aboutsummaryrefslogtreecommitdiff
path: root/drivers
diff options
context:
space:
mode:
Diffstat (limited to 'drivers')
-rw-r--r--drivers/md/Kconfig31
-rw-r--r--drivers/md/Makefile16
-rw-r--r--drivers/md/bitmap.c49
-rw-r--r--drivers/md/bitmap.h288
-rw-r--r--drivers/md/faulty.c19
-rw-r--r--drivers/md/linear.c25
-rw-r--r--drivers/md/linear.h29
-rw-r--r--drivers/md/md.c615
-rw-r--r--drivers/md/md.h436
-rw-r--r--drivers/md/mktables.c14
-rw-r--r--drivers/md/multipath.c17
-rw-r--r--drivers/md/multipath.h40
-rw-r--r--drivers/md/raid0.c66
-rw-r--r--drivers/md/raid0.h28
-rw-r--r--drivers/md/raid1.c35
-rw-r--r--drivers/md/raid1.h132
-rw-r--r--drivers/md/raid10.c42
-rw-r--r--drivers/md/raid10.h121
-rw-r--r--drivers/md/raid5.c1494
-rw-r--r--drivers/md/raid5.h474
-rw-r--r--drivers/md/raid6.h130
-rw-r--r--drivers/md/raid6algos.c21
-rw-r--r--drivers/md/raid6altivec.uc4
-rw-r--r--drivers/md/raid6int.uc4
-rw-r--r--drivers/md/raid6mmx.c4
-rw-r--r--drivers/md/raid6recov.c13
-rw-r--r--drivers/md/raid6sse1.c4
-rw-r--r--drivers/md/raid6sse2.c4
-rw-r--r--drivers/md/raid6test/Makefile2
-rw-r--r--drivers/md/raid6test/test.c2
-rw-r--r--drivers/md/raid6x86.h2
31 files changed, 3324 insertions, 837 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2281b5098e9..36e0675be9f 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -121,6 +121,7 @@ config MD_RAID10
config MD_RAID456
tristate "RAID-4/RAID-5/RAID-6 mode"
depends on BLK_DEV_MD
+ select MD_RAID6_PQ
select ASYNC_MEMCPY
select ASYNC_XOR
---help---
@@ -151,34 +152,8 @@ config MD_RAID456
If unsure, say Y.
-config MD_RAID5_RESHAPE
- bool "Support adding drives to a raid-5 array"
- depends on MD_RAID456
- default y
- ---help---
- A RAID-5 set can be expanded by adding extra drives. This
- requires "restriping" the array which means (almost) every
- block must be written to a different place.
-
- This option allows such restriping to be done while the array
- is online.
-
- You will need mdadm version 2.4.1 or later to use this
- feature safely. During the early stage of reshape there is
- a critical section where live data is being over-written. A
- crash during this time needs extra care for recovery. The
- newer mdadm takes a copy of the data in the critical section
- and will restore it, if necessary, after a crash.
-
- The mdadm usage is e.g.
- mdadm --grow /dev/md1 --raid-disks=6
- to grow '/dev/md1' to having 6 disks.
-
- Note: The array can only be expanded, not contracted.
- There should be enough spares already present to make the new
- array workable.
-
- If unsure, say Y.
+config MD_RAID6_PQ
+ tristate
config MD_MULTIPATH
tristate "Multipath I/O support"
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 72880b7e28d..45cc5951d92 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -2,20 +2,21 @@
