Commit 21b9f1c7 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'afs-fixes-20180514' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs 

Pull AFS fixes from David Howells:
 "Here's a set of patches that fix a number of bugs in the in-kernel AFS
  client, including:

   - Fix directory locking to not use individual page locks for
     directory reading/scanning but rather to use a semaphore on the
     afs_vnode struct as the directory contents must be read in a single
     blob and data from different reads must not be mixed as the entire
     contents may be shuffled about between reads.

   - Fix address list parsing to handle port specifiers correctly.

   - Only give up callback records on a server if we actually talked to
     that server (we might not be able to access a server).

   - Fix some callback handling bugs, including refcounting,
     whole-volume callbacks and when callbacks actually get broken in
     response to a CB.CallBack op.

   - Fix some server/address rotation bugs, including giving up if we
     can't probe a server; giving up if a server says it doesn't have a
     volume, but there are more servers to try.

   - Fix the decoding of fetched statuses to be OpenAFS compatible.

   - Fix the handling of server lookups in Cache Manager ops (such as
     CB.InitCallBackState3) to use a UUID if possible and to handle no
     server being found.

   - Fix a bug in server lookup where not all addresses are compared.

   - Fix the non-encryption of calls that prevents some servers from
     being accessed (this also requires an AF_RXRPC patch that has
     already gone in through the net tree).

  There's also a patch that adds tracepoints to log Cache Manager ops
  that don't find a matching server, either by UUID or by address"

* tag 'afs-fixes-20180514' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs:
  afs: Fix the non-encryption of calls
  afs: Fix CB.CallBack handling
  afs: Fix whole-volume callback handling
  afs: Fix afs_find_server search loop
  afs: Fix the handling of an unfound server in CM operations
  afs: Add a tracepoint to record callbacks from unlisted servers
  afs: Fix the handling of CB.InitCallBackState3 to find the server by UUID
  afs: Fix VNOVOL handling in address rotation
  afs: Fix AFSFetchStatus decoder to provide OpenAFS compatibility
  afs: Fix server rotation's handling of fileserver probe failure
  afs: Fix refcounting in callback registration
  afs: Fix giving up callbacks on server destruction
  afs: Fix address list parsing
  afs: Fix directory page locking
parents eeba2dfa 4776cab4

fs/afs/addr_list.c

+15 −10
Original line number Diff line number Diff line
@@ -121,7 +121,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, 
	p = text;

	do {

		struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs];

		char tdelim = delim;

		const char *q, *stop;



		if (*p == delim) {

			p++;
@@ -130,28 +130,33 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, 


		if (*p == '[') {

			p++;

			tdelim = ']';

			q = memchr(p, ']', end - p);

		} else {

			for (q = p; q < end; q++)

				if (*q == '+' || *q == delim)

					break;

		}



		if (in4_pton(p, end - p,

		if (in4_pton(p, q - p,

			     (u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3],

			     tdelim, &p)) {

			     -1, &stop)) {

			srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;

			srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;

			srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);

		} else if (in6_pton(p, end - p,

		} else if (in6_pton(p, q - p,

				    srx->transport.sin6.sin6_addr.s6_addr,

				    tdelim, &p)) {

				    -1, &stop)) {

			/* Nothing to do */

		} else {

			goto bad_address;

		}



		if (tdelim == ']') {

			if (p == end || *p != ']')

		if (stop != q)

			goto bad_address;



		p = q;

		if (q < end && *q == ']')

			p++;

		}



		if (p < end) {

			if (*p == '+') {

fs/afs/callback.c

+61 −23
Original line number Diff line number Diff line
@@ -23,36 +23,55 @@ 
/*

 * Set up an interest-in-callbacks record for a volume on a server and

 * register it with the server.

 * - Called with volume->server_sem held.

 * - Called with vnode->io_lock held.

 */

int afs_register_server_cb_interest(struct afs_vnode *vnode,

				    struct afs_server_entry *entry)

				    struct afs_server_list *slist,

				    unsigned int index)

{

	struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x;

	struct afs_server_entry *entry = &slist->servers[index];

	struct afs_cb_interest *cbi, *vcbi, *new, *old;

	struct afs_server *server = entry->server;



again:

	if (vnode->cb_interest &&

	    likely(vnode->cb_interest == entry->cb_interest))

		return 0;



	read_lock(&slist->lock);

	cbi = afs_get_cb_interest(entry->cb_interest);

	read_unlock(&slist->lock);



	vcbi = vnode->cb_interest;

	if (vcbi) {

		if (vcbi == cbi)

		if (vcbi == cbi) {

			afs_put_cb_interest(afs_v2net(vnode), cbi);

			return 0;

		}



		/* Use a new interest in the server list for the same server

		 * rather than an old one that's still attached to a vnode.

