diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2011-10-26 23:39:42 +0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2011-10-26 23:39:42 +0400 |
commit | c3ae1f33569e06984f0426a7834ff63251d44d84 (patch) | |
tree | 0d7f6f6b49c331e440850cf2e8a7bc0cf220f8bc /drivers | |
parent | c28cfd60e4ec3f494b73ef7d6c661f5f491cd84f (diff) | |
parent | d890fa2b0586b6177b119643ff66932127d58afa (diff) | |
download | linux-c3ae1f33569e06984f0426a7834ff63251d44d84.tar.xz |
Merge branch 'for-linus' of git://neil.brown.name/md
* 'for-linus' of git://neil.brown.name/md: (34 commits)
md: Fix some bugs in recovery_disabled handling.
md/raid5: fix bug that could result in reads from a failed device.
lib/raid6: Fix filename emitted in generated code
md.c: trivial comment fix
MD: Allow restarting an interrupted incremental recovery.
md: clear In_sync bit on devices added to an active array.
md: add proper write-congestion reporting to RAID1 and RAID10.
md: rename "mdk_personality" to "md_personality"
md/bitmap remove fault injection options.
md/raid5: typedef removal: raid5_conf_t -> struct r5conf
md/raid1: typedef removal: conf_t -> struct r1conf
md/raid10: typedef removal: conf_t -> struct r10conf
md/raid0: typedef removal: raid0_conf_t -> struct r0conf
md/multipath: typedef removal: multipath_conf_t -> struct mpconf
md/linear: typedef removal: linear_conf_t -> struct linear_conf
md/faulty: remove typedef: conf_t -> struct faulty_conf
md/linear: remove typedefs: dev_info_t -> struct dev_info
md: remove typedefs: mirror_info_t -> struct mirror_info
md: remove typedefs: r10bio_t -> struct r10bio and r1bio_t -> struct r1bio
md: remove typedefs: mdk_thread_t -> struct md_thread
...
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/md/bitmap.c | 188 | ||||
-rw-r--r-- | drivers/md/bitmap.h | 12 | ||||
-rw-r--r-- | drivers/md/dm-raid.c | 28 | ||||
-rw-r--r-- | drivers/md/faulty.c | 38 | ||||
-rw-r--r-- | drivers/md/linear.c | 46 | ||||
-rw-r--r-- | drivers/md/linear.h | 12 | ||||
-rw-r--r-- | drivers/md/md.c | 631 | ||||
-rw-r--r-- | drivers/md/md.h | 153 | ||||
-rw-r--r-- | drivers/md/multipath.c | 64 | ||||
-rw-r--r-- | drivers/md/multipath.h | 10 | ||||
-rw-r--r-- | drivers/md/raid0.c | 191 | ||||
-rw-r--r-- | drivers/md/raid0.h | 10 | ||||
-rw-r--r-- | drivers/md/raid1.c | 335 | ||||
-rw-r--r-- | drivers/md/raid1.h | 85 | ||||
-rw-r--r-- | drivers/md/raid10.c | 280 | ||||
-rw-r--r-- | drivers/md/raid10.h | 22 | ||||
-rw-r--r-- | drivers/md/raid5.c | 363 | ||||
-rw-r--r-- | drivers/md/raid5.h | 20 |
18 files changed, 1216 insertions, 1272 deletions
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 0dc6546b77a8..7878712721bf 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -29,35 +29,6 @@ #include "md.h" #include "bitmap.h" -/* debug macros */ - -#define DEBUG 0 - -#if DEBUG -/* these are for debugging purposes only! */ - -/* define one and only one of these */ -#define INJECT_FAULTS_1 0 /* cause bitmap_alloc_page to fail always */ -#define INJECT_FAULTS_2 0 /* cause bitmap file to be kicked when first bit set*/ -#define INJECT_FAULTS_3 0 /* treat bitmap file as kicked at init time */ -#define INJECT_FAULTS_4 0 /* undef */ -#define INJECT_FAULTS_5 0 /* undef */ -#define INJECT_FAULTS_6 0 - -/* if these are defined, the driver will fail! debug only */ -#define INJECT_FATAL_FAULT_1 0 /* fail kmalloc, causing bitmap_create to fail */ -#define INJECT_FATAL_FAULT_2 0 /* undef */ -#define INJECT_FATAL_FAULT_3 0 /* undef */ -#endif - -#ifndef PRINTK -# if DEBUG > 0 -# define PRINTK(x...) printk(KERN_DEBUG x) -# else -# define PRINTK(x...) -# endif -#endif - static inline char *bmname(struct bitmap *bitmap) { return bitmap->mddev ? mdname(bitmap->mddev) : "mdX"; @@ -70,16 +41,12 @@ static unsigned char *bitmap_alloc_page(struct bitmap *bitmap) { unsigned char *page; -#ifdef INJECT_FAULTS_1 - page = NULL; -#else page = kzalloc(PAGE_SIZE, GFP_NOIO); -#endif if (!page) printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap)); else - PRINTK("%s: bitmap_alloc_page: allocated page at %p\n", - bmname(bitmap), page); + pr_debug("%s: bitmap_alloc_page: allocated page at %p\n", + bmname(bitmap), page); return page; } @@ -88,7 +55,7 @@ static unsigned char *bitmap_alloc_page(struct bitmap *bitmap) */ static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page) { - PRINTK("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page); + pr_debug("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page); kfree(page); } @@ -133,8 +100,8 @@ __acquires(bitmap->lock) spin_lock_irq(&bitmap->lock); if (mappage == NULL) { - PRINTK("%s: bitmap map page allocation failed, hijacking\n", - bmname(bitmap)); + pr_debug("%s: bitmap map page allocation failed, hijacking\n", + bmname(bitmap)); /* failed - set the hijacked flag so that we can use the * pointer as a counter */ if (!bitmap->bp[page].map) @@ -187,13 +154,13 @@ static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page) */ /* IO operations when bitmap is stored near all superblocks */ -static struct page *read_sb_page(mddev_t *mddev, loff_t offset, +static struct page *read_sb_page(struct mddev *mddev, loff_t offset, struct page *page, unsigned long index, int size) { /* choose a good rdev and read the page from there */ - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t target; int did_alloc = 0; @@ -226,7 +193,7 @@ static struct page *read_sb_page(mddev_t *mddev, loff_t offset, } -static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev) +static struct md_rdev *next_active_rdev(struct md_rdev *rdev, struct mddev *mddev) { /* Iterate the disks of an mddev, using rcu to protect access to the * linked list, and raising the refcount of devices we return to ensure @@ -247,7 +214,7 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev) pos = &rdev->same_set; } list_for_each_continue_rcu(pos, &mddev->disks) { - rdev = list_entry(pos, mdk_rdev_t, same_set); + rdev = list_entry(pos, struct md_rdev, same_set); if (rdev->raid_disk >= 0 && !test_bit(Faulty, &rdev->flags)) { /* this is a usable devices */ @@ -262,9 +229,9 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev) static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait) { - mdk_rdev_t *rdev = NULL; + struct md_rdev *rdev = NULL; struct block_device *bdev; - mddev_t *mddev = bitmap->mddev; + struct mddev *mddev = bitmap->mddev; while ((rdev = next_active_rdev(rdev, mddev)) != NULL) { int size = PAGE_SIZE; @@ -409,8 +376,8 @@ static struct page *read_page(struct file *file, unsigned long index, struct buffer_head *bh; sector_t block; - PRINTK("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE, - (unsigned long long)index << PAGE_SHIFT); + pr_debug("read bitmap file (%dB @ %llu)\n", (int)PAGE_SIZE, + (unsigned long long)index << PAGE_SHIFT); page = alloc_page(GFP_KERNEL); if (!page) @@ -868,7 +835,8 @@ static void bitmap_file_kick(struct bitmap *bitmap) enum bitmap_page_attr { BITMAP_PAGE_DIRTY = 0, /* there are set bits that need to be synced */ - BITMAP_PAGE_CLEAN = 1, /* there are bits that might need to be cleared */ + BITMAP_PAGE_PENDING = 1, /* there are bits that are being cleaned. + * i.e. counter is 1 or 2. */ BITMAP_PAGE_NEEDWRITE = 2, /* there are cleared bits that need to be synced */ }; @@ -919,7 +887,7 @@ static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block) else __set_bit_le(bit, kaddr); kunmap_atomic(kaddr, KM_USER0); - PRINTK("set file bit %lu page %lu\n", bit, page->index); + pr_debug("set file bit %lu page %lu\n", bit, page->index); /* record page number so it gets flushed to disk when unplug occurs */ set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY); } @@ -997,11 +965,7 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) BUG_ON(!file && !bitmap->mddev->bitmap_info.offset); -#ifdef INJECT_FAULTS_3 - outofdate = 1; -#else outofdate = bitmap->flags & BITMAP_STALE; -#endif if (outofdate) printk(KERN_INFO "%s: bitmap file is out of date, doing full " "recovery\n", bmname(bitmap)); @@ -1111,7 +1075,6 @@ static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start) (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap), needed); bit_cnt++; - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); } } @@ -1146,6 +1109,7 @@ void bitmap_write_all(struct bitmap *bitmap) for (i = 0; i < bitmap->file_pages; i++) set_page_attr(bitmap, bitmap->filemap[i], BITMAP_PAGE_NEEDWRITE); + bitmap->allclean = 0; } static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc) @@ -1164,7 +1128,7 @@ static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap, * out to disk */ -void bitmap_daemon_work(mddev_t *mddev) +void bitmap_daemon_work(struct mddev *mddev) { struct bitmap *bitmap; unsigned long j; @@ -1204,17 +1168,15 @@ void bitmap_daemon_work(mddev_t *mddev) if (page != lastpage) { /* skip this page unless it's marked as needing cleaning */ - if (!test_page_attr(bitmap, page, BITMAP_PAGE_CLEAN)) { + if (!test_page_attr(bitmap, page, BITMAP_PAGE_PENDING)) { int need_write = test_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); if (need_write) clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); - if (need_write) { + if (need_write) write_page(bitmap, page, 0); - bitmap->allclean = 0; - } spin_lock_irqsave(&bitmap->lock, flags); j |= (PAGE_BITS - 1); continue; @@ -1222,12 +1184,16 @@ void bitmap_daemon_work(mddev_t *mddev) /* grab the new page, sync and release the old */ if (lastpage != NULL) { - if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) { - clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); + if (test_page_attr(bitmap, lastpage, + BITMAP_PAGE_NEEDWRITE)) { + clear_page_attr(bitmap, lastpage, + BITMAP_PAGE_NEEDWRITE); spin_unlock_irqrestore(&bitmap->lock, flags); write_page(bitmap, lastpage, 0); } else { - set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); + set_page_attr(bitmap, lastpage, + BITMAP_PAGE_NEEDWRITE); + bitmap->allclean = 0; spin_unlock_irqrestore(&bitmap->lock, flags); } } else @@ -1249,19 +1215,17 @@ void bitmap_daemon_work(mddev_t *mddev) } spin_lock_irqsave(&bitmap->lock, flags); if (!bitmap->need_sync) - clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); + clear_page_attr(bitmap, page, BITMAP_PAGE_PENDING); + else + bitmap->allclean = 0; } bmc = bitmap_get_counter(bitmap, (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap), &blocks, 0); - if (bmc) { - if (*bmc) - bitmap->allclean = 0; - - if (*bmc == 2) { - *bmc = 1; /* maybe clear the bit next time */ - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); - } else if (*bmc == 1 && !bitmap->need_sync) { + if (!bmc) + j |= PAGE_COUNTER_MASK; + else if (*bmc) { + if (*bmc == 1 && !bitmap->need_sync) { /* we can clear the bit */ *bmc = 0; bitmap_count_page(bitmap, @@ -1275,13 +1239,16 @@ void bitmap_daemon_work(mddev_t *mddev) paddr); else __clear_bit_le( - file_page_offset(bitmap, - j), - paddr); + file_page_offset(bitmap, + j), + paddr); kunmap_atomic(paddr, KM_USER0); + } else if (*bmc <= 2) { + *bmc = 1; /* maybe clear the bit next time */ + set_page_attr(bitmap, page, BITMAP_PAGE_PENDING); + bitmap->allclean = 0; } - } else - j |= PAGE_COUNTER_MASK; + } } spin_unlock_irqrestore(&bitmap->lock, flags); @@ -1294,6 +1261,7 @@ void bitmap_daemon_work(mddev_t *mddev) write_page(bitmap, lastpage, 0); } else { set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE); + bitmap->allclean = 0; spin_unlock_irqrestore(&bitmap->lock, flags); } } @@ -1359,8 +1327,8 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect if (bw > bitmap->behind_writes_used) bitmap->behind_writes_used = bw; - PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n", - bw, bitmap->max_write_behind); + pr_debug("inc write-behind count %d/%lu\n", + bw, bitmap->mddev->bitmap_info.max_write_behind); } while (sectors) { @@ -1407,7 +1375,6 @@ int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sect else sectors = 0; } - bitmap->allclean = 0; return 0; } EXPORT_SYMBOL(bitmap_startwrite); @@ -1420,8 +1387,9 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto if (behind) { if (atomic_dec_and_test(&bitmap->behind_writes)) wake_up(&bitmap->behind_wait); - PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n", - atomic_read(&bitmap->behind_writes), bitmap->max_write_behind); + pr_debug("dec write-behind count %d/%lu\n", + atomic_read(&bitmap->behind_writes), + bitmap->mddev->bitmap_info.max_write_behind); } if (bitmap->mddev->degraded) /* Never clear bits or update events_cleared when degraded */ @@ -1453,13 +1421,14 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto wake_up(&bitmap->overflow_wait); (*bmc)--; - if (*bmc <= 2) + if (*bmc <= 2) { set_page_attr(bitmap, filemap_get_page( bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)), - BITMAP_PAGE_CLEAN); - + BITMAP_PAGE_PENDING); + bitmap->allclean = 0; + } spin_unlock_irqrestore(&bitmap->lock, flags); offset += blocks; if (sectors > blocks) @@ -1495,7 +1464,6 @@ static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t } } spin_unlock_irq(&bitmap->lock); - bitmap->allclean = 0; return rv; } @@ -1543,15 +1511,16 @@ void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, i if (!NEEDED(*bmc) && aborted) *bmc |= NEEDED_MASK; else { - if (*bmc <= 2) + if (*bmc <= 2) { set_page_attr(bitmap, filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)), - BITMAP_PAGE_CLEAN); + BITMAP_PAGE_PENDING); + bitmap->allclean = 0; + } } } unlock: spin_unlock_irqrestore(&bitmap->lock, flags); - bitmap->allclean = 0; } EXPORT_SYMBOL(bitmap_end_sync); @@ -1622,10 +1591,10 @@ static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int n *bmc = 1 | (needed ? NEEDED_MASK : 0); bitmap_count_page(bitmap, offset, 1); page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)); - set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN); + set_page_attr(bitmap, page, BITMAP_PAGE_PENDING); + bitmap->allclean = 0; } spin_unlock_irq(&bitmap->lock); - bitmap->allclean = 0; } /* dirty the memory and file bits for bitmap chunks "s" to "e" */ @@ -1649,7 +1618,7 @@ void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e) /* * flush out any pending updates */ -void bitmap_flush(mddev_t *mddev) +void bitmap_flush(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; long sleep; @@ -1697,7 +1666,7 @@ static void bitmap_free(struct bitmap *bitmap) kfree(bitmap); } -void bitmap_destroy(mddev_t *mddev) +void bitmap_destroy(struct mddev *mddev) { struct bitmap *bitmap = mddev->bitmap; @@ -1720,7 +1689,7 @@ void bitmap_destroy(mddev_t *mddev) * initialize the bitmap structure * if this returns an error, bitmap_destroy must be called to do clean up */ -int bitmap_create(mddev_t *mddev) +int bitmap_create(struct mddev *mddev) { struct bitmap *bitmap; sector_t blocks = mddev->resync_max_sectors; @@ -1802,11 +1771,8 @@ int bitmap_create(mddev_t *mddev) bitmap->pages = pages; bitmap->missing_pages = pages; -#ifdef INJECT_FATAL_FAULT_1 - bitmap->bp = NULL; -#else bitmap->bp = kzalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL); -#endif + err = -ENOMEM; if (!bitmap->bp) goto error; @@ -1824,7 +1790,7 @@ int bitmap_create(mddev_t *mddev) return err; } -int bitmap_load(mddev_t *mddev) +int bitmap_load(struct mddev *mddev) { int err = 0; sector_t start = 0; @@ -1870,7 +1836,7 @@ out: EXPORT_SYMBOL_GPL(bitmap_load); static ssize_t -location_show(mddev_t *mddev, char *page) +location_show(struct mddev *mddev, char *page) { ssize_t len; if (mddev->bitmap_info.file) @@ -1884,7 +1850,7 @@ location_show(mddev_t *mddev, char *page) } static ssize_t -location_store(mddev_t *mddev, const char *buf, size_t len) +location_store(struct mddev *mddev, const char *buf, size_t len) { if (mddev->pers) { @@ -1961,7 +1927,7 @@ static struct md_sysfs_entry bitmap_location = __ATTR(location, S_IRUGO|S_IWUSR, location_show, location_store); static ssize_t -timeout_show(mddev_t *mddev, char *page) +timeout_show(struct mddev *mddev, char *page) { ssize_t len; unsigned long secs = mddev->bitmap_info.daemon_sleep / HZ; @@ -1975,7 +1941,7 @@ timeout_show(mddev_t *mddev, char *page) } static ssize_t -timeout_store(mddev_t *mddev, const char *buf, size_t len) +timeout_store(struct mddev *mddev, const char *buf, size_t len) { /* timeout can be set at any time */ unsigned long timeout; @@ -2011,13 +1977,13 @@ static struct md_sysfs_entry bitmap_timeout = __ATTR(time_base, S_IRUGO|S_IWUSR, timeout_show, timeout_store); static ssize_t -backlog_show(mddev_t *mddev, char *page) +backlog_show(struct mddev *mddev, char *page) { return sprintf(page, "%lu\n", mddev->bitmap_info.max_write_behind); } static ssize_t -backlog_store(mddev_t *mddev, const char *buf, size_t len) +backlog_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long backlog; int rv = strict_strtoul(buf, 10, &backlog); @@ -2033,13 +1999,13 @@ static struct md_sysfs_entry bitmap_backlog = __ATTR(backlog, S_IRUGO|S_IWUSR, backlog_show, backlog_store); static ssize_t -chunksize_show(mddev_t *mddev, char *page) +chunksize_show(struct mddev *mddev, char *page) { return sprintf(page, "%lu\n", mddev->bitmap_info.chunksize); } static ssize_t -chunksize_store(mddev_t *mddev, const char *buf, size_t len) +chunksize_store(struct mddev *mddev, const char *buf, size_t len) { /* Can only be changed when no bitmap is active */ int rv; @@ -2059,13 +2025,13 @@ chunksize_store(mddev_t *mddev, const char *buf, size_t len) static struct md_sysfs_entry bitmap_chunksize = __ATTR(chunksize, S_IRUGO|S_IWUSR, chunksize_show, chunksize_store); -static ssize_t metadata_show(mddev_t *mddev, char *page) +static ssize_t metadata_show(struct mddev *mddev, char *page) { return sprintf(page, "%s\n", (mddev->bitmap_info.external ? "external" : "internal")); } -static ssize_t metadata_store(mddev_t *mddev, const char *buf, size_t len) +static ssize_t metadata_store(struct mddev *mddev, const char *buf, size_t len) { if (mddev->bitmap || mddev->bitmap_info.file || @@ -2083,7 +2049,7 @@ static ssize_t metadata_store(mddev_t *mddev, const char *buf, size_t len) static struct md_sysfs_entry bitmap_metadata = __ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store); -static ssize_t can_clear_show(mddev_t *mddev, char *page) +static ssize_t can_clear_show(struct mddev *mddev, char *page) { int len; if (mddev->bitmap) @@ -2094,7 +2060,7 @@ static ssize_t can_clear_show(mddev_t *mddev, char *page) return len; } -static ssize_t can_clear_store(mddev_t *mddev, const char *buf, size_t len) +static ssize_t can_clear_store(struct mddev *mddev, const char *buf, size_t len) { if (mddev->bitmap == NULL) return -ENOENT; @@ -2113,7 +2079,7 @@ static struct md_sysfs_entry bitmap_can_clear = __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store); static ssize_t -behind_writes_used_show(mddev_t *mddev, char *page) +behind_writes_used_show(struct mddev *mddev, char *page) { if (mddev->bitmap == NULL) return sprintf(page, "0\n"); @@ -2122,7 +2088,7 @@ behind_writes_used_show(mddev_t *mddev, char *page) } static ssize_t -behind_writes_used_reset(mddev_t *mddev, const char *buf, size_t len) +behind_writes_used_reset(struct mddev *mddev, const char *buf, size_t len) { if (mddev->bitmap) mddev->bitmap->behind_writes_used = 0; diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index a28f2e5588c6..a15436dd9b3e 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -193,7 +193,7 @@ struct bitmap { 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 */ + struct mddev *mddev; /* the md device that the bitmap is for */ /* bitmap chunksize -- how much data does each bit represent? */ unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */ @@ -238,10 +238,10 @@ struct bitmap { /* the bitmap API */ /* these are used only by md/bitmap */ -int bitmap_create(mddev_t *mddev); -int bitmap_load(mddev_t *mddev); -void bitmap_flush(mddev_t *mddev); -void bitmap_destroy(mddev_t *mddev); +int bitmap_create(struct mddev *mddev); +int bitmap_load(struct mddev *mddev); +void bitmap_flush(struct mddev *mddev); +void bitmap_destroy(struct mddev *mddev); void bitmap_print_sb(struct bitmap *bitmap); void bitmap_update_sb(struct bitmap *bitmap); @@ -262,7 +262,7 @@ 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(mddev_t *mddev); +void bitmap_daemon_work(struct mddev *mddev); #endif #endif diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 86df8b2cf927..37a37266a1e3 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -37,7 +37,7 @@ struct raid_dev { */ struct dm_dev *meta_dev; struct dm_dev *data_dev; - struct mdk_rdev_s rdev; + struct md_rdev rdev; }; /* @@ -57,7 +57,7 @@ struct raid_set { uint64_t print_flags; - struct mddev_s md; + struct mddev md; struct raid_type *raid_type; struct dm_target_callbacks callbacks; @@ -594,7 +594,7 @@ struct dm_raid_superblock { /* Always set to 0 when writing. */ } __packed; -static int read_disk_sb(mdk_rdev_t *rdev, int size) +static int read_disk_sb(struct md_rdev *rdev, int size) { BUG_ON(!rdev->sb_page); @@ -611,9 +611,9 @@ static int read_disk_sb(mdk_rdev_t *rdev, int size) return 0; } -static void super_sync(mddev_t *mddev, mdk_rdev_t *rdev) +static void super_sync(struct mddev *mddev, struct md_rdev *rdev) { - mdk_rdev_t *r, *t; + struct md_rdev *r, *t; uint64_t failed_devices; struct dm_raid_superblock *sb; @@ -651,7 +651,7 @@ static void super_sync(mddev_t *mddev, mdk_rdev_t *rdev) * * Return: 1 if use rdev, 0 if use refdev, -Exxx otherwise */ -static int super_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev) +static int super_load(struct md_rdev *rdev, struct md_rdev *refdev) { int ret; struct dm_raid_superblock *sb; @@ -689,7 +689,7 @@ static int super_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev) return (events_sb > events_refsb) ? 