badblocks: Add core badblock management code

Take the core badblocks implementation from md, and make it generally
available. This follows the same style as kernel implementations of
linked lists, rb-trees etc, where you can have a structure that can be
embedded anywhere, and accessor functions to manipulate the data.

The only changes in this copy of the code are ones to generalize
function/variable names from md-specific ones. Also add init and free
functions.

Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

2 files changed, 562 insertions, 1 deletions

diff --git a/block/Makefile b/block/Makefile
index 00ecc97629db..db5f622c9d67 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -8,7 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
                         blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \
                         blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
                         genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
-                        partitions/
+                        badblocks.o partitions/
 
 obj-$(CONFIG_BOUNCE)    += bounce.o
 obj-$(CONFIG_BLK_DEV_BSG)       += bsg.o
diff --git a/block/badblocks.c b/block/badblocks.c
new file mode 100644
index 000000000000..96aeb9194a2e
--- /dev/null
+++ b/block/badblocks.c
@@ -0,0 +1,561 @@
+/*
+ * Bad block management
+ *
+ * - Heavily based on MD badblocks code from Neil Brown
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/badblocks.h>
+#include <linux/seqlock.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+
+/**
+ * badblocks_check() - check a given range for bad sectors
+ * @bb:         the badblocks structure that holds all badblock information
+ * @s:          sector (start) at which to check for badblocks
+ * @sectors:    number of sectors to check for badblocks
+ * @first_bad:  pointer to store location of the first badblock
+ * @bad_sectors: pointer to store number of badblocks after @first_bad
+ *
+ * We can record which blocks on each device are 'bad' and so just
+ * fail those blocks, or that stripe, rather than the whole device.
+ * Entries in the bad-block table are 64bits wide.  This comprises:
+ * Length of bad-range, in sectors: 0-511 for lengths 1-512
+ * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes)
+ *  A 'shift' can be set so that larger blocks are tracked and
+ *  consequently larger devices can be covered.
+ * 'Acknowledged' flag - 1 bit. - the most significant bit.
+ *
+ * Locking of the bad-block table uses a seqlock so badblocks_check
+ * might need to retry if it is very unlucky.
+ * We will sometimes want to check for bad blocks in a bi_end_io function,
+ * so we use the write_seqlock_irq variant.
+ *
+ * When looking for a bad block we specify a range and want to
+ * know if any block in the range is bad.  So we binary-search
+ * to the last range that starts at-or-before the given endpoint,
+ * (or "before the sector after the target range")
+ * then see if it ends after the given start.
+ *
+ * Return:
+ *  0: there are no known bad blocks in the range
+ *  1: there are known bad block which are all acknowledged
+ * -1: there are bad blocks which have not yet been acknowledged in metadata.
+ * plus the start/length of the first bad section we overlap.
+ */
+int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
+                        sector_t *first_bad, int *bad_sectors)
+{
+        int hi;
+        int lo;
+        u64 *p = bb->page;
+        int rv;
+        sector_t target = s + sectors;
+        unsigned seq;
+
+        if (bb->shift > 0) {
+                /* round the start down, and the end up */
+                s >>= bb->shift;
+                target += (1<<bb->shift) - 1;
+                target >>= bb->shift;
+                sectors = target - s;
+        }
+        /* 'target' is now the first block after the bad range */
+
+retry:
+        seq = read_seqbegin(&bb->lock);
+        lo = 0;
+        rv = 0;
+        hi = bb->count;
+
+        /* Binary search between lo and hi for 'target'
+         * i.e. for the last range that starts before 'target'
+         */
+        /* INVARIANT: ranges before 'lo' and at-or-after 'hi'
+         * are known not to be the last range before target.
+         * VARIANT: hi-lo is the number of possible
+         * ranges, and decreases until it reaches 1
+         */
+        while (hi - lo > 1) {
+                int mid = (lo + hi) / 2;
+                sector_t a = BB_OFFSET(p[mid]);
+
+                if (a < target)
+                        /* This could still be the one, earlier ranges
+                         * could not.
+                         */
+                        lo = mid;
+                else
+                        /* This and later ranges are definitely out. */
+                        hi = mid;
+        }
+        /* 'lo' might be the last that started before target, but 'hi' isn't */
+        if (hi > lo) {
+                /* need to check all range that end after 's' to see if
+                 * any are unacknowledged.