		 */

		if (cbi && vcbi->server == cbi->server) {

			write_seqlock(&vnode->cb_lock);

			vnode->cb_interest = afs_get_cb_interest(cbi);

			old = vnode->cb_interest;

			vnode->cb_interest = cbi;

			write_sequnlock(&vnode->cb_lock);

			afs_put_cb_interest(afs_v2net(vnode), cbi);

			afs_put_cb_interest(afs_v2net(vnode), old);

			return 0;

		}



		/* Re-use the one attached to the vnode. */

		if (!cbi && vcbi->server == server) {

			afs_get_cb_interest(vcbi);

			x = cmpxchg(&entry->cb_interest, cbi, vcbi);

			if (x != cbi) {

				cbi = x;

				afs_put_cb_interest(afs_v2net(vnode), vcbi);

			write_lock(&slist->lock);

			if (entry->cb_interest) {

				write_unlock(&slist->lock);

				afs_put_cb_interest(afs_v2net(vnode), cbi);

				goto again;

			}



			entry->cb_interest = cbi;

			write_unlock(&slist->lock);

			return 0;

		}

	}
@@ -72,13 +91,16 @@ again: 
		list_add_tail(&new->cb_link, &server->cb_interests);

		write_unlock(&server->cb_break_lock);



		x = cmpxchg(&entry->cb_interest, cbi, new);

		if (x == cbi) {

		write_lock(&slist->lock);

		if (!entry->cb_interest) {

			entry->cb_interest = afs_get_cb_interest(new);

			cbi = new;

			new = NULL;

		} else {

			cbi = x;

			afs_put_cb_interest(afs_v2net(vnode), new);

			cbi = afs_get_cb_interest(entry->cb_interest);

		}

		write_unlock(&slist->lock);

		afs_put_cb_interest(afs_v2net(vnode), new);

	}



	ASSERT(cbi);
@@ -88,11 +110,14 @@ again: 
	 */

	write_seqlock(&vnode->cb_lock);



	vnode->cb_interest = afs_get_cb_interest(cbi);

	old = vnode->cb_interest;

	vnode->cb_interest = cbi;

	vnode->cb_s_break = cbi->server->cb_s_break;

	vnode->cb_v_break = vnode->volume->cb_v_break;

	clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);



	write_sequnlock(&vnode->cb_lock);

	afs_put_cb_interest(afs_v2net(vnode), old);

	return 0;

}
@@ -171,15 +196,26 @@ static void afs_break_one_callback(struct afs_server *server, 
		if (cbi->vid != fid->vid)

			continue;



		if (fid->vnode == 0 && fid->unique == 0) {

			/* The callback break applies to an entire volume. */

			struct afs_super_info *as = AFS_FS_S(cbi->sb);

			struct afs_volume *volume = as->volume;



			write_lock(&volume->cb_break_lock);

			volume->cb_v_break++;

			write_unlock(&volume->cb_break_lock);

		} else {

			data.volume = NULL;

			data.fid = *fid;

		inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data);

			inode = ilookup5_nowait(cbi->sb, fid->vnode,

						afs_iget5_test, &data);

			if (inode) {

				vnode = AFS_FS_I(inode);

				afs_break_callback(vnode);

				iput(inode);

			}

		}

	}



	read_unlock(&server->cb_break_lock);

}
@@ -195,6 +231,8 @@ void afs_break_callbacks(struct afs_server *server, size_t count, 
	ASSERT(server != NULL);

	ASSERTCMP(count, <=, AFSCBMAX);



	/* TODO: Sort the callback break list by volume ID */



	for (; count > 0; callbacks++, count--) {

		_debug("- Fid { vl=%08x n=%u u=%u }  CB { v=%u x=%u t=%u }",

		       callbacks->fid.vid,

fs/afs/cmservice.c

+21 −46
Original line number Diff line number Diff line
@@ -133,21 +133,10 @@ bool afs_cm_incoming_call(struct afs_call *call) 
}



/*

 * clean up a cache manager call

 * Clean up a cache manager call.