# Makefile for the kernel software RAID and LVM drivers.
#
-dm-mod-objs := dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
+dm-mod-y += dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o
-dm-multipath-objs := dm-path-selector.o dm-mpath.o
-dm-snapshot-objs := dm-snap.o dm-exception-store.o dm-snap-transient.o \
+dm-multipath-y += dm-path-selector.o dm-mpath.o
+dm-snapshot-y += dm-snap.o dm-exception-store.o dm-snap-transient.o \
dm-snap-persistent.o
-dm-mirror-objs := dm-raid1.o
-md-mod-objs := md.o bitmap.o
-raid456-objs := raid5.o raid6algos.o raid6recov.o raid6tables.o \
+dm-mirror-y += dm-raid1.o
+md-mod-y += md.o bitmap.o
+raid456-y += raid5.o
+raid6_pq-y += raid6algos.o raid6recov.o raid6tables.o \
raid6int1.o raid6int2.o raid6int4.o \
raid6int8.o raid6int16.o raid6int32.o \
raid6altivec1.o raid6altivec2.o raid6altivec4.o \
raid6altivec8.o \
raid6mmx.o raid6sse1.o raid6sse2.o
-hostprogs-y := mktables
+hostprogs-y += mktables
# Note: link order is important. All raid personalities
# and must come before md.o, as they each initialise
@@ -26,6 +27,7 @@ obj-$(CONFIG_MD_LINEAR) += linear.o
obj-$(CONFIG_MD_RAID0) += raid0.o
obj-$(CONFIG_MD_RAID1) += raid1.o
obj-$(CONFIG_MD_RAID10) += raid10.o
+obj-$(CONFIG_MD_RAID6_PQ) += raid6_pq.o
obj-$(CONFIG_MD_RAID456) += raid456.o
obj-$(CONFIG_MD_MULTIPATH) += multipath.o
obj-$(CONFIG_MD_FAULTY) += faulty.o
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 71994376339..f8a9f7ab2cb 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -16,6 +16,7 @@
* wait if count gets too high, wake when it drops to half.
*/
+#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
@@ -26,8 +27,8 @@
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/buffer_head.h>
-#include <linux/raid/md.h>
-#include <linux/raid/bitmap.h>
+#include "md.h"
+#include "bitmap.h"
/* debug macros */
@@ -111,9 +112,10 @@ static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int creat
unsigned char *mappage;
if (page >= bitmap->pages) {
- printk(KERN_ALERT
- "%s: invalid bitmap page request: %lu (> %lu)\n",
- bmname(bitmap), page, bitmap->pages-1);
+ /* This can happen if bitmap_start_sync goes beyond
+ * End-of-device while looking for a whole page.
+ * It is harmless.
+ */
return -EINVAL;
}
@@ -265,7 +267,6 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
list_for_each_continue_rcu(pos, &mddev->disks) {
rdev = list_entry(pos, mdk_rdev_t, same_set);
if (rdev->raid_disk >= 0 &&
- test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags)) {
/* this is a usable devices */
atomic_inc(&rdev->nr_pending);
@@ -297,7 +298,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
+ size/512 > 0)
/* bitmap runs in to metadata */
goto bad_alignment;
- if (rdev->data_offset + mddev->size*2
+ if (rdev->data_offset + mddev->dev_sectors
> rdev->sb_start + bitmap->offset)
/* data runs in to bitmap */
goto bad_alignment;
@@ -570,7 +571,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
reason = "unrecognized superblock version";
- else if (chunksize < PAGE_SIZE)
+ else if (chunksize < 512)
reason = "bitmap chunksize too small";
else if ((1 << ffz(~chunksize)) != chunksize)
reason = "bitmap chunksize not a power of 2";
@@ -1306,6 +1307,9 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
}
+ if (bitmap->mddev->degraded)
+ /* Never clear bits or update events_cleared when degraded */
+ success = 0;
while (sectors) {
int blocks;
@@ -1345,8 +1349,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
}
}
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
- int degraded)
+static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+ int degraded)
{
bitmap_counter_t *bmc;
int rv;
@@ -1374,6 +1378,29 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
return rv;
}
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+ int degraded)
+{
+ /* bitmap_start_sync must always report on multiples of whole
+ * pages, otherwise resync (which is very PAGE_SIZE based) will
+ * get confused.
+ * So call __bitmap_start_sync repeatedly (if needed) until
+ * At least PAGE_SIZE>>9 blocks are covered.
+ * Return the 'or' of the result.
