kgid(&init_user_ns, ret->n_gid),
 		from_kuid(&init_user_ns, ret->n_muid));
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return ret;
 
 error:
@@ -1755,10 +1751,10 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "A", ret);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "A", ret);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1783,7 +1779,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 		ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec,
 		ret->st_gen, ret->st_data_version);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return ret;
 
 error:
@@ -1852,7 +1848,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 
 	p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1884,7 +1880,7 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr)
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid);
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1907,12 +1903,12 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
-		&sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
-		&sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
+			  &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
+			  &sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1923,7 +1919,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
 		sb->blocks, sb->bfree, sb->bavail, sb->files,  sb->ffree,
 		sb->fsid, (long int)sb->namelen);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1951,7 +1947,7 @@ int p9_client_rename(struct p9_fid *fid,
 
 	p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1981,7 +1977,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
 	p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n",
 		   newdirfid->fid, new_name);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2015,13 +2011,13 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
 		err = PTR_ERR(req);
 		goto error;
 	}
-	err = p9pdu_readf(req->rc, clnt->proto_version, "q", attr_size);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "q", attr_size);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto clunk_fid;
 	}
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	p9_debug(P9_DEBUG_9P, "<<<  RXATTRWALK fid %d size %llu\n",
 		attr_fid->fid, *attr_size);
 	return attr_fid;
@@ -2055,7 +2051,7 @@ int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid);
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2103,9 +2099,9 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &count, &dataptr);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 	if (rsize < count) {
@@ -2118,11 +2114,11 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	if (non_zc)
 		memmove(data, dataptr, count);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return count;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2144,16 +2140,16 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type,
 				(unsigned long long)qid->path, qid->version);
 
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2175,16 +2171,16 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type,
 				(unsigned long long)qid->path, qid->version);
 
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2210,14 +2206,14 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "b", status);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "b", status);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2241,18 +2237,18 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "bqqds", &glock->type,
-			&glock->start, &glock->length, &glock->proc_id,
-			&glock->client_id);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "bqqds", &glock->type,
+			  &glock->start, &glock->length, &glock->proc_id,
+			  &glock->client_id);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld "
 		"proc_id %d client_id %s\n", glock->type, glock->start,
 		glock->length, glock->proc_id, glock->client_id);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_getlock_dotl);
@@ -2271,14 +2267,25 @@ int p9_client_readlink(struct p9_fid *fid, char **target)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "s", target);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "s", target);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_readlink);
+
+int __init p9_client_init(void)
+{
+	p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU);
+	return p9_req_cache ? 0 : -ENOMEM;
+}
+
+void __exit p9_client_exit(void)
+{
+	kmem_cache_destroy(p9_req_cache);
+}

net/9p/mod.c

@@ -171,11 +171,17 @@ void v9fs_put_trans(struct p9_trans_module *m)
  */
 static int __init init_p9(void)
 {
+	int ret;
+
+	ret = p9_client_init();
+	if (ret)
+		return ret;
+
 	p9_error_init();
 	pr_info("Installing 9P2000 support\n");
 	p9_trans_fd_init();
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -188,6 +194,7 @@ static void __exit exit_p9(void)
 	pr_info("Unloading 9P2000 support\n");
 
 	p9_trans_fd_exit();
+	p9_client_exit();
 }
 
 module_init(init_p9)

net/9p/protocol.c

@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
+	stbuf->name = NULL;
 	kfree(stbuf->uid);
+	stbuf->uid = NULL;
 	kfree(stbuf->gid);
+	stbuf->gid = NULL;
 	kfree(stbuf->muid);
+	stbuf->muid = NULL;
 	kfree(stbuf->extension);
+	stbuf->extension = NULL;
 }
 EXPORT_SYMBOL(p9stat_free);
 
@@ -566,9 +571,10 @@ int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
 	if (ret) {
 		p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
 		trace_9p_protocol_dump(clnt, &fake_pdu);
+		return ret;
 	}
 