 */

static void afs_cm_destructor(struct afs_call *call)

{

	_enter("");



	/* Break the callbacks here so that we do it after the final ACK is

	 * received.  The step number here must match the final number in

	 * afs_deliver_cb_callback().

	 */

	if (call->unmarshall == 5) {

		ASSERT(call->cm_server && call->count && call->request);

		afs_break_callbacks(call->cm_server, call->count, call->request);

	}



	kfree(call->buffer);

	call->buffer = NULL;

}
@@ -161,14 +150,14 @@ static void SRXAFSCB_CallBack(struct work_struct *work) 


	_enter("");



	/* be sure to send the reply *before* attempting to spam the AFS server

	 * with FSFetchStatus requests on the vnodes with broken callbacks lest

	 * the AFS server get into a vicious cycle of trying to break further

	 * callbacks because it hadn't received completion of the CBCallBack op

	 * yet */

	afs_send_empty_reply(call);



	/* We need to break the callbacks before sending the reply as the

	 * server holds up change visibility till it receives our reply so as

	 * to maintain cache coherency.

	 */

	if (call->cm_server)

		afs_break_callbacks(call->cm_server, call->count, call->request);



	afs_send_empty_reply(call);

	afs_put_call(call);

	_leave("");

}
@@ -180,7 +169,6 @@ static int afs_deliver_cb_callback(struct afs_call *call) 
{

	struct afs_callback_break *cb;

	struct sockaddr_rxrpc srx;

	struct afs_server *server;

	__be32 *bp;

	int ret, loop;
@@ -267,15 +255,6 @@ static int afs_deliver_cb_callback(struct afs_call *call) 


		call->offset = 0;

		call->unmarshall++;



		/* Record that the message was unmarshalled successfully so

		 * that the call destructor can know do the callback breaking

		 * work, even if the final ACK isn't received.

		 *

		 * If the step number changes, then afs_cm_destructor() must be

		 * updated also.

		 */

		call->unmarshall++;

	case 5:

		break;

	}
@@ -286,10 +265,9 @@ static int afs_deliver_cb_callback(struct afs_call *call) 
	/* we'll need the file server record as that tells us which set of

	 * vnodes to operate upon */

	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);

	server = afs_find_server(call->net, &srx);

	if (!server)

		return -ENOTCONN;

	call->cm_server = server;

	call->cm_server = afs_find_server(call->net, &srx);

	if (!call->cm_server)

		trace_afs_cm_no_server(call, &srx);



	return afs_queue_call_work(call);

}
@@ -303,6 +281,7 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) 


	_enter("{%p}", call->cm_server);



	if (call->cm_server)

		afs_init_callback_state(call->cm_server);

	afs_send_empty_reply(call);

	afs_put_call(call);
@@ -315,7 +294,6 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) 
static int afs_deliver_cb_init_call_back_state(struct afs_call *call)

{

	struct sockaddr_rxrpc srx;

	struct afs_server *server;

	int ret;



	_enter("");
@@ -328,10 +306,9 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) 


	/* we'll need the file server record as that tells us which set of

	 * vnodes to operate upon */

	server = afs_find_server(call->net, &srx);

	if (!server)

		return -ENOTCONN;

	call->cm_server = server;

	call->cm_server = afs_find_server(call->net, &srx);

	if (!call->cm_server)

		trace_afs_cm_no_server(call, &srx);



	return afs_queue_call_work(call);

}
@@ -341,8 +318,6 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) 
 */

static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)

{

	struct sockaddr_rxrpc srx;

	struct afs_server *server;

	struct afs_uuid *r;

	unsigned loop;

	__be32 *b;
@@ -398,11 +373,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) 


	/* we'll need the file server record as that tells us which set of

	 * vnodes to operate upon */

	rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx);

	server = afs_find_server(call->net, &srx);

	if (!server)

		return -ENOTCONN;

	call->cm_server = server;

	rcu_read_lock();

	call->cm_server = afs_find_server_by_uuid(call->net, call->request);

	rcu_read_unlock();

	if (!call->cm_server)

		trace_afs_cm_no_server_u(call, call->request);



	return afs_queue_call_work(call);

}

fs/afs/dir.c

+26 −28
Original line number Diff line number Diff line
@@ -180,6 +180,7 @@ static int afs_dir_open(struct inode *inode, struct file *file) 
 * get reclaimed during the iteration.

