IB/qib: Do not write EEPROM

commit 18c0b82a upstream.

This changeset removes all the code that allows the driver to write to
the EEPROM and update the recorded error counters and power on hours.

These two stats are unused and writing them exposes a timing risk
which could leave the EEPROM in a bad state preventing further normal
operation of the HCA.
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mitko Haralanov <mitko.haralanov@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
[lizf: Backported to 3.4: adjust context]
Signed-off-by: Zefan Li <lizefan@huawei.com>

drivers/infiniband/hw/qib/qib.h

@@ -1013,12 +1013,6 @@ struct qib_devdata {
 	/* control high-level access to EEPROM */
 	struct mutex eep_lock;
 	uint64_t traffic_wds;
-	/* active time is kept in seconds, but logged in hours */
-	atomic_t active_time;
-	/* Below are nominal shadow of EEPROM, new since last EEPROM update */
-	uint8_t eep_st_errs[QIB_EEP_LOG_CNT];
-	uint8_t eep_st_new_errs[QIB_EEP_LOG_CNT];
-	uint16_t eep_hrs;
 	/*
 	 * masks for which bits of errs, hwerrs that cause
 	 * each of the counters to increment.
@@ -1235,8 +1229,7 @@ int qib_twsi_blk_rd(struct qib_devdata *dd, int dev, int addr, void *buffer,
 int qib_twsi_blk_wr(struct qib_devdata *dd, int dev, int addr,
 		    const void *buffer, int len);
 void qib_get_eeprom_info(struct qib_devdata *);
-int qib_update_eeprom_log(struct qib_devdata *dd);
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr);
+#define qib_inc_eeprom_err(dd, eidx, incr)
 void qib_dump_lookup_output_queue(struct qib_devdata *);
 void qib_force_pio_avail_update(struct qib_devdata *);
 void qib_clear_symerror_on_linkup(unsigned long opaque);

drivers/infiniband/hw/qib/qib_eeprom.c

@@ -263,189 +263,8 @@ void qib_get_eeprom_info(struct qib_devdata *dd)
 		qib_dev_err(dd, "Board SN %s did not pass functional "
 			    "test: %s\n", dd->serial, ifp->if_comment);
 
-	memcpy(&dd->eep_st_errs, &ifp->if_errcntp, QIB_EEP_LOG_CNT);
-	/*
-	 * Power-on (actually "active") hours are kept as little-endian value
-	 * in EEPROM, but as seconds in a (possibly as small as 24-bit)
-	 * atomic_t while running.
-	 */
-	atomic_set(&dd->active_time, 0);
-	dd->eep_hrs = ifp->if_powerhour[0] | (ifp->if_powerhour[1] << 8);
-
 done:
 	vfree(buf);
 