1 : 0; } -static int super_init_validation(mddev_t *mddev, mdk_rdev_t *rdev) +static int super_init_validation(struct mddev *mddev, struct md_rdev *rdev) { int role; struct raid_set *rs = container_of(mddev, struct raid_set, md); @@ -698,7 +698,7 @@ static int super_init_validation(mddev_t *mddev, mdk_rdev_t *rdev) struct dm_raid_superblock *sb; uint32_t new_devs = 0; uint32_t rebuilds = 0; - mdk_rdev_t *r, *t; + struct md_rdev *r, *t; struct dm_raid_superblock *sb2; sb = page_address(rdev->sb_page); @@ -809,7 +809,7 @@ static int super_init_validation(mddev_t *mddev, mdk_rdev_t *rdev) return 0; } -static int super_validate(mddev_t *mddev, mdk_rdev_t *rdev) +static int super_validate(struct mddev *mddev, struct md_rdev *rdev) { struct dm_raid_superblock *sb = page_address(rdev->sb_page); @@ -849,8 +849,8 @@ static int super_validate(mddev_t *mddev, mdk_rdev_t *rdev) static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) { int ret; - mdk_rdev_t *rdev, *freshest, *tmp; - mddev_t *mddev = &rs->md; + struct md_rdev *rdev, *freshest, *tmp; + struct mddev *mddev = &rs->md; freshest = NULL; rdev_for_each(rdev, tmp, mddev) { @@ -1004,7 +1004,7 @@ static void raid_dtr(struct dm_target *ti) static int raid_map(struct dm_target *ti, struct bio *bio, union map_info *map_context) { struct raid_set *rs = ti->private; - mddev_t *mddev = &rs->md; + struct mddev *mddev = &rs->md; mddev->pers->make_request(mddev, bio); @@ -1097,7 +1097,7 @@ static int raid_status(struct dm_target *ti, status_type_t type, rs->md.bitmap_info.max_write_behind); if (rs->print_flags & DMPF_STRIPE_CACHE) { - raid5_conf_t *conf = rs->md.private; + struct r5conf *conf = rs->md.private; /* convert from kiB to sectors */ DMEMIT(" stripe_cache %d", @@ -1146,7 +1146,7 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct raid_set *rs = ti->private; unsigned chunk_size = rs->md.chunk_sectors << 9; - raid5_conf_t *conf = rs->md.private; + struct r5conf *conf = rs->md.private; blk_limits_io_min(limits, chunk_size); blk_limits_io_opt(limits, chunk_size * (conf->raid_disks - conf->max_degraded)); diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c index 23078dabb6df..60816b132c2e 100644 --- a/drivers/md/faulty.c +++ b/drivers/md/faulty.c @@ -81,16 +81,16 @@ static void faulty_fail(struct bio *bio, int error) bio_io_error(b); } -typedef struct faulty_conf { +struct faulty_conf { int period[Modes]; atomic_t counters[Modes]; sector_t faults[MaxFault]; int modes[MaxFault]; int nfaults; - mdk_rdev_t *rdev; -} conf_t; + struct md_rdev *rdev; +}; -static int check_mode(conf_t *conf, int mode) +static int check_mode(struct faulty_conf *conf, int mode) { if (conf->period[mode] == 0 && atomic_read(&conf->counters[mode]) <= 0) @@ -105,7 +105,7 @@ static int check_mode(conf_t *conf, int mode) return 0; } -static int check_sector(conf_t *conf, sector_t start, sector_t end, int dir) +static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir) { /* If we find a ReadFixable sector, we fix it ... */ int i; @@ -129,7 +129,7 @@ static int check_sector(conf_t *conf, sector_t start, sector_t end, int dir) return 0; } -static void add_sector(conf_t *conf, sector_t start, int mode) +static void add_sector(struct faulty_conf *conf, sector_t start, int mode) { int i; int n = conf->nfaults; @@ -169,9 +169,9 @@ static void add_sector(conf_t *conf, sector_t start, int mode) conf->nfaults = n+1; } -static int make_request(mddev_t *mddev, struct bio *bio) +static int make_request(struct mddev *mddev, struct bio *bio) { - conf_t *conf = mddev->private; + struct faulty_conf *conf = mddev->private; int failit = 0; if (bio_data_dir(bio) == WRITE) { @@ -222,9 +222,9 @@ static int make_request(mddev_t *mddev, struct bio *bio) } } -static void status(struct seq_file *seq, mddev_t *mddev) +static void status(struct seq_file *seq, struct mddev *mddev) { - conf_t *conf = mddev->private; + struct faulty_conf *conf = mddev->private; int n; if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) @@ -255,11 +255,11 @@ static void status(struct seq_file *seq, mddev_t *mddev) } -static int reshape(mddev_t *mddev) +static int reshape(struct mddev *mddev) { int mode = mddev->new_layout & ModeMask; int count = mddev->new_layout >> ModeShift; - conf_t *conf = mddev->private; + struct faulty_conf *conf = mddev->private; if (mddev->new_layout < 0) return 0; @@ -284,7 +284,7 @@ static int reshape(mddev_t *mddev) return 0; } -static sector_t faulty_size(mddev_t *mddev, sector_t sectors, int raid_disks) +static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks) { WARN_ONCE(raid_disks, "%s does not support generic reshape\n", __func__); @@ -295,11 +295,11 @@ static sector_t faulty_size(mddev_t *mddev, sector_t sectors, int raid_disks) return sectors; } -static int run(mddev_t *mddev) +static int run(struct mddev *mddev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; int i; - conf_t *conf; + struct faulty_conf *conf; if (md_check_no_bitmap(mddev)) return -EINVAL; @@ -325,16 +325,16 @@ static int run(mddev_t *mddev) return 0; } -static int stop(mddev_t *mddev) +static int stop(struct mddev *mddev) { - conf_t *conf = mddev->private; + struct faulty_conf *conf = mddev->private; kfree(conf); mddev->private = NULL; return 0; } -static struct mdk_personality faulty_personality = +static struct md_personality faulty_personality = { .name = "faulty", .level = LEVEL_FAULTY, diff --git a/drivers/md/linear.c b/drivers/md/linear.c index 6cd2c313e800..10c5844460cb 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -26,10 +26,10 @@ /* * find which device holds a particular offset */ -static inline dev_info_t *which_dev(mddev_t *mddev, sector_t sector) +static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) { int lo, mid, hi; - linear_conf_t *conf; + struct linear_conf *conf; lo = 0; hi = mddev->raid_disks - 1; @@ -63,8 +63,8 @@ static int linear_mergeable_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *biovec) { - mddev_t *mddev = q->queuedata; - dev_info_t *dev0; + struct mddev *mddev = q->queuedata; + struct dev_info *dev0; unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9; sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); @@ -89,8 +89,8 @@ static int linear_mergeable_bvec(struct request_queue *q, static int linear_congested(void *data, int bits) { - mddev_t *mddev = data; - linear_conf_t *conf; + struct mddev *mddev = data; + struct linear_conf *conf; int i, ret = 0; if (mddev_congested(mddev, bits)) @@ -108,9 +108,9 @@ static int linear_congested(void *data, int bits) return ret; } -static sector_t linear_size(mddev_t *mddev, sector_t sectors, int raid_disks) +static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) { - linear_conf_t *conf; + struct linear_conf *conf; sector_t array_sectors; rcu_read_lock(); @@ -123,13 +123,13 @@ static sector_t linear_size(mddev_t *mddev, sector_t sectors, int raid_disks) return array_sectors; } -static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) +static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) { - linear_conf_t *conf; - mdk_rdev_t *rdev; + struct linear_conf *conf; + struct md_rdev *rdev; int i, cnt; - conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(dev_info_t), + conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info), GFP_KERNEL); if (!conf) return NULL; @@ -139,7 +139,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks) list_for_each_entry(rdev, &mddev->disks, same_set) { int j = rdev->raid_disk; - dev_info_t *disk = conf->disks + j; + struct dev_info *disk = conf->disks + j; sector_t sectors; if (j < 0 || j >= raid_disks || disk->rdev) { @@ -194,9 +194,9 @@ out: return NULL; } -static int linear_run (mddev_t *mddev) +static int linear_run (struct mddev *mddev) { - linear_conf_t *conf; + struct linear_conf *conf; if (md_check_no_bitmap(mddev)) return -EINVAL; @@ -213,7 +213,7 @@ static int linear_run (mddev_t *mddev) return md_integrity_register(mddev); } -static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev) +static int linear_add(struct mddev *mddev, struct md_rdev *rdev) { /* Adding a drive to a linear array allows the array to grow. * It is permitted if the new drive has a matching superblock @@ -223,7 +223,7 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev) * The current one is never freed until the array is stopped. * This avoids races. */ - linear_conf_t *newconf, *oldconf; + struct linear_conf *newconf, *oldconf; if (rdev->saved_raid_disk != mddev->raid_disks) return -EINVAL; @@ -245,9 +245,9 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev) return 0; } -static int linear_stop (mddev_t *mddev) +static int linear_stop (struct mddev *mddev) { - linear_conf_t *conf = mddev->private; + struct linear_conf *conf = mddev->private; /* * We do not require rcu protection here since @@ -264,9 +264,9 @@ static int linear_stop (mddev_t *mddev) return 0; } -static int linear_make_request (mddev_t *mddev, struct bio *bio) +static int linear_make_request (struct mddev *mddev, struct bio *bio) { - dev_info_t *tmp_dev; + struct dev_info *tmp_dev; sector_t start_sector; if (unlikely(bio->bi_rw & REQ_FLUSH)) { @@ -323,14 +323,14 @@ static int linear_make_request (mddev_t *mddev, struct bio *bio) return 1; } -static void linear_status (struct seq_file *seq, mddev_t *mddev) +static void linear_status (struct seq_file *seq, struct mddev *mddev) { seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); } -static struct mdk_personality linear_personality = +static struct md_personality linear_personality = { .name = "linear", .level = LEVEL_LINEAR, diff --git a/drivers/md/linear.h b/drivers/md/linear.h index 2f2da05b2ce9..b685ddd7d7f7 100644 --- a/drivers/md/linear.h +++ b/drivers/md/linear.h @@ -2,20 +2,14 @@ #define _LINEAR_H struct dev_info { - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t end_sector; }; -typedef struct dev_info dev_info_t; - -struct linear_private_data +struct linear_conf { struct rcu_head rcu; sector_t array_sectors; - dev_info_t disks[0]; + struct dev_info disks[0]; }; - - -typedef struct linear_private_data linear_conf_t; - #endif diff --git a/drivers/md/md.c b/drivers/md/md.c index 5c95ccb59500..266e82ebaf11 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -54,9 +54,6 @@ #include "md.h" #include "bitmap.h" -#define DEBUG 0 -#define dprintk(x...) ((void)(DEBUG && printk(x))) - #ifndef MODULE static void autostart_arrays(int part); #endif @@ -98,13 +95,13 @@ static struct workqueue_struct *md_misc_wq; static int sysctl_speed_limit_min = 1000; static int sysctl_speed_limit_max = 200000; -static inline int speed_min(mddev_t *mddev) +static inline int speed_min(struct mddev *mddev) { return mddev->sync_speed_min ? mddev->sync_speed_min : sysctl_speed_limit_min; } -static inline int speed_max(mddev_t *mddev) +static inline int speed_max(struct mddev *mddev) { return mddev->sync_speed_max ? mddev->sync_speed_max : sysctl_speed_limit_max; @@ -160,7 +157,7 @@ static int start_readonly; static void mddev_bio_destructor(struct bio *bio) { - mddev_t *mddev, **mddevp; + struct mddev *mddev, **mddevp; mddevp = (void*)bio; mddev = mddevp[-1]; @@ -169,10 +166,10 @@ static void mddev_bio_destructor(struct bio *bio) } struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, - mddev_t *mddev) + struct mddev *mddev) { struct bio *b; - mddev_t **mddevp; + struct mddev **mddevp; if (!mddev || !mddev->bio_set) return bio_alloc(gfp_mask, nr_iovecs); @@ -189,10 +186,10 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, EXPORT_SYMBOL_GPL(bio_alloc_mddev); struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, - mddev_t *mddev) + struct mddev *mddev) { struct bio *b; - mddev_t **mddevp; + struct mddev **mddevp; if (!mddev || !mddev->bio_set) return bio_clone(bio, gfp_mask); @@ -281,7 +278,7 @@ EXPORT_SYMBOL_GPL(md_trim_bio); */ static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters); static atomic_t md_event_count; -void md_new_event(mddev_t *mddev) +void md_new_event(struct mddev *mddev) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); @@ -291,7 +288,7 @@ EXPORT_SYMBOL_GPL(md_new_event); /* Alternate version that can be called from interrupts * when calling sysfs_notify isn't needed. */ -static void md_new_event_inintr(mddev_t *mddev) +static void md_new_event_inintr(struct mddev *mddev) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); @@ -312,19 +309,19 @@ static DEFINE_SPINLOCK(all_mddevs_lock); * Any code which breaks out of this loop while own * a reference to the current mddev and must mddev_put it. */ -#define for_each_mddev(mddev,tmp) \ +#define for_each_mddev(_mddev,_tmp) \ \ for (({ spin_lock(&all_mddevs_lock); \ - tmp = all_mddevs.next; \ - mddev = NULL;}); \ - ({ if (tmp != &all_mddevs) \ - mddev_get(list_entry(tmp, mddev_t, all_mddevs));\ + _tmp = all_mddevs.next; \ + _mddev = NULL;}); \ + ({ if (_tmp != &all_mddevs) \ + mddev_get(list_entry(_tmp, struct mddev, all_mddevs));\ spin_unlock(&all_mddevs_lock); \ - if (mddev) mddev_put(mddev); \ - mddev = list_entry(tmp, mddev_t, all_mddevs); \ - tmp != &all_mddevs;}); \ + if (_mddev) mddev_put(_mddev); \ + _mddev = list_entry(_tmp, struct mddev, all_mddevs); \ + _tmp != &all_mddevs;}); \ ({ spin_lock(&all_mddevs_lock); \ - tmp = tmp->next;}) \ + _tmp = _tmp->next;}) \ ) @@ -338,7 +335,7 @@ static DEFINE_SPINLOCK(all_mddevs_lock); static int md_make_request(struct request_queue *q, struct bio *bio) { const int rw = bio_data_dir(bio); - mddev_t *mddev = q->queuedata; + struct mddev *mddev = q->queuedata; int rv; int cpu; unsigned int sectors; @@ -390,7 +387,7 @@ static int md_make_request(struct request_queue *q, struct bio *bio) * Once ->stop is called and completes, the module will be completely * unused. */ -void mddev_suspend(mddev_t *mddev) +void mddev_suspend(struct mddev *mddev) { BUG_ON(mddev->suspended); mddev->suspended = 1; @@ -400,7 +397,7 @@ void mddev_suspend(mddev_t *mddev) } EXPORT_SYMBOL_GPL(mddev_suspend); -void mddev_resume(mddev_t *mddev) +void mddev_resume(struct mddev *mddev) { mddev->suspended = 0; wake_up(&mddev->sb_wait); @@ -411,7 +408,7 @@ void mddev_resume(mddev_t *mddev) } EXPORT_SYMBOL_GPL(mddev_resume); -int mddev_congested(mddev_t *mddev, int bits) +int mddev_congested(struct mddev *mddev, int bits) { return mddev->suspended; } @@ -423,8 +420,8 @@ EXPORT_SYMBOL(mddev_congested); static void md_end_flush(struct bio *bio, int err) { - mdk_rdev_t *rdev = bio->bi_private; - mddev_t *mddev = rdev->mddev; + struct md_rdev *rdev = bio->bi_private; + struct mddev *mddev = rdev->mddev; rdev_dec_pending(rdev, mddev); @@ -439,8 +436,8 @@ static void md_submit_flush_data(struct work_struct *ws); static void submit_flushes(struct work_struct *ws) { - mddev_t *mddev = container_of(ws, mddev_t, flush_work); - mdk_rdev_t *rdev; + struct mddev *mddev = container_of(ws, struct mddev, flush_work); + struct md_rdev *rdev; INIT_WORK(&mddev->flush_work, md_submit_flush_data); atomic_set(&mddev->flush_pending, 1); @@ -472,7 +469,7 @@ static void submit_flushes(struct work_struct *ws) static void md_submit_flush_data(struct work_struct *ws) { - mddev_t *mddev = container_of(ws, mddev_t, flush_work); + struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct bio *bio = mddev->flush_bio; if (bio->bi_size == 0) @@ -488,7 +485,7 @@ static void md_submit_flush_data(struct work_struct *ws) wake_up(&mddev->sb_wait); } -void md_flush_request(mddev_t *mddev, struct bio *bio) +void md_flush_request(struct mddev *mddev, struct bio *bio) { spin_lock_irq(&mddev->write_lock); wait_event_lock_irq(mddev->sb_wait, @@ -512,7 +509,7 @@ EXPORT_SYMBOL(md_flush_request); */ struct md_plug_cb { struct blk_plug_cb cb; - mddev_t *mddev; + struct mddev *mddev; }; static void plugger_unplug(struct blk_plug_cb *cb) @@ -526,7 +523,7 @@ static void plugger_unplug(struct blk_plug_cb *cb) /* Check that an unplug wakeup will come shortly. * If not, wakeup the md thread immediately */ -int mddev_check_plugged(mddev_t *mddev) +int mddev_check_plugged(struct mddev *mddev) { struct blk_plug *plug = current->plug; struct md_plug_cb *mdcb; @@ -558,7 +555,7 @@ int mddev_check_plugged(mddev_t *mddev) } EXPORT_SYMBOL_GPL(mddev_check_plugged); -static inline mddev_t *mddev_get(mddev_t *mddev) +static inline struct mddev *mddev_get(struct mddev *mddev) { atomic_inc(&mddev->active); return mddev; @@ -566,7 +563,7 @@ static inline mddev_t *mddev_get(mddev_t *mddev) static void mddev_delayed_delete(struct work_struct *ws); -static void mddev_put(mddev_t *mddev) +static void mddev_put(struct mddev *mddev) { struct bio_set *bs = NULL; @@ -595,7 +592,7 @@ static void mddev_put(mddev_t *mddev) bioset_free(bs); } -void mddev_init(mddev_t *mddev) +void mddev_init(struct mddev *mddev) { mutex_init(&mddev->open_mutex); mutex_init(&mddev->reconfig_mutex); @@ -618,9 +615,9 @@ void mddev_init(mddev_t *mddev) } EXPORT_SYMBOL_GPL(mddev_init); -static mddev_t * mddev_find(dev_t unit) +static struct mddev * mddev_find(dev_t unit) { - mddev_t *mddev, *new = NULL; + struct mddev *mddev, *new = NULL; if (unit && MAJOR(unit) != MD_MAJOR) unit &= ~((1<<MdpMinorShift)-1); @@ -692,24 +689,24 @@ static mddev_t * mddev_find(dev_t unit) goto retry; } -static inline int mddev_lock(mddev_t * mddev) +static inline int mddev_lock(struct mddev * mddev) { return mutex_lock_interruptible(&mddev->reconfig_mutex); } -static inline int mddev_is_locked(mddev_t *mddev) +static