nfsd: rework refcounting in filecache

The filecache refcounting is a bit non-standard for something searchable
by RCU, in that we maintain a sentinel reference while it's hashed. This
in turn requires that we have to do things differently in the "put"
depending on whether its hashed, which we believe to have led to races.

There are other problems in here too. nfsd_file_close_inode_sync can end
up freeing an nfsd_file while there are still outstanding references to
it, and there are a number of subtle ToC/ToU races.

Rework the code so that the refcount is what drives the lifecycle. When
the refcount goes to zero, then unhash and rcu free the object. A task
searching for a nfsd_file is allowed to bump its refcount, but only if
it's not already 0. Ensure that we don't make any other changes to it
until a reference is held.

With this change, the LRU carries a reference. Take special care to deal
with it when removing an entry from the list, and ensure that we only
repurpose the nf_lru list_head when the refcount is 0 to ensure
exclusive access to it.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

1 files changed, 19 insertions, 32 deletions

diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 46b8f68a2497..c852ae8eaf37 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -876,8 +876,8 @@ DEFINE_CLID_EVENT(confirmed_r);
 	__print_flags(val, "|",						\
 		{ 1 << NFSD_FILE_HASHED,	"HASHED" },		\
 		{ 1 << NFSD_FILE_PENDING,	"PENDING" },		\
-		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED"},		\
-		{ 1 << NFSD_FILE_GC,		"GC"})
+		{ 1 << NFSD_FILE_REFERENCED,	"REFERENCED" },		\
+		{ 1 << NFSD_FILE_GC,		"GC" })
 
 DECLARE_EVENT_CLASS(nfsd_file_class,
 	TP_PROTO(struct nfsd_file *nf),
@@ -912,6 +912,7 @@ DEFINE_EVENT(nfsd_file_class, name, \
 DEFINE_NFSD_FILE_EVENT(nfsd_file_free);
 DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash);
 DEFINE_NFSD_FILE_EVENT(nfsd_file_put);
+DEFINE_NFSD_FILE_EVENT(nfsd_file_closing);
 DEFINE_NFSD_FILE_EVENT(nfsd_file_unhash_and_queue);
 
 TRACE_EVENT(nfsd_file_alloc,
@@ -1103,35 +1104,6 @@ TRACE_EVENT(nfsd_file_open,
 		__entry->nf_file)
 )
 
-DECLARE_EVENT_CLASS(nfsd_file_search_class,
-	TP_PROTO(
-		const struct inode *inode,
-		unsigned int count
-	),
-	TP_ARGS(inode, count),
-	TP_STRUCT__entry(
-		__field(const struct inode *, inode)
-		__field(unsigned int, count)
-	),
-	TP_fast_assign(
-		__entry->inode = inode;
-		__entry->count = count;
-	),
-	TP_printk("inode=%p count=%u",
-		__entry->inode, __entry->count)
-);
-
-#define DEFINE_NFSD_FILE_SEARCH_EVENT(name)				\
-DEFINE_EVENT(nfsd_file_search_class, name,				\
-	TP_PROTO(							\
-		const struct inode *inode,				\
-		unsigned int count					\
-	),								\
-	TP_ARGS(inode, count))
-
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode_sync);
-DEFINE_NFSD_FILE_SEARCH_EVENT(nfsd_file_close_inode);
-
 TRACE_EVENT(nfsd_file_is_cached,
 	TP_PROTO(
 		const struct inode *inode,
@@ -1209,7 +1181,6 @@ DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced);
-DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_hashed);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed);
 
 DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class,
@@ -1241,6 +1212,22 @@ DEFINE_EVENT(nfsd_file_lruwalk_class, name,				\
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed);
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed);
 
+TRACE_EVENT(nfsd_file_close,
+	TP_PROTO(
+		const struct inode *inode
+	),
+	TP_ARGS(inode),
+	TP_STRUCT__entry(
+		__field(const void *, inode)
+	),
+	TP_fast_assign(
+		__entry->inode = inode;
+	),
+	TP_printk("inode=%p",
+		__entry->inode
+	)
+);
+
 TRACE_EVENT(nfsd_file_fsync,
 	TP_PROTO(
 		const struct nfsd_file *nf,