afs: Fix application of status and callback to be under same lock

When applying the status and callback in the response of an operation,
apply them in the same critical section so that there's no race between
checking the callback state and checking status-dependent state (such as
the data version).

Fix this by:

 (1) Allocating a joint {status,callback} record (afs_status_cb) before
     calling the RPC function for each vnode for which the RPC reply
     contains a status or a status plus a callback.  A flag is set in the
     record to indicate if a callback was actually received.

 (2) These records are passed into the RPC functions to be filled in.  The
     afs_decode_status() and yfs_decode_status() functions are removed and
     the cb_lock is no longer taken.

 (3) xdr_decode_AFSFetchStatus() and xdr_decode_YFSFetchStatus() no longer
     update the vnode.

 (4) xdr_decode_AFSCallBack() and xdr_decode_YFSCallBack() no longer update
     the vnode.

 (5) vnodes, expected data-version numbers and callback break counters
     (cb_break) no longer need to be passed to the reply delivery
     functions.

     Note that, for the moment, the file locking functions still need
     access to both the call and the vnode at the same time.

 (6) afs_vnode_commit_status() is now given the cb_break value and the
     expected data_version and the task of applying the status and the
     callback to the vnode are now done here.

     This is done under a single taking of vnode->cb_lock.

 (7) afs_pages_written_back() is now called by afs_store_data() rather than
     by the reply delivery function.

     afs_pages_written_back() has been moved to before the call point and
     is now given the first and last page numbers rather than a pointer to
     the call.

 (8) The indicator from YFS.RemoveFile2 as to whether the target file
     actually got removed (status.abort_code == VNOVNODE) rather than
     merely dropping a link is now checked in afs_unlink rather than in
     xdr_decode_YFSFetchStatus().

Supplementary fixes:

 (*) afs_cache_permit() now gets the caller_access mask from the
     afs_status_cb object rather than picking it out of the vnode's status
     record.  afs_fetch_status() returns caller_access through its argument
     list for this purpose also.

 (*) afs_inode_init_from_status() now uses a write lock on cb_lock rather
     than a read lock and now sets the callback inside the same critical
     section.

Fixes: c435ee34551e ("afs: Overhaul the callback handling")
Signed-off-by: David Howells <dhowells@redhat.com>

1 files changed, 55 insertions, 43 deletions

diff --git a/fs/afs/write.c b/fs/afs/write.c
index e669f2fae873..8bcab95f1127 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -314,6 +314,46 @@ static void afs_redirty_pages(struct writeback_control *wbc,
 }
 
 /*
+ * completion of write to server
+ */
+static void afs_pages_written_back(struct afs_vnode *vnode,
+				   pgoff_t first, pgoff_t last)
+{
+	struct pagevec pv;
+	unsigned long priv;
+	unsigned count, loop;
+
+	_enter("{%llx:%llu},{%lx-%lx}",
+	       vnode->fid.vid, vnode->fid.vnode, first, last);
+
+	pagevec_init(&pv);
+
+	do {
+		_debug("done %lx-%lx", first, last);
+
+		count = last - first + 1;
+		if (count > PAGEVEC_SIZE)
+			count = PAGEVEC_SIZE;
+		pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping,
+					      first, count, pv.pages);
+		ASSERTCMP(pv.nr, ==, count);
+
+		for (loop = 0; loop < count; loop++) {
+			priv = page_private(pv.pages[loop]);
+			trace_afs_page_dirty(vnode, tracepoint_string("clear"),
+					     pv.pages[loop]->index, priv);
+			set_page_private(pv.pages[loop], 0);
+			end_page_writeback(pv.pages[loop]);
+		}
+		first += count;
+		__pagevec_release(&pv);
+	} while (first <= last);
+
+	afs_prune_wb_keys(vnode);
+	_leave("");
+}
+
+/*
  * write to a file
  */
 static int afs_store_data(struct address_space *mapping,
@@ -322,6 +362,7 @@ static int afs_store_data(struct address_space *mapping,
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
 	struct afs_fs_cursor fc;
+	struct afs_status_cb *scb;
 	struct afs_wb_key *wbk = NULL;
 	struct list_head *p;
 	int ret = -ENOKEY, ret2;
@@ -333,6 +374,10 @@ static int afs_store_data(struct address_space *mapping,
 	       vnode->fid.unique,
 	       first, last, offset, to);
 
+	scb = kzalloc(sizeof(struct afs_status_cb), GFP_NOFS);
+	if (!scb)
+		return -ENOMEM;
+
 	spin_lock(&vnode->wb_lock);
 	p = vnode->wb_keys.next;
 
@@ -351,6 +396,7 @@ try_next_key:
 
 	spin_unlock(&vnode->wb_lock);
 	afs_put_wb_key(wbk);
+	kfree(scb);
 	_leave(" = %d [no keys]", ret);
 	return ret;
 
@@ -362,13 +408,18 @@ found_key:
 
 	ret = -ERESTARTSYS;
 	if (afs_begin_vnode_operation(&fc, vnode, wbk->key, false)) {
+		afs_dataversion_t data_version = vnode->status.data_version + 1;
+
 		while (afs_select_fileserver(&fc)) {
 			fc.cb_break = afs_calc_vnode_cb_break(vnode);
-			afs_fs_store_data(&fc, mapping, first, last, offset, to);
+			afs_fs_store_data(&fc, mapping, first, last, offset, to, scb);
 		}
 
-		afs_check_for_remote_deletion(&fc, fc.vnode);
-		afs_vnode_commit_status(&fc, vnode, fc.cb_break);
+		afs_check_for_remote_deletion(&fc, vnode);
+		afs_vnode_commit_status(&fc, vnode, fc.cb_break,
+					&data_version, scb);
+		if (fc.ac.error == 0)
+			afs_pages_written_back(vnode, first, last);
 		ret = afs_end_vnode_operation(&fc);
 	}
 
@@ -393,6 +444,7 @@ found_key:
 	}
 
 	afs_put_wb_key(wbk);
+	kfree(scb);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -679,46 +731,6 @@ int afs_writepages(struct address_space *mapping,
 }
 
 /*
- * completion of write to server
- */
-void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call)
-{
-	struct pagevec pv;
-	unsigned long priv;
-	unsigned count, loop;
-	pgoff_t first = call->first, last = call->last;
-
-	_enter("{%llx:%llu},{%lx-%lx}",
-	       vnode->fid.vid, vnode->fid.vnode, first, last);
-
-	pagevec_init(&pv);
-
-	do {
-		_debug("done %lx-%lx", first, last);
-
-		count = last - first + 1;
-		if (count > PAGEVEC_SIZE)
-			count = PAGEVEC_SIZE;
-		pv.nr = find_get_pages_contig(vnode->vfs_inode.i_mapping,
-					      first, count, pv.pages);
-		ASSERTCMP(pv.nr, ==, count);
-
-		for (loop = 0; loop < count; loop++) {
-			priv = page_private(pv.pages[loop]);
-			trace_afs_page_dirty(vnode, tracepoint_string("clear"),
-					     pv.pages[loop]->index, priv);
-			set_page_private(pv.pages[loop], 0);
-			end_page_writeback(pv.pages[loop]);
-		}
-		first += count;
-		__pagevec_release(&pv);
-	} while (first <= last);
-
-	afs_prune_wb_keys(vnode);
-	_leave("");
-}
-
-/*
  * write to an AFS file
  */
 ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from)