Manual merge with Linus

6 files changed, 69 insertions, 74 deletions

diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
index 4bf1659f8aa8..9de99198caf1 100644
--- a/include/linux/raid/bitmap.h
+++ b/include/linux/raid/bitmap.h
@@ -7,7 +7,7 @@
 #define BITMAP_H 1
 
 #define BITMAP_MAJOR 3
-#define BITMAP_MINOR 38
+#define BITMAP_MINOR 39
 
 /*
  * in-memory bitmap:
@@ -147,8 +147,9 @@ typedef struct bitmap_super_s {
         __u32 state;        /* 48  bitmap state information */
         __u32 chunksize;    /* 52  the bitmap chunk size in bytes */
         __u32 daemon_sleep; /* 56  seconds between disk flushes */
+        __u32 write_behind; /* 60  number of outstanding write-behind writes */
 
-        __u8  pad[256 - 60]; /* set to zero */
+        __u8  pad[256 - 64]; /* set to zero */
 } bitmap_super_t;
 
 /* notes:
@@ -226,6 +227,9 @@ struct bitmap {
 
         unsigned long flags;
 
+        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
@@ -260,9 +264,10 @@ int  bitmap_setallbits(struct bitmap *bitmap);
 void bitmap_write_all(struct bitmap *bitmap);
 
 /* these are exported */
-int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors);
-void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
-                     int success);
+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);
diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h
index e04c4fe45b53..7eaf290e10e7 100644
--- a/include/linux/raid/linear.h
+++ b/include/linux/raid/linear.h
@@ -14,8 +14,8 @@ typedef struct dev_info dev_info_t;
 struct linear_private_data
 {
         dev_info_t              **hash_table;
-        dev_info_t              *smallest;
-        int                     nr_zones;
+        sector_t                hash_spacing;
+        int                     preshift; /* shift before dividing by hash_spacing */
         dev_info_t              disks[0];
 };
 
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
index 8c14ba565a45..ebce949b1443 100644
--- a/include/linux/raid/md_k.h
+++ b/include/linux/raid/md_k.h
@@ -86,70 +86,6 @@ typedef struct mdk_rdev_s mdk_rdev_t;
 #define MAX_CHUNK_SIZE (4096*1024)
 
 /*
- * default readahead
- */
-
-static inline int disk_faulty(mdp_disk_t * d)
-{
-        return d->state & (1 << MD_DISK_FAULTY);
-}
-
-static inline int disk_active(mdp_disk_t * d)
-{
-        return d->state & (1 << MD_DISK_ACTIVE);
-}
-
-static inline int disk_sync(mdp_disk_t * d)
-{
-        return d->state & (1 << MD_DISK_SYNC);
-}
-
-static inline int disk_spare(mdp_disk_t * d)
-{
-        return !disk_sync(d) && !disk_active(d) && !disk_faulty(d);
-}
-
-static inline int disk_removed(mdp_disk_t * d)
-{
-        return d->state & (1 << MD_DISK_REMOVED);
-}
-
-static inline void mark_disk_faulty(mdp_disk_t * d)
-{
-        d->state |= (1 << MD_DISK_FAULTY);
-}
-
-static inline void mark_disk_active(mdp_disk_t * d)
-{
-        d->state |= (1 << MD_DISK_ACTIVE);
-}
-
-static inline void mark_disk_sync(mdp_disk_t * d)
-{
-        d->state |= (1 << MD_DISK_SYNC);
-}
-
-static inline void mark_disk_spare(mdp_disk_t * d)
-{
-        d->state = 0;
-}
-
-static inline void mark_disk_removed(mdp_disk_t * d)
-{
-        d->state = (1 << MD_DISK_FAULTY) | (1 << MD_DISK_REMOVED);
-}
-
-static inline void mark_disk_inactive(mdp_disk_t * d)
-{
-        d->state &= ~(1 << MD_DISK_ACTIVE);
-}
-
-static inline void mark_disk_nonsync(mdp_disk_t * d)
-{
-        d->state &= ~(1 << MD_DISK_SYNC);
-}
-
-/*
  * MD's 'extended' device
  */
 struct mdk_rdev_s
@@ -166,6 +102,7 @@ struct mdk_rdev_s
         int             sb_loaded;
         sector_t        data_offset;    /* start of data in array */
         sector_t        sb_offset;
+        int             sb_size;        /* bytes in the superblock */
         int             preferred_minor;        /* autorun support */
 
         /* A device can be in one of three states based on two flags:
@@ -181,6 +118,9 @@ struct mdk_rdev_s
         int faulty;                     /* if faulty do not issue IO requests */
         int in_sync;                    /* device is a full member of the array */
 
+        unsigned long   flags;          /* Should include faulty and in_sync here. */
+#define WriteMostly     4               /* Avoid reading if at all possible */
+
         int desc_nr;                    /* descriptor index in the superblock */
         int raid_disk;                  /* role of device in array */
         int saved_raid_disk;            /* role that device used to have in the
@@ -272,12 +212,19 @@ struct mddev_s
         atomic_t                        writes_pending; 
         request_queue_t                 *queue; /* for plugging ... */
 