inline int mddev_is_locked(struct mddev *mddev) { return mutex_is_locked(&mddev->reconfig_mutex); } -static inline int mddev_trylock(mddev_t * mddev) +static inline int mddev_trylock(struct mddev * mddev) { return mutex_trylock(&mddev->reconfig_mutex); } static struct attribute_group md_redundancy_group; -static void mddev_unlock(mddev_t * mddev) +static void mddev_unlock(struct mddev * mddev) { if (mddev->to_remove) { /* These cannot be removed under reconfig_mutex as @@ -744,17 +741,17 @@ static void mddev_unlock(mddev_t * mddev) } else mutex_unlock(&mddev->reconfig_mutex); - /* was we've dropped the mutex we need a spinlock to - * make sur the thread doesn't disappear + /* As we've dropped the mutex we need a spinlock to + * make sure the thread doesn't disappear */ spin_lock(&pers_lock); md_wakeup_thread(mddev->thread); spin_unlock(&pers_lock); } -static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr) +static struct md_rdev * find_rdev_nr(struct mddev *mddev, int nr) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->desc_nr == nr) @@ -763,9 +760,9 @@ static mdk_rdev_t * find_rdev_nr(mddev_t *mddev, int nr) return NULL; } -static mdk_rdev_t * find_rdev(mddev_t * mddev, dev_t dev) +static struct md_rdev * find_rdev(struct mddev * mddev, dev_t dev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->bdev->bd_dev == dev) @@ -774,9 +771,9 @@ static mdk_rdev_t * find_rdev(mddev_t * mddev, dev_t dev) return NULL; } -static struct mdk_personality *find_pers(int level, char *clevel) +static struct md_personality *find_pers(int level, char *clevel) { - struct mdk_personality *pers; + struct md_personality *pers; list_for_each_entry(pers, &pers_list, list) { if (level != LEVEL_NONE && pers->level == level) return pers; @@ -787,13 +784,13 @@ static struct mdk_personality *find_pers(int level, char *clevel) } /* return the offset of the super block in 512byte sectors */ -static inline sector_t calc_dev_sboffset(mdk_rdev_t *rdev) +static inline sector_t calc_dev_sboffset(struct md_rdev *rdev) { sector_t num_sectors = i_size_read(rdev->bdev->bd_inode) / 512; return MD_NEW_SIZE_SECTORS(num_sectors); } -static int alloc_disk_sb(mdk_rdev_t * rdev) +static int alloc_disk_sb(struct md_rdev * rdev) { if (rdev->sb_page) MD_BUG(); @@ -807,7 +804,7 @@ static int alloc_disk_sb(mdk_rdev_t * rdev) return 0; } -static void free_disk_sb(mdk_rdev_t * rdev) +static void free_disk_sb(struct md_rdev * rdev) { if (rdev->sb_page) { put_page(rdev->sb_page); @@ -825,8 +822,8 @@ static void free_disk_sb(mdk_rdev_t * rdev) static void super_written(struct bio *bio, int error) { - mdk_rdev_t *rdev = bio->bi_private; - mddev_t *mddev = rdev->mddev; + struct md_rdev *rdev = bio->bi_private; + struct mddev *mddev = rdev->mddev; if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) { printk("md: super_written gets error=%d, uptodate=%d\n", @@ -840,7 +837,7 @@ static void super_written(struct bio *bio, int error) bio_put(bio); } -void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, +void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page) { /* write first size bytes of page to sector of rdev @@ -861,7 +858,7 @@ void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, submit_bio(WRITE_FLUSH_FUA, bio); } -void md_super_wait(mddev_t *mddev) +void md_super_wait(struct mddev *mddev) { /* wait for all superblock writes that were scheduled to complete */ DEFINE_WAIT(wq); @@ -879,7 +876,7 @@ static void bi_complete(struct bio *bio, int error) complete((struct completion*)bio->bi_private); } -int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, +int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, int rw, bool metadata_op) { struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev); @@ -907,7 +904,7 @@ int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, } EXPORT_SYMBOL_GPL(sync_page_io); -static int read_disk_sb(mdk_rdev_t * rdev, int size) +static int read_disk_sb(struct md_rdev * rdev, int size) { char b[BDEVNAME_SIZE]; if (!rdev->sb_page) { @@ -1014,7 +1011,7 @@ static unsigned int calc_sb_csum(mdp_super_t * sb) * We rely on user-space to write the initial superblock, and support * reading and updating of superblocks. * Interface methods are: - * int load_super(mdk_rdev_t *dev, mdk_rdev_t *refdev, int minor_version) + * int load_super(struct md_rdev *dev, struct md_rdev *refdev, int minor_version) * loads and validates a superblock on dev. * if refdev != NULL, compare superblocks on both devices * Return: @@ -1024,13 +1021,13 @@ static unsigned int calc_sb_csum(mdp_super_t * sb) * -EINVAL superblock incompatible or invalid * -othererror e.g. -EIO * - * int validate_super(mddev_t *mddev, mdk_rdev_t *dev) + * int validate_super(struct mddev *mddev, struct md_rdev *dev) * Verify that dev is acceptable into mddev. * The first time, mddev->raid_disks will be 0, and data from * dev should be merged in. Subsequent calls check that dev * is new enough. Return 0 or -EINVAL * - * void sync_super(mddev_t *mddev, mdk_rdev_t *dev) + * void sync_super(struct mddev *mddev, struct md_rdev *dev) * Update the superblock for rdev with data in mddev * This does not write to disc. * @@ -1039,11 +1036,11 @@ static unsigned int calc_sb_csum(mdp_super_t * sb) struct super_type { char *name; struct module *owner; - int (*load_super)(mdk_rdev_t *rdev, mdk_rdev_t *refdev, + int (*load_super)(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version); - int (*validate_super)(mddev_t *mddev, mdk_rdev_t *rdev); - void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); - unsigned long long (*rdev_size_change)(mdk_rdev_t *rdev, + int (*validate_super)(struct mddev *mddev, struct md_rdev *rdev); + void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); + unsigned long long (*rdev_size_change)(struct md_rdev *rdev, sector_t num_sectors); }; @@ -1055,7 +1052,7 @@ struct super_type { * has a bitmap. Otherwise, it returns 0. * */ -int md_check_no_bitmap(mddev_t *mddev) +int md_check_no_bitmap(struct mddev *mddev) { if (!mddev->bitmap_info.file && !mddev->bitmap_info.offset) return 0; @@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(md_check_no_bitmap); /* * load_super for 0.90.0 */ -static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) +static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version) { char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; mdp_super_t *sb; @@ -1163,7 +1160,7 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version /* * validate_super for 0.90.0 */ -static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) +static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) { mdp_disk_t *desc; mdp_super_t *sb = page_address(rdev->sb_page); @@ -1275,10 +1272,10 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev) /* * sync_super for 0.90.0 */ -static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) +static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev) { mdp_super_t *sb; - mdk_rdev_t *rdev2; + struct md_rdev *rdev2; int next_spare = mddev->raid_disks; @@ -1419,7 +1416,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev) * rdev_size_change for 0.90.0 */ static unsigned long long -super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors) +super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) { if (num_sectors && num_sectors < rdev->mddev->dev_sectors) return 0; /* component must fit device */ @@ -1469,7 +1466,7 @@ static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb) static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, int acknowledged); -static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) +static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_version) { struct mdp_superblock_1 *sb; int ret; @@ -1625,7 +1622,7 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version) return ret; } -static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) +static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) { struct mdp_superblock_1 *sb = page_address(rdev->sb_page); __u64 ev1 = le64_to_cpu(sb->events); @@ -1726,10 +1723,10 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev) return 0; } -static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev) +static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) { struct mdp_superblock_1 *sb; - mdk_rdev_t *rdev2; + struct md_rdev *rdev2; int max_dev, i; /* make rdev->sb match mddev and rdev data. */ @@ -1851,7 +1848,7 @@ retry: } static unsigned long long -super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors) +super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) { struct mdp_superblock_1 *sb; sector_t max_sectors; @@ -1905,7 +1902,7 @@ static struct super_type super_types[] = { }, }; -static void sync_super(mddev_t *mddev, mdk_rdev_t *rdev) +static void sync_super(struct mddev *mddev, struct md_rdev *rdev) { if (mddev->sync_super) { mddev->sync_super(mddev, rdev); @@ -1917,9 +1914,9 @@ static void sync_super(mddev_t *mddev, mdk_rdev_t *rdev) super_types[mddev->major_version].sync_super(mddev, rdev); } -static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2) +static int match_mddev_units(struct mddev *mddev1, struct mddev *mddev2) { - mdk_rdev_t *rdev, *rdev2; + struct md_rdev *rdev, *rdev2; rcu_read_lock(); rdev_for_each_rcu(rdev, mddev1) @@ -1942,9 +1939,9 @@ static LIST_HEAD(pending_raid_disks); * from the array. It only succeeds if all working and active component devices * are integrity capable with matching profiles. */ -int md_integrity_register(mddev_t *mddev) +int md_integrity_register(struct mddev *mddev) { - mdk_rdev_t *rdev, *reference = NULL; + struct md_rdev *rdev, *reference = NULL; if (list_empty(&mddev->disks)) return 0; /* nothing to do */ @@ -1989,7 +1986,7 @@ int md_integrity_register(mddev_t *mddev) EXPORT_SYMBOL(md_integrity_register); /* Disable data integrity if non-capable/non-matching disk is being added */ -void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev) +void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev) { struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev); struct blk_integrity *bi_mddev = blk_get_integrity(mddev->gendisk); @@ -2006,7 +2003,7 @@ void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev) } EXPORT_SYMBOL(md_integrity_add_rdev); -static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) +static int bind_rdev_to_array(struct md_rdev * rdev, struct mddev * mddev) { char b[BDEVNAME_SIZE]; struct kobject *ko; @@ -2086,12 +2083,12 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev) static void md_delayed_delete(struct work_struct *ws) { - mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work); + struct md_rdev *rdev = container_of(ws, struct md_rdev, del_work); kobject_del(&rdev->kobj); kobject_put(&rdev->kobj); } -static void unbind_rdev_from_array(mdk_rdev_t * rdev) +static void unbind_rdev_from_array(struct md_rdev * rdev) { char b[BDEVNAME_SIZE]; if (!rdev->mddev) { @@ -2123,14 +2120,14 @@ static void unbind_rdev_from_array(mdk_rdev_t * rdev) * otherwise reused by a RAID array (or any other kernel * subsystem), by bd_claiming the device. */ -static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared) +static int lock_rdev(struct md_rdev *rdev, dev_t dev, int shared) { int err = 0; struct block_device *bdev; char b[BDEVNAME_SIZE]; bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, - shared ? (mdk_rdev_t *)lock_rdev : rdev); + shared ? (struct md_rdev *)lock_rdev : rdev); if (IS_ERR(bdev)) { printk(KERN_ERR "md: could not open %s.\n", __bdevname(dev, b)); @@ -2140,7 +2137,7 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared) return err; } -static void unlock_rdev(mdk_rdev_t *rdev) +static void unlock_rdev(struct md_rdev *rdev) { struct block_device *bdev = rdev->bdev; rdev->bdev = NULL; @@ -2151,7 +2148,7 @@ static void unlock_rdev(mdk_rdev_t *rdev) void md_autodetect_dev(dev_t dev); -static void export_rdev(mdk_rdev_t * rdev) +static void export_rdev(struct md_rdev * rdev) { char b[BDEVNAME_SIZE]; printk(KERN_INFO "md: export_rdev(%s)\n", @@ -2167,15 +2164,15 @@ static void export_rdev(mdk_rdev_t * rdev) kobject_put(&rdev->kobj); } -static void kick_rdev_from_array(mdk_rdev_t * rdev) +static void kick_rdev_from_array(struct md_rdev * rdev) { unbind_rdev_from_array(rdev); export_rdev(rdev); } -static void export_array(mddev_t *mddev) +static void export_array(struct mddev *mddev) { - mdk_rdev_t *rdev, *tmp; + struct md_rdev *rdev, *tmp; rdev_for_each(rdev, tmp, mddev) { if (!rdev->mddev) { @@ -2271,7 +2268,7 @@ static void print_sb_1(struct mdp_superblock_1 *sb) ); } -static void print_rdev(mdk_rdev_t *rdev, int major_version) +static void print_rdev(struct md_rdev *rdev, int major_version) { char b[BDEVNAME_SIZE]; printk(KERN_INFO "md: rdev %s, Sect:%08llu F:%d S:%d DN:%u\n", @@ -2295,8 +2292,8 @@ static void print_rdev(mdk_rdev_t *rdev, int major_version) static void md_print_devices(void) { struct list_head *tmp; - mdk_rdev_t *rdev; - mddev_t *mddev; + struct md_rdev *rdev; + struct mddev *mddev; char b[BDEVNAME_SIZE]; printk("\n"); @@ -2321,7 +2318,7 @@ static void md_print_devices(void) } -static void sync_sbs(mddev_t * mddev, int nospares) +static void sync_sbs(struct mddev * mddev, int nospares) { /* Update each superblock (in-memory image), but * if we are allowed to, skip spares which already @@ -2329,7 +2326,7 @@ static void sync_sbs(mddev_t * mddev, int nospares) * (which would mean they aren't being marked as dirty * with the rest of the array) */ - mdk_rdev_t *rdev; + struct md_rdev *rdev; list_for_each_entry(rdev, &mddev->disks, same_set) { if (rdev->sb_events == mddev->events || (nospares && @@ -2344,9 +2341,9 @@ static void sync_sbs(mddev_t * mddev, int nospares) } } -static void md_update_sb(mddev_t * mddev, int force_change) +static void md_update_sb(struct mddev * mddev, int force_change) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; int sync_req; int nospares = 0; int any_badblocks_changed = 0; @@ -2442,27 +2439,24 @@ repeat: sync_sbs(mddev, nospares); spin_unlock_irq(&mddev->write_lock); - dprintk(KERN_INFO - "md: updating %s RAID superblock on device (in sync %d)\n", - mdname(mddev),mddev->in_sync); + pr_debug("md: updating %s RAID superblock on device (in sync %d)\n", + mdname(mddev), mddev->in_sync); bitmap_update_sb(mddev->bitmap); list_for_each_entry(rdev, &mddev->disks, same_set) { char b[BDEVNAME_SIZE]; - dprintk(KERN_INFO "md: "); + if (rdev->sb_loaded != 1) continue; /* no noise on spare devices */ - if (test_bit(Faulty, &rdev->flags)) - dprintk("(skipping faulty "); - dprintk("%s ", bdevname(rdev->bdev,b)); - if (!test_bit(Faulty, &rdev->flags)) { + if (!test_bit(Faulty, &rdev->flags) && + rdev->saved_raid_disk == -1) { md_super_write(mddev,rdev, rdev->sb_start, rdev->sb_size, rdev->sb_page); - dprintk(KERN_INFO "(write) %s's sb offset: %llu\n", - bdevname(rdev->bdev,b), - (unsigned long long)rdev->sb_start); + pr_debug("md: (write) %s's sb offset: %llu\n", + bdevname(rdev->bdev, b), + (unsigned long long)rdev->sb_start); rdev->sb_events = mddev->events; if (rdev->badblocks.size) { md_super_write(mddev, rdev, @@ -2472,8 +2466,12 @@ repeat: rdev->badblocks.size = 0; } - } else - dprintk(")\n"); + } else if (test_bit(Faulty, &rdev->flags)) + pr_debug("md: %s (skipping faulty)\n", + bdevname(rdev->bdev, b)); + else + pr_debug("(skipping incremental s/r "); + if (mddev->level == LEVEL_MULTIPATH) /* only need to write one superblock... */ break; @@ -2527,12 +2525,12 @@ static int cmd_match(const char *cmd, const char *str) struct rdev_sysfs_entry { struct attribute attr; - ssize_t (*show)(mdk_rdev_t *, char *); - ssize_t (*store)(mdk_rdev_t *, const char *, size_t); + ssize_t (*show)(struct md_rdev *, char *); + ssize_t (*store)(struct md_rdev *, const char *, size_t); }; static ssize_t -state_show(mdk_rdev_t *rdev, char *page) +state_show(struct md_rdev *rdev, char *page) { char *sep = ""; size_t len = 0; @@ -2568,7 +2566,7 @@ state_show(mdk_rdev_t *rdev, char *page) } static ssize_t -state_store(mdk_rdev_t *rdev, const char *buf, size_t len) +state_store(struct md_rdev *rdev, const char *buf, size_t len) { /* can write * faulty - simulates an error @@ -2592,7 +2590,7 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len) if (rdev->raid_disk >= 0) err = -EBUSY; else { - mddev_t *mddev = rdev->mddev; + struct mddev *mddev = rdev->mddev; kick_rdev_from_array(rdev); if (mddev->pers) md_update_sb(mddev, 1); @@ -2641,13 +2639,13 @@ static struct rdev_sysfs_entry rdev_state = __ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store); static ssize_t -errors_show(mdk_rdev_t *rdev, char *page) +errors_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%d\n", atomic_read(&rdev->corrected_errors)); } static ssize_t -errors_store(mdk_rdev_t *rdev, const char *buf, size_t len) +errors_store(struct md_rdev *rdev, const char *buf, size_t len) { char *e; unsigned long n = simple_strtoul(buf, &e, 10); @@ -2661,7 +2659,7 @@ static struct rdev_sysfs_entry rdev_errors = __ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store); static ssize_t -slot_show(mdk_rdev_t *rdev, char *page) +slot_show(struct md_rdev *rdev, char *page) { if (rdev->raid_disk < 0) return sprintf(page, "none\n"); @@ -2670,7 +2668,7 @@ slot_show(mdk_rdev_t *rdev, char *page) } static ssize_t -slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) +slot_store(struct md_rdev *rdev, const char *buf, size_t len) { char *e; int err; @@ -2701,7 +2699,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); md_wakeup_thread(rdev->mddev->thread); } else if (rdev->mddev->pers) { - mdk_rdev_t *rdev2; + struct md_rdev *rdev2; /* Activating a spare .. or possibly reactivating * if we ever get bitmaps working here. */ @@ -2728,6 +2726,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) rdev->saved_raid_disk = slot; else rdev->saved_raid_disk = -1; + clear_bit(In_sync, &rdev->flags); err = rdev->mddev->pers-> hot_add_disk(rdev->mddev, rdev); if (err) { @@ -2757,13 +2756,13 @@ static struct rdev_sysfs_entry rdev_slot = __ATTR(slot, S_IRUGO|S_IWUSR, slot_show, slot_store); static ssize_t -offset_show(mdk_rdev_t *rdev, char *page) +offset_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->data_offset); } static ssize_t -offset_store(mdk_rdev_t *rdev, const char *buf, size_t len) +offset_store(struct md_rdev *rdev, const char *buf, size_t len) { char *e; unsigned long long offset = simple_strtoull(buf, &e, 10); @@ -2783,7 +2782,7 @@ static struct rdev_sysfs_entry rdev_offset = __ATTR(offset, S_IRUGO|S_IWUSR, offset_show, offset_store); static ssize_t -rdev_size_show(mdk_rdev_t *rdev, char *page) +rdev_size_show(struct md_rdev *rdev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)rdev->sectors / 2); } @@ -2818,9 +2817,9 @@ static int strict_blocks_to_sectors(const char *buf, sector_t *sectors) } static ssize_t -rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) +rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len) { - mddev_t *my_mddev = rdev->mddev; + struct mddev *my_mddev = rdev->mddev; sector_t oldsectors = rdev->sectors; sector_t sectors; @@ -2846,13 +2845,13 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len) * a deadlock. We have already changed rdev->sectors, and if * we have to change it back, we will have the lock again. */ - mddev_t *mddev; + struct mddev *mddev; int overlap = 0; struct list_head *tmp; mddev_unlock(my_mddev); for_each_mddev(mddev, tmp) { - mdk_rdev_t *rdev2; + struct md_rdev *rdev2; mddev_lock(mddev); list_for_each_entry(rdev2, &mddev->disks, same_set) @@ -2889,7 +2888,7 @@ static struct rdev_sysfs_entry rdev_size = __ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store); -static ssize_t recovery_start_show(mdk_rdev_t *rdev, char *page) +static ssize_t recovery_start_show(struct md_rdev *rdev, char *page) { unsigned long long recovery_start = rdev->recovery_offset; @@ -2900,7 +2899,7 @@ static ssize_t recovery_start_show(mdk_rdev_t *rdev, char *page) return sprintf(page, "%llu\n", recovery_start); } -static ssize_t recovery_start_store(mdk_rdev_t *rdev, const char *buf, size_t len) +static ssize_t recovery_start_store(struct md_rdev *rdev, const char *buf, size_t len) { unsigned long long recovery_start; @@ -2930,11 +2929,11 @@ badblocks_show(struct badblocks *bb, char *page, int unack); static ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); -static ssize_t bb_show(mdk_rdev_t *rdev, char *page) +static ssize_t bb_show(struct md_rdev *rdev, char *page) { return badblocks_show(&rdev->badblocks, page, 0); } -static ssize_t bb_store(mdk_rdev_t *rdev, const char *page, size_t len) +static ssize_t bb_store(struct md_rdev *rdev, const char *page, size_t len) { int rv = badblocks_store(&rdev->badblocks, page, len, 0); /* Maybe that ack was all we needed */ @@ -2946,11 +2945,11 @@ static struct rdev_sysfs_entry rdev_bad_blocks = __ATTR(bad_blocks, S_IRUGO|S_IWUSR, bb_show, bb_store); -static ssize_t ubb_show(mdk_rdev_t *rdev, char *page) +static ssize_t ubb_show(struct md_rdev *rdev, char *page) { return badblocks_show(&rdev->badblocks, page, 1); } -static ssize_t ubb_store(mdk_rdev_t *rdev, const char *page, size_t len) +static ssize_t ubb_store(struct md_rdev *rdev, const char *page, size_t len) { return badblocks_store(&rdev->badblocks, page, len, 1); } @@ -2972,8 +2971,8 @@ static ssize_t rdev_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); - mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj); - mddev_t *mddev = rdev->mddev; + struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); + struct mddev *mddev = rdev->mddev; ssize_t rv; if (!entry->show) @@ -2995,9 +2994,9 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct rdev_sysfs_entry *entry = container_of(attr, struct rdev_sysfs_entry, attr); - mdk_rdev_t *rdev = container_of(kobj, mdk_rdev_t, kobj); + struct md_rdev *rdev = container_of(kobj, struct md_rdev, kobj); ssize_t rv; - mddev_t *mddev = rdev->mddev; + struct mddev *mddev = rdev->mddev; if (!entry->store) return -EIO; @@ -3016,7 +3015,7 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, static void rdev_free(struct kobject *ko) { - mdk_rdev_t *rdev = container_of(ko, mdk_rdev_t, kobj); + struct md_rdev *rdev = container_of(ko, struct md_rdev, kobj); kfree(rdev); } static const struct sysfs_ops rdev_sysfs_ops = { @@ -3029,7 +3028,7 @@ static struct kobj_type rdev_ktype = { .default_attrs = rdev_default_attrs, }; -int md_rdev_init(mdk_rdev_t *rdev) +int md_rdev_init(struct md_rdev *rdev) { rdev->desc_nr = -1; rdev->saved_raid_disk = -1; @@ -3072,11 +3071,11 @@ EXPORT_SYMBOL_GPL(md_rdev_init); * * a faulty rdev _never_ has rdev->sb set. */ -static mdk_rdev_t *md_import_device(dev_t newdev, int super_format, int super_minor) +static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor) { char b[BDEVNAME_SIZE]; int err; - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t size; rdev = kzalloc(sizeof(*rdev), GFP_KERNEL); @@ -3145,10 +3144,10 @@ abort_free: */ -static void analyze_sbs(mddev_t * mddev) +static void analyze_sbs(struct mddev * mddev) { int i; - mdk_rdev_t *rdev, *freshest, *tmp; + struct md_rdev *rdev, *freshest, *tmp; char b[BDEVNAME_SIZE]; freshest = NULL; @@ -3248,13 +3247,13 @@ int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale) static void md_safemode_timeout(unsigned long data); static ssize_t -safe_delay_show(mddev_t *mddev, char *page) +safe_delay_show(struct mddev *mddev, char *page) { int msec = (mddev->safemode_delay*1000)/HZ; return sprintf(page, "%d.%03d\n", msec/1000, msec%1000); } static ssize_t -safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len) +safe_delay_store(struct mddev *mddev, const char *cbuf, size_t len) { unsigned long msec; @@ -3276,9 +3275,9 @@ static struct md_sysfs_entry md_safe_delay = __ATTR(safe_mode_delay, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store); static ssize_t -level_show(mddev_t *mddev, char *page) +level_show(struct mddev *mddev, char *page) { - struct mdk_personality *p = mddev->pers; + struct md_personality *p = mddev->pers; if (p) return sprintf(page, "%s\n", p->name); else if (mddev->clevel[0]) @@ -3290,14 +3289,14 @@ level_show(mddev_t *mddev, char *page) } static ssize_t -level_store(mddev_t *mddev, const char *buf, size_t len) +level_store(struct mddev *mddev, const char *buf, size_t len) { char clevel[16]; ssize_t rv = len; - struct mdk_personality *pers; + struct md_personality *pers; long level; void *priv; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (mddev->pers == NULL) { if (len == 0) @@ -3471,7 +3470,7 @@ __ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store); static ssize_t -layout_show(mddev_t *mddev, char *page) +layout_show(struct mddev *mddev, char *page) { /* just a number, not meaningful for all levels */ if (mddev->reshape_position != MaxSector && @@ -3482,7 +3481,7 @@ layout_show(mddev_t *mddev, char *page) } static ssize_t -layout_store(mddev_t *mddev, const char *buf, size_t len) +layout_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long n = simple_strtoul(buf, &e, 10); @@ -3512,7 +3511,7 @@ __ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store); static ssize_t -raid_disks_show(mddev_t *mddev, char *page) +raid_disks_show(struct mddev *mddev, char *page) { if (mddev->raid_disks == 0) return 0; @@ -3523,10 +3522,10 @@ raid_disks_show(mddev_t *mddev, char *page) return sprintf(page, "%d\n", mddev->raid_disks); } -static int update_raid_disks(mddev_t *mddev, int raid_disks); +static int update_raid_disks(struct mddev *mddev, int raid_disks); static ssize_t -raid_disks_store(mddev_t *mddev, const char *buf, size_t len) +raid_disks_store(struct mddev *mddev, const char *buf, size_t len) { char *e; int rv = 0; @@ -3549,7 +3548,7 @@ static struct md_sysfs_entry md_raid_disks = __ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store); static ssize_t -chunk_size_show(mddev_t *mddev, char *page) +chunk_size_show(struct mddev *mddev, char *page) { if (mddev->reshape_position != MaxSector && mddev->chunk_sectors != mddev->new_chunk_sectors) @@ -3560,7 +3559,7 @@ chunk_size_show(mddev_t *mddev, char *page) } static ssize_t -chunk_size_store(mddev_t *mddev, const char *buf, size_t len) +chunk_size_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long n = simple_strtoul(buf, &e, 10); @@ -3589,7 +3588,7 @@ static struct md_sysfs_entry md_chunk_size = __ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store); static ssize_t -resync_start_show(mddev_t *mddev, char *page) +resync_start_show(struct mddev *mddev, char *page) { if (mddev->recovery_cp == MaxSector) return sprintf(page, "none\n"); @@ -3597,7 +3596,7 @@ resync_start_show(mddev_t *mddev, char *page) } static ssize_t -resync_start_store(mddev_t *mddev, const char *buf, size_t len) +resync_start_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long long n = simple_strtoull(buf, &e, 10); @@ -3667,7 +3666,7 @@ static int match_word(const char *word, char **list) } static ssize_t -array_state_show(mddev_t *mddev, char *page) +array_state_show(struct mddev *mddev, char *page) { enum array_state st = inactive; @@ -3700,13 +3699,13 @@ array_state_show(mddev_t *mddev, char *page) return sprintf(page, "%s\n", array_states[st]); } -static int do_md_stop(mddev_t * mddev, int ro, int is_open); -static int md_set_readonly(mddev_t * mddev, int is_open); -static int do_md_run(mddev_t * mddev); -static int restart_array(mddev_t *mddev); +static int do_md_stop(struct mddev * mddev, int ro, int is_open); +static int md_set_readonly(struct mddev * mddev, int is_open); +static int do_md_run(struct mddev * mddev); +static int restart_array(struct mddev *mddev); static ssize_t -array_state_store(mddev_t *mddev, const char *buf, size_t len) +array_state_store(struct mddev *mddev, const char *buf, size_t len) { int err = -EINVAL; enum array_state st = match_word(buf, array_states); @@ -3800,13 +3799,13 @@ static struct md_sysfs_entry md_array_state = __ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store); static ssize_t -max_corrected_read_errors_show(mddev_t *mddev, char *page) { +max_corrected_read_errors_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", atomic_read(&mddev->max_corr_read_errors)); } static ssize_t -max_corrected_read_errors_store(mddev_t *mddev, const char *buf, size_t len) +max_corrected_read_errors_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long n = simple_strtoul(buf, &e, 10); @@ -3823,13 +3822,13 @@ __ATTR(max_read_errors, S_IRUGO|S_IWUSR, max_corrected_read_errors_show, max_corrected_read_errors_store); static ssize_t -null_show(mddev_t *mddev, char *page) +null_show(struct mddev *mddev, char *page) { return -EINVAL; } static ssize_t -new_dev_store(mddev_t *mddev, const char *buf, size_t len) +new_dev_store(struct mddev *mddev, const char *buf, size_t len) { /* buf must be %d:%d\n? giving major and minor numbers */ /* The new device is added to the array. @@ -3842,7 +3841,7 @@ new_dev_store(mddev_t *mddev, const char *buf, size_t len) int major = simple_strtoul(buf, &e, 10); int minor; dev_t dev; - mdk_rdev_t *rdev; + struct md_rdev *rdev; int err; if (!*buf || *e != ':' || !e[1] || e[1] == '\n') @@ -3860,8 +3859,9 @@ new_dev_store(mddev_t *mddev, const char *buf, size_t len) rdev = md_import_device(dev, mddev->major_version, mddev->minor_version); if (!IS_ERR(rdev) && !list_empty(&mddev->disks)) { - mdk_rdev_t *rdev0 = list_entry(mddev->disks.next, - mdk_rdev_t, same_set); + struct md_rdev *rdev0 + = list_entry(mddev->disks.next, + struct md_rdev, same_set); err = super_types[mddev->major_version] .load_super(rdev, rdev0, mddev->minor_version); if (err < 0) @@ -3885,7 +3885,7 @@ 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) +bitmap_store(struct mddev *mddev, const char *buf, size_t len) { char *end; unsigned long chunk, end_chunk; @@ -3914,16 +3914,16 @@ 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) +size_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->dev_sectors / 2); } -static int update_size(mddev_t *mddev, sector_t num_sectors); +static int update_size(struct mddev *mddev, sector_t num_sectors); static ssize_t -size_store(mddev_t *mddev, const char *buf, size_t len) +size_store(struct mddev *mddev, const char *buf, size_t len) { /* If array is inactive, we can reduce the component size, but * not increase it (except from 0). @@ -3958,7 +3958,7 @@ __ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store); * or N.M for internally known formats */ static ssize_t -metadata_show(mddev_t *mddev, char *page) +metadata_show(struct mddev *mddev, char *page) { if (mddev->persistent) return sprintf(page, "%d.%d\n", @@ -3970,7 +3970,7 @@ metadata_show(mddev_t *mddev, char *page) } static ssize_t -metadata_store(mddev_t *mddev, const char *buf, size_t len) +metadata_store(struct mddev *mddev, const char *buf, size_t len) { int major, minor; char *e; @@ -4024,7 +4024,7 @@ static struct md_sysfs_entry md_metadata = __ATTR(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store); static ssize_t -action_show(mddev_t *mddev, char *page) +action_show(struct mddev *mddev, char *page) { char *type = "idle"; if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery)) @@ -4046,10 +4046,10 @@ action_show(mddev_t *mddev, char *page) return sprintf(page, "%s\n", type); } -static void reap_sync_thread(mddev_t *mddev); +static void reap_sync_thread(struct mddev *mddev); static ssize_t -action_store(mddev_t *mddev, const char *page, size_t len) +action_store(struct mddev *mddev, const char *page, size_t len) { if (!mddev->pers || !mddev->pers->sync_request) return -EINVAL; @@ -4095,7 +4095,7 @@ action_store(mddev_t *mddev, const char *page, size_t len) } static ssize_t -mismatch_cnt_show(mddev_t *mddev, char *page) +mismatch_cnt_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long) mddev->resync_mismatches); @@ -4108,14 +4108,14 @@ __ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store); static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt); static ssize_t -sync_min_show(mddev_t *mddev, char *page) +sync_min_show(struct mddev *mddev, char *page) { return sprintf(page, "%d (%s)\n", speed_min(mddev), mddev->sync_speed_min ? "local": "system"); } static ssize_t -sync_min_store(mddev_t *mddev, const char *buf, size_t len) +sync_min_store(struct mddev *mddev, const char *buf, size_t len) { int min; char *e; @@ -4134,14 +4134,14 @@ static struct md_sysfs_entry md_sync_min = __ATTR(sync_speed_min, S_IRUGO|S_IWUSR, sync_min_show, sync_min_store); static ssize_t -sync_max_show(mddev_t *mddev, char *page) +sync_max_show(struct mddev *mddev, char *page) { return sprintf(page, "%d (%s)\n", speed_max(mddev), mddev->sync_speed_max ? "local": "system"); } static ssize_t -sync_max_store(mddev_t *mddev, const char *buf, size_t len) +sync_max_store(struct mddev *mddev, const char *buf, size_t len) { int max; char *e; @@ -4160,20 +4160,20 @@ static struct md_sysfs_entry md_sync_max = __ATTR(sync_speed_max, S_IRUGO|S_IWUSR, sync_max_show, sync_max_store); static ssize_t -degraded_show(mddev_t *mddev, char *page) +degraded_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", mddev->degraded); } static struct md_sysfs_entry md_degraded = __ATTR_RO(degraded); static ssize_t -sync_force_parallel_show(mddev_t *mddev, char *page) +sync_force_parallel_show(struct mddev *mddev, char *page) { return sprintf(page, "%d\n", mddev->parallel_resync); } static ssize_t -sync_force_parallel_store(mddev_t *mddev, const char *buf, size_t len) +sync_force_parallel_store(struct mddev *mddev, const char *buf, size_t len) { long n; @@ -4197,7 +4197,7 @@ __ATTR(sync_force_parallel, S_IRUGO|S_IWUSR, sync_force_parallel_show, sync_force_parallel_store); static ssize_t -sync_speed_show(mddev_t *mddev, char *page) +sync_speed_show(struct mddev *mddev, char *page) { unsigned long resync, dt, db; if (mddev->curr_resync == 0) @@ -4212,7 +4212,7 @@ sync_speed_show(mddev_t *mddev, char *page) static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed); static ssize_t -sync_completed_show(mddev_t *mddev, char *page) +sync_completed_show(struct mddev *mddev, char *page) { unsigned long long max_sectors, resync; @@ -4231,13 +4231,13 @@ sync_completed_show(mddev_t *mddev, char *page) static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed); static ssize_t -min_sync_show(mddev_t *mddev, char *page) +min_sync_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->resync_min); } static ssize_t -min_sync_store(mddev_t *mddev, const char *buf, size_t len) +min_sync_store(struct mddev *mddev, const char *buf, size_t len) { unsigned long long min; if (strict_strtoull(buf, 10, &min)) @@ -4262,7 +4262,7 @@ static struct md_sysfs_entry md_min_sync = __ATTR(sync_min, S_IRUGO|S_IWUSR, min_sync_show, min_sync_store); static ssize_t -max_sync_show(mddev_t *mddev, char *page) +max_sync_show(struct mddev *mddev, char *page) { if (mddev->resync_max == MaxSector) return sprintf(page, "max\n"); @@ -4271,7 +4271,7 @@ max_sync_show(mddev_t *mddev, char *page) (unsigned long long)mddev->resync_max); } static ssize_t -max_sync_store(mddev_t *mddev, const char *buf, size_t len) +max_sync_store(struct mddev *mddev, const char *buf, size_t len) { if (strncmp(buf, "max", 3) == 0) mddev->resync_max = MaxSector; @@ -4302,13 +4302,13 @@ static struct md_sysfs_entry md_max_sync = __ATTR(sync_max, S_IRUGO|S_IWUSR, max_sync_show, max_sync_store); static ssize_t -suspend_lo_show(mddev_t *mddev, char *page) +suspend_lo_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_lo); } static ssize_t -suspend_lo_store(mddev_t *mddev, const char *buf, size_t len) +suspend_lo_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long long new = simple_strtoull(buf, &e, 10); @@ -4336,13 +4336,13 @@ __ATTR(suspend_lo, S_IRUGO|S_IWUSR, suspend_lo_show, suspend_lo_store); static ssize_t -suspend_hi_show(mddev_t *mddev, char *page) +suspend_hi_show(struct mddev *mddev, char *page) { return sprintf(page, "%llu\n", (unsigned long long)mddev->suspend_hi); } static ssize_t -suspend_hi_store(mddev_t *mddev, const char *buf, size_t len) +suspend_hi_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long long new = simple_strtoull(buf, &e, 10); @@ -4369,7 +4369,7 @@ static struct md_sysfs_entry md_suspend_hi = __ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store); static ssize_t -reshape_position_show(mddev_t *mddev, char *page) +reshape_position_show(struct mddev *mddev, char *page) { if (mddev->reshape_position != MaxSector) return sprintf(page, "%llu\n", @@ -4379,7 +4379,7 @@ reshape_position_show(mddev_t *mddev, char *page) } static ssize_t -reshape_position_store(mddev_t *mddev, const char *buf, size_t len) +reshape_position_store(struct mddev *mddev, const char *buf, size_t len) { char *e; unsigned long long new = simple_strtoull(buf, &e, 10); @@ -4400,7 +4400,7 @@ __ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show, reshape_position_store); static ssize_t -array_size_show(mddev_t *mddev, char *page) +array_size_show(struct mddev *mddev, char *page) { if (mddev->external_size) return sprintf(page, "%llu\n", @@ -4410,7 +4410,7 @@ array_size_show(mddev_t *mddev, char *page) } static ssize_t -array_size_store(mddev_t *mddev, const char *buf, size_t len) +array_size_store(struct mddev *mddev, const char *buf, size_t len) { sector_t sectors; @@ -4485,7 +4485,7 @@ static ssize_t md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr); - mddev_t *mddev = container_of(kobj, struct mddev_s, kobj); + struct mddev *mddev = container_of(kobj, struct mddev, kobj); ssize_t rv; if (!entry->show) @@ -4503,7 +4503,7 @@ md_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr); - mddev_t *mddev = container_of(kobj, struct mddev_s, kobj); + struct mddev *mddev = container_of(kobj, struct mddev, kobj); ssize_t rv; if (!entry->store) @@ -4522,7 +4522,7 @@ md_attr_store(struct kobject *kobj, struct attribute *attr, static void md_free(struct kobject *ko) { - mddev_t *mddev = container_of(ko, mddev_t, kobj); + struct mddev *mddev = container_of(ko, struct mddev, kobj); if (mddev->sysfs_state) sysfs_put(mddev->sysfs_state); @@ -4551,7 +4551,7 @@ int mdp_major = 0; static void mddev_delayed_delete(struct work_struct *ws) { - mddev_t *mddev = container_of(ws, mddev_t, del_work); + struct mddev *mddev = container_of(ws, struct mddev, del_work); sysfs_remove_group(&mddev->kobj, &md_bitmap_group); kobject_del(&mddev->kobj); @@ -4561,7 +4561,7 @@ static void mddev_delayed_delete(struct work_struct *ws) static int md_alloc(dev_t dev, char *name) { static DEFINE_MUTEX(disks_mutex); - mddev_t *mddev = mddev_find(dev); + struct mddev *mddev = mddev_find(dev); struct gendisk *disk; int partitioned; int shift; @@ -4588,7 +4588,7 @@ static int md_alloc(dev_t dev, char *name) if (name) { /* Need to ensure that 'name' is not a duplicate. */ - mddev_t *mddev2; + struct mddev *mddev2; spin_lock(&all_mddevs_lock); list_for_each_entry(mddev2, &all_mddevs, all_mddevs) @@ -4689,7 +4689,7 @@ static int add_named_array(const char *val, struct kernel_param *kp) static void md_safemode_timeout(unsigned