 bail:;
 }
-
-/**
- * qib_update_eeprom_log - copy active-time and error counters to eeprom
- * @dd: the qlogic_ib device
- *
- * Although the time is kept as seconds in the qib_devdata struct, it is
- * rounded to hours for re-write, as we have only 16 bits in EEPROM.
- * First-cut code reads whole (expected) struct qib_flash, modifies,
- * re-writes. Future direction: read/write only what we need, assuming
- * that the EEPROM had to have been "good enough" for driver init, and
- * if not, we aren't making it worse.
- *
- */
-int qib_update_eeprom_log(struct qib_devdata *dd)
-{
-	void *buf;
-	struct qib_flash *ifp;
-	int len, hi_water;
-	uint32_t new_time, new_hrs;
-	u8 csum;
-	int ret, idx;
-	unsigned long flags;
-
-	/* first, check if we actually need to do anything. */
-	ret = 0;
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		if (dd->eep_st_new_errs[idx]) {
-			ret = 1;
-			break;
-		}
-	}
-	new_time = atomic_read(&dd->active_time);
-
-	if (ret == 0 && new_time < 3600)
-		goto bail;
-
-	/*
-	 * The quick-check above determined that there is something worthy
-	 * of logging, so get current contents and do a more detailed idea.
-	 * read full flash, not just currently used part, since it may have
-	 * been written with a newer definition
-	 */
-	len = sizeof(struct qib_flash);
-	buf = vmalloc(len);
-	ret = 1;
-	if (!buf) {
-		qib_dev_err(dd, "Couldn't allocate memory to read %u "
-			    "bytes from eeprom for logging\n", len);
-		goto bail;
-	}
-
-	/* Grab semaphore and read current EEPROM. If we get an
-	 * error, let go, but if not, keep it until we finish write.
-	 */
-	ret = mutex_lock_interruptible(&dd->eep_lock);
-	if (ret) {
-		qib_dev_err(dd, "Unable to acquire EEPROM for logging\n");
-		goto free_bail;
-	}
-	ret = qib_twsi_blk_rd(dd, dd->twsi_eeprom_dev, 0, buf, len);
-	if (ret) {
-		mutex_unlock(&dd->eep_lock);
-		qib_dev_err(dd, "Unable read EEPROM for logging\n");
-		goto free_bail;
-	}
-	ifp = (struct qib_flash *)buf;
-
-	csum = flash_csum(ifp, 0);
-	if (csum != ifp->if_csum) {
-		mutex_unlock(&dd->eep_lock);
-		qib_dev_err(dd, "EEPROM cks err (0x%02X, S/B 0x%02X)\n",
-			    csum, ifp->if_csum);
-		ret = 1;
-		goto free_bail;
-	}
-	hi_water = 0;
-	spin_lock_irqsave(&dd->eep_st_lock, flags);
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		int new_val = dd->eep_st_new_errs[idx];
-		if (new_val) {
-			/*
-			 * If we have seen any errors, add to EEPROM values
-			 * We need to saturate at 0xFF (255) and we also
-			 * would need to adjust the checksum if we were
-			 * trying to minimize EEPROM traffic
-			 * Note that we add to actual current count in EEPROM,
-			 * in case it was altered while we were running.
-			 */
-			new_val += ifp->if_errcntp[idx];
-			if (new_val > 0xFF)
-				new_val = 0xFF;
-			if (ifp->if_errcntp[idx] != new_val) {
-				ifp->if_errcntp[idx] = new_val;
-				hi_water = offsetof(struct qib_flash,
-						    if_errcntp) + idx;
-			}
-			/*
-			 * update our shadow (used to minimize EEPROM
-			 * traffic), to match what we are about to write.
-			 */
-			dd->eep_st_errs[idx] = new_val;
-			dd->eep_st_new_errs[idx] = 0;
-		}
-	}
-	/*
-	 * Now update active-time. We would like to round to the nearest hour
-	 * but unless atomic_t are sure to be proper signed ints we cannot,
-	 * because we need to account for what we "transfer" to EEPROM and
-	 * if we log an hour at 31 minutes, then we would need to set
-	 * active_time to -29 to accurately count the _next_ hour.
-	 */
-	if (new_time >= 3600) {
-		new_hrs = new_time / 3600;
-		atomic_sub((new_hrs * 3600), &dd->active_time);
-		new_hrs += dd->eep_hrs;
-		if (new_hrs > 0xFFFF)
-			new_hrs = 0xFFFF;
-		dd->eep_hrs = new_hrs;
-		if ((new_hrs & 0xFF) != ifp->if_powerhour[0]) {
-			ifp->if_powerhour[0] = new_hrs & 0xFF;
-			hi_water = offsetof(struct qib_flash, if_powerhour);
-		}
-		if ((new_hrs >> 8) != ifp->if_powerhour[1]) {
-			ifp->if_powerhour[1] = new_hrs >> 8;
-			hi_water = offsetof(struct qib_flash, if_powerhour) + 1;
-		}
-	}
-	/*
-	 * There is a tiny possibility that we could somehow fail to write
-	 * the EEPROM after updating our shadows, but problems from holding
-	 * the spinlock too long are a much bigger issue.
-	 */
-	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
-	if (hi_water) {
-		/* we made some change to the data, uopdate cksum and write */
-		csum = flash_csum(ifp, 1);
-		ret = eeprom_write_with_enable(dd, 0, buf, hi_water + 1);
-	}
-	mutex_unlock(&dd->eep_lock);
-	if (ret)
-		qib_dev_err(dd, "Failed updating EEPROM\n");
-
-free_bail:
-	vfree(buf);
-bail:
-	return ret;
-}
-
-/**
- * qib_inc_eeprom_err - increment one of the four error counters
- * that are logged to EEPROM.
- * @dd: the qlogic_ib device
- * @eidx: 0..3, the counter to increment
- * @incr: how much to add
- *
- * Each counter is 8-bits, and saturates at 255 (0xFF). They
- * are copied to the EEPROM (aka flash) whenever qib_update_eeprom_log()
- * is called, but it can only be called in a context that allows sleep.
- * This function can be called even at interrupt level.
- */
-void qib_inc_eeprom_err(struct qib_devdata *dd, u32 eidx, u32 incr)
-{
-	uint new_val;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dd->eep_st_lock, flags);
-	new_val = dd->eep_st_new_errs[eidx] + incr;
-	if (new_val > 255)
-		new_val = 255;
-	dd->eep_st_new_errs[eidx] = new_val;
-	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
-}