-	return ret;
+	return fake_pdu.offset;
 }
 EXPORT_SYMBOL(p9stat_read);
 
@@ -617,13 +623,19 @@ int p9dirent_read(struct p9_client *clnt, char *buf, int len,
 	if (ret) {
 		p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
 		trace_9p_protocol_dump(clnt, &fake_pdu);
-		goto out;
+		return ret;
 	}
 
-	strcpy(dirent->d_name, nameptr);
+	ret = strscpy(dirent->d_name, nameptr, sizeof(dirent->d_name));
+	if (ret < 0) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "On the wire dirent name too long: %s\n",
+			 nameptr);
+		kfree(nameptr);
+		return ret;
+	}
 	kfree(nameptr);
 
-out:
 	return fake_pdu.offset;
 }
 EXPORT_SYMBOL(p9dirent_read);

net/9p/trans_fd.c

@@ -131,7 +131,8 @@ struct p9_conn {
 	int err;
 	struct list_head req_list;
 	struct list_head unsent_req_list;
-	struct p9_req_t *req;
+	struct p9_req_t *rreq;
+	struct p9_req_t *wreq;
 	char tmp_buf[7];
 	struct p9_fcall rc;
 	int wpos;
@@ -291,7 +292,6 @@ static void p9_read_work(struct work_struct *work)
 	__poll_t n;
 	int err;
 	struct p9_conn *m;
-	int status = REQ_STATUS_ERROR;
 
 	m = container_of(work, struct p9_conn, rq);
 
@@ -322,7 +322,7 @@ static void p9_read_work(struct work_struct *work)
 	m->rc.offset += err;
 
 	/* header read in */
-	if ((!m->req) && (m->rc.offset == m->rc.capacity)) {
+	if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) {
 		p9_debug(P9_DEBUG_TRANS, "got new header\n");
 
 		/* Header size */
@@ -346,23 +346,23 @@ static void p9_read_work(struct work_struct *work)
 			 "mux %p pkt: size: %d bytes tag: %d\n",
 			 m, m->rc.size, m->rc.tag);
 
-		m->req = p9_tag_lookup(m->client, m->rc.tag);
-		if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
+		m->rreq = p9_tag_lookup(m->client, m->rc.tag);
+		if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) {
 			p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
 				 m->rc.tag);
 			err = -EIO;
 			goto error;
 		}
 
-		if (m->req->rc == NULL) {
+		if (!m->rreq->rc.sdata) {
 			p9_debug(P9_DEBUG_ERROR,
 				 "No recv fcall for tag %d (req %p), disconnecting!\n",
-				 m->rc.tag, m->req);
-			m->req = NULL;
+				 m->rc.tag, m->rreq);
+			m->rreq = NULL;
 			err = -EIO;
 			goto error;
 		}
-		m->rc.sdata = (char *)m->req->rc + sizeof(struct p9_fcall);
+		m->rc.sdata = m->rreq->rc.sdata;
 		memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity);
 		m->rc.capacity = m->rc.size;
 	}
@@ -370,20 +370,27 @@ static void p9_read_work(struct work_struct *work)
 	/* packet is read in
 	 * not an else because some packets (like clunk) have no payload
 	 */
-	if ((m->req) && (m->rc.offset == m->rc.capacity)) {
+	if ((m->rreq) && (m->rc.offset == m->rc.capacity)) {
 		p9_debug(P9_DEBUG_TRANS, "got new packet\n");
-		m->req->rc->size = m->rc.offset;
+		m->rreq->rc.size = m->rc.offset;
 		spin_lock(&m->client->lock);
-		if (m->req->status != REQ_STATUS_ERROR)
-			status = REQ_STATUS_RCVD;
-		list_del(&m->req->req_list);
-		/* update req->status while holding client->lock  */
-		p9_client_cb(m->client, m->req, status);
+		if (m->rreq->status == REQ_STATUS_SENT) {
+			list_del(&m->rreq->req_list);
+			p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD);
+		} else {
+			spin_unlock(&m->client->lock);
+			p9_debug(P9_DEBUG_ERROR,
+				 "Request tag %d errored out while we were reading the reply\n",
+				 m->rc.tag);
+			err = -EIO;
+			goto error;
+		}
 		spin_unlock(&m->client->lock);
 		m->rc.sdata = NULL;
 		m->rc.offset = 0;
 		m->rc.capacity = 0;
-		m->req = NULL;
+		p9_req_put(m->rreq);
+		m->rreq = NULL;
 	}
 