+                 */
+                while (lo >= 0 &&
+                       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+                        if (BB_OFFSET(p[lo]) < target) {
+                                /* starts before the end, and finishes after
+                                 * the start, so they must overlap
+                                 */
+                                if (rv != -1 && BB_ACK(p[lo]))
+                                        rv = 1;
+                                else
+                                        rv = -1;
+                                *first_bad = BB_OFFSET(p[lo]);
+                                *bad_sectors = BB_LEN(p[lo]);
+                        }
+                        lo--;
+                }
+        }
+
+        if (read_seqretry(&bb->lock, seq))
+                goto retry;
+
+        return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_check);
+
+/**
+ * badblocks_set() - Add a range of bad blocks to the table.
+ * @bb:         the badblocks structure that holds all badblock information
+ * @s:          first sector to mark as bad
+ * @sectors:    number of sectors to mark as bad
+ * @acknowledged: weather to mark the bad sectors as acknowledged
+ *
+ * This might extend the table, or might contract it if two adjacent ranges
+ * can be merged. We binary-search to find the 'insertion' point, then
+ * decide how best to handle it.
+ *
+ * Return:
+ *  0: success
+ *  1: failed to set badblocks (out of space)
+ */
+int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
+                        int acknowledged)
+{
+        u64 *p;
+        int lo, hi;
+        int rv = 0;
+        unsigned long flags;
+
+        if (bb->shift < 0)
+                /* badblocks are disabled */
+                return 0;
+
+        if (bb->shift) {
+                /* round the start down, and the end up */
+                sector_t next = s + sectors;
+
+                s >>= bb->shift;
+                next += (1<<bb->shift) - 1;
+                next >>= bb->shift;
+                sectors = next - s;
+        }
+
+        write_seqlock_irqsave(&bb->lock, flags);
+
+        p = bb->page;
+        lo = 0;
+        hi = bb->count;
+        /* Find the last range that starts at-or-before 's' */
+        while (hi - lo > 1) {
+                int mid = (lo + hi) / 2;
+                sector_t a = BB_OFFSET(p[mid]);
+
+                if (a <= s)
+                        lo = mid;
+                else
+                        hi = mid;
+        }
+        if (hi > lo && BB_OFFSET(p[lo]) > s)
+                hi = lo;
+
+        if (hi > lo) {
+                /* we found a range that might merge with the start
+                 * of our new range
+                 */
+                sector_t a = BB_OFFSET(p[lo]);
+                sector_t e = a + BB_LEN(p[lo]);
+                int ack = BB_ACK(p[lo]);
+
+                if (e >= s) {
+                        /* Yes, we can merge with a previous range */
+                        if (s == a && s + sectors >= e)
+                                /* new range covers old */
+                                ack = acknowledged;
+                        else
+                                ack = ack && acknowledged;
+
+                        if (e < s + sectors)
+                                e = s + sectors;
+                        if (e - a <= BB_MAX_LEN) {
+                                p[lo] = BB_MAKE(a, e-a, ack);
+                                s = e;
+                        } else {
+                                /* does not all fit in one range,
+                                 * make p[lo] maximal
+                                 */
+                                if (BB_LEN(p[lo]) != BB_MAX_LEN)
+                                        p[lo] = BB_MAKE(a, BB_MAX_LEN, ack);
+                                s = a + BB_MAX_LEN;
+                        }
+                        sectors = e - s;
+                }
+        }
+        if (sectors && hi < bb->count) {
+                /* 'hi' points to the first range that starts after 's'.
+                 * Maybe we can merge with the start of that range
+                 */
+                sector_t a = BB_OFFSET(p[hi]);
+                sector_t e = a + BB_LEN(p[hi]);
+                int ack = BB_ACK(p[hi]);
+
+                if (a <= s + sectors) {
+                        /* merging is possible */
+                        if (e <= s + sectors) {
+                                /* full overlap */
+                                e = s + sectors;
+                                ack = acknowledged;
+                        } else
+                                ack = ack && acknowledged;
+
+                        a = s;
+                        if (e - a <= BB_MAX_LEN) {
+                                p[hi] = BB_MAKE(a, e-a, ack);
+                                s = e;
+                        } else {
+                                p[hi] = BB_MAKE(a, BB_MAX_LEN, ack);
+                                s = a + BB_MAX_LEN;
+                        }
+                        sectors = e - s;
+                        lo = hi;
+                        hi++;
+                }
+        }
+        if (sectors == 0 && hi < bb->count) {
+                /* we might be able to combine lo and hi */
+                /* Note: 's' is at the end of 'lo' */
+                sector_t a = BB_OFFSET(p[hi]);
+                int lolen = BB_LEN(p[lo]);
+                int hilen = BB_LEN(p[hi]);
+                int newlen = lolen + hilen - (s - a);
+
+                if (s >= a && newlen < BB_MAX_LEN) {
+                        /* yes, we can combine them */
+                        int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]);
+
+                        p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack);
+                        memmove(p + hi, p + hi + 1,
+                                (bb->count - hi - 1) * 8);
+                        bb->count--;
+                }
+        }
+        while (sectors) {
+                /* didn't merge (it all).