drivers/infiniband/hw/qib/qib_iba6120.c

@@ -2674,8 +2674,6 @@ static void qib_get_6120_faststats(unsigned long opaque)
 	spin_lock_irqsave(&dd->eep_st_lock, flags);
 	traffic_wds -= dd->traffic_wds;
 	dd->traffic_wds += traffic_wds;
-	if (traffic_wds  >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-		atomic_add(5, &dd->active_time); /* S/B #define */
 	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
 
 	qib_chk_6120_errormask(dd);

drivers/infiniband/hw/qib/qib_iba7220.c

@@ -3292,8 +3292,6 @@ static void qib_get_7220_faststats(unsigned long opaque)
 	spin_lock_irqsave(&dd->eep_st_lock, flags);
 	traffic_wds -= dd->traffic_wds;
 	dd->traffic_wds += traffic_wds;
-	if (traffic_wds  >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-		atomic_add(5, &dd->active_time); /* S/B #define */
 	spin_unlock_irqrestore(&dd->eep_st_lock, flags);
 done:
 	mod_timer(&dd->stats_timer, jiffies + HZ * ACTIVITY_TIMER);

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -4841,8 +4841,6 @@ static void qib_get_7322_faststats(unsigned long opaque)
 		spin_lock_irqsave(&ppd->dd->eep_st_lock, flags);
 		traffic_wds -= ppd->dd->traffic_wds;
 		ppd->dd->traffic_wds += traffic_wds;
-		if (traffic_wds >= QIB_TRAFFIC_ACTIVE_THRESHOLD)
-			atomic_add(ACTIVITY_TIMER, &ppd->dd->active_time);
 		spin_unlock_irqrestore(&ppd->dd->eep_st_lock, flags);
 		if (ppd->cpspec->qdr_dfe_on && (ppd->link_speed_active &
 						QIB_IB_QDR) &&

drivers/infiniband/hw/qib/qib_init.c

@@ -765,7 +765,6 @@ static void qib_shutdown_device(struct qib_devdata *dd)
 		dd->f_quiet_serdes(ppd);
 	}
 
-	qib_update_eeprom_log(dd);
 }
 
 /**

drivers/infiniband/hw/qib/qib_sysfs.c

@@ -550,28 +550,6 @@ static ssize_t store_chip_reset(struct device *device,
 	return ret < 0 ? ret : count;
 }
 
-static ssize_t show_logged_errs(struct device *device,
-				struct device_attribute *attr, char *buf)
-{
-	struct qib_ibdev *dev =
-		container_of(device, struct qib_ibdev, ibdev.dev);
-	struct qib_devdata *dd = dd_from_dev(dev);
-	int idx, count;
-
-	/* force consistency with actual EEPROM */
-	if (qib_update_eeprom_log(dd) != 0)
-		return -ENXIO;
-
-	count = 0;
-	for (idx = 0; idx < QIB_EEP_LOG_CNT; ++idx) {
-		count += scnprintf(buf + count, PAGE_SIZE - count, "%d%c",
-				   dd->eep_st_errs[idx],
-				   idx == (QIB_EEP_LOG_CNT - 1) ? '\n' : ' ');
-	}
-
-	return count;
-}
-
 /*
  * Dump tempsense regs. in decimal, to ease shell-scripts.
  */
@@ -618,7 +596,6 @@ static DEVICE_ATTR(nctxts, S_IRUGO, show_nctxts, NULL);
 static DEVICE_ATTR(nfreectxts, S_IRUGO, show_nfreectxts, NULL);
 static DEVICE_ATTR(serial, S_IRUGO, show_serial, NULL);
 static DEVICE_ATTR(boardversion, S_IRUGO, show_boardversion, NULL);
-static DEVICE_ATTR(logged_errors, S_IRUGO, show_logged_errs, NULL);
 static DEVICE_ATTR(tempsense, S_IRUGO, show_tempsense, NULL);
 static DEVICE_ATTR(localbus_info, S_IRUGO, show_localbus_info, NULL);
 static DEVICE_ATTR(chip_reset, S_IWUSR, NULL, store_chip_reset);
@@ -632,7 +609,6 @@ static struct device_attribute *qib_attributes[] = {
 	&dev_attr_nfreectxts,
 	&dev_attr_serial,
 	&dev_attr_boardversion,
-	&dev_attr_logged_errors,
 	&dev_attr_tempsense,
 	&dev_attr_localbus_info,
 	&dev_attr_chip_reset,