netfs: Add a tracepoint to log failures that would be otherwise unseen

Add a tracepoint to log internal failures (such as cache errors) that we
don't otherwise want to pass back to the netfs.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Dave Wysochanski <dwysocha@redhat.com>
Tested-By: Marc Dionne <marc.dionne@auristor.com>
cc: Matthew Wilcox <willy@infradead.org>
cc: linux-mm@kvack.org
cc: linux-cachefs@redhat.com
cc: linux-afs@lists.infradead.org
cc: linux-nfs@vger.kernel.org
cc: linux-cifs@vger.kernel.org
cc: ceph-devel@vger.kernel.org
cc: v9fs-developer@lists.sourceforge.net
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/161781048813.463527.1557000804674707986.stgit@warthog.procyon.org.uk/
Link: https://lore.kernel.org/r/161789082749.6155.15498680577213140870.stgit@warthog.procyon.org.uk/ # v6

2 files changed, 70 insertions, 2 deletions

diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c
index cd3b61d5e192..1d3b50c5db6d 100644
--- a/fs/netfs/read_helper.c
+++ b/fs/netfs/read_helper.c
@@ -271,6 +271,8 @@ static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
 
 	if (IS_ERR_VALUE(transferred_or_error)) {
 		netfs_stat(&netfs_n_rh_write_failed);
+		trace_netfs_failure(rreq, subreq, transferred_or_error,
+				    netfs_fail_copy_to_cache);
 	} else {
 		netfs_stat(&netfs_n_rh_write_done);
 	}
@@ -323,6 +325,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq)
 		ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
 					       rreq->i_size);
 		if (ret < 0) {
+			trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
 			trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
 			continue;
 		}
@@ -627,6 +630,8 @@ void netfs_subreq_terminated(struct netfs_read_subrequest *subreq,
 
 	if (IS_ERR_VALUE(transferred_or_error)) {
 		subreq->error = transferred_or_error;
+		trace_netfs_failure(rreq, subreq, transferred_or_error,
+				    netfs_fail_read);
 		goto failed;
 	}
 
@@ -996,8 +1001,10 @@ int netfs_readpage(struct file *file,
 	} while (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags));
 
 	ret = rreq->error;
-	if (ret == 0 && rreq->submitted < rreq->len)
+	if (ret == 0 && rreq->submitted < rreq->len) {
+		trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_readpage);
 		ret = -EIO;
+	}
 out:
 	netfs_put_read_request(rreq, false);
 	return ret;
@@ -1069,6 +1076,7 @@ retry:
 		/* Allow the netfs (eg. ceph) to flush conflicts. */
 		ret = ops->check_write_begin(file, pos, len, page, _fsdata);
 		if (ret < 0) {
+			trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin);
 			if (ret == -EAGAIN)
 				goto retry;
 			goto error;
@@ -1145,8 +1153,10 @@ retry:
 	}
 
 	ret = rreq->error;
-	if (ret == 0 && rreq->submitted < rreq->len)
+	if (ret == 0 && rreq->submitted < rreq->len) {
+		trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_write_begin);
 		ret = -EIO;
+	}
 	netfs_put_read_request(rreq, false);
 	if (ret < 0)
 		goto error;
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index e3ebeabd3852..de1c64635e42 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -47,6 +47,15 @@ enum netfs_sreq_trace {
 	netfs_sreq_trace_write_term,
 };
 
+enum netfs_failure {
+	netfs_fail_check_write_begin,
+	netfs_fail_copy_to_cache,
+	netfs_fail_read,
+	netfs_fail_short_readpage,
+	netfs_fail_short_write_begin,
+	netfs_fail_prepare_write,
+};
+
 #endif
 
 #define netfs_read_traces					\
@@ -81,6 +90,14 @@ enum netfs_sreq_trace {
 	EM(netfs_sreq_trace_write_skip,		"SKIP ")	\
 	E_(netfs_sreq_trace_write_term,		"WTERM")
 
+#define netfs_failures							\
+	EM(netfs_fail_check_write_begin,	"check-write-begin")	\
+	EM(netfs_fail_copy_to_cache,		"copy-to-cache")	\
+	EM(netfs_fail_read,			"read")			\
+	EM(netfs_fail_short_readpage,		"short-readpage")	\
+	EM(netfs_fail_short_write_begin,	"short-write-begin")	\
+	E_(netfs_fail_prepare_write,		"prep-write")
+
 
 /*
  * Export enum symbols via userspace.
@@ -94,6 +111,7 @@ netfs_read_traces;
 netfs_rreq_traces;
 netfs_sreq_sources;
 netfs_sreq_traces;
+netfs_failures;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -197,6 +215,46 @@ TRACE_EVENT(netfs_sreq,
 		      __entry->error)
 	    );
 
+TRACE_EVENT(netfs_failure,
+	    TP_PROTO(struct netfs_read_request *rreq,
+		     struct netfs_read_subrequest *sreq,
+		     int error, enum netfs_failure what),
+
+	    TP_ARGS(rreq, sreq, error, what),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		rreq		)
+		    __field(unsigned short,		index		)
+		    __field(short,			error		)
+		    __field(unsigned short,		flags		)
+		    __field(enum netfs_read_source,	source		)
+		    __field(enum netfs_failure,		what		)
+		    __field(size_t,			len		)
+		    __field(size_t,			transferred	)
+		    __field(loff_t,			start		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->rreq	= rreq->debug_id;
+		    __entry->index	= sreq ? sreq->debug_index : 0;
+		    __entry->error	= error;
+		    __entry->flags	= sreq ? sreq->flags : 0;
+		    __entry->source	= sreq ? sreq->source : NETFS_INVALID_READ;
+		    __entry->what	= what;
+		    __entry->len	= sreq ? sreq->len : 0;
+		    __entry->transferred = sreq ? sreq->transferred : 0;
+		    __entry->start	= sreq ? sreq->start : 0;
+			   ),
+
+	    TP_printk("R=%08x[%u] %s f=%02x s=%llx %zx/%zx %s e=%d",
+		      __entry->rreq, __entry->index,
+		      __print_symbolic(__entry->source, netfs_sreq_sources),
+		      __entry->flags,
+		      __entry->start, __entry->transferred, __entry->len,
+		      __print_symbolic(__entry->what, netfs_failures),
+		      __entry->error)
+	    );
+
 #endif /* _TRACE_NETFS_H */
 
 /* This part must be outside protection */