X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=blobdiff_plain;f=libcfs%2Finclude%2Flibcfs%2Flibcfs_fail.h;h=511db0209f6f8ee7db47d2272678ec8080f374eb;hp=51f07bc3990cb7f3bee98a8ba88556105e89b1aa;hb=82835a1952dcb37e8aac8c9d0666016557ea58e7;hpb=381604c5c45c7f7394185f434bb8ad1dd4ed88af

diff --git a/libcfs/include/libcfs/libcfs_fail.h b/libcfs/include/libcfs/libcfs_fail.h
index 51f07bc..511db02 100644
--- a/libcfs/include/libcfs/libcfs_fail.h
+++ b/libcfs/include/libcfs/libcfs_fail.h
@@ -16,17 +16,13 @@
  * You should have received a copy of the GNU General Public License
  * version 2 along with this program; If not, see http://www.gnu.org/licenses
  *
- * Please contact Oracle Corporation, Inc., 500 Oracle Parkway, Redwood Shores,
- * CA 94065 USA or visit www.oracle.com if you need additional information or
- * have any questions.
- *
  * GPL HEADER END
  */
 /*
  * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
  * Use is subject to license terms.
  *
- * Copyright (c) 2011, 2012, Intel Corporation.
+ * Copyright (c) 2011, 2014, Intel Corporation.
  */
 /*
  * This file is part of Lustre, http://www.lustre.org/
@@ -38,6 +34,7 @@
 
 extern unsigned long cfs_fail_loc;
 extern unsigned int cfs_fail_val;
+extern int cfs_fail_err;
 
 extern wait_queue_head_t cfs_race_waitq;
 extern int cfs_race_state;
@@ -52,17 +49,21 @@ enum {
         CFS_FAIL_LOC_VALUE      = 3
 };
 
+/* Failure ranges
+	"0x0100 - 0x3fff" for Lustre
+	"0xe000 - 0xefff" for LNet
+	"0xf000 - 0xffff" for LNDs */
 /* Failure injection control */
 #define CFS_FAIL_MASK_SYS    0x0000FF00
 #define CFS_FAIL_MASK_LOC   (0x000000FF | CFS_FAIL_MASK_SYS)
 
 #define CFS_FAILED_BIT       30
 /* CFS_FAILED is 0x40000000 */
-#define CFS_FAILED          (1 << CFS_FAILED_BIT)
+#define CFS_FAILED          BIT(CFS_FAILED_BIT)
 
 #define CFS_FAIL_ONCE_BIT    31
 /* CFS_FAIL_ONCE is 0x80000000 */
-#define CFS_FAIL_ONCE       (1 << CFS_FAIL_ONCE_BIT)
+#define CFS_FAIL_ONCE       BIT(CFS_FAIL_ONCE_BIT)
 
 /* The following flags aren't made to be combined */
 #define CFS_FAIL_SKIP        0x20000000 /* skip N times then fail */
@@ -70,9 +71,15 @@ enum {
 #define CFS_FAIL_RAND        0x08000000 /* fail 1/N of the times */
 #define CFS_FAIL_USR1        0x04000000 /* user flag */
 
-#define CFS_FAIL_PRECHECK(id) (cfs_fail_loc &&                                \
-                              (cfs_fail_loc & CFS_FAIL_MASK_LOC) ==           \
-                              ((id) & CFS_FAIL_MASK_LOC))
+/* CFS_FAULT may be combined with any one of the above flags. */
+#define CFS_FAULT	     0x02000000 /* match any CFS_FAULT_CHECK */
+
+static inline bool CFS_FAIL_PRECHECK(__u32 id)
+{
+	return cfs_fail_loc != 0 &&
+	      ((cfs_fail_loc & CFS_FAIL_MASK_LOC) == (id & CFS_FAIL_MASK_LOC) ||
+	       (cfs_fail_loc & id & CFS_FAULT));
+}
 
 static inline int cfs_fail_check_set(__u32 id, __u32 value,
 				     int set, int quiet)
@@ -146,7 +153,9 @@ static inline int cfs_fail_timeout_set(__u32 id, __u32 value, int ms, int set)
 #define CFS_FAIL_TIMEOUT_MS_ORSET(id, value, ms) \
         cfs_fail_timeout_set(id, value, ms, CFS_FAIL_LOC_ORSET)
 
-#ifdef __KERNEL__
+#define CFS_FAULT_CHECK(id)			\
+	CFS_FAIL_CHECK(CFS_FAULT | (id))
+
 /* The idea here is to synchronise two threads to force a race. The
  * first thread that calls this with a matching fail_loc is put to
  * sleep. The next thread that calls with the same fail_loc wakes up
@@ -158,9 +167,15 @@ static inline void cfs_race(__u32 id)
 			int rc;
 			cfs_race_state = 0;
 			CERROR("cfs_race id %x sleeping\n", id);
-			rc = wait_event_interruptible(cfs_race_waitq,
-						      cfs_race_state != 0);
-			CERROR("cfs_fail_race id %x awake, rc=%d\n", id, rc);
+			/*
+			 * XXX: don't wait forever as there is no guarantee
+			 * that this branch is executed first. for testing
+			 * purposes this construction works good enough
+			 */
+			rc = wait_event_interruptible_timeout(cfs_race_waitq,
+						      cfs_race_state != 0,
+						      cfs_time_seconds(5));
+			CERROR("cfs_fail_race id %x awake: rc=%d\n", id, rc);
 		} else {
 			CERROR("cfs_fail_race id %x waking\n", id);
 			cfs_race_state = 1;
@@ -169,9 +184,43 @@ static inline void cfs_race(__u32 id)
 	}
 }
 #define CFS_RACE(id) cfs_race(id)
-#else
-/* sigh.  an expedient fix until CFS_RACE is fixed up */
-#define CFS_RACE(foo) do {} while(0)
-#endif
+
+/**
+ * Wait on race.
+ *
+ * The first thread that calls this with a matching fail_loc is put to sleep,
+ * but subseqent callers of this won't sleep. Until another thread that calls
+ * cfs_race_wakeup(), the first thread will be woken up and continue.
+ */
+static inline void cfs_race_wait(__u32 id)
+{
+	if (CFS_FAIL_PRECHECK(id)) {
+		if (unlikely(__cfs_fail_check_set(id, 0, CFS_FAIL_LOC_NOSET))) {
+			int rc;
+
+			cfs_race_state = 0;
+			CERROR("cfs_race id %x sleeping\n", id);
+			rc = wait_event_interruptible(cfs_race_waitq,
+						      cfs_race_state != 0);
+			CERROR("cfs_fail_race id %x awake: rc=%d\n", id, rc);
+		}
+	}
+}
+#define CFS_RACE_WAIT(id) cfs_race_wait(id)
+
+/**
+ * Wake up the thread that is waiting on the matching fail_loc.
+ */
+static inline void cfs_race_wakeup(__u32 id)
+{
+	if (CFS_FAIL_PRECHECK(id)) {
+		if (likely(!__cfs_fail_check_set(id, 0, CFS_FAIL_LOC_NOSET))) {
+			CERROR("cfs_fail_race id %x waking\n", id);
+			cfs_race_state = 1;
+			wake_up(&cfs_race_waitq);
+		}
+	}
+}
+#define CFS_RACE_WAKEUP(id) cfs_race_wakeup(id)
 
 #endif /* _LIBCFS_FAIL_H */