+                 * Need to add a range just before 'hi'
+                 */
+                if (bb->count >= MAX_BADBLOCKS) {
+                        /* No room for more */
+                        rv = 1;
+                        break;
+                } else {
+                        int this_sectors = sectors;
+
+                        memmove(p + hi + 1, p + hi,
+                                (bb->count - hi) * 8);
+                        bb->count++;
+
+                        if (this_sectors > BB_MAX_LEN)
+                                this_sectors = BB_MAX_LEN;
+                        p[hi] = BB_MAKE(s, this_sectors, acknowledged);
+                        sectors -= this_sectors;
+                        s += this_sectors;
+                }
+        }
+
+        bb->changed = 1;
+        if (!acknowledged)
+                bb->unacked_exist = 1;
+        write_sequnlock_irqrestore(&bb->lock, flags);
+
+        return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_set);
+
+/**
+ * badblocks_clear() - Remove a range of bad blocks to the table.
+ * @bb:         the badblocks structure that holds all badblock information
+ * @s:          first sector to mark as bad
+ * @sectors:    number of sectors to mark as bad
+ *
+ * This may involve extending the table if we spilt a region,
+ * but it must not fail.  So if the table becomes full, we just
+ * drop the remove request.
+ *
+ * Return:
+ *  0: success
+ *  1: failed to clear badblocks
+ */
+int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
+{
+        u64 *p;
+        int lo, hi;
+        sector_t target = s + sectors;
+        int rv = 0;
+
+        if (bb->shift > 0) {
+                /* When clearing we round the start up and the end down.
+                 * This should not matter as the shift should align with
+                 * the block size and no rounding should ever be needed.
+                 * However it is better the think a block is bad when it
+                 * isn't than to think a block is not bad when it is.
+                 */
+                s += (1<<bb->shift) - 1;
+                s >>= bb->shift;
+                target >>= bb->shift;
+                sectors = target - s;
+        }
+
+        write_seqlock_irq(&bb->lock);
+
+        p = bb->page;
+        lo = 0;
+        hi = bb->count;
+        /* Find the last range that starts before 'target' */
+        while (hi - lo > 1) {
+                int mid = (lo + hi) / 2;
+                sector_t a = BB_OFFSET(p[mid]);
+
+                if (a < target)
+                        lo = mid;
+                else
+                        hi = mid;
+        }
+        if (hi > lo) {
+                /* p[lo] is the last range that could overlap the
+                 * current range.  Earlier ranges could also overlap,
+                 * but only this one can overlap the end of the range.
+                 */
+                if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) {
+                        /* Partial overlap, leave the tail of this range */
+                        int ack = BB_ACK(p[lo]);
+                        sector_t a = BB_OFFSET(p[lo]);
+                        sector_t end = a + BB_LEN(p[lo]);
+
+                        if (a < s) {
+                                /* we need to split this range */
+                                if (bb->count >= MAX_BADBLOCKS) {
+                                        rv = -ENOSPC;
+                                        goto out;
+                                }
+                                memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
+                                bb->count++;
+                                p[lo] = BB_MAKE(a, s-a, ack);
+                                lo++;
+                        }
+                        p[lo] = BB_MAKE(target, end - target, ack);
+                        /* there is no longer an overlap */
+                        hi = lo;
+                        lo--;
+                }
+                while (lo >= 0 &&
+                       BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) {
+                        /* This range does overlap */
+                        if (BB_OFFSET(p[lo]) < s) {
+                                /* Keep the early parts of this range. */
+                                int ack = BB_ACK(p[lo]);
+                                sector_t start = BB_OFFSET(p[lo]);
+
+                                p[lo] = BB_MAKE(start, s - start, ack);
+                                /* now low doesn't overlap, so.. */
+                                break;
+                        }
+                        lo--;
+                }
+                /* 'lo' is strictly before, 'hi' is strictly after,
+                 * anything between needs to be discarded
+                 */
+                if (hi - lo > 1) {
+                        memmove(p+lo+1, p+hi, (bb->count - hi) * 8);
+                        bb->count -= (hi - lo - 1);
+                }
+        }
+
+        bb->changed = 1;
+out:
+        write_sequnlock_irq(&bb->lock);
+        return rv;
+}
+EXPORT_SYMBOL_GPL(badblocks_clear);
+
+/**
+ * ack_all_badblocks() - Acknowledge all bad blocks in a list.