long data) { - mddev_t *mddev = (mddev_t *) data; + struct mddev *mddev = (struct mddev *) data; if (!atomic_read(&mddev->writes_pending)) { mddev->safemode = 1; @@ -4701,11 +4701,11 @@ static void md_safemode_timeout(unsigned long data) static int start_dirty_degraded; -int md_run(mddev_t *mddev) +int md_run(struct mddev *mddev) { int err; - mdk_rdev_t *rdev; - struct mdk_personality *pers; + struct md_rdev *rdev; + struct md_personality *pers; if (list_empty(&mddev->disks)) /* cannot run an array with no devices.. */ @@ -4769,7 +4769,7 @@ int md_run(mddev_t *mddev) if (mddev->bio_set == NULL) mddev->bio_set = bioset_create(BIO_POOL_SIZE, - sizeof(mddev_t *)); + sizeof(struct mddev *)); spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -4804,7 +4804,7 @@ int md_run(mddev_t *mddev) * configuration. */ char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; - mdk_rdev_t *rdev2; + struct md_rdev *rdev2; int warned = 0; list_for_each_entry(rdev, &mddev->disks, same_set) @@ -4903,7 +4903,7 @@ int md_run(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_run); -static int do_md_run(mddev_t *mddev) +static int do_md_run(struct mddev *mddev) { int err; @@ -4927,7 +4927,7 @@ out: return err; } -static int restart_array(mddev_t *mddev) +static int restart_array(struct mddev *mddev) { struct gendisk *disk = mddev->gendisk; @@ -4977,7 +4977,7 @@ void restore_bitmap_write_access(struct file *file) spin_unlock(&inode->i_lock); } -static void md_clean(mddev_t *mddev) +static void md_clean(struct mddev *mddev) { mddev->array_sectors = 0; mddev->external_size = 0; @@ -5020,7 +5020,7 @@ static void md_clean(mddev_t *mddev) mddev->bitmap_info.max_write_behind = 0; } -static void __md_stop_writes(mddev_t *mddev) +static void __md_stop_writes(struct mddev *mddev) { if (mddev->sync_thread) { set_bit(MD_RECOVERY_FROZEN, &mddev->recovery); @@ -5040,7 +5040,7 @@ static void __md_stop_writes(mddev_t *mddev) } } -void md_stop_writes(mddev_t *mddev) +void md_stop_writes(struct mddev *mddev) { mddev_lock(mddev); __md_stop_writes(mddev); @@ -5048,7 +5048,7 @@ void md_stop_writes(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_stop_writes); -void md_stop(mddev_t *mddev) +void md_stop(struct mddev *mddev) { mddev->ready = 0; mddev->pers->stop(mddev); @@ -5060,7 +5060,7 @@ void md_stop(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_stop); -static int md_set_readonly(mddev_t *mddev, int is_open) +static int md_set_readonly(struct mddev *mddev, int is_open) { int err = 0; mutex_lock(&mddev->open_mutex); @@ -5090,10 +5090,10 @@ out: * 0 - completely stop and dis-assemble array * 2 - stop but do not disassemble array */ -static int do_md_stop(mddev_t * mddev, int mode, int is_open) +static int do_md_stop(struct mddev * mddev, int mode, int is_open) { struct gendisk *disk = mddev->gendisk; - mdk_rdev_t *rdev; + struct md_rdev *rdev; mutex_lock(&mddev->open_mutex); if (atomic_read(&mddev->openers) > is_open || @@ -5156,9 +5156,9 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open) } #ifndef MODULE -static void autorun_array(mddev_t *mddev) +static void autorun_array(struct mddev *mddev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; int err; if (list_empty(&mddev->disks)) @@ -5193,8 +5193,8 @@ static void autorun_array(mddev_t *mddev) */ static void autorun_devices(int part) { - mdk_rdev_t *rdev0, *rdev, *tmp; - mddev_t *mddev; + struct md_rdev *rdev0, *rdev, *tmp; + struct mddev *mddev; char b[BDEVNAME_SIZE]; printk(KERN_INFO "md: autorun ...\n"); @@ -5203,7 +5203,7 @@ static void autorun_devices(int part) dev_t dev; LIST_HEAD(candidates); rdev0 = list_entry(pending_raid_disks.next, - mdk_rdev_t, same_set); + struct md_rdev, same_set); printk(KERN_INFO "md: considering %s ...\n", bdevname(rdev0->bdev,b)); @@ -5289,11 +5289,11 @@ static int get_version(void __user * arg) return 0; } -static int get_array_info(mddev_t * mddev, void __user * arg) +static int get_array_info(struct mddev * mddev, void __user * arg) { mdu_array_info_t info; int nr,working,insync,failed,spare; - mdk_rdev_t *rdev; + struct md_rdev *rdev; nr=working=insync=failed=spare=0; list_for_each_entry(rdev, &mddev->disks, same_set) { @@ -5342,7 +5342,7 @@ static int get_array_info(mddev_t * mddev, void __user * arg) return 0; } -static int get_bitmap_file(mddev_t * mddev, void __user * arg) +static int get_bitmap_file(struct mddev * mddev, void __user * arg) { mdu_bitmap_file_t *file = NULL; /* too big for stack allocation */ char *ptr, *buf = NULL; @@ -5382,10 +5382,10 @@ out: return err; } -static int get_disk_info(mddev_t * mddev, void __user * arg) +static int get_disk_info(struct mddev * mddev, void __user * arg) { mdu_disk_info_t info; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; @@ -5416,10 +5416,10 @@ static int get_disk_info(mddev_t * mddev, void __user * arg) return 0; } -static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) +static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) { char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE]; - mdk_rdev_t *rdev; + struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) @@ -5436,8 +5436,9 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) return PTR_ERR(rdev); } if (!list_empty(&mddev->disks)) { - mdk_rdev_t *rdev0 = list_entry(mddev->disks.next, - mdk_rdev_t, same_set); + struct md_rdev *rdev0 + = list_entry(mddev->disks.next, + struct md_rdev, same_set); err = super_types[mddev->major_version] .load_super(rdev, rdev0, mddev->minor_version); if (err < 0) { @@ -5587,10 +5588,10 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info) return 0; } -static int hot_remove_disk(mddev_t * mddev, dev_t dev) +static int hot_remove_disk(struct mddev * mddev, dev_t dev) { char b[BDEVNAME_SIZE]; - mdk_rdev_t *rdev; + struct md_rdev *rdev; rdev = find_rdev(mddev, dev); if (!rdev) @@ -5610,11 +5611,11 @@ busy: return -EBUSY; } -static int hot_add_disk(mddev_t * mddev, dev_t dev) +static int hot_add_disk(struct mddev * mddev, dev_t dev) { char b[BDEVNAME_SIZE]; int err; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (!mddev->pers) return -ENODEV; @@ -5684,7 +5685,7 @@ abort_export: return err; } -static int set_bitmap_file(mddev_t *mddev, int fd) +static int set_bitmap_file(struct mddev *mddev, int fd) { int err; @@ -5757,7 +5758,7 @@ static int set_bitmap_file(mddev_t *mddev, int fd) * The minor and patch _version numbers are also kept incase the * super_block handler wishes to interpret them. */ -static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) +static int set_array_info(struct mddev * mddev, mdu_array_info_t *info) { if (info->raid_disks == 0) { @@ -5827,7 +5828,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info) return 0; } -void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors) +void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors) { WARN(!mddev_is_locked(mddev), "%s: unlocked mddev!\n", __func__); @@ -5838,9 +5839,9 @@ void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors) } EXPORT_SYMBOL(md_set_array_sectors); -static int update_size(mddev_t *mddev, sector_t num_sectors) +static int update_size(struct mddev *mddev, sector_t num_sectors) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; int rv; int fit = (num_sectors == 0); @@ -5876,7 +5877,7 @@ static int update_size(mddev_t *mddev, sector_t num_sectors) return rv; } -static int update_raid_disks(mddev_t *mddev, int raid_disks) +static int update_raid_disks(struct mddev *mddev, int raid_disks) { int rv; /* change the number of raid disks */ @@ -5904,7 +5905,7 @@ static int update_raid_disks(mddev_t *mddev, int raid_disks) * Any differences that cannot be handled will cause an error. * Normally, only one change can be managed at a time. */ -static int update_array_info(mddev_t *mddev, mdu_array_info_t *info) +static int update_array_info(struct mddev *mddev, mdu_array_info_t *info) { int rv = 0; int cnt = 0; @@ -5997,9 +5998,9 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info) return rv; } -static int set_disk_faulty(mddev_t *mddev, dev_t dev) +static int set_disk_faulty(struct mddev *mddev, dev_t dev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (mddev->pers == NULL) return -ENODEV; @@ -6022,7 +6023,7 @@ static int set_disk_faulty(mddev_t *mddev, dev_t dev) */ static int md_getgeo(struct block_device *bdev, struct hd_geometry *geo) { - mddev_t *mddev = bdev->bd_disk->private_data; + struct mddev *mddev = bdev->bd_disk->private_data; geo->heads = 2; geo->sectors = 4; @@ -6035,7 +6036,7 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, { int err = 0; void __user *argp = (void __user *)arg; - mddev_t *mddev = NULL; + struct mddev *mddev = NULL; int ro; if (!capable(CAP_SYS_ADMIN)) @@ -6298,7 +6299,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) * Succeed if we can lock the mddev, which confirms that * it isn't being stopped right now. */ - mddev_t *mddev = mddev_find(bdev->bd_dev); + struct mddev *mddev = mddev_find(bdev->bd_dev); int err; if (mddev->gendisk != bdev->bd_disk) { @@ -6327,7 +6328,7 @@ static int md_open(struct block_device *bdev, fmode_t mode) static int md_release(struct gendisk *disk, fmode_t mode) { - mddev_t *mddev = disk->private_data; + struct mddev *mddev = disk->private_data; BUG_ON(!mddev); atomic_dec(&mddev->openers); @@ -6338,14 +6339,14 @@ static int md_release(struct gendisk *disk, fmode_t mode) static int md_media_changed(struct gendisk *disk) { - mddev_t *mddev = disk->private_data; + struct mddev *mddev = disk->private_data; return mddev->changed; } static int md_revalidate(struct gendisk *disk) { - mddev_t *mddev = disk->private_data; + struct mddev *mddev = disk->private_data; mddev->changed = 0; return 0; @@ -6366,7 +6367,7 @@ static const struct block_device_operations md_fops = static int md_thread(void * arg) { - mdk_thread_t *thread = arg; + struct md_thread *thread = arg; /* * md_thread is a 'system-thread', it's priority should be very @@ -6405,21 +6406,21 @@ static int md_thread(void * arg) return 0; } -void md_wakeup_thread(mdk_thread_t *thread) +void md_wakeup_thread(struct md_thread *thread) { if (thread) { - dprintk("md: waking up MD thread %s.\n", thread->tsk->comm); + pr_debug("md: waking up MD thread %s.\n", thread->tsk->comm); set_bit(THREAD_WAKEUP, &thread->flags); wake_up(&thread->wqueue); } } -mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev, +struct md_thread *md_register_thread(void (*run) (struct mddev *), struct mddev *mddev, const char *name) { - mdk_thread_t *thread; + struct md_thread *thread; - thread = kzalloc(sizeof(mdk_thread_t), GFP_KERNEL); + thread = kzalloc(sizeof(struct md_thread), GFP_KERNEL); if (!thread) return NULL; @@ -6439,12 +6440,12 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev, return thread; } -void md_unregister_thread(mdk_thread_t **threadp) +void md_unregister_thread(struct md_thread **threadp) { - mdk_thread_t *thread = *threadp; + struct md_thread *thread = *threadp; if (!thread) return; - dprintk("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk)); + pr_debug("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk)); /* Locking ensures that mddev_unlock does not wake_up a * non-existent thread */ @@ -6456,7 +6457,7 @@ void md_unregister_thread(mdk_thread_t **threadp) kfree(thread); } -void md_error(mddev_t *mddev, mdk_rdev_t *rdev) +void md_error(struct mddev *mddev, struct md_rdev *rdev) { if (!mddev) { MD_BUG(); @@ -6485,7 +6486,7 @@ void md_error(mddev_t *mddev, mdk_rdev_t *rdev) static void status_unused(struct seq_file *seq) { int i = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; seq_printf(seq, "unused devices: "); @@ -6502,7 +6503,7 @@ static void status_unused(struct seq_file *seq) } -static void status_resync(struct seq_file *seq, mddev_t * mddev) +static void status_resync(struct seq_file *seq, struct mddev * mddev) { sector_t max_sectors, resync, res; unsigned long dt, db; @@ -6593,7 +6594,7 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos) { struct list_head *tmp; loff_t l = *pos; - mddev_t *mddev; + struct mddev *mddev; if (l >= 0x10000) return NULL; @@ -6604,7 +6605,7 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos) spin_lock(&all_mddevs_lock); list_for_each(tmp,&all_mddevs) if (!l--) { - mddev = list_entry(tmp, mddev_t, all_mddevs); + mddev = list_entry(tmp, struct mddev, all_mddevs); mddev_get(mddev); spin_unlock(&all_mddevs_lock); return mddev; @@ -6618,7 +6619,7 @@ static void *md_seq_start(struct seq_file *seq, loff_t *pos) static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *tmp; - mddev_t *next_mddev, *mddev = v; + struct mddev *next_mddev, *mddev = v; ++*pos; if (v == (void*)2) @@ -6630,7 +6631,7 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) else tmp = mddev->all_mddevs.next; if (tmp != &all_mddevs) - next_mddev = mddev_get(list_entry(tmp,mddev_t,all_mddevs)); + next_mddev = mddev_get(list_entry(tmp,struct mddev,all_mddevs)); else { next_mddev = (void*)2; *pos = 0x10000; @@ -6645,7 +6646,7 @@ static void *md_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void md_seq_stop(struct seq_file *seq, void *v) { - mddev_t *mddev = v; + struct mddev *mddev = v; if (mddev && v != (void*)1 && v != (void*)2) mddev_put(mddev); @@ -6653,13 +6654,13 @@ static void md_seq_stop(struct seq_file *seq, void *v) static int md_seq_show(struct seq_file *seq, void *v) { - mddev_t *mddev = v; + struct mddev *mddev = v; sector_t sectors; - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct bitmap *bitmap; if (v == (void*)1) { - struct mdk_personality *pers; + struct md_personality *pers; seq_printf(seq, "Personalities : "); spin_lock(&pers_lock); list_for_each_entry(pers, &pers_list, list) @@ -6815,7 +6816,7 @@ static const struct file_operations md_seq_fops = { .poll = mdstat_poll, }; -int register_md_personality(struct mdk_personality *p) +int register_md_personality(struct md_personality *p) { spin_lock(&pers_lock); list_add_tail(&p->list, &pers_list); @@ -6824,7 +6825,7 @@ int register_md_personality(struct mdk_personality *p) return 0; } -int unregister_md_personality(struct mdk_personality *p) +int unregister_md_personality(struct md_personality *p) { printk(KERN_INFO "md: %s personality unregistered\n", p->name); spin_lock(&pers_lock); @@ -6833,9 +6834,9 @@ int unregister_md_personality(struct mdk_personality *p) return 0; } -static int is_mddev_idle(mddev_t *mddev, int init) +static int is_mddev_idle(struct mddev *mddev, int init) { - mdk_rdev_t * rdev; + struct md_rdev * rdev; int idle; int curr_events; @@ -6877,7 +6878,7 @@ static int is_mddev_idle(mddev_t *mddev, int init) return idle; } -void md_done_sync(mddev_t *mddev, int blocks, int ok) +void md_done_sync(struct mddev *mddev, int blocks, int ok) { /* another "blocks" (512byte) blocks have been synced */ atomic_sub(blocks, &mddev->recovery_active); @@ -6895,7 +6896,7 @@ void md_done_sync(mddev_t *mddev, int blocks, int ok) * in superblock) before writing, schedule a superblock update * and wait for it to complete. */ -void md_write_start(mddev_t *mddev, struct bio *bi) +void md_write_start(struct mddev *mddev, struct bio *bi) { int did_change = 0; if (bio_data_dir(bi) != WRITE) @@ -6930,7 +6931,7 @@ void md_write_start(mddev_t *mddev, struct bio *bi) !test_bit(MD_CHANGE_PENDING, &mddev->flags)); } -void md_write_end(mddev_t *mddev) +void md_write_end(struct mddev *mddev) { if (atomic_dec_and_test(&mddev->writes_pending)) { if (mddev->safemode == 2) @@ -6949,7 +6950,7 @@ void md_write_end(mddev_t *mddev) * In the ->external case MD_CHANGE_CLEAN can not be cleared until mddev->lock * is dropped, so return -EAGAIN after notifying userspace. */ -int md_allow_write(mddev_t *mddev) +int md_allow_write(struct mddev *mddev) { if (!mddev->pers) return 0; @@ -6981,9 +6982,9 @@ EXPORT_SYMBOL_GPL(md_allow_write); #define SYNC_MARKS 10 #define SYNC_MARK_STEP (3*HZ) -void md_do_sync(mddev_t *mddev) +void md_do_sync(struct mddev *mddev) { - mddev_t *mddev2; + struct mddev *mddev2; unsigned int currspeed = 0, window; sector_t max_sectors,j, io_sectors; @@ -6993,7 +6994,7 @@ void md_do_sync(mddev_t *mddev) struct list_head *tmp; sector_t last_check; int skipped = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; char *desc; /* just incase thread restarts... */ @@ -7308,9 +7309,9 @@ void md_do_sync(mddev_t *mddev) } EXPORT_SYMBOL_GPL(md_do_sync); -static int remove_and_add_spares(mddev_t *mddev) +static int remove_and_add_spares(struct mddev *mddev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; int spares = 0; mddev->curr_resync_completed = 0; @@ -7352,9 +7353,9 @@ static int remove_and_add_spares(mddev_t *mddev) return spares; } -static void reap_sync_thread(mddev_t *mddev) +static void reap_sync_thread(struct mddev *mddev) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; /* resync has finished, collect result */ md_unregister_thread(&mddev->sync_thread); @@ -7369,15 +7370,19 @@ static void reap_sync_thread(mddev_t *mddev) if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && mddev->pers->finish_reshape) mddev->pers->finish_reshape(mddev); - md_update_sb(mddev, 1); - /* if array is no-longer degraded, then any saved_raid_disk - * information must be scrapped + /* If array is no-longer degraded, then any saved_raid_disk + * information must be scrapped. Also if any device is now + * In_sync we must scrape the saved_raid_disk for that device + * do the superblock for an incrementally recovered device + * written out. */ - if (!mddev->degraded) - list_for_each_entry(rdev, &mddev->disks, same_set) + list_for_each_entry(rdev, &mddev->disks, same_set) + if (!mddev->degraded || + test_bit(In_sync, &rdev->flags)) rdev->saved_raid_disk = -1; + md_update_sb(mddev, 1); clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery); clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); @@ -7413,7 +7418,7 @@ static void reap_sync_thread(mddev_t *mddev) * 5/ If array is degraded, try to add spares devices * 6/ If array has spares or is not in-sync, start a resync thread. */ -void md_check_recovery(mddev_t *mddev) +void md_check_recovery(struct mddev *mddev) { if (mddev->suspended) return; @@ -7449,7 +7454,7 @@ void md_check_recovery(mddev_t *mddev) /* Only thing we do on a ro array is remove * failed devices. */ - mdk_rdev_t *rdev; + struct md_rdev *rdev; list_for_each_entry(rdev, &mddev->disks, same_set) if (rdev->raid_disk >= 0 && !test_bit(Blocked, &rdev->flags) && @@ -7573,7 +7578,7 @@ void md_check_recovery(mddev_t *mddev) } } -void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev) +void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev) { sysfs_notify_dirent_safe(rdev->sysfs_state); wait_event_timeout(rdev->blocked_wait, @@ -7831,7 +7836,7 @@ static int md_set_badblocks(struct badblocks *bb, sector_t s, int sectors, return rv; } -int rdev_set_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors, +int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int acknowledged) { int rv = md_set_badblocks(&rdev->badblocks, @@ -7940,7 +7945,7 @@ out: return rv; } -int rdev_clear_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors) +int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors) { return md_clear_badblocks(&rdev->badblocks, s + rdev->data_offset, @@ -8074,13 +8079,14 @@ static int md_notify_reboot(struct notifier_block *this, unsigned long code, void *x) { struct list_head *tmp; - mddev_t *mddev; + struct mddev *mddev; + int need_delay = 0; if ((code == SYS_DOWN) || (code == SYS_HALT) || (code == SYS_POWER_OFF)) { printk(KERN_INFO "md: stopping all md devices.