 end_clear:
@@ -469,9 +476,11 @@ static void p9_write_work(struct work_struct *work)
 		p9_debug(P9_DEBUG_TRANS, "move req %p\n", req);
 		list_move_tail(&req->req_list, &m->req_list);
 
-		m->wbuf = req->tc->sdata;
-		m->wsize = req->tc->size;
+		m->wbuf = req->tc.sdata;
+		m->wsize = req->tc.size;
 		m->wpos = 0;
+		p9_req_get(req);
+		m->wreq = req;
 		spin_unlock(&m->client->lock);
 	}
 
@@ -492,8 +501,11 @@ static void p9_write_work(struct work_struct *work)
 	}
 
 	m->wpos += err;
-	if (m->wpos == m->wsize)
+	if (m->wpos == m->wsize) {
 		m->wpos = m->wsize = 0;
+		p9_req_put(m->wreq);
+		m->wreq = NULL;
+	}
 
 end_clear:
 	clear_bit(Wworksched, &m->wsched);
@@ -663,7 +675,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 	struct p9_conn *m = &ts->conn;
 
 	p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
-		 m, current, req->tc, req->tc->id);
+		 m, current, &req->tc, req->tc.id);
 	if (m->err < 0)
 		return m->err;
 
@@ -694,6 +706,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	if (req->status == REQ_STATUS_UNSENT) {
 		list_del(&req->req_list);
 		req->status = REQ_STATUS_FLSHD;
+		p9_req_put(req);
 		ret = 0;
 	}
 	spin_unlock(&client->lock);
@@ -711,6 +724,7 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 	spin_lock(&client->lock);
 	list_del(&req->req_list);
 	spin_unlock(&client->lock);
+	p9_req_put(req);
 
 	return 0;
 }
@@ -862,7 +876,15 @@ static void p9_conn_destroy(struct p9_conn *m)
 
 	p9_mux_poll_stop(m);
 	cancel_work_sync(&m->rq);
+	if (m->rreq) {
+		p9_req_put(m->rreq);
+		m->rreq = NULL;
+	}
 	cancel_work_sync(&m->wq);
+	if (m->wreq) {
+		p9_req_put(m->wreq);
+		m->wreq = NULL;
+	}
 
 	p9_conn_cancel(m, -ECONNRESET);
 

net/9p/trans_rdma.c

@@ -122,7 +122,7 @@ struct p9_rdma_context {
 	dma_addr_t busa;
 	union {
 		struct p9_req_t *req;
-		struct p9_fcall *rc;
+		struct p9_fcall rc;
 	};
 };
 
@@ -274,8 +274,7 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DISCONNECTED:
 		if (rdma)
 			rdma->state = P9_RDMA_CLOSED;
-		if (c)
-			c->status = Disconnected;
+		c->status = Disconnected;
 		break;
 
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
@@ -320,8 +319,8 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	if (wc->status != IB_WC_SUCCESS)
 		goto err_out;
 
-	c->rc->size = wc->byte_len;
-	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	c->rc.size = wc->byte_len;
+	err = p9_parse_header(&c->rc, NULL, NULL, &tag, 1);
 	if (err)
 		goto err_out;
 
@@ -331,12 +330,13 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	/* Check that we have not yet received a reply for this request.
 	 */
-	if (unlikely(req->rc)) {
+	if (unlikely(req->rc.sdata)) {
 		pr_err("Duplicate reply for request %d", tag);
 		goto err_out;
 	}
 