+        atomic_t                        write_behind; /* outstanding async IO */
+        unsigned int                    max_write_behind; /* 0 = sync */
+
         struct bitmap                   *bitmap; /* the bitmap for the device */
         struct file                     *bitmap_file; /* the bitmap file */
         long                            bitmap_offset; /* offset from superblock of
                                                         * start of bitmap. May be
                                                         * negative, but not '0'
                                                         */
+        long                            default_bitmap_offset; /* this is the offset to use when
+                                                                * hot-adding a bitmap.  It should
+                                                                * eventually be settable by sysfs.
+                                                                */
 
         struct list_head                all_mddevs;
 };
@@ -314,6 +261,12 @@ struct mdk_personality_s
         int (*resize) (mddev_t *mddev, sector_t sectors);
         int (*reshape) (mddev_t *mddev, int raid_disks);
         int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
+        /* quiesce moves between quiescence states
+         * 0 - fully active
+         * 1 - no new requests allowed
+         * others - reserved
+         */
+        void (*quiesce) (mddev_t *mddev, int state);
 };
 
 
diff --git a/include/linux/raid/md_p.h b/include/linux/raid/md_p.h
index dc65cd435494..c100fa5d4bfa 100644
--- a/include/linux/raid/md_p.h
+++ b/include/linux/raid/md_p.h
@@ -79,6 +79,11 @@
 #define MD_DISK_SYNC            2 /* disk is in sync with the raid set */
 #define MD_DISK_REMOVED         3 /* disk is in sync with the raid set */
 
+#define MD_DISK_WRITEMOSTLY     9 /* disk is "write-mostly" is RAID1 config.
+                                   * read requests will only be sent here in
+                                   * dire need
+                                   */
+
 typedef struct mdp_device_descriptor_s {
         __u32 number;           /* 0 Device number in the entire set          */
         __u32 major;            /* 1 Device major number                      */
@@ -193,7 +198,7 @@ struct mdp_superblock_1 {
 
         __u64   ctime;          /* lo 40 bits are seconds, top 24 are microseconds or 0*/
         __u32   level;          /* -4 (multipath), -1 (linear), 0,1,4,5 */
-        __u32   layout;         /* only for raid5 currently */
+        __u32   layout;         /* only for raid5 and raid10 currently */
         __u64   size;           /* used size of component devices, in 512byte sectors */
 
         __u32   chunksize;      /* in 512byte sectors */
@@ -212,7 +217,9 @@ struct mdp_superblock_1 {
         __u32   dev_number;     /* permanent identifier of this  device - not role in raid */
         __u32   cnt_corrected_read; /* number of read errors that were corrected by re-writing */
         __u8    device_uuid[16]; /* user-space setable, ignored by kernel */
-        __u8    pad2[64-56];    /* set to 0 when writing */
+        __u8    devflags;       /* per-device flags.  Only one defined...*/
+#define WriteMostly1    1       /* mask for writemostly flag in above */
+        __u8    pad2[64-57];    /* set to 0 when writing */
 
         /* array state information - 64 bytes */
         __u64   utime;          /* 40 bits second, 24 btes microseconds */
@@ -231,5 +238,10 @@ struct mdp_superblock_1 {
         __u16   dev_roles[0];   /* role in array, or 0xffff for a spare, or 0xfffe for faulty */
 };
 
+/* feature_map bits */
+#define MD_FEATURE_BITMAP_OFFSET        1
+
+#define MD_FEATURE_ALL                  1
+
 #endif 
 
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
index 9d93cf12e890..60e19b667548 100644
--- a/include/linux/raid/raid1.h
+++ b/include/linux/raid/raid1.h
@@ -80,6 +80,9 @@ struct r1bio_s {
         atomic_t                remaining; /* 'have we finished' count,
                                             * used from IRQ handlers
                                             */
+        atomic_t                behind_remaining; /* number of write-behind ios remaining
+                                                 * in this BehindIO request
+                                                 */
         sector_t                sector;
         int                     sectors;
         unsigned long           state;
@@ -107,4 +110,14 @@ struct r1bio_s {
 #define R1BIO_Uptodate  0
 #define R1BIO_IsSync    1
 #define R1BIO_Degraded  2
+#define R1BIO_BehindIO   3
+/* For write-behind requests, we call bi_end_io when
+ * the last non-write-behind device completes, providing
+ * any write was successful.  Otherwise we call when
+ * any write-behind write succeeds, otherwise we call
+ * with failure when last write completes (and all failed).
+ * Record that bi_end_io was called with this flag...
+ */
+#define R1BIO_Returned 4
+
 #endif
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index d63ddcb4afad..176fc653c284 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -134,6 +134,7 @@ struct stripe_head {
         unsigned long           state;                  /* state flags */
         atomic_t                count;                  /* nr of active thread/requests */
         spinlock_t              lock;
+        int                     bm_seq; /* sequence number for bitmap flushes */
         struct r5dev {
                 struct bio      req;
                 struct bio_vec  vec;
@@ -165,12 +166,13 @@ struct stripe_head {
 /*
  * Stripe state
  */
-#define STRIPE_ERROR            1
 #define STRIPE_HANDLE           2
 #define STRIPE_SYNCING          3
 #define STRIPE_INSYNC           4
 #define STRIPE_PREREAD_ACTIVE   5
 #define STRIPE_DELAYED          6
+#define STRIPE_DEGRADED         7
+#define STRIPE_BIT_DELAY        8
 
 /*
  * Plugging:
@@ -210,10 +212,20 @@ struct raid5_private_data {
 
         struct list_head        handle_list; /* stripes needing handling */
         struct list_head        delayed_list; /* stripes that have plugged requests */
+        struct list_head        bitmap_list; /* stripes delaying awaiting bitmap update */
         atomic_t                preread_active_stripes; /* stripes with scheduled io */
 
         char                    cache_name[20];
         kmem_cache_t            *slab_cache; /* for allocating stripes */
+
+        int                     seq_flush, seq_write;
+        int                     quiesce;
+
+        int                     fullsync;  /* set to 1 if a full sync is needed,
+                                            * (fresh device added).
+                                            * Cleared when a sync completes.
+                                            */
+
         /*
          * Free stripes pool
          */