\n"); - for_each_mddev(mddev, tmp) + for_each_mddev(mddev, tmp) { if (mddev_trylock(mddev)) { /* Force a switch to readonly even array * appears to still be in use. Hence @@ -8089,13 +8095,16 @@ static int md_notify_reboot(struct notifier_block *this, md_set_readonly(mddev, 100); mddev_unlock(mddev); } + need_delay = 1; + } /* * certain more exotic SCSI devices are known to be * volatile wrt too early system reboots. While the * right place to handle this issue is the given * driver, we do want to have a safe RAID driver ... */ - mdelay(1000*1); + if (need_delay) + mdelay(1000*1); } return NOTIFY_DONE; } @@ -8108,7 +8117,7 @@ static struct notifier_block md_notifier = { static void md_geninit(void) { - dprintk("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t)); + pr_debug("md: sizeof(mdp_super_t) = %d\n", (int)sizeof(mdp_super_t)); proc_create("mdstat", S_IRUGO, NULL, &md_seq_fops); } @@ -8183,7 +8192,7 @@ void md_autodetect_dev(dev_t dev) static void autostart_arrays(int part) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct detected_devices_node *node_detected_dev; dev_t dev; int i_scanned, i_passed; @@ -8223,7 +8232,7 @@ static void autostart_arrays(int part) static __exit void md_exit(void) { - mddev_t *mddev; + struct mddev *mddev; struct list_head *tmp; blk_unregister_region(MKDEV(MD_MAJOR,0), 1U << MINORBITS); diff --git a/drivers/md/md.h b/drivers/md/md.h index 0a309dc29b45..51c1d91557e0 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -1,5 +1,5 @@ /* - md_k.h : kernel internal structure of the Linux MD driver + md.h : kernel internal structure of the Linux MD driver Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman This program is free software; you can redistribute it and/or modify @@ -26,9 +26,6 @@ #define MaxSector (~(sector_t)0) -typedef struct mddev_s mddev_t; -typedef struct mdk_rdev_s mdk_rdev_t; - /* Bad block numbers are stored sorted in a single page. * 64bits is used for each block or extent. * 54 bits are sector number, 9 bits are extent size, @@ -39,12 +36,11 @@ typedef struct mdk_rdev_s mdk_rdev_t; /* * MD's 'extended' device */ -struct mdk_rdev_s -{ +struct md_rdev { struct list_head same_set; /* RAID devices within the same set */ sector_t sectors; /* Device size (in 512bytes sectors) */ - mddev_t *mddev; /* RAID array if running */ + struct mddev *mddev; /* RAID array if running */ int last_events; /* IO event timestamp */ /* @@ -168,7 +164,7 @@ struct mdk_rdev_s extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors); -static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors, +static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors, sector_t *first_bad, int *bad_sectors) { if (unlikely(rdev->badblocks.count)) { @@ -181,15 +177,14 @@ static inline int is_badblock(mdk_rdev_t *rdev, sector_t s, int sectors, } return 0; } -extern int rdev_set_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors, +extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors, int acknowledged); -extern int rdev_clear_badblocks(mdk_rdev_t *rdev, sector_t s, int sectors); +extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors); extern void md_ack_all_badblocks(struct badblocks *bb); -struct mddev_s -{ +struct mddev { void *private; - struct mdk_personality *pers; + struct md_personality *pers; dev_t unit; int md_minor; struct list_head disks; @@ -256,8 +251,8 @@ struct mddev_s atomic_t plug_cnt; /* If device is expecting * more bios soon. */ - struct mdk_thread_s *thread; /* management thread */ - struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */ + struct md_thread *thread; /* management thread */ + struct md_thread *sync_thread; /* doing resync or reconstruct */ sector_t curr_resync; /* last block scheduled */ /* As resync requests can complete out of order, we cannot easily track * how much resync has been completed. So we occasionally pause until @@ -402,11 +397,11 @@ struct mddev_s atomic_t flush_pending; struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ - void (*sync_super)(mddev_t *mddev, mdk_rdev_t *rdev); + void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); }; -static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev) +static inline void rdev_dec_pending(struct md_rdev *rdev, struct mddev *mddev) { int faulty = test_bit(Faulty, &rdev->flags); if (atomic_dec_and_test(&rdev->nr_pending) && faulty) @@ -418,35 +413,35 @@ static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sect atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io); } -struct mdk_personality +struct md_personality { char *name; int level; struct list_head list; struct module *owner; - int (*make_request)(mddev_t *mddev, struct bio *bio); - int (*run)(mddev_t *mddev); - int (*stop)(mddev_t *mddev); - void (*status)(struct seq_file *seq, mddev_t *mddev); + int (*make_request)(struct mddev *mddev, struct bio *bio); + int (*run)(struct mddev *mddev); + int (*stop)(struct mddev *mddev); + void (*status)(struct seq_file *seq, struct mddev *mddev); /* error_handler must set ->faulty and clear ->in_sync * if appropriate, and should abort recovery if needed */ - void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev); - int (*hot_remove_disk) (mddev_t *mddev, int number); - int (*spare_active) (mddev_t *mddev); - sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster); - int (*resize) (mddev_t *mddev, sector_t sectors); - sector_t (*size) (mddev_t *mddev, sector_t sectors, int raid_disks); - int (*check_reshape) (mddev_t *mddev); - int (*start_reshape) (mddev_t *mddev); - void (*finish_reshape) (mddev_t *mddev); + void (*error_handler)(struct mddev *mddev, struct md_rdev *rdev); + int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev); + int (*hot_remove_disk) (struct mddev *mddev, int number); + int (*spare_active) (struct mddev *mddev); + sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster); + int (*resize) (struct mddev *mddev, sector_t sectors); + sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks); + int (*check_reshape) (struct mddev *mddev); + int (*start_reshape) (struct mddev *mddev); + void (*finish_reshape) (struct mddev *mddev); /* quiesce moves between quiescence states * 0 - fully active * 1 - no new requests allowed * others - reserved */ - void (*quiesce) (mddev_t *mddev, int state); + void (*quiesce) (struct mddev *mddev, int state); /* takeover is used to transition an array from one * personality to another. The new personality must be able * to handle the data in the current layout. @@ -456,14 +451,14 @@ struct mdk_personality * This needs to be installed and then ->run used to activate the * array. */ - void *(*takeover) (mddev_t *mddev); + void *(*takeover) (struct mddev *mddev); }; struct md_sysfs_entry { struct attribute attr; - ssize_t (*show)(mddev_t *, char *); - ssize_t (*store)(mddev_t *, const char *, size_t); + ssize_t (*show)(struct mddev *, char *); + ssize_t (*store)(struct mddev *, const char *, size_t); }; extern struct attribute_group md_bitmap_group; @@ -479,19 +474,19 @@ static inline void sysfs_notify_dirent_safe(struct sysfs_dirent *sd) sysfs_notify_dirent(sd); } -static inline char * mdname (mddev_t * mddev) +static inline char * mdname (struct mddev * mddev) { return mddev->gendisk ? mddev->gendisk->disk_name : "mdX"; } -static inline int sysfs_link_rdev(mddev_t *mddev, mdk_rdev_t *rdev) +static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; sprintf(nm, "rd%d", rdev->raid_disk); return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); } -static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev) +static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; sprintf(nm, "rd%d", rdev->raid_disk); @@ -514,14 +509,14 @@ static inline void sysfs_unlink_rdev(mddev_t *mddev, mdk_rdev_t *rdev) #define rdev_for_each_rcu(rdev, mddev) \ list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set) -typedef struct mdk_thread_s { - void (*run) (mddev_t *mddev); - mddev_t *mddev; +struct md_thread { + void (*run) (struct mddev *mddev); + struct mddev *mddev; wait_queue_head_t wqueue; unsigned long flags; struct task_struct *tsk; unsigned long timeout; -} mdk_thread_t; +}; #define THREAD_WAKEUP 0 @@ -556,48 +551,50 @@ static inline void safe_put_page(struct page *p) if (p) put_page(p); } -extern int register_md_personality(struct mdk_personality *p); -extern int unregister_md_personality(struct mdk_personality *p); -extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), - mddev_t *mddev, const char *name); -extern void md_unregister_thread(mdk_thread_t **threadp); -extern void md_wakeup_thread(mdk_thread_t *thread); -extern void md_check_recovery(mddev_t *mddev); -extern void md_write_start(mddev_t *mddev, struct bio *bi); -extern void md_write_end(mddev_t *mddev); -extern void md_done_sync(mddev_t *mddev, int blocks, int ok); -extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev); - -extern int mddev_congested(mddev_t *mddev, int bits); -extern void md_flush_request(mddev_t *mddev, struct bio *bio); -extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev, +extern int register_md_personality(struct md_personality *p); +extern int unregister_md_personality(struct md_personality *p); +extern struct md_thread *md_register_thread( + void (*run)(struct mddev *mddev), + struct mddev *mddev, + const char *name); +extern void md_unregister_thread(struct md_thread **threadp); +extern void md_wakeup_thread(struct md_thread *thread); +extern void md_check_recovery(struct mddev *mddev); +extern void md_write_start(struct mddev *mddev, struct bio *bi); +extern void md_write_end(struct mddev *mddev); +extern void md_done_sync(struct mddev *mddev, int blocks, int ok); +extern void md_error(struct mddev *mddev, struct md_rdev *rdev); + +extern int mddev_congested(struct mddev *mddev, int bits); +extern void md_flush_request(struct mddev *mddev, struct bio *bio); +extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); -extern void md_super_wait(mddev_t *mddev); -extern int sync_page_io(mdk_rdev_t *rdev, sector_t sector, int size, +extern void md_super_wait(struct mddev *mddev); +extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, int rw, bool metadata_op); -extern void md_do_sync(mddev_t *mddev); -extern void md_new_event(mddev_t *mddev); -extern int md_allow_write(mddev_t *mddev); -extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); -extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors); -extern int md_check_no_bitmap(mddev_t *mddev); -extern int md_integrity_register(mddev_t *mddev); -extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev); +extern void md_do_sync(struct mddev *mddev); +extern void md_new_event(struct mddev *mddev); +extern int md_allow_write(struct mddev *mddev); +extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); +extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); +extern int md_check_no_bitmap(struct mddev *mddev); +extern int md_integrity_register(struct mddev *mddev); +extern void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev); extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale); extern void restore_bitmap_write_access(struct file *file); -extern void mddev_init(mddev_t *mddev); -extern int md_run(mddev_t *mddev); -extern void md_stop(mddev_t *mddev); -extern void md_stop_writes(mddev_t *mddev); -extern int md_rdev_init(mdk_rdev_t *rdev); +extern void mddev_init(struct mddev *mddev); +extern int md_run(struct mddev *mddev); +extern void md_stop(struct mddev *mddev); +extern void md_stop_writes(struct mddev *mddev); +extern int md_rdev_init(struct md_rdev *rdev); -extern void mddev_suspend(mddev_t *mddev); -extern void mddev_resume(mddev_t *mddev); +extern void mddev_suspend(struct mddev *mddev); +extern void mddev_resume(struct mddev *mddev); extern struct bio *bio_clone_mddev(struct bio *bio, gfp_t gfp_mask, - mddev_t *mddev); + struct mddev *mddev); extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, - mddev_t *mddev); -extern int mddev_check_plugged(mddev_t *mddev); + struct mddev *mddev); +extern int mddev_check_plugged(struct mddev *mddev); extern void md_trim_bio(struct bio *bio, int offset, int size); #endif /* _MD_MD_H */ diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c index d5b5fb300171..d32c785e17d4 100644 --- a/drivers/md/multipath.c +++ b/drivers/md/multipath.c @@ -31,7 +31,7 @@ #define NR_RESERVED_BUFS 32 -static int multipath_map (multipath_conf_t *conf) +static int multipath_map (struct mpconf *conf) { int i, disks = conf->raid_disks; @@ -42,7 +42,7 @@ static int multipath_map (multipath_conf_t *conf) rcu_read_lock(); for (i = 0; i < disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); if (rdev && test_bit(In_sync, &rdev->flags)) { atomic_inc(&rdev->nr_pending); rcu_read_unlock(); @@ -58,8 +58,8 @@ static int multipath_map (multipath_conf_t *conf) static void multipath_reschedule_retry (struct multipath_bh *mp_bh) { unsigned long flags; - mddev_t *mddev = mp_bh->mddev; - multipath_conf_t *conf = mddev->private; + struct mddev *mddev = mp_bh->mddev; + struct mpconf *conf = mddev->private; spin_lock_irqsave(&conf->device_lock, flags); list_add(&mp_bh->retry_list, &conf->retry_list); @@ -76,7 +76,7 @@ static void multipath_reschedule_retry (struct multipath_bh *mp_bh) static void multipath_end_bh_io (struct multipath_bh *mp_bh, int err) { struct bio *bio = mp_bh->master_bio; - multipath_conf_t *conf = mp_bh->mddev->private; + struct mpconf *conf = mp_bh->mddev->private; bio_endio(bio, err); mempool_free(mp_bh, conf->pool); @@ -86,8 +86,8 @@ static void multipath_end_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct multipath_bh *mp_bh = bio->bi_private; - multipath_conf_t *conf = mp_bh->mddev->private; - mdk_rdev_t *rdev = conf->multipaths[mp_bh->path].rdev; + struct mpconf *conf = mp_bh->mddev->private; + struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev; if (uptodate) multipath_end_bh_io(mp_bh, 0); @@ -106,9 +106,9 @@ static void multipath_end_request(struct bio *bio, int error) rdev_dec_pending(rdev, conf->mddev); } -static int multipath_make_request(mddev_t *mddev, struct bio * bio) +static int multipath_make_request(struct mddev *mddev, struct bio * bio) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; struct multipath_bh * mp_bh; struct multipath_info *multipath; @@ -140,9 +140,9 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio) return 0; } -static void multipath_status (struct seq_file *seq, mddev_t *mddev) +static void multipath_status (struct seq_file *seq, struct mddev *mddev) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; int i; seq_printf (seq, " [%d/%d] [", conf->raid_disks, @@ -156,8 +156,8 @@ static void multipath_status (struct seq_file *seq, mddev_t *mddev) static int multipath_congested(void *data, int bits) { - mddev_t *mddev = data; - multipath_conf_t *conf = mddev->private; + struct mddev *mddev = data; + struct mpconf *conf = mddev->private; int i, ret = 0; if (mddev_congested(mddev, bits)) @@ -165,7 +165,7 @@ static int multipath_congested(void *data, int bits) rcu_read_lock(); for (i = 0; i < mddev->raid_disks ; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -183,9 +183,9 @@ static int multipath_congested(void *data, int bits) /* * Careful, this can execute in IRQ contexts as well! */ -static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev) +static void multipath_error (struct mddev *mddev, struct md_rdev *rdev) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; char b[BDEVNAME_SIZE]; if (conf->raid_disks - mddev->degraded <= 1) { @@ -218,7 +218,7 @@ static void multipath_error (mddev_t *mddev, mdk_rdev_t *rdev) conf->raid_disks - mddev->degraded); } -static void print_multipath_conf (multipath_conf_t *conf) +static void print_multipath_conf (struct mpconf *conf) { int i; struct multipath_info *tmp; @@ -242,9 +242,9 @@ static void print_multipath_conf (multipath_conf_t *conf) } -static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) +static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; struct request_queue *q; int err = -EEXIST; int path; @@ -291,11 +291,11 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) return err; } -static int multipath_remove_disk(mddev_t *mddev, int number) +static int multipath_remove_disk(struct mddev *mddev, int number) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; int err = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct multipath_info *p = conf->multipaths + number; print_multipath_conf(conf); @@ -335,12 +335,12 @@ abort: * 3. Performs writes following reads for array syncronising. */ -static void multipathd (mddev_t *mddev) +static void multipathd (struct mddev *mddev) { struct multipath_bh *mp_bh; struct bio *bio; unsigned long flags; - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; struct list_head *head = &conf->retry_list; md_check_recovery(mddev); @@ -379,7 +379,7 @@ static void multipathd (mddev_t *mddev) spin_unlock_irqrestore(&conf->device_lock, flags); } -static sector_t multipath_size(mddev_t *mddev, sector_t sectors, int raid_disks) +static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks) { WARN_ONCE(sectors || raid_disks, "%s does not support generic reshape\n", __func__); @@ -387,12 +387,12 @@ static sector_t multipath_size(mddev_t *mddev, sector_t sectors, int raid_disks) return mddev->dev_sectors; } -static int multipath_run (mddev_t *mddev) +static int multipath_run (struct mddev *mddev) { - multipath_conf_t *conf; + struct mpconf *conf; int disk_idx; struct multipath_info *disk; - mdk_rdev_t *rdev; + struct md_rdev *rdev; int working_disks; if (md_check_no_bitmap(mddev)) @@ -409,7 +409,7 @@ static int multipath_run (mddev_t *mddev) * should be freed in multipath_stop()] */ - conf = kzalloc(sizeof(multipath_conf_t), GFP_KERNEL); + conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL); mddev->private = conf; if (!conf) { printk(KERN_ERR @@ -510,9 +510,9 @@ out: } -static int multipath_stop (mddev_t *mddev) +static int multipath_stop (struct mddev *mddev) { - multipath_conf_t *conf = mddev->private; + struct mpconf *conf = mddev->private; md_unregister_thread(&mddev->thread); blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ @@ -523,7 +523,7 @@ static int multipath_stop (mddev_t *mddev) return 0; } -static struct mdk_personality multipath_personality = +static struct md_personality multipath_personality = { .name = "multipath", .level = LEVEL_MULTIPATH, diff --git a/drivers/md/multipath.h b/drivers/md/multipath.h index 3c5a45eb5f8a..717c60f62898 100644 --- a/drivers/md/multipath.h +++ b/drivers/md/multipath.h @@ -2,11 +2,11 @@ #define _MULTIPATH_H struct multipath_info { - mdk_rdev_t *rdev; + struct md_rdev *rdev; }; -struct multipath_private_data { - mddev_t *mddev; +struct mpconf { + struct mddev *mddev; struct multipath_info *multipaths; int raid_disks; spinlock_t device_lock; @@ -15,8 +15,6 @@ struct multipath_private_data { mempool_t *pool; }; -typedef struct multipath_private_data multipath_conf_t; - /* * this is our 'private' 'collective' MULTIPATH buffer head. * it contains information about what kind of IO operations were started @@ -24,7 +22,7 @@ typedef struct multipath_private_data multipath_conf_t; */ struct multipath_bh { - mddev_t *mddev; + struct mddev *mddev; struct bio *master_bio; struct bio bio; int path; diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index e86bf3682e1e..0eb08a4df759 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -27,9 +27,9 @@ static int raid0_congested(void *data, int bits) { - mddev_t *mddev = data; - raid0_conf_t *conf = mddev->private; - mdk_rdev_t **devlist = conf->devlist; + struct mddev *mddev = data; + struct r0conf *conf = mddev->private; + struct md_rdev **devlist = conf->devlist; int raid_disks = conf->strip_zone[0].nb_dev; int i, ret = 0; @@ -47,52 +47,53 @@ static int raid0_congested(void *data, int bits) /* * inform the user of the raid configuration */ -static void dump_zones(mddev_t *mddev) +static void dump_zones(struct mddev *mddev) { - int j, k, h; + int j, k; sector_t zone_size = 0; sector_t zone_start = 0; char b[BDEVNAME_SIZE]; - raid0_conf_t *conf = mddev->private; + struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; - printk(KERN_INFO "******* %s configuration *********\n", - mdname(mddev)); - h = 0; + printk(KERN_INFO "md: RAID0 configuration for %s - %d zone%s\n", + mdname(mddev), + conf->nr_strip_zones, conf->nr_strip_zones==1?"":"s"); for (j = 0; j < conf->nr_strip_zones; j++) { - printk(KERN_INFO "zone%d=[", j); + printk(KERN_INFO "md: zone%d=[", j); for (k = 0; k < conf->strip_zone[j].nb_dev; k++) - printk(KERN_CONT "%s/", + printk(KERN_CONT "%s%s", k?"