-	req->rc = c->rc;
+	req->rc.size = c->rc.size;
+	req->rc.sdata = c->rc.sdata;
 	p9_client_cb(client, req, REQ_STATUS_RCVD);
 
  out:
@@ -361,9 +361,10 @@ send_done(struct ib_cq *cq, struct ib_wc *wc)
 		container_of(wc->wr_cqe, struct p9_rdma_context, cqe);
 
 	ib_dma_unmap_single(rdma->cm_id->device,
-			    c->busa, c->req->tc->size,
+			    c->busa, c->req->tc.size,
 			    DMA_TO_DEVICE);
 	up(&rdma->sq_sem);
+	p9_req_put(c->req);
 	kfree(c);
 }
 
@@ -401,7 +402,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c)
 	struct ib_sge sge;
 
 	c->busa = ib_dma_map_single(rdma->cm_id->device,
-				    c->rc->sdata, client->msize,
+				    c->rc.sdata, client->msize,
 				    DMA_FROM_DEVICE);
 	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
 		goto error;
@@ -443,9 +444,9 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	 **/
 	if (unlikely(atomic_read(&rdma->excess_rc) > 0)) {
 		if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) {
-			/* Got one ! */
-			kfree(req->rc);
-			req->rc = NULL;
+			/* Got one! */
+			p9_fcall_fini(&req->rc);
+			req->rc.sdata = NULL;
 			goto dont_need_post_recv;
 		} else {
 			/* We raced and lost. */
@@ -459,7 +460,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 		err = -ENOMEM;
 		goto recv_error;
 	}
-	rpl_context->rc = req->rc;
+	rpl_context->rc.sdata = req->rc.sdata;
 
 	/*
 	 * Post a receive buffer for this request. We need to ensure
@@ -475,11 +476,11 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 
 	err = post_recv(client, rpl_context);
 	if (err) {
-		p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n");
+		p9_debug(P9_DEBUG_ERROR, "POST RECV failed: %d\n", err);
 		goto recv_error;
 	}
 	/* remove posted receive buffer from request structure */
-	req->rc = NULL;
+	req->rc.sdata = NULL;
 
 dont_need_post_recv:
 	/* Post the request */
@@ -491,7 +492,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	c->req = req;
 
 	c->busa = ib_dma_map_single(rdma->cm_id->device,
-				    c->req->tc->sdata, c->req->tc->size,
+				    c->req->tc.sdata, c->req->tc.size,
 				    DMA_TO_DEVICE);
 	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) {
 		err = -EIO;
@@ -501,7 +502,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	c->cqe.done = send_done;
 
 	sge.addr = c->busa;
-	sge.length = c->req->tc->size;
+	sge.length = c->req->tc.size;
 	sge.lkey = rdma->pd->local_dma_lkey;
 
 	wr.next = NULL;
@@ -544,7 +545,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
  recv_error:
 	kfree(rpl_context);
 	spin_lock_irqsave(&rdma->req_lock, flags);
-	if (rdma->state < P9_RDMA_CLOSING) {
+	if (err != -EINTR && rdma->state < P9_RDMA_CLOSING) {
 		rdma->state = P9_RDMA_CLOSING;
 		spin_unlock_irqrestore(&rdma->req_lock, flags);
 		rdma_disconnect(rdma->cm_id);

net/9p/trans_virtio.c

@@ -155,7 +155,7 @@ static void req_done(struct virtqueue *vq)
 		}
 
 		if (len) {
-			req->rc->size = len;
+			req->rc.size = len;
 			p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
 		}
 	}
@@ -207,6 +207,13 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 	return 1;
 }
 
+/* Reply won't come, so drop req ref */
+static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	p9_req_put(req);
+	return 0;
+}
+
 /**
  * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
  * this takes a list of pages.
@@ -273,12 +280,12 @@ p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 	out_sgs = in_sgs = 0;
 	/* Handle out VirtIO ring buffers */
 	out = pack_sg_list(chan->sg, 0,
-			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
 	if (out)
 		sgs[out_sgs++] = chan->sg;
 
 	in = pack_sg_list(chan->sg, out,
-			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+			  VIRTQUEUE_NUM, req->rc.sdata, req->rc.capacity);
 	if (in)
 		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
@@ -404,6 +411,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	struct scatterlist *sgs[4];
 	size_t offs;
 	int need_drop = 0;
+	int kicked = 0;
 
