mtd: bitflip_threshold added to mtd_info and sysfs

An element 'bitflip_threshold' is added to struct mtd_info, and also exposed as
a read/write variable in sysfs.  This will be used to determine whether or not
mtd_read() returns -EUCLEAN or 0 (absent a hard error).  If the driver leaves it
as zero, mtd will set it to a default value of ecc_strength.

This v2 adds the line that propagates bitflip_threshold from the master to the
partitions - thanks Ivan¹.

¹ http://lists.infradead.org/pipermail/linux-mtd/2012-April/040900.html

Signed-off-by: Mike Dunn <mikedunn@newsguy.com>
Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

4 files changed, 80 insertions, 0 deletions

diff --git a/Documentation/ABI/testing/sysfs-class-mtd b/Documentation/ABI/testing/sysfs-class-mtd
index 43d1818..7883508 100644
--- a/Documentation/ABI/testing/sysfs-class-mtd
+++ b/Documentation/ABI/testing/sysfs-class-mtd
@@ -135,3 +135,39 @@ Description:
 		have multiple ecc steps within each writesize region.
 
 		In the case of devices lacking any ECC capability, it is 0.
+
+What:		/sys/class/mtd/mtdX/bitflip_threshold
+Date:		April 2012
+KernelVersion:	3.4
+Contact:	linux-mtd@lists.infradead.org
+Description:
+		This allows the user to examine and adjust the criteria by which
+		mtd returns -EUCLEAN from mtd_read().  If the maximum number of
+		bit errors that were corrected on any single region comprising
+		an ecc step (as reported by the driver) equals or exceeds this
+		value, -EUCLEAN is returned.  Otherwise, absent an error, 0 is
+		returned.  Higher layers (e.g., UBI) use this return code as an
+		indication that an erase block may be degrading and should be
+		scrutinized as a candidate for being marked as bad.
+
+		The initial value may be specified by the flash device driver.
+		If not, then the default value is ecc_strength.
+
+		The introduction of this feature brings a subtle change to the
+		meaning of the -EUCLEAN return code.  Previously, it was
+		interpreted to mean simply "one or more bit errors were
+		corrected".  Its new interpretation can be phrased as "a
+		dangerously high number of bit errors were corrected on one or
+		more regions comprising an ecc step".  The precise definition of
+		"dangerously high" can be adjusted by the user with
+		bitflip_threshold.  Users are discouraged from doing this,
+		however, unless they know what they are doing and have intimate
+		knowledge of the properties of their device.  Broadly speaking,
+		bitflip_threshold should be low enough to detect genuine erase
+		block degradation, but high enough to avoid the consequences of
+		a persistent return value of -EUCLEAN on devices where sticky
+		bitflips occur.  Note that if bitflip_threshold exceeds
+		ecc_strength, -EUCLEAN is never returned by the read functions.
+
+		This is generally applicable only to NAND flash devices with ECC
+		capability.  It is ignored on devices lacking ECC capability.
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 090e849..6a7cba1 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -259,6 +259,34 @@ static ssize_t mtd_ecc_strength_show(struct device *dev,
 }
 static DEVICE_ATTR(ecc_strength, S_IRUGO, mtd_ecc_strength_show, NULL);
 
+static ssize_t mtd_bitflip_threshold_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct mtd_info *mtd = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", mtd->bitflip_threshold);
+}
+
+static ssize_t mtd_bitflip_threshold_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
+{
+	struct mtd_info *mtd = dev_get_drvdata(dev);
+	unsigned int bitflip_threshold;
+	int retval;
+
+	retval = kstrtouint(buf, 0, &bitflip_threshold);
+	if (retval)
+		return retval;
+
+	mtd->bitflip_threshold = bitflip_threshold;
+	return count;
+}
+static DEVICE_ATTR(bitflip_threshold, S_IRUGO | S_IWUSR,
+		   mtd_bitflip_threshold_show,
+		   mtd_bitflip_threshold_store);
+
 static struct attribute *mtd_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_flags.attr,
@@ -270,6 +298,7 @@ static struct attribute *mtd_attrs[] = {
 	&dev_attr_numeraseregions.attr,
 	&dev_attr_name.attr,
 	&dev_attr_ecc_strength.attr,
+	&dev_attr_bitflip_threshold.attr,
 	NULL,
 };
 
@@ -332,6 +361,10 @@ int add_mtd_device(struct mtd_info *mtd)
 	mtd->index = i;
 	mtd->usecount = 0;
 
+	/* default value if not set by driver */
+	if (mtd->bitflip_threshold == 0)
+		mtd->bitflip_threshold = mtd->ecc_strength;
+
 	if (is_power_of_2(mtd->erasesize))
 		mtd->erasesize_shift = ffs(mtd->erasesize) - 1;
 	else
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 9651c06..ec75d44 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -517,6 +517,8 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 
 	slave->mtd.ecclayout = master->ecclayout;
 	slave->mtd.ecc_strength = master->ecc_strength;
+	slave->mtd.bitflip_threshold = master->bitflip_threshold;
+
 	if (master->_block_isbad) {
 		uint64_t offs = 0;
 
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index cd0119d19..63dadc0 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -157,6 +157,15 @@ struct mtd_info {
 	unsigned int erasesize_mask;
 	unsigned int writesize_mask;
 
+	/*
+	 * read ops return -EUCLEAN if max number of bitflips corrected on any
+	 * one region comprising an ecc step equals or exceeds this value.
+	 * Settable by driver, else defaults to ecc_strength.  User can override
+	 * in sysfs.  N.B. The meaning of the -EUCLEAN return code has changed;
+	 * see Documentation/ABI/testing/sysfs-class-mtd for more detail.
+	 */
+	unsigned int bitflip_threshold;
+
 	// Kernel-only stuff starts here.
 	const char *name;
 	int index;