/":"", bdevname(conf->devlist[j*raid_disks + k]->bdev, b)); printk(KERN_CONT "]\n"); zone_size = conf->strip_zone[j].zone_end - zone_start; - printk(KERN_INFO " zone offset=%llukb " - "device offset=%llukb size=%llukb\n", + printk(KERN_INFO " zone-offset=%10lluKB, " + "device-offset=%10lluKB, size=%10lluKB\n", (unsigned long long)zone_start>>1, (unsigned long long)conf->strip_zone[j].dev_start>>1, (unsigned long long)zone_size>>1); zone_start = conf->strip_zone[j].zone_end; } - printk(KERN_INFO "**********************************\n\n"); + printk(KERN_INFO "\n"); } -static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) +static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) { int i, c, err; sector_t curr_zone_end, sectors; - mdk_rdev_t *smallest, *rdev1, *rdev2, *rdev, **dev; + struct md_rdev *smallest, *rdev1, *rdev2, *rdev, **dev; struct strip_zone *zone; int cnt; char b[BDEVNAME_SIZE]; - raid0_conf_t *conf = kzalloc(sizeof(*conf), GFP_KERNEL); + char b2[BDEVNAME_SIZE]; + struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL); if (!conf) return -ENOMEM; list_for_each_entry(rdev1, &mddev->disks, same_set) { - printk(KERN_INFO "md/raid0:%s: looking at %s\n", - mdname(mddev), - bdevname(rdev1->bdev, b)); + pr_debug("md/raid0:%s: looking at %s\n", + mdname(mddev), + bdevname(rdev1->bdev, b)); c = 0; /* round size to chunk_size */ @@ -101,16 +102,16 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) rdev1->sectors = sectors * mddev->chunk_sectors; list_for_each_entry(rdev2, &mddev->disks, same_set) { - printk(KERN_INFO "md/raid0:%s: comparing %s(%llu)", - mdname(mddev), - bdevname(rdev1->bdev,b), - (unsigned long long)rdev1->sectors); - printk(KERN_CONT " with %s(%llu)\n", - bdevname(rdev2->bdev,b), - (unsigned long long)rdev2->sectors); + pr_debug("md/raid0:%s: comparing %s(%llu)" + " with %s(%llu)\n", + mdname(mddev), + bdevname(rdev1->bdev,b), + (unsigned long long)rdev1->sectors, + bdevname(rdev2->bdev,b2), + (unsigned long long)rdev2->sectors); if (rdev2 == rdev1) { - printk(KERN_INFO "md/raid0:%s: END\n", - mdname(mddev)); + pr_debug("md/raid0:%s: END\n", + mdname(mddev)); break; } if (rdev2->sectors == rdev1->sectors) { @@ -118,30 +119,30 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) * Not unique, don't count it as a new * group */ - printk(KERN_INFO "md/raid0:%s: EQUAL\n", - mdname(mddev)); + pr_debug("md/raid0:%s: EQUAL\n", + mdname(mddev)); c = 1; break; } - printk(KERN_INFO "md/raid0:%s: NOT EQUAL\n", - mdname(mddev)); + pr_debug("md/raid0:%s: NOT EQUAL\n", + mdname(mddev)); } if (!c) { - printk(KERN_INFO "md/raid0:%s: ==> UNIQUE\n", - mdname(mddev)); + pr_debug("md/raid0:%s: ==> UNIQUE\n", + mdname(mddev)); conf->nr_strip_zones++; - printk(KERN_INFO "md/raid0:%s: %d zones\n", - mdname(mddev), conf->nr_strip_zones); + pr_debug("md/raid0:%s: %d zones\n", + mdname(mddev), conf->nr_strip_zones); } } - printk(KERN_INFO "md/raid0:%s: FINAL %d zones\n", - mdname(mddev), conf->nr_strip_zones); + pr_debug("md/raid0:%s: FINAL %d zones\n", + mdname(mddev), conf->nr_strip_zones); err = -ENOMEM; conf->strip_zone = kzalloc(sizeof(struct strip_zone)* conf->nr_strip_zones, GFP_KERNEL); if (!conf->strip_zone) goto abort; - conf->devlist = kzalloc(sizeof(mdk_rdev_t*)* + conf->devlist = kzalloc(sizeof(struct md_rdev*)* conf->nr_strip_zones*mddev->raid_disks, GFP_KERNEL); if (!conf->devlist) @@ -218,44 +219,45 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) zone = conf->strip_zone + i; dev = conf->devlist + i * mddev->raid_disks; - printk(KERN_INFO "md/raid0:%s: zone %d\n", - mdname(mddev), i); + pr_debug("md/raid0:%s: zone %d\n", mdname(mddev), i); zone->dev_start = smallest->sectors; smallest = NULL; c = 0; for (j=0; j<cnt; j++) { rdev = conf->devlist[j]; - printk(KERN_INFO "md/raid0:%s: checking %s ...", - mdname(mddev), - bdevname(rdev->bdev, b)); if (rdev->sectors <= zone->dev_start) { - printk(KERN_CONT " nope.\n"); + pr_debug("md/raid0:%s: checking %s ... nope\n", + mdname(mddev), + bdevname(rdev->bdev, b)); continue; } - printk(KERN_CONT " contained as device %d\n", c); + pr_debug("md/raid0:%s: checking %s ..." + " contained as device %d\n", + mdname(mddev), + bdevname(rdev->bdev, b), c); dev[c] = rdev; c++; if (!smallest || rdev->sectors < smallest->sectors) { smallest = rdev; - printk(KERN_INFO "md/raid0:%s: (%llu) is smallest!.\n", - mdname(mddev), - (unsigned long long)rdev->sectors); + pr_debug("md/raid0:%s: (%llu) is smallest!.\n", + mdname(mddev), + (unsigned long long)rdev->sectors); } } zone->nb_dev = c; sectors = (smallest->sectors - zone->dev_start) * c; - printk(KERN_INFO "md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n", - mdname(mddev), - zone->nb_dev, (unsigned long long)sectors); + pr_debug("md/raid0:%s: zone->nb_dev: %d, sectors: %llu\n", + mdname(mddev), + zone->nb_dev, (unsigned long long)sectors); curr_zone_end += sectors; zone->zone_end = curr_zone_end; - printk(KERN_INFO "md/raid0:%s: current zone start: %llu\n", - mdname(mddev), - (unsigned long long)smallest->sectors); + pr_debug("md/raid0:%s: current zone start: %llu\n", + mdname(mddev), + (unsigned long long)smallest->sectors); } mddev->queue->backing_dev_info.congested_fn = raid0_congested; mddev->queue->backing_dev_info.congested_data = mddev; @@ -275,7 +277,7 @@ static int create_strip_zones(mddev_t *mddev, raid0_conf_t **private_conf) blk_queue_io_opt(mddev->queue, (mddev->chunk_sectors << 9) * mddev->raid_disks); - printk(KERN_INFO "md/raid0:%s: done.\n", mdname(mddev)); + pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; return 0; @@ -299,7 +301,7 @@ static int raid0_mergeable_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *biovec) { - mddev_t *mddev = q->queuedata; + struct mddev *mddev = q->queuedata; sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); int max; unsigned int chunk_sectors = mddev->chunk_sectors; @@ -318,10 +320,10 @@ static int raid0_mergeable_bvec(struct request_queue *q, return max; } -static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks) +static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks) { sector_t array_sectors = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; WARN_ONCE(sectors || raid_disks, "%s does not support generic reshape\n", __func__); @@ -332,9 +334,9 @@ static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks) return array_sectors; } -static int raid0_run(mddev_t *mddev) +static int raid0_run(struct mddev *mddev) { - raid0_conf_t *conf; + struct r0conf *conf; int ret; if (mddev->chunk_sectors == 0) { @@ -382,9 +384,9 @@ static int raid0_run(mddev_t *mddev) return md_integrity_register(mddev); } -static int raid0_stop(mddev_t *mddev) +static int raid0_stop(struct mddev *mddev) { - raid0_conf_t *conf = mddev->private; + struct r0conf *conf = mddev->private; blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/ kfree(conf->strip_zone); @@ -397,7 +399,7 @@ static int raid0_stop(mddev_t *mddev) /* Find the zone which holds a particular offset * Update *sectorp to be an offset in that zone */ -static struct strip_zone *find_zone(struct raid0_private_data *conf, +static struct strip_zone *find_zone(struct r0conf *conf, sector_t *sectorp) { int i; @@ -417,12 +419,12 @@ static struct strip_zone *find_zone(struct raid0_private_data *conf, * remaps the bio to the target device. we separate two flows. * power 2 flow and a general flow for the sake of perfromance */ -static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone, +static struct md_rdev *map_sector(struct mddev *mddev, struct strip_zone *zone, sector_t sector, sector_t *sector_offset) { unsigned int sect_in_chunk; sector_t chunk; - raid0_conf_t *conf = mddev->private; + struct r0conf *conf = mddev->private; int raid_disks = conf->strip_zone[0].nb_dev; unsigned int chunk_sects = mddev->chunk_sectors; @@ -453,7 +455,7 @@ static mdk_rdev_t *map_sector(mddev_t *mddev, struct strip_zone *zone, /* * Is io distribute over 1 or more chunks ? */ -static inline int is_io_in_chunk_boundary(mddev_t *mddev, +static inline int is_io_in_chunk_boundary(struct mddev *mddev, unsigned int chunk_sects, struct bio *bio) { if (likely(is_power_of_2(chunk_sects))) { @@ -466,12 +468,12 @@ static inline int is_io_in_chunk_boundary(mddev_t *mddev, } } -static int raid0_make_request(mddev_t *mddev, struct bio *bio) +static int raid0_make_request(struct mddev *mddev, struct bio *bio) { unsigned int chunk_sects; sector_t sector_offset; struct strip_zone *zone; - mdk_rdev_t *tmp_dev; + struct md_rdev *tmp_dev; if (unlikely(bio->bi_rw & REQ_FLUSH)) { md_flush_request(mddev, bio); @@ -526,43 +528,16 @@ bad_map: return 0; } -static void raid0_status(struct seq_file *seq, mddev_t *mddev) +static void raid0_status(struct seq_file *seq, struct mddev *mddev) { -#undef MD_DEBUG -#ifdef MD_DEBUG - int j, k, h; - char b[BDEVNAME_SIZE]; - raid0_conf_t *conf = mddev->private; - int raid_disks = conf->strip_zone[0].nb_dev; - - sector_t zone_size; - sector_t zone_start = 0; - h = 0; - - for (j = 0; j < conf->nr_strip_zones; j++) { - seq_printf(seq, " z%d", j); - seq_printf(seq, "=["); - for (k = 0; k < conf->strip_zone[j].nb_dev; k++) - seq_printf(seq, "%s/", bdevname( - conf->devlist[j*raid_disks + k] - ->bdev, b)); - - zone_size = conf->strip_zone[j].zone_end - zone_start; - seq_printf(seq, "] ze=%lld ds=%lld s=%lld\n", - (unsigned long long)zone_start>>1, - (unsigned long long)conf->strip_zone[j].dev_start>>1, - (unsigned long long)zone_size>>1); - zone_start = conf->strip_zone[j].zone_end; - } -#endif seq_printf(seq, " %dk chunks", mddev->chunk_sectors / 2); return; } -static void *raid0_takeover_raid45(mddev_t *mddev) +static void *raid0_takeover_raid45(struct mddev *mddev) { - mdk_rdev_t *rdev; - raid0_conf_t *priv_conf; + struct md_rdev *rdev; + struct r0conf *priv_conf; if (mddev->degraded != 1) { printk(KERN_ERR "md/raid0:%s: raid5 must be degraded! Degraded disks: %d\n", @@ -593,9 +568,9 @@ static void *raid0_takeover_raid45(mddev_t *mddev) return priv_conf; } -static void *raid0_takeover_raid10(mddev_t *mddev) +static void *raid0_takeover_raid10(struct mddev *mddev) { - raid0_conf_t *priv_conf; + struct r0conf *priv_conf; /* Check layout: * - far_copies must be 1 @@ -634,9 +609,9 @@ static void *raid0_takeover_raid10(mddev_t *mddev) return priv_conf; } -static void *raid0_takeover_raid1(mddev_t *mddev) +static void *raid0_takeover_raid1(struct mddev *mddev) { - raid0_conf_t *priv_conf; + struct r0conf *priv_conf; /* Check layout: * - (N - 1) mirror drives must be already faulty @@ -660,7 +635,7 @@ static void *raid0_takeover_raid1(mddev_t *mddev) return priv_conf; } -static void *raid0_takeover(mddev_t *mddev) +static void *raid0_takeover(struct mddev *mddev) { /* raid0 can take over: * raid4 - if all data disks are active. @@ -691,11 +666,11 @@ static void *raid0_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } -static void raid0_quiesce(mddev_t *mddev, int state) +static void raid0_quiesce(struct mddev *mddev, int state) { } -static struct mdk_personality raid0_personality= +static struct md_personality raid0_personality= { .name = "raid0", .level = 0, diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 91f8e876ee64..0884bba8df4c 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -1,20 +1,16 @@ #ifndef _RAID0_H #define _RAID0_H -struct strip_zone -{ +struct strip_zone { sector_t zone_end; /* Start of the next zone (in sectors) */ sector_t dev_start; /* Zone offset in real dev (in sectors) */ int nb_dev; /* # of devices attached to the zone */ }; -struct raid0_private_data -{ +struct r0conf { struct strip_zone *strip_zone; - mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */ + struct md_rdev **devlist; /* lists of rdevs, pointed to by strip_zone->dev */ int nr_strip_zones; }; -typedef struct raid0_private_data raid0_conf_t; - #endif diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d9587dffe533..4602fc57c961 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -40,22 +40,24 @@ #include "raid1.h" #include "bitmap.h" -#define DEBUG 0 -#define PRINTK(x...) do { if (DEBUG) printk(x); } while (0) - /* * Number of guaranteed r1bios in case of extreme VM load: */ #define NR_RAID1_BIOS 256 +/* When there are this many requests queue to be written by + * the raid1 thread, we become 'congested' to provide back-pressure + * for writeback. + */ +static int max_queued_requests = 1024; -static void allow_barrier(conf_t *conf); -static void lower_barrier(conf_t *conf); +static void allow_barrier(struct r1conf *conf); +static void lower_barrier(struct r1conf *conf); static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data) { struct pool_info *pi = data; - int size = offsetof(r1bio_t, bios[pi->raid_disks]); + int size = offsetof(struct r1bio, bios[pi->raid_disks]); /* allocate a r1bio with room for raid_disks entries in the bios array */ return kzalloc(size, gfp_flags); @@ -76,7 +78,7 @@ static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data) { struct pool_info *pi = data; struct page *page; - r1bio_t *r1_bio; + struct r1bio *r1_bio; struct bio *bio; int i, j; @@ -142,7 +144,7 @@ static void r1buf_pool_free(void *__r1_bio, void *data) { struct pool_info *pi = data; int i,j; - r1bio_t *r1bio = __r1_bio; + struct r1bio *r1bio = __r1_bio; for (i = 0; i < RESYNC_PAGES; i++) for (j = pi->raid_disks; j-- ;) { @@ -157,7 +159,7 @@ static void r1buf_pool_free(void *__r1_bio, void *data) r1bio_pool_free(r1bio, data); } -static void put_all_bios(conf_t *conf, r1bio_t *r1_bio) +static void put_all_bios(struct r1conf *conf, struct r1bio *r1_bio) { int i; @@ -169,17 +171,17 @@ static void put_all_bios(conf_t *conf, r1bio_t *r1_bio) } } -static void free_r1bio(r1bio_t *r1_bio) +static void free_r1bio(struct r1bio *r1_bio) { - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; put_all_bios(conf, r1_bio); mempool_free(r1_bio, conf->r1bio_pool); } -static void put_buf(r1bio_t *r1_bio) +static void put_buf(struct r1bio *r1_bio) { - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; int i; for (i=0; i<conf->raid_disks; i++) { @@ -193,11 +195,11 @@ static void put_buf(r1bio_t *r1_bio) lower_barrier(conf); } -static void reschedule_retry(r1bio_t *r1_bio) +static void reschedule_retry(struct r1bio *r1_bio) { unsigned long flags; - mddev_t *mddev = r1_bio->mddev; - conf_t *conf = mddev->private; + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; spin_lock_irqsave(&conf->device_lock, flags); list_add(&r1_bio->retry_list, &conf->retry_list); @@ -213,11 +215,11 @@ static void reschedule_retry(r1bio_t *r1_bio) * operation and are ready to return a success/failure code to the buffer * cache layer. */ -static void call_bio_endio(r1bio_t *r1_bio) +static void call_bio_endio(struct r1bio *r1_bio) { struct bio *bio = r1_bio->master_bio; int done; - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; if (bio->bi_phys_segments) { unsigned long flags; @@ -240,17 +242,17 @@ static void call_bio_endio(r1bio_t *r1_bio) } } -static void raid_end_bio_io(r1bio_t *r1_bio) +static void raid_end_bio_io(struct r1bio *r1_bio) { struct bio *bio = r1_bio->master_bio; /* if nobody has done the final endio yet, do it now */ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) { - PRINTK(KERN_DEBUG "raid1: sync end %s on sectors %llu-%llu\n", - (bio_data_dir(bio) == WRITE) ? "write" : "read", - (unsigned long long) bio->bi_sector, - (unsigned long long) bio->bi_sector + - (bio->bi_size >> 9) - 1); + pr_debug("raid1: sync end %s on sectors %llu-%llu\n", + (bio_data_dir(bio) == WRITE) ? "write" : "read", + (unsigned long long) bio->bi_sector, + (unsigned long long) bio->bi_sector + + (bio->bi_size >> 9) - 1); call_bio_endio(r1_bio); } @@ -260,20 +262,38 @@ static void raid_end_bio_io(r1bio_t *r1_bio) /* * Update disk head position estimator based on IRQ completion info. */ -static inline void update_head_pos(int disk, r1bio_t *r1_bio) +static inline void update_head_pos(int disk, struct r1bio *r1_bio) { - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; conf->mirrors[disk].head_position = r1_bio->sector + (r1_bio->sectors); } +/* + * Find the disk number which triggered given bio + */ +static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio) +{ + int mirror; + int raid_disks = r1_bio->mddev->raid_disks; + + for (mirror = 0; mirror < raid_disks; mirror++) + if (r1_bio->bios[mirror] == bio) + break; + + BUG_ON(mirror == raid_disks); + update_head_pos(mirror, r1_bio); + + return mirror; +} + static void raid1_end_read_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t *r1_bio = bio->bi_private; + struct r1bio *r1_bio = bio->bi_private; int mirror; - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; mirror = r1_bio->read_disk; /* @@ -318,7 +338,7 @@ static void raid1_end_read_request(struct bio *bio, int error) rdev_dec_pending(conf->mirrors[mirror].rdev, conf->mddev); } -static void close_write(r1bio_t *r1_bio) +static void close_write(struct r1bio *r1_bio) { /* it really is the end of this request */ if (test_bit(R1BIO_BehindIO, &r1_bio->state)) { @@ -337,7 +357,7 @@ static void close_write(r1bio_t *r1_bio) md_write_end(r1_bio->mddev); } -static void r1_bio_write_done(r1bio_t *r1_bio) +static void r1_bio_write_done(struct r1bio *r1_bio) { if (!atomic_dec_and_test(&r1_bio->remaining)) return; @@ -356,15 +376,12 @@ static void r1_bio_write_done(r1bio_t *r1_bio) static void raid1_end_write_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t *r1_bio = bio->bi_private; + struct r1bio *r1_bio = bio->bi_private; int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state); - conf_t *conf = r1_bio->mddev->private; + struct r1conf *conf = r1_bio->mddev->private; struct bio *to_put = NULL; - - for (mirror = 0; mirror < conf->raid_disks; mirror++) - if (r1_bio->bios[mirror] == bio) - break; + mirror = find_bio_disk(r1_bio, bio); /* * 'one mirror IO has finished' event handler: @@ -400,8 +417,6 @@ static void raid1_end_write_request(struct bio *bio, int error) } } - update_head_pos(mirror, r1_bio); - if (behind) { if (test_bit(WriteMostly, &conf->mirrors[mirror].rdev->flags)) atomic_dec(&r1_bio->behind_remaining); @@ -418,10 +433,11 @@ static void raid1_end_write_request(struct bio *bio, int error) /* Maybe we can return now */ if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) { struct bio *mbio = r1_bio->master_bio; - PRINTK(KERN_DEBUG "raid1: behind end write