 */

static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key)

	__acquires(&dvnode->validate_lock)

{

	struct afs_read *req;

	loff_t i_size;
@@ -261,18 +262,21 @@ retry: 
	/* If we're going to reload, we need to lock all the pages to prevent

	 * races.

	 */

	if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {

	ret = -ERESTARTSYS;

		for (i = 0; i < req->nr_pages; i++)

			if (lock_page_killable(req->pages[i]) < 0)

				goto error_unlock;

	if (down_read_killable(&dvnode->validate_lock) < 0)

		goto error;



	if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))

		goto success;



	up_read(&dvnode->validate_lock);

	if (down_write_killable(&dvnode->validate_lock) < 0)

		goto error;



	if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) {

		ret = afs_fetch_data(dvnode, key, req);

		if (ret < 0)

			goto error_unlock_all;

			goto error_unlock;



		task_io_account_read(PAGE_SIZE * req->nr_pages);
@@ -284,33 +288,26 @@ retry: 
		for (i = 0; i < req->nr_pages; i++)

			if (!afs_dir_check_page(dvnode, req->pages[i],

						req->actual_len))

				goto error_unlock_all;

				goto error_unlock;



		// TODO: Trim excess pages



		set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags);

	}



	downgrade_write(&dvnode->validate_lock);

success:

	i = req->nr_pages;

	while (i > 0)

		unlock_page(req->pages[--i]);

	return req;



error_unlock_all:

	i = req->nr_pages;

error_unlock:

	while (i > 0)

		unlock_page(req->pages[--i]);

	up_write(&dvnode->validate_lock);

error:

	afs_put_read(req);

	_leave(" = %d", ret);

	return ERR_PTR(ret);



content_has_grown:

	i = req->nr_pages;

	while (i > 0)

		unlock_page(req->pages[--i]);

	up_write(&dvnode->validate_lock);

	afs_put_read(req);

	goto retry;

}
@@ -473,6 +470,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, 
	}



out:

	up_read(&dvnode->validate_lock);

	afs_put_read(req);

	_leave(" = %d", ret);

	return ret;
@@ -1143,7 +1141,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, dvnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			afs_fs_create(&fc, dentry->d_name.name, mode, data_version,

				      &newfid, &newstatus, &newcb);

		}
@@ -1213,7 +1211,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, dvnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			afs_fs_remove(&fc, dentry->d_name.name, true,

				      data_version);

		}
@@ -1316,7 +1314,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, dvnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			afs_fs_remove(&fc, dentry->d_name.name, false,

				      data_version);

		}
@@ -1373,7 +1371,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, dvnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			afs_fs_create(&fc, dentry->d_name.name, mode, data_version,

				      &newfid, &newstatus, &newcb);

		}
@@ -1443,8 +1441,8 @@ static int afs_link(struct dentry *from, struct inode *dir, 
		}



		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			fc.cb_break_2 = afs_calc_vnode_cb_break(vnode);

			afs_fs_link(&fc, vnode, dentry->d_name.name, data_version);

		}
@@ -1512,7 +1510,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, dvnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = dvnode->cb_break + dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(dvnode);

			afs_fs_symlink(&fc, dentry->d_name.name,

				       content, data_version,

				       &newfid, &newstatus);
@@ -1588,8 +1586,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, 
			}

		}

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break;

			fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode);

			fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode);

			afs_fs_rename(&fc, old_dentry->d_name.name,

				      new_dvnode, new_dentry->d_name.name,

				      orig_data_version, new_data_version);

fs/afs/file.c

+1 −1
Original line number Diff line number Diff line
@@ -238,7 +238,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de 
	ret = -ERESTARTSYS;

	if (afs_begin_vnode_operation(&fc, vnode, key)) {

		while (afs_select_fileserver(&fc)) {

			fc.cb_break = vnode->cb_break + vnode->cb_s_break;

			fc.cb_break = afs_calc_vnode_cb_break(vnode);

			afs_fs_fetch_data(&fc, desc);

		}

CRA Git | Maintained and supported by SUSTech CRA and CCSE