+ */
+ int rv = 0;
+ int blocks1;
+
+ *blocks = 0;
+ while (*blocks < (PAGE_SIZE>>9)) {
+ rv |= __bitmap_start_sync(bitmap, offset,
+ &blocks1, degraded);
+ offset += blocks1;
+ *blocks += blocks1;
+ }
+ return rv;
+}
+
void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
{
bitmap_counter_t *bmc;
@@ -1443,6 +1470,8 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
wait_event(bitmap->mddev->recovery_wait,
atomic_read(&bitmap->mddev->recovery_active) == 0);
+ bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
+ set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
s = 0;
while (s < sector && s < bitmap->mddev->resync_max_sectors) {
diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h
new file mode 100644
index 00000000000..e98900671ca
--- /dev/null
+++ b/drivers/md/bitmap.h
@@ -0,0 +1,288 @@
+/*
+ * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
+ *
+ * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
+ */
+#ifndef BITMAP_H
+#define BITMAP_H 1
+
+#define BITMAP_MAJOR_LO 3
+/* version 4 insists the bitmap is in little-endian order
+ * with version 3, it is host-endian which is non-portable
+ */
+#define BITMAP_MAJOR_HI 4
+#define BITMAP_MAJOR_HOSTENDIAN 3
+
+#define BITMAP_MINOR 39
+
+/*
+ * in-memory bitmap:
+ *
+ * Use 16 bit block counters to track pending writes to each "chunk".
+ * The 2 high order bits are special-purpose, the first is a flag indicating
+ * whether a resync is needed. The second is a flag indicating whether a
+ * resync is active.
+ * This means that the counter is actually 14 bits:
+ *
+ * +--------+--------+------------------------------------------------+
+ * | resync | resync | counter |
+ * | needed | active | |
+ * | (0-1) | (0-1) | (0-16383) |
+ * +--------+--------+------------------------------------------------+
+ *
+ * The "resync needed" bit is set when:
+ * a '1' bit is read from storage at startup.
+ * a write request fails on some drives
+ * a resync is aborted on a chunk with 'resync active' set
+ * It is cleared (and resync-active set) when a resync starts across all drives
+ * of the chunk.
+ *
+ *
+ * The "resync active" bit is set when:
+ * a resync is started on all drives, and resync_needed is set.
+ * resync_needed will be cleared (as long as resync_active wasn't already set).
+ * It is cleared when a resync completes.
+ *
+ * The counter counts pending write requests, plus the on-disk bit.
+ * When the counter is '1' and the resync bits are clear, the on-disk
+ * bit can be cleared aswell, thus setting the counter to 0.
+ * When we set a bit, or in the counter (to start a write), if the fields is
+ * 0, we first set the disk bit and set the counter to 1.
+ *
+ * If the counter is 0, the on-disk bit is clear and the stipe is clean
+ * Anything that dirties the stipe pushes the counter to 2 (at least)
+ * and sets the on-disk bit (lazily).
+ * If a periodic sweep find the counter at 2, it is decremented to 1.
+ * If the sweep find the counter at 1, the on-disk bit is cleared and the
+ * counter goes to zero.
+ *
+ * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
+ * counters as a fallback when "page" memory cannot be allocated:
+ *
+ * Normal case (page memory allocated):
+ *
+ * page pointer (32-bit)
+ *
+ * [ ] ------+
+ * |
+ * +-------> [ ][ ]..[ ] (4096 byte page == 2048 counters)
+ * c1 c2 c2048
+ *
+ * Hijacked case (page memory allocation failed):
+ *
+ * hijacked page pointer (32-bit)
+ *
+ * [ ][ ] (no page memory allocated)
+ * counter #1 (16-bit) counter #2 (16-bit)
+ *
+ */
+
+#ifdef __KERNEL__
+
+#define PAGE_BITS (PAGE_SIZE << 3)
+#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
+
+typedef __u16 bitmap_counter_t;
+#define COUNTER_BITS 16
+#define COUNTER_BIT_SHIFT 4
+#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
+#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
+
+#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
+#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
+#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
+#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
+#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
+#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
+
+/* how many counters per page? */
+#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
+/* same, except a shift value for more efficient bitops */
+#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
+/* same, except a mask value for more efficient bitops */
+#define PAGE_COUNTER_MASK (PAGE_COUNTER_RATIO - 1)
+
+#define BITMAP_BLOCK_SIZE 512
+#define BITMAP_BLOCK_SHIFT 9
+
+/* how many blocks per chunk? (this is variable) */
+#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT)
+#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT)
+#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1)
+
+/* when hijacked, the counters and bits represent even larger "chunks" */
+/* there will be 1024 chunks represented by each counter in the page pointers */
+#define PAGEPTR_BLOCK_RATIO(bitmap) \
+ (CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1)
+#define PAGEPTR_BLOCK_SHIFT(bitmap) \
+ (CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1)
+#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1)
+
+/*
+ * on-disk bitmap:
+ *
+ * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap
+ * file a page at a time. There's a superblock at the start of the file.