sectors %llu-%llu\n", - (unsigned long long) mbio->bi_sector, - (unsigned long long) mbio->bi_sector + - (mbio->bi_size >> 9) - 1); + pr_debug("raid1: behind end write sectors" + " %llu-%llu\n", + (unsigned long long) mbio->bi_sector, + (unsigned long long) mbio->bi_sector + + (mbio->bi_size >> 9) - 1); call_bio_endio(r1_bio); } } @@ -455,7 +471,7 @@ static void raid1_end_write_request(struct bio *bio, int error) * * The rdev for the device selected will have nr_pending incremented. */ -static int read_balance(conf_t *conf, r1bio_t *r1_bio, int *max_sectors) +static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors) { const sector_t this_sector = r1_bio->sector; int sectors; @@ -464,7 +480,7 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio, int *max_sectors) int best_disk; int i; sector_t best_dist; - mdk_rdev_t *rdev; + struct md_rdev *rdev; int choose_first; rcu_read_lock(); @@ -582,14 +598,18 @@ static int read_balance(conf_t *conf, r1bio_t *r1_bio, int *max_sectors) return best_disk; } -int md_raid1_congested(mddev_t *mddev, int bits) +int md_raid1_congested(struct mddev *mddev, int bits) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int i, ret = 0; + if ((bits & (1 << BDI_async_congested)) && + conf->pending_count >= max_queued_requests) + return 1; + rcu_read_lock(); for (i = 0; i < mddev->raid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -611,13 +631,13 @@ EXPORT_SYMBOL_GPL(md_raid1_congested); static int raid1_congested(void *data, int bits) { - mddev_t *mddev = data; + struct mddev *mddev = data; return mddev_congested(mddev, bits) || md_raid1_congested(mddev, bits); } -static void flush_pending_writes(conf_t *conf) +static void flush_pending_writes(struct r1conf *conf) { /* Any writes that have been queued but are awaiting * bitmap updates get flushed here. @@ -627,10 +647,12 @@ static void flush_pending_writes(conf_t *conf) if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); + conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to * disk before proceeding w/ I/O */ bitmap_unplug(conf->mddev->bitmap); + wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; @@ -665,7 +687,7 @@ static void flush_pending_writes(conf_t *conf) */ #define RESYNC_DEPTH 32 -static void raise_barrier(conf_t *conf) +static void raise_barrier(struct r1conf *conf) { spin_lock_irq(&conf->resync_lock); @@ -684,7 +706,7 @@ static void raise_barrier(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static void lower_barrier(conf_t *conf) +static void lower_barrier(struct r1conf *conf) { unsigned long flags; BUG_ON(conf->barrier <= 0); @@ -694,7 +716,7 @@ static void lower_barrier(conf_t *conf) wake_up(&conf->wait_barrier); } -static void wait_barrier(conf_t *conf) +static void wait_barrier(struct r1conf *conf) { spin_lock_irq(&conf->resync_lock); if (conf->barrier) { @@ -708,7 +730,7 @@ static void wait_barrier(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static void allow_barrier(conf_t *conf) +static void allow_barrier(struct r1conf *conf) { unsigned long flags; spin_lock_irqsave(&conf->resync_lock, flags); @@ -717,7 +739,7 @@ static void allow_barrier(conf_t *conf) wake_up(&conf->wait_barrier); } -static void freeze_array(conf_t *conf) +static void freeze_array(struct r1conf *conf) { /* stop syncio and normal IO and wait for everything to * go quite. @@ -740,7 +762,7 @@ static void freeze_array(conf_t *conf) flush_pending_writes(conf)); spin_unlock_irq(&conf->resync_lock); } -static void unfreeze_array(conf_t *conf) +static void unfreeze_array(struct r1conf *conf) { /* reverse the effect of the freeze */ spin_lock_irq(&conf->resync_lock); @@ -753,7 +775,7 @@ static void unfreeze_array(conf_t *conf) /* duplicate the data pages for behind I/O */ -static void alloc_behind_pages(struct bio *bio, r1bio_t *r1_bio) +static void alloc_behind_pages(struct bio *bio, struct r1bio *r1_bio) { int i; struct bio_vec *bvec; @@ -782,14 +804,14 @@ do_sync_io: if (bvecs[i].bv_page) put_page(bvecs[i].bv_page); kfree(bvecs); - PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size); + pr_debug("%dB behind alloc failed, doing sync I/O\n", bio->bi_size); } -static int make_request(mddev_t *mddev, struct bio * bio) +static int make_request(struct mddev *mddev, struct bio * bio) { - conf_t *conf = mddev->private; - mirror_info_t *mirror; - r1bio_t *r1_bio; + struct r1conf *conf = mddev->private; + struct mirror_info *mirror; + struct r1bio *r1_bio; struct bio *read_bio; int i, disks; struct bitmap *bitmap; @@ -797,7 +819,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) const int rw = bio_data_dir(bio); const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA)); - mdk_rdev_t *blocked_rdev; + struct md_rdev *blocked_rdev; int plugged; int first_clone; int sectors_handled; @@ -934,6 +956,11 @@ read_again: /* * WRITE: */ + if (conf->pending_count >= max_queued_requests) { + md_wakeup_thread(mddev->thread); + wait_event(conf->wait_barrier, + conf->pending_count < max_queued_requests); + } /* first select target devices under rcu_lock and * inc refcount on their rdev. Record them by setting * bios[x] to bio @@ -952,7 +979,7 @@ read_again: rcu_read_lock(); max_sectors = r1_bio->sectors; for (i = 0; i < disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { atomic_inc(&rdev->nr_pending); blocked_rdev = rdev; @@ -1097,6 +1124,7 @@ read_again: atomic_inc(&r1_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); + conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); } /* Mustn't call r1_bio_write_done before this next test, @@ -1127,16 +1155,16 @@ read_again: return 0; } -static void status(struct seq_file *seq, mddev_t *mddev) +static void status(struct seq_file *seq, struct mddev *mddev) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int i; seq_printf(seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded); rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); seq_printf(seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); } @@ -1145,10 +1173,10 @@ static void status(struct seq_file *seq, mddev_t *mddev) } -static void error(mddev_t *mddev, mdk_rdev_t *rdev) +static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; /* * If it is not operational, then we have already marked it as dead @@ -1188,7 +1216,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) mdname(mddev), conf->raid_disks - mddev->degraded); } -static void print_conf(conf_t *conf) +static void print_conf(struct r1conf *conf) { int i; @@ -1203,7 +1231,7 @@ static void print_conf(conf_t *conf) rcu_read_lock(); for (i = 0; i < conf->raid_disks; i++) { char b[BDEVNAME_SIZE]; - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev) printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n", i, !test_bit(In_sync, &rdev->flags), @@ -1213,7 +1241,7 @@ static void print_conf(conf_t *conf) rcu_read_unlock(); } -static void close_sync(conf_t *conf) +static void close_sync(struct r1conf *conf) { wait_barrier(conf); allow_barrier(conf); @@ -1222,10 +1250,10 @@ static void close_sync(conf_t *conf) conf->r1buf_pool = NULL; } -static int raid1_spare_active(mddev_t *mddev) +static int raid1_spare_active(struct mddev *mddev) { int i; - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int count = 0; unsigned long flags; @@ -1235,7 +1263,7 @@ static int raid1_spare_active(mddev_t *mddev) * Called under mddev lock, so rcu protection not needed. */ for (i = 0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev = conf->mirrors[i].rdev; + struct md_rdev *rdev = conf->mirrors[i].rdev; if (rdev && !test_bit(Faulty, &rdev->flags) && !test_and_set_bit(In_sync, &rdev->flags)) { @@ -1252,12 +1280,12 @@ static int raid1_spare_active(mddev_t *mddev) } -static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) +static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int err = -EEXIST; int mirror = 0; - mirror_info_t *p; + struct mirror_info *p; int first = 0; int last = mddev->raid_disks - 1; @@ -1300,12 +1328,12 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) return err; } -static int raid1_remove_disk(mddev_t *mddev, int number) +static int raid1_remove_disk(struct mddev *mddev, int number) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int err = 0; - mdk_rdev_t *rdev; - mirror_info_t *p = conf->mirrors+ number; + struct md_rdev *rdev; + struct mirror_info *p = conf->mirrors+ number; print_conf(conf); rdev = p->rdev; @@ -1343,14 +1371,10 @@ abort: static void end_sync_read(struct bio *bio, int error) { - r1bio_t *r1_bio = bio->bi_private; - int i; + struct r1bio *r1_bio = bio->bi_private; + + update_head_pos(r1_bio->read_disk, r1_bio); - for (i=r1_bio->mddev->raid_disks; i--; ) - if (r1_bio->bios[i] == bio) - break; - BUG_ON(i < 0); - update_head_pos(i, r1_bio); /* * we have read a block, now it needs to be re-written, * or re-read if the read failed. @@ -1366,19 +1390,15 @@ static void end_sync_read(struct bio *bio, int error) static void end_sync_write(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r1bio_t *r1_bio = bio->bi_private; - mddev_t *mddev = r1_bio->mddev; - conf_t *conf = mddev->private; - int i; + struct r1bio *r1_bio = bio->bi_private; + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; int mirror=0; sector_t first_bad; int bad_sectors; - for (i = 0; i < conf->raid_disks; i++) - if (r1_bio->bios[i] == bio) { - mirror = i; - break; - } + mirror = find_bio_disk(r1_bio, bio); + if (!uptodate) { sector_t sync_blocks = 0; sector_t s = r1_bio->sector; @@ -1404,8 +1424,6 @@ static void end_sync_write(struct bio *bio, int error) ) set_bit(R1BIO_MadeGood, &r1_bio->state); - update_head_pos(mirror, r1_bio); - if (atomic_dec_and_test(&r1_bio->remaining)) { int s = r1_bio->sectors; if (test_bit(R1BIO_MadeGood, &r1_bio->state) || @@ -1418,7 +1436,7 @@ static void end_sync_write(struct bio *bio, int error) } } -static int r1_sync_page_io(mdk_rdev_t *rdev, sector_t sector, +static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector, int sectors, struct page *page, int rw) { if (sync_page_io(rdev, sector, sectors << 9, page, rw, false)) @@ -1432,7 +1450,7 @@ static int r1_sync_page_io(mdk_rdev_t *rdev, sector_t sector, return 0; } -static int fix_sync_read_error(r1bio_t *r1_bio) +static int fix_sync_read_error(struct r1bio *r1_bio) { /* Try some synchronous reads of other devices to get * good data, much like with normal read errors. Only @@ -1445,8 +1463,8 @@ static int fix_sync_read_error(r1bio_t *r1_bio) * made sure that anything with a bad block in range * will have bi_end_io clear. */ - mddev_t *mddev = r1_bio->mddev; - conf_t *conf = mddev->private; + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; struct bio *bio = r1_bio->bios[r1_bio->read_disk]; sector_t sect = r1_bio->sector; int sectors = r1_bio->sectors; @@ -1456,7 +1474,7 @@ static int fix_sync_read_error(r1bio_t *r1_bio) int s = sectors; int d = r1_bio->read_disk; int success = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; int start; if (s > (PAGE_SIZE>>9)) @@ -1501,7 +1519,8 @@ static int fix_sync_read_error(r1bio_t *r1_bio) abort = 1; } if (abort) { - mddev->recovery_disabled = 1; + conf->recovery_disabled = + mddev->recovery_disabled; set_bit(MD_RECOVERY_INTR, &mddev->recovery); md_done_sync(mddev, r1_bio->sectors, 0); put_buf(r1_bio); @@ -1552,7 +1571,7 @@ static int fix_sync_read_error(r1bio_t *r1_bio) return 1; } -static int process_checks(r1bio_t *r1_bio) +static int process_checks(struct r1bio *r1_bio) { /* We have read all readable devices. If we haven't * got the block, then there is no hope left. @@ -1561,8 +1580,8 @@ static int process_checks(r1bio_t *r1_bio) * If any blocks failed to read, then we need to * attempt an over-write */ - mddev_t *mddev = r1_bio->mddev; - conf_t *conf = mddev->private; + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; int primary; int i; @@ -1634,9 +1653,9 @@ static int process_checks(r1bio_t *r1_bio) return 0; } -static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio) +static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; int i; int disks = conf->raid_disks; struct bio *bio, *wbio; @@ -1686,16 +1705,16 @@ static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio) * 3. Performs writes following reads for array synchronising. */ -static void fix_read_error(conf_t *conf, int read_disk, +static void fix_read_error(struct r1conf *conf, int read_disk, sector_t sect, int sectors) { - mddev_t *mddev = conf->mddev; + struct mddev *mddev = conf->mddev; while(sectors) { int s = sectors; int d = read_disk; int success = 0; int start; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (s > (PAGE_SIZE>>9)) s = PAGE_SIZE >> 9; @@ -1726,7 +1745,7 @@ static void fix_read_error(conf_t *conf, int read_disk, if (!success) { /* Cannot read from anywhere - mark it bad */ - mdk_rdev_t *rdev = conf->mirrors[read_disk].rdev; + struct md_rdev *rdev = conf->mirrors[read_disk].rdev; if (!rdev_set_badblocks(rdev, sect, s, 0)) md_error(mddev, rdev); break; @@ -1789,11 +1808,11 @@ static int submit_bio_wait(int rw, struct bio *bio) return test_bit(BIO_UPTODATE, &bio->bi_flags); } -static int narrow_write_error(r1bio_t *r1_bio, int i) +static int narrow_write_error(struct r1bio *r1_bio, int i) { - mddev_t *mddev = r1_bio->mddev; - conf_t *conf = mddev->private; - mdk_rdev_t *rdev = conf->mirrors[i].rdev; + struct mddev *mddev = r1_bio->mddev; + struct r1conf *conf = mddev->private; + struct md_rdev *rdev = conf->mirrors[i].rdev; int vcnt, idx; struct bio_vec *vec; @@ -1865,12 +1884,12 @@ static int narrow_write_error(r1bio_t *r1_bio, int i) return ok; } -static void handle_sync_write_finished(conf_t *conf, r1bio_t *r1_bio) +static void handle_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio) { int m; int s = r1_bio->sectors; for (m = 0; m < conf->raid_disks ; m++) { - mdk_rdev_t *rdev = conf->mirrors[m].rdev; + struct md_rdev *rdev = conf->mirrors[m].rdev; struct bio *bio = r1_bio->bios[m]; if (bio->bi_end_io == NULL) continue; @@ -1888,12 +1907,12 @@ static void handle_sync_write_finished(conf_t *conf, r1bio_t *r1_bio) md_done_sync(conf->mddev, s, 1); } -static void handle_write_finished(conf_t *conf, r1bio_t *r1_bio) +static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio) { int m; for (m = 0; m < conf->raid_disks ; m++) if (r1_bio->bios[m] == IO_MADE_GOOD) { - mdk_rdev_t *rdev = conf->mirrors[m].rdev; + struct md_rdev *rdev = conf->mirrors[m].rdev; rdev_clear_badblocks(rdev, r1_bio->sector, r1_bio->sectors); @@ -1917,14 +1936,14 @@ static void handle_write_finished(conf_t *conf, r1bio_t *r1_bio) raid_end_bio_io(r1_bio); } -static void handle_read_error(conf_t *conf, r1bio_t *r1_bio) +static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio) { int disk; int max_sectors; - mddev_t *mddev = conf->mddev; + struct mddev *mddev = conf->mddev; struct bio *bio; char b[BDEVNAME_SIZE]; - mdk_rdev_t *rdev; + struct md_rdev *rdev; clear_bit(R1BIO_ReadError, &r1_bio->state); /* we got a read error. Maybe the drive is bad. Maybe just @@ -2007,11 +2026,11 @@ read_more: } } -static void raid1d(mddev_t *mddev) +static void raid1d(struct mddev *mddev) { - r1bio_t *r1_bio; + struct r1bio *r1_bio; unsigned long flags; - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; struct list_head *head = &conf->retry_list; struct blk_plug plug; @@ -2028,7 +2047,7 @@ static void raid1d(mddev_t *mddev) spin_unlock_irqrestore(&conf->device_lock, flags); break; } - r1_bio = list_entry(head->prev, r1bio_t, retry_list); + r1_bio = list_entry(head->prev, struct r1bio, retry_list); list_del(head->prev); conf->nr_queued--; spin_unlock_irqrestore(&conf->device_lock, flags); @@ -2060,7 +2079,7 @@ static void raid1d(mddev_t *mddev) } -static int init_resync(conf_t *conf) +static int init_resync(struct r1conf *conf) { int buffs; @@ -2084,10 +2103,10 @@ static int init_resync(conf_t *conf) * that can be installed to exclude normal IO requests. */ -static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster) +static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) { - conf_t *conf = mddev->private; - r1bio_t *r1_bio; + struct r1conf *conf = mddev->private; + struct r1bio *r1_bio; struct bio *bio; sector_t max_sector, nr_sectors; int disk = -1; @@ -2167,7 +2186,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i set_bit(R1BIO_IsSync, &r1_bio->state); for (i=0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; bio = r1_bio->bios[i]; /* take from bio_init */ @@ -2239,7 +2258,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i int ok = 1; for (i = 0 ; i < conf->raid_disks ; i++) if (r1_bio->bios[i]->bi_end_io == end_sync_write) { - mdk_rdev_t *rdev = + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); ok = rdev_set_badblocks(rdev, sector_nr, min_bad, 0 @@ -2356,7 +2375,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i return nr_sectors; } -static sector_t raid1_size(mddev_t *mddev, sector_t sectors, int raid_disks) +static sector_t raid1_size(struct mddev *mddev, sector_t sectors, int raid_disks) { if (sectors) return sectors; @@ -2364,15 +2383,15 @@ static sector_t raid1_size(mddev_t *mddev, sector_t sectors, int raid_disks) return mddev->dev_sectors; } -static conf_t *setup_conf(mddev_t *mddev) +static struct r1conf *setup_conf(struct mddev *mddev) { - conf_t *conf; + struct r1conf *conf; int i; - mirror_info_t *disk; - mdk_rdev_t *rdev; + struct mirror_info *disk; + struct md_rdev *rdev; int err = -ENOMEM; - conf = kzalloc(sizeof(conf_t), GFP_KERNEL); + conf = kzalloc(sizeof(struct r1conf), GFP_KERNEL); if (!conf) goto abort; @@ -2417,6 +2436,8 @@ static conf_t *setup_conf(mddev_t *mddev) init_waitqueue_head(&conf->wait_barrier); bio_list_init(&conf->pending_bio_list); + conf->pending_count = 0; + conf->recovery_disabled = mddev->recovery_disabled - 1; conf->last_used = -1; for (i = 0; i < conf->raid_disks; i++) { @@ -2465,11 +2486,11 @@ static conf_t *setup_conf(mddev_t *mddev) return ERR_PTR(err); } -static int run(mddev_t *mddev) +static int run(struct mddev *mddev) { - conf_t *conf; + struct r1conf *conf; int i; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (mddev->level != 1) { printk(KERN_ERR "md/raid1:%s: raid level not set to mirroring (%d)\n", @@ -2545,9 +2566,9 @@ static int run(mddev_t *mddev) return md_integrity_register(mddev); } -static int stop(mddev_t *mddev) +static int stop(struct mddev *mddev) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; struct bitmap *bitmap = mddev->bitmap; /* wait for behind writes to complete */ @@ -2572,7 +2593,7 @@ static int stop(mddev_t *mddev) return 0; } -static int raid1_resize(mddev_t *mddev, sector_t sectors) +static int raid1_resize(struct mddev *mddev, sector_t sectors) { /* no resync is happening, and there is enough space * on all devices, so we can resize. @@ -2596,7 +2617,7 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors) return 0; } -static int raid1_reshape(mddev_t *mddev) +static int raid1_reshape(struct mddev *mddev) { /* We need to: * 1/ resize the r1bio_pool @@ -2611,8 +2632,8 @@ static int raid1_reshape(mddev_t *mddev) */ mempool_t *newpool, *oldpool; struct pool_info *newpoolinfo; - mirror_info_t *newmirrors; - conf_t *conf = mddev->private; + struct mirror_info *newmirrors; + struct r1conf *conf = mddev->private; int cnt, raid_disks; unsigned long flags; int d, d2, err; @@ -2668,7 +2689,7 @@ static int raid1_reshape(mddev_t *mddev) conf->r1bio_pool = newpool; for (d = d2 = 0; d < conf->raid_disks; d++) { - mdk_rdev_t *rdev = conf->mirrors[d].rdev; + struct md_rdev *rdev = conf->mirrors[d].rdev; if (rdev && rdev->raid_