[PATCH] s390: dasd extended error reporting

The DASD extended error reporting is a facility that allows to get detailed
information about certain problems in the DASD I/O.  This information can be
used to implement fail-over applications that can recover these problems.
Signed-off-by: Stefan Weinhuber <wein@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

drivers/s390/block/Kconfig

@@ -55,4 +55,12 @@ config DASD_DIAG
 	  Disks under VM.  If you are not running under VM or unsure what it is,
 	  say "N".
 
+config DASD_EER
+	bool "Extended error reporting (EER)"
+	depends on DASD
+	help
+	  This driver provides a character device interface to the
+	  DASD extended error reporting. This is only needed if you want to
+	  use applications written for the EER facility.
+
 endif

drivers/s390/block/Makefile

@@ -7,6 +7,9 @@ dasd_fba_mod-objs  := dasd_fba.o dasd_3370_erp.o dasd_9336_erp.o
 dasd_diag_mod-objs := dasd_diag.o
 dasd_mod-objs      := dasd.o dasd_ioctl.o dasd_proc.o dasd_devmap.o \
 			dasd_genhd.o dasd_erp.o
+ifdef CONFIG_DASD_EER
+dasd_mod-objs      += dasd_eer.o
+endif
 
 obj-$(CONFIG_DASD) += dasd_mod.o
 obj-$(CONFIG_DASD_DIAG) += dasd_diag_mod.o

drivers/s390/block/dasd.c

@@ -151,6 +151,8 @@ dasd_state_new_to_known(struct dasd_device *device)
 static inline void
 dasd_state_known_to_new(struct dasd_device * device)
 {
+	/* Disable extended error reporting for this device. */
+	dasd_eer_disable(device);
 	/* Forget the discipline information. */
 	if (device->discipline)
 		module_put(device->discipline->owner);
@@ -892,6 +894,9 @@ dasd_handle_state_change_pending(struct dasd_device *device)
 	struct dasd_ccw_req *cqr;
 	struct list_head *l, *n;
 
+	/* First of all start sense subsystem status request. */
+	dasd_eer_snss(device);
+
 	device->stopped &= ~DASD_STOPPED_PENDING;
 
         /* restart all 'running' IO on queue */
@@ -1111,6 +1116,19 @@ restart:
 			}
 			goto restart;
 		}
+
+		/* First of all call extended error reporting. */
+		if (dasd_eer_enabled(device) &&
+		    cqr->status == DASD_CQR_FAILED) {
+			dasd_eer_write(device, cqr, DASD_EER_FATALERROR);
+
+			/* restart request  */
+			cqr->status = DASD_CQR_QUEUED;
+			cqr->retries = 255;
+			device->stopped |= DASD_STOPPED_QUIESCE;
+			goto restart;
+		}
+
 		/* Process finished ERP request. */
 		if (cqr->refers) {
 			__dasd_process_erp(device, cqr);
@@ -1248,7 +1266,8 @@ __dasd_start_head(struct dasd_device * device)
 	cqr = list_entry(device->ccw_queue.next, struct dasd_ccw_req, list);
         /* check FAILFAST */
 	if (device->stopped & ~DASD_STOPPED_PENDING &&
-	    test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags)) {
+	    test_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags) &&
+	    (!dasd_eer_enabled(device))) {
 		cqr->status = DASD_CQR_FAILED;
 		dasd_schedule_bh(device);
 	}
@@ -1807,6 +1826,7 @@ dasd_exit(void)
 #ifdef CONFIG_PROC_FS
 	dasd_proc_exit();
 #endif
+	dasd_eer_exit();
         if (dasd_page_cache != NULL) {
 		kmem_cache_destroy(dasd_page_cache);
 		dasd_page_cache = NULL;
@@ -2003,6 +2023,9 @@ dasd_generic_notify(struct ccw_device *cdev, int event)
 	switch (event) {
 	case CIO_GONE:
 	case CIO_NO_PATH:
+		/* First of all call extended error reporting. */
+		dasd_eer_write(device, NULL, DASD_EER_NOPATH);
+
 		if (device->state < DASD_STATE_BASIC)
 			break;
 		/* Device is active. We want to keep it. */
@@ -2060,6 +2083,7 @@ dasd_generic_auto_online (struct ccw_driver *dasd_discipline_driver)
 	put_driver(drv);
 }
 
+
 static int __init
 dasd_init(void)
 {
@@ -2092,6 +2116,9 @@ dasd_init(void)
 	rc = dasd_parse();
 	if (rc)
 		goto failed;
+	rc = dasd_eer_init();
+	if (rc)
+		goto failed;
 #ifdef CONFIG_PROC_FS
 	rc = dasd_proc_init();
 	if (rc)

drivers/s390/block/dasd_3990_erp.c

@@ -1108,6 +1108,9 @@ dasd_3990_handle_env_data(struct dasd_ccw_req * erp, char *sense)
 		case 0x0B:
 			DEV_MESSAGE(KERN_WARNING, device, "%s",
 				    "FORMAT F - Volume is suspended duplex");
+			/* call extended error reporting (EER) */
+			dasd_eer_write(device, erp->refers,
+				       DASD_EER_PPRCSUSPEND);
 			break;
 		case 0x0C:
 			DEV_MESSAGE(KERN_WARNING, device, "%s",

drivers/s390/block/dasd_devmap.c

@@ -715,10 +715,51 @@ dasd_discipline_show(struct device *dev, struct device_attribute *attr, char *bu
 
 static DEVICE_ATTR(discipline, 0444, dasd_discipline_show, NULL);
 
