[PATCH] md: new sysfs interface for setting bits in the write-intent-bitmap

Add a new sysfs interface that allows the bitmap of an array to be dirtied.
The interface is write-only, and is used as follows:

echo "1000" > /sys/block/md2/md/bitmap

(dirty the bit for chunk 1000 [offset 0] in the in-memory and on-disk
bitmaps of array md2)

echo "1000-2000" > /sys/block/md1/md/bitmap

(dirty the bits for chunks 1000-2000 in md1's bitmap)

This is useful, for example, in cluster environments where you may need to
combine two disjoint bitmaps into one (following a server failure, after a
secondary server has taken over the array).  By combining the bitmaps on
the two servers, a full resync can be avoided (This was discussed on the
list back on March 18, 2005, "[PATCH 1/2] md bitmap bug fixes" thread).

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 56 insertions, 0 deletions

diff --git a/Documentation/md.txt b/Documentation/md.txt
index 0668f9dc9d29..084ecf4eb2f8 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -410,6 +410,15 @@ also have
       than sectors, this my be larger than the number of actual errors
       by a factor of the number of sectors in a page.
 
+   bitmap_set_bits
+      If the array has a write-intent bitmap, then writing to this
+      attribute can set bits in the bitmap, indicating that a resync
+      would need to check the corresponding blocks. Either individual
+      numbers or start-end pairs can be written.  Multiple numbers
+      can be separated by a space.
+      Note that the numbers are 'bit' numbers, not 'block' numbers.
+      They should be scaled by the bitmap_chunksize.
+
 Each active md device may also have attributes specific to the
 personality module that manages it.
 These are specific to the implementation of the module and could
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index ecc56765d949..0a44298fb353 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -613,6 +613,7 @@ static inline unsigned long file_page_offset(unsigned long chunk)
 static inline struct page *filemap_get_page(struct bitmap *bitmap,
                                         unsigned long chunk)
 {
+        if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
         return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
 }
 
@@ -739,6 +740,7 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
         }
 
         page = filemap_get_page(bitmap, chunk);
+        if (!page) return;
         bit = file_page_offset(chunk);
 
         /* set the bit */
@@ -1322,6 +1324,18 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n
 
 }
 
+/* dirty the memory and file bits for bitmap chunks "s" to "e" */
+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
+{
+        unsigned long chunk;
+
+        for (chunk = s; chunk <= e; chunk++) {
+                sector_t sec = chunk << CHUNK_BLOCK_SHIFT(bitmap);
+                bitmap_set_memory_bits(bitmap, sec, 1);
+                bitmap_file_set_bit(bitmap, sec);
+        }
+}
+
 /*
  * flush out any pending updates
  */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8b08043f07ef..b95dd8a183ec 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2524,6 +2524,36 @@ static struct md_sysfs_entry md_new_device =
 __ATTR(new_dev, S_IWUSR, null_show, new_dev_store);
 
 static ssize_t
+bitmap_store(mddev_t *mddev, const char *buf, size_t len)
+{
+        char *end;
+        unsigned long chunk, end_chunk;
+
+        if (!mddev->bitmap)
+                goto out;
+        /* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
+        while (*buf) {
+                chunk = end_chunk = simple_strtoul(buf, &end, 0);
+                if (buf == end) break;
+                if (*end == '-') { /* range */
+                        buf = end + 1;
+                        end_chunk = simple_strtoul(buf, &end, 0);
+                        if (buf == end) break;
+                }
+                if (*end && !isspace(*end)) break;
+                bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
+                buf = end;
+                while (isspace(*buf)) buf++;
+        }
+        bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
+out:
+        return len;
+}
+
+static struct md_sysfs_entry md_bitmap =
+__ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);
+
+static ssize_t
 size_show(mddev_t *mddev, char *page)
 {
         return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
@@ -2843,6 +2873,7 @@ static struct attribute *md_redundancy_attrs[] = {
         &md_sync_completed.attr,
         &md_suspend_lo.attr,
         &md_suspend_hi.attr,
+        &md_bitmap.attr,
         NULL,
 };
 static struct attribute_group md_redundancy_group = {
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
index 63df898fe2e9..84d887751855 100644
--- a/include/linux/raid/bitmap.h
+++ b/include/linux/raid/bitmap.h
@@ -265,6 +265,8 @@ int bitmap_update_sb(struct bitmap *bitmap);
 int  bitmap_setallbits(struct bitmap *bitmap);
 void bitmap_write_all(struct bitmap *bitmap);
 
+void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
+
 /* these are exported */
 int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
                         unsigned long sectors, int behind);