+ */
+
+/* map chunks (bits) to file pages - offset by the size of the superblock */
+#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3))
+
+#endif
+
+/*
+ * bitmap structures:
+ */
+
+#define BITMAP_MAGIC 0x6d746962
+
+/* use these for bitmap->flags and bitmap->sb->state bit-fields */
+enum bitmap_state {
+ BITMAP_STALE = 0x002, /* the bitmap file is out of date or had -EIO */
+ BITMAP_WRITE_ERROR = 0x004, /* A write error has occurred */
+ BITMAP_HOSTENDIAN = 0x8000,
+};
+
+/* the superblock at the front of the bitmap file -- little endian */
+typedef struct bitmap_super_s {
+ __le32 magic; /* 0 BITMAP_MAGIC */
+ __le32 version; /* 4 the bitmap major for now, could change... */
+ __u8 uuid[16]; /* 8 128 bit uuid - must match md device uuid */
+ __le64 events; /* 24 event counter for the bitmap (1)*/
+ __le64 events_cleared;/*32 event counter when last bit cleared (2) */
+ __le64 sync_size; /* 40 the size of the md device's sync range(3) */
+ __le32 state; /* 48 bitmap state information */
+ __le32 chunksize; /* 52 the bitmap chunk size in bytes */
+ __le32 daemon_sleep; /* 56 seconds between disk flushes */
+ __le32 write_behind; /* 60 number of outstanding write-behind writes */
+
+ __u8 pad[256 - 64]; /* set to zero */
+} bitmap_super_t;
+
+/* notes:
+ * (1) This event counter is updated before the eventcounter in the md superblock
+ * When a bitmap is loaded, it is only accepted if this event counter is equal
+ * to, or one greater than, the event counter in the superblock.
+ * (2) This event counter is updated when the other one is *if*and*only*if* the
+ * array is not degraded. As bits are not cleared when the array is degraded,
+ * this represents the last time that any bits were cleared.
+ * If a device is being added that has an event count with this value or
+ * higher, it is accepted as conforming to the bitmap.
+ * (3)This is the number of sectors represented by the bitmap, and is the range that
+ * resync happens across. For raid1 and raid5/6 it is the size of individual
+ * devices. For raid10 it is the size of the array.
+ */
+
+#ifdef __KERNEL__
+
+/* the in-memory bitmap is represented by bitmap_pages */
+struct bitmap_page {
+ /*
+ * map points to the actual memory page
+ */
+ char *map;
+ /*
+ * in emergencies (when map cannot be alloced), hijack the map
+ * pointer and use it as two counters itself
+ */
+ unsigned int hijacked:1;
+ /*
+ * count of dirty bits on the page
+ */
+ unsigned int count:31;
+};
+
+/* keep track of bitmap file pages that have pending writes on them */
+struct page_list {
+ struct list_head list;
+ struct page *page;
+};
+
+/* the main bitmap structure - one per mddev */
+struct bitmap {
+ struct bitmap_page *bp;
+ unsigned long pages; /* total number of pages in the bitmap */
+ unsigned long missing_pages; /* number of pages not yet allocated */
+
+ mddev_t *mddev; /* the md device that the bitmap is for */
+
+ int counter_bits; /* how many bits per block counter */
+
+ /* bitmap chunksize -- how much data does each bit represent? */
+ unsigned long chunksize;
+ unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
+ unsigned long chunks; /* total number of data chunks for the array */
+
+ /* We hold a count on the chunk currently being synced, and drop
+ * it when the last block is started. If the resync is aborted
+ * midway, we need to be able to drop that count, so we remember
+ * the counted chunk..