 	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
 
@@ -411,29 +419,33 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 		__le32 sz;
 		int n = p9_get_mapped_pages(chan, &out_pages, uodata,
 					    outlen, &offs, &need_drop);
-		if (n < 0)
-			return n;
+		if (n < 0) {
+			err = n;
+			goto err_out;
+		}
 		out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
 		if (n != outlen) {
 			__le32 v = cpu_to_le32(n);
-			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
 			outlen = n;
 		}
 		/* The size field of the message must include the length of the
 		 * header and the length of the data.  We didn't actually know
 		 * the length of the data until this point so add it in now.
 		 */
-		sz = cpu_to_le32(req->tc->size + outlen);
-		memcpy(&req->tc->sdata[0], &sz, sizeof(sz));
+		sz = cpu_to_le32(req->tc.size + outlen);
+		memcpy(&req->tc.sdata[0], &sz, sizeof(sz));
 	} else if (uidata) {
 		int n = p9_get_mapped_pages(chan, &in_pages, uidata,
 					    inlen, &offs, &need_drop);
-		if (n < 0)
-			return n;
+		if (n < 0) {
+			err = n;
+			goto err_out;
+		}
 		in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
 		if (n != inlen) {
 			__le32 v = cpu_to_le32(n);
-			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
 			inlen = n;
 		}
 	}
@@ -445,7 +457,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 
 	/* out data */
 	out = pack_sg_list(chan->sg, 0,
-			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
 
 	if (out)
 		sgs[out_sgs++] = chan->sg;
@@ -464,7 +476,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	 * alloced memory and payload onto the user buffer.
 	 */
 	in = pack_sg_list(chan->sg, out,
-			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+			  VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len);
 	if (in)
 		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
@@ -498,6 +510,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	}
 	virtqueue_kick(chan->vq);
 	spin_unlock_irqrestore(&chan->lock, flags);
+	kicked = 1;
 	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
 	err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
 	/*
@@ -518,6 +531,10 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	}
 	kvfree(in_pages);
 	kvfree(out_pages);
+	if (!kicked) {
+		/* reply won't come */
+		p9_req_put(req);
+	}
 	return err;
 }
 
@@ -750,6 +767,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.request = p9_virtio_request,
 	.zc_request = p9_virtio_zc_request,
 	.cancel = p9_virtio_cancel,
+	.cancelled = p9_virtio_cancelled,
 	/*
 	 * We leave one entry for input and one entry for response
 	 * headers. We also skip one more entry to accomodate, address

net/9p/trans_xen.c

@@ -141,7 +141,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	struct xen_9pfs_front_priv *priv = NULL;
 	RING_IDX cons, prod, masked_cons, masked_prod;
 	unsigned long flags;
-	u32 size = p9_req->tc->size;
+	u32 size = p9_req->tc.size;
 	struct xen_9pfs_dataring *ring;
 	int num;
 
@@ -154,7 +154,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	if (!priv || priv->client != client)
 		return -EINVAL;
 
-	num = p9_req->tc->tag % priv->num_rings;
+	num = p9_req->tc.tag % priv->num_rings;
 	ring = &priv->rings[num];
 
 again:
@@ -176,7 +176,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE);
 	masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
 
-	xen_9pfs_write_packet(ring->data.out, p9_req->tc->sdata, size,
+	xen_9pfs_write_packet(ring->data.out, p9_req->tc.sdata, size,
 			      &masked_prod, masked_cons, XEN_9PFS_RING_SIZE);
 
 	p9_req->status = REQ_STATUS_SENT;
@@ -185,6 +185,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	ring->intf->out_prod = prod;
 	spin_unlock_irqrestore(&ring->lock, flags);
 	notify_remote_via_irq(ring->irq);
+	p9_req_put(p9_req);
 
 	return 0;
 }
@@ -229,12 +230,12 @@ static void p9_xen_response(struct work_struct *work)
 			continue;
 		}
 