+/*
+ * extended error-reporting
+ */
+static ssize_t
+dasd_eer_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct dasd_devmap *devmap;
+	int eer_flag;
+
+	devmap = dasd_find_busid(dev->bus_id);
+	if (!IS_ERR(devmap) && devmap->device)
+		eer_flag = dasd_eer_enabled(devmap->device);
+	else
+		eer_flag = 0;
+	return snprintf(buf, PAGE_SIZE, eer_flag ? "1\n" : "0\n");
+}
+
+static ssize_t
+dasd_eer_store(struct device *dev, struct device_attribute *attr,
+	       const char *buf, size_t count)
+{
+	struct dasd_devmap *devmap;
+	int rc;
+
+	devmap = dasd_devmap_from_cdev(to_ccwdev(dev));
+	if (IS_ERR(devmap))
+		return PTR_ERR(devmap);
+	if (!devmap->device)
+		return count;
+	if (buf[0] == '1') {
+		rc = dasd_eer_enable(devmap->device);
+		if (rc)
+			return rc;
+	} else
+		dasd_eer_disable(devmap->device);
+	return count;
+}
+
+static DEVICE_ATTR(eer_enabled, 0644, dasd_eer_show, dasd_eer_store);
+
 static struct attribute * dasd_attrs[] = {
 	&dev_attr_readonly.attr,
 	&dev_attr_discipline.attr,
 	&dev_attr_use_diag.attr,
+	&dev_attr_eer_enabled.attr,
 	NULL,
 };
 

drivers/s390/block/dasd_eckd.h

@@ -29,6 +29,7 @@
 #define DASD_ECKD_CCW_PSF		 0x27
 #define DASD_ECKD_CCW_RSSD		 0x3e
 #define DASD_ECKD_CCW_LOCATE_RECORD	 0x47
+#define DASD_ECKD_CCW_SNSS		 0x54
 #define DASD_ECKD_CCW_DEFINE_EXTENT	 0x63
 #define DASD_ECKD_CCW_WRITE_MT		 0x85
 #define DASD_ECKD_CCW_READ_MT		 0x86

drivers/s390/block/dasd_int.h

@@ -268,6 +268,23 @@ struct dasd_discipline {
 
 extern struct dasd_discipline *dasd_diag_discipline_pointer;
 
+
+/*
+ * Notification numbers for extended error reporting notifications:
+ * The DASD_EER_DISABLE notification is sent before a dasd_device (and it's
+ * eer pointer) is freed. The error reporting module needs to do all necessary
+ * cleanup steps.
+ * The DASD_EER_TRIGGER notification sends the actual error reports (triggers).
+ */
+#define DASD_EER_DISABLE 0
+#define DASD_EER_TRIGGER 1
+
+/* Trigger IDs for extended error reporting DASD_EER_TRIGGER notification */
+#define DASD_EER_FATALERROR  1
+#define DASD_EER_NOPATH      2
+#define DASD_EER_STATECHANGE 3
+#define DASD_EER_PPRCSUSPEND 4
+
 struct dasd_device {
 	/* Block device stuff. */
 	struct gendisk *gdp;
@@ -281,6 +298,9 @@ struct dasd_device {
 	unsigned long flags;		/* per device flags */
 	unsigned short features;        /* copy of devmap-features (read-only!) */
 
+	/* extended error reporting stuff (eer) */
+	struct dasd_ccw_req *eer_cqr;
+
 	/* Device discipline stuff. */
 	struct dasd_discipline *discipline;
 	struct dasd_discipline *base_discipline;
@@ -326,6 +346,8 @@ struct dasd_device {
 /* per device flags */
 #define DASD_FLAG_DSC_ERROR	2	/* return -EIO when disconnected */
 #define DASD_FLAG_OFFLINE	3	/* device is in offline processing */
+#define DASD_FLAG_EER_SNSS	4	/* A SNSS is required */
+#define DASD_FLAG_EER_IN_USE	5	/* A SNSS request is running */
 
 void dasd_put_device_wake(struct dasd_device *);
 
@@ -545,6 +567,30 @@ dasd_era_t dasd_9336_erp_examine(struct dasd_ccw_req *, struct irb *);
 dasd_era_t dasd_9343_erp_examine(struct dasd_ccw_req *, struct irb *);
 struct dasd_ccw_req *dasd_9343_erp_action(struct dasd_ccw_req *);
 
+/* externals in dasd_eer.c */
+#ifdef CONFIG_DASD_EER
+int dasd_eer_init(void);
+void dasd_eer_exit(void);
+int dasd_eer_enable(struct dasd_device *);
+void dasd_eer_disable(struct dasd_device *);
+void dasd_eer_write(struct dasd_device *, struct dasd_ccw_req *cqr,
+		    unsigned int id);
+void dasd_eer_snss(struct dasd_device *);
+
+static inline int dasd_eer_enabled(struct dasd_device *device)
+{
+	return device->eer_cqr != NULL;
+}
+#else
+#define dasd_eer_init()		(0)
+#define dasd_eer_exit()		do { } while (0)
+#define dasd_eer_enable(d)	(0)
+#define dasd_eer_disable(d)	do { } while (0)
+#define dasd_eer_write(d,c,i)	do { } while (0)
+#define dasd_eer_snss(d)	do { } while (0)
+#define dasd_eer_enabled(d)	(0)
+#endif	/* CONFIG_DASD_ERR */
+
 #endif				/* __KERNEL__ */
 
 #endif				/* DASD_H */