+ */
+ unsigned long syncchunk;
+
+ __u64 events_cleared;
+ int need_sync;
+
+ /* bitmap spinlock */
+ spinlock_t lock;
+
+ long offset; /* offset from superblock if file is NULL */
+ struct file *file; /* backing disk file */
+ struct page *sb_page; /* cached copy of the bitmap file superblock */
+ struct page **filemap; /* list of cache pages for the file */
+ unsigned long *filemap_attr; /* attributes associated w/ filemap pages */
+ unsigned long file_pages; /* number of pages in the file */
+ int last_page_size; /* bytes in the last page */
+
+ unsigned long flags;
+
+ int allclean;
+
+ unsigned long max_write_behind; /* write-behind mode */
+ atomic_t behind_writes;
+
+ /*
+ * the bitmap daemon - periodically wakes up and sweeps the bitmap
+ * file, cleaning up bits and flushing out pages to disk as necessary
+ */
+ unsigned long daemon_lastrun; /* jiffies of last run */
+ unsigned long daemon_sleep; /* how many seconds between updates? */
+ unsigned long last_end_sync; /* when we lasted called end_sync to
+ * update bitmap with resync progress */
+
+ atomic_t pending_writes; /* pending writes to the bitmap file */
+ wait_queue_head_t write_wait;
+ wait_queue_head_t overflow_wait;
+
+};
+
+/* the bitmap API */
+
+/* these are used only by md/bitmap */
+int bitmap_create(mddev_t *mddev);
+void bitmap_flush(mddev_t *mddev);
+void bitmap_destroy(mddev_t *mddev);
+
+void bitmap_print_sb(struct bitmap *bitmap);
+void 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);
+void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
+ unsigned long sectors, int success, int behind);
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded);
+void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
+void bitmap_close_sync(struct bitmap *bitmap);
+void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
+
+void bitmap_unplug(struct bitmap *bitmap);
+void bitmap_daemon_work(struct bitmap *bitmap);
+#endif
+
+#endif
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 86d9adf90e7..8695809b24b 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -62,7 +62,10 @@
#define ModeShift 5
#define MaxFault 50
-#include <linux/raid/md.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include "md.h"
+#include <linux/seq_file.h>
static void faulty_fail(struct bio *bio, int error)
@@ -280,6 +283,17 @@ static int reconfig(mddev_t *mddev, int layout, int chunk_size)
return 0;
}
+static sector_t faulty_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+ WARN_ONCE(raid_disks,
+ "%s does not support generic reshape\n", __func__);
+
+ if (sectors == 0)
+ return mddev->dev_sectors;
+
+ return sectors;
+}
+
static int run(mddev_t *mddev)
{
mdk_rdev_t *rdev;
@@ -298,7 +312,7 @@ static int run(mddev_t *mddev)
list_for_each_entry(rdev, &mddev->disks, same_set)
conf->rdev = rdev;
- mddev->array_sectors = mddev->size * 2;
+ md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
mddev->private = conf;
reconfig(mddev, mddev->layout, -1);
@@ -325,6 +339,7 @@ static struct mdk_personality faulty_personality =
.stop = stop,
.status = status,
.reconfig = reconfig,
+ .size = faulty_size,
};
static int __init raid_init(void)
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 09658b21847..7a36e38393a 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -16,7 +16,11 @@
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
-#include <linux/raid/linear.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "linear.h"
/*
* find which device holds a particular offset
@@ -97,6 +101,16 @@ static int linear_congested(void *data, int bits)