-		memcpy(req->rc, &h, sizeof(h));
-		req->rc->offset = 0;
+		memcpy(&req->rc, &h, sizeof(h));
+		req->rc.offset = 0;
 
 		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
 		/* Then, read the whole packet (including the header) */
-		xen_9pfs_read_packet(req->rc->sdata, ring->data.in, h.size,
+		xen_9pfs_read_packet(req->rc.sdata, ring->data.in, h.size,
 				     masked_prod, &masked_cons,
 				     XEN_9PFS_RING_SIZE);
 
@@ -391,8 +392,8 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
 	unsigned int max_rings, max_ring_order, len = 0;
 
 	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
-	if (!len)
-		return -EINVAL;
+	if (IS_ERR(versions))
+		return PTR_ERR(versions);
 	if (strcmp(versions, "1")) {
 		kfree(versions);
 		return -EINVAL;

net/9p/util.c

-/*
- *  net/9p/util.c
- *
- *  This file contains some helper functions
- *
- *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
- *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
- *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to:
- *  Free Software Foundation
- *  51 Franklin Street, Fifth Floor
- *  Boston, MA  02111-1301  USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
-#include <linux/parser.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <net/9p/9p.h>
-
-/**
- * struct p9_idpool - per-connection accounting for tag idpool
- * @lock: protects the pool
- * @pool: idr to allocate tag id from
- *
- */
-
-struct p9_idpool {
-	spinlock_t lock;
-	struct idr pool;
-};
-
-/**
- * p9_idpool_create - create a new per-connection id pool
- *
- */
-
-struct p9_idpool *p9_idpool_create(void)
-{
-	struct p9_idpool *p;
-
-	p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
-	if (!p)
-		return ERR_PTR(-ENOMEM);
-
-	spin_lock_init(&p->lock);
-	idr_init(&p->pool);
-
-	return p;
-}
-EXPORT_SYMBOL(p9_idpool_create);
-
-/**
- * p9_idpool_destroy - create a new per-connection id pool
- * @p: idpool to destroy
- */
-
-void p9_idpool_destroy(struct p9_idpool *p)
-{
-	idr_destroy(&p->pool);
-	kfree(p);
-}
-EXPORT_SYMBOL(p9_idpool_destroy);
-
-/**
- * p9_idpool_get - allocate numeric id from pool
- * @p: pool to allocate from
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- *            the lock included in struct idr?
- */
-
-int p9_idpool_get(struct p9_idpool *p)
-{
-	int i;
-	unsigned long flags;
-
-	idr_preload(GFP_NOFS);
-	spin_lock_irqsave(&p->lock, flags);
-
-	/* no need to store exactly p, we just need something non-null */
-	i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
-
-	spin_unlock_irqrestore(&p->lock, flags);
-	idr_preload_end();
-	if (i < 0)
-		return -1;
-
-	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
-	return i;
-}
-EXPORT_SYMBOL(p9_idpool_get);
-
-/**
- * p9_idpool_put - release numeric id from pool
- * @id: numeric id which is being released
- * @p: pool to release id into
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- *            the lock included in struct idr?
- */
-
-void p9_idpool_put(int id, struct p9_idpool *p)
-{
-	unsigned long flags;
-
-	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
-
-	spin_lock_irqsave(&p->lock, flags);
-	idr_remove(&p->pool, id);
-	spin_unlock_irqrestore(&p->lock, flags);
-}
-EXPORT_SYMBOL(p9_idpool_put);
-
-/**
- * p9_idpool_check - check if the specified id is available
- * @id: id to check
- * @p: pool to check
- */
-
-int p9_idpool_check(int id, struct p9_idpool *p)
-{
-	return idr_find(&p->pool, id) != NULL;
-}
-EXPORT_SYMBOL(p9_idpool_check);