+ * @bb:         the badblocks structure that holds all badblock information
+ *
+ * This only succeeds if ->changed is clear.  It is used by
+ * in-kernel metadata updates
+ */
+void ack_all_badblocks(struct badblocks *bb)
+{
+        if (bb->page == NULL || bb->changed)
+                /* no point even trying */
+                return;
+        write_seqlock_irq(&bb->lock);
+
+        if (bb->changed == 0 && bb->unacked_exist) {
+                u64 *p = bb->page;
+                int i;
+
+                for (i = 0; i < bb->count ; i++) {
+                        if (!BB_ACK(p[i])) {
+                                sector_t start = BB_OFFSET(p[i]);
+                                int len = BB_LEN(p[i]);
+
+                                p[i] = BB_MAKE(start, len, 1);
+                        }
+                }
+                bb->unacked_exist = 0;
+        }
+        write_sequnlock_irq(&bb->lock);
+}
+EXPORT_SYMBOL_GPL(ack_all_badblocks);
+
+/**
+ * badblocks_show() - sysfs access to bad-blocks list
+ * @bb:         the badblocks structure that holds all badblock information
+ * @page:       buffer received from sysfs
+ * @unack:      weather to show unacknowledged badblocks
+ *
+ * Return:
+ *  Length of returned data
+ */
+ssize_t badblocks_show(struct badblocks *bb, char *page, int unack)
+{
+        size_t len;
+        int i;
+        u64 *p = bb->page;
+        unsigned seq;
+
+        if (bb->shift < 0)
+                return 0;
+
+retry:
+        seq = read_seqbegin(&bb->lock);
+
+        len = 0;
+        i = 0;
+
+        while (len < PAGE_SIZE && i < bb->count) {
+                sector_t s = BB_OFFSET(p[i]);
+                unsigned int length = BB_LEN(p[i]);
+                int ack = BB_ACK(p[i]);
+
+                i++;
+
+                if (unack && ack)
+                        continue;
+
+                len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n",
+                                (unsigned long long)s << bb->shift,
+                                length << bb->shift);
+        }
+        if (unack && len == 0)
+                bb->unacked_exist = 0;
+
+        if (read_seqretry(&bb->lock, seq))
+                goto retry;
+
+        return len;
+}
+EXPORT_SYMBOL_GPL(badblocks_show);
+
+/**
+ * badblocks_store() - sysfs access to bad-blocks list
+ * @bb:         the badblocks structure that holds all badblock information
+ * @page:       buffer received from sysfs
+ * @len:        length of data received from sysfs
+ * @unack:      weather to show unacknowledged badblocks
+ *
+ * Return:
+ *  Length of the buffer processed or -ve error.
+ */
+ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
+                        int unack)
+{
+        unsigned long long sector;
+        int length;
+        char newline;
+
+        switch (sscanf(page, "%llu %d%c", &sector, &length, &newline)) {
+        case 3:
+                if (newline != '\n')
+                        return -EINVAL;
+        case 2:
+                if (length <= 0)
+                        return -EINVAL;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        if (badblocks_set(bb, sector, length, !unack))
+                return -ENOSPC;
+        else
+                return len;
+}
+EXPORT_SYMBOL_GPL(badblocks_store);
+
+/**
+ * badblocks_init() - initialize the badblocks structure
+ * @bb:         the badblocks structure that holds all badblock information
+ * @enable:     weather to enable badblocks accounting
+ *
+ * Return:
+ *  0: success
+ *  -ve errno: on error
+ */
+int badblocks_init(struct badblocks *bb, int enable)
+{
+        bb->count = 0;
+        if (enable)
+                bb->shift = 0;
+        else
+                bb->shift = -1;
+        bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+        if (bb->page == (u64 *)0) {
+                bb->shift = -1;
+                return -ENOMEM;
+        }
+        seqlock_init(&bb->lock);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(badblocks_init);
+
+/**
+ * badblocks_free() - free the badblocks structure
+ * @bb:         the badblocks structure that holds all badblock information
+ */
+void badblocks_free(struct badblocks *bb)
+{
+        kfree(bb->page);
+        bb->page = NULL;
+}
+EXPORT_SYMBOL_GPL(badblocks_free);