return ret;
}
+static sector_t linear_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+ linear_conf_t *conf = mddev_to_conf(mddev);
+
+ WARN_ONCE(sectors || raid_disks,
+ "%s does not support generic reshape\n", __func__);
+
+ return conf->array_sectors;
+}
+
static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
{
linear_conf_t *conf;
@@ -135,8 +149,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
mddev->queue->max_sectors > (PAGE_SIZE>>9))
blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
- disk->num_sectors = rdev->size * 2;
- conf->array_sectors += rdev->size * 2;
+ disk->num_sectors = rdev->sectors;
+ conf->array_sectors += rdev->sectors;
cnt++;
}
@@ -249,7 +263,7 @@ static int linear_run (mddev_t *mddev)
if (!conf)
return 1;
mddev->private = conf;
- mddev->array_sectors = conf->array_sectors;
+ md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
mddev->queue->unplug_fn = linear_unplug;
@@ -283,7 +297,7 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
newconf->prev = mddev_to_conf(mddev);
mddev->private = newconf;
mddev->raid_disks++;
- mddev->array_sectors = newconf->array_sectors;
+ md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
set_capacity(mddev->gendisk, mddev->array_sectors);
return 0;
}
@@ -381,6 +395,7 @@ static struct mdk_personality linear_personality =
.stop = linear_stop,
.status = linear_status,
.hot_add_disk = linear_add,
+ .size = linear_size,
};
static int __init linear_init (void)
diff --git a/drivers/md/linear.h b/drivers/md/linear.h
new file mode 100644
index 00000000000..bf8179587f9
--- /dev/null
+++ b/drivers/md/linear.h
@@ -0,0 +1,29 @@
+#ifndef _LINEAR_H
+#define _LINEAR_H
+
+struct dev_info {
+ mdk_rdev_t *rdev;
+ sector_t num_sectors;
+ sector_t start_sector;
+};
+
+typedef struct dev_info dev_info_t;
+
+struct linear_private_data
+{
+ struct linear_private_data *prev; /* earlier version */
+ dev_info_t **hash_table;
+ sector_t spacing;
+ sector_t array_sectors;
+ int sector_shift; /* shift before dividing
+ * by spacing
+ */
+ dev_info_t disks[0];
+};
+
+
+typedef struct linear_private_data linear_conf_t;
+
+#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private)
+
+#endif
diff --git a/drivers/md/md.c b/drivers/md/md.c
index a307f87eb90..ed5727c089a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -33,9 +33,9 @@
*/
#include <linux/kthread.h>
-#include <linux/raid/md.h>
-#include <linux/raid/bitmap.h>
+#include <linux/blkdev.h>
#include <linux/sysctl.h>
+#include <linux/seq_file.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
#include <linux/poll.h>
#include <linux/ctype.h>
@@ -45,11 +45,10 @@
#include <linux/reboot.h>
#include <linux/file.h>
#include <linux/delay.h>
-
-#define MAJOR_NR MD_MAJOR
-
-/* 63 partitions with the alternate major number (mdp) */
-#define MdpMinorShift 6
+#include <linux/raid/md_p.h>
+#include <linux/raid/md_u.h>
+#include "md.h"
+#include "bitmap.h"
#define DEBUG 0
#define dprintk(x...) ((void)(DEBUG && printk(x)))
@@ -202,12 +201,68 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
)
-static int md_fail_request(struct request_queue *q, struct bio *bio)
+/* Rather than calling directly into the personality make_request function,
+ * IO requests come here first so that we can check if the device is
+ * being suspended pending a reconfiguration.
+ * We hold a refcount over the call to ->make_request. By the time that
+ * call has finished, the bio has been linked into some internal structure
+ * and so is visible to ->quiesce(), so we don't need the refcount any more.
+ */
+static int md_make_request(struct request_queue *q, struct bio *bio)
{
- bio_io_error(bio);
- return 0;
+ mddev_t *mddev = q->queuedata;
+ int rv;
+ if (mddev == NULL || mddev->pers == NULL) {
+ bio_io_error(bio);
+ return 0;
+ }
+ rcu_read_lock();
+ if (mddev->suspended) {
+ DEFINE_WAIT(__wait);
+ for (;;) {
+ prepare_to_wait(&mddev->sb_wait, &__wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!mddev->suspended)
+ break;
+ rcu_read_unlock();
+ schedule();
+ rcu_read_lock();
+ }
+ finish_wait(&mddev->sb_wait, &__wait);
+ }
+ atomic_inc(&mddev->active_io);
+ rcu_read_unlock();
+ rv = mddev->pers->make_request(q, bio);
+ if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+ wake_up(&mddev->sb_wait);
+
+ return rv;
+}
+
+static void mddev_suspend(mddev_t *mddev)
+{
+ BUG_ON(mddev->suspended);
+ mddev->suspended = 1;
+ synchronize_rcu();
+ wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
+ mddev->pers->quiesce(mddev, 1);
+ md_unregister_thread(mddev->thread);
+ mddev->thread = NULL;
+ /* we now know that no code is executing in the personality module,
+ * except possibly the tail end of a ->bi_end_io function, but that
+ * is certain to complete before the module has a chance to get
+ * unloaded
+ */
+}
+
+static void mddev_resume(mddev_t *mddev)
+{
+ mddev->suspended = 0;
+ wake_up(&mddev->sb_wait);
+ mddev->pers->quiesce(mddev, 0);
}
+
static inline mddev_t *mddev_get(mddev_t *mddev)
{
atomic_inc(&mddev->active);
@@ -310,6 +365,7 @@ static mddev_t * mddev_find(dev_t unit)
init_timer(&new->safemode_timer);
atomic_set(&new->active, 1);
atomic_set(&new->openers, 0);
+ atomic_set(&new->active_io, 0);
spin_lock_init(&new->write_lock);
init_waitqueue_head(&new->sb_wait);
init_waitqueue_head(&new->recovery_wait);
@@ -326,6 +382,11 @@ static inline int mddev_lock(mddev_t * mddev)
return mutex_lock_interruptible(&mddev->reconfig_mutex);
}
+static inline int mddev_is_locked(mddev_t *mddev)
+{
+ return mutex_is_locked(&mddev->reconfig_mutex);
+}
+
static inline int mddev_trylock(mddev_t * mddev)
{
return mutex_trylock(&mddev->reconfig_mutex);
@@ -409,7 +470,7 @@ static void free_disk_sb(mdk_rdev_t * rdev)
rdev->sb_loaded = 0;
rdev->sb_page = NULL;
rdev->sb_start = 0;
- rdev->size = 0;
+ rdev->sectors = 0;
}
}
@@ -775,9 +836,9 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
else
ret = 0;
}
- rdev->size = calc_num_sectors(rdev, sb->chunk_size) / 2;
+ rdev->sectors = calc_num_sectors(rdev, sb->chunk_size);
- if (rdev->size < sb->size && sb->level > 1)
+ if (rdev->sectors < sb->size * 2 && sb->level > 1)
/* "this cannot possibly happen" ... */
ret = -EINVAL;
@@ -812,7 +873,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
mddev->clevel[0] = 0;
mddev->layout = sb->layout;
mddev->raid_disks = sb->raid_disks;
- mddev->size = sb->size;
+ mddev->dev_sectors = sb->size * 2;
mddev->events = ev1;
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
@@ -926,7 +987,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
sb->ctime = mddev->ctime;
sb->level = mddev->level;
- sb->size = mddev->size;
+ sb->size = mddev->dev_sectors / 2;
sb->raid_disks = mddev->raid_disks;
sb->md_minor = mddev->md_minor;
sb->not_persistent = 0;
@@ -1024,7 +1085,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
static unsigned long long
super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
{
- if (num_sectors && num_sectors < rdev->mddev->size * 2)
+ if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
return 0; /* component must fit device */
if (rdev->mddev->bitmap_offset)
return 0; /* can't move bitmap */
@@ -1180,16 +1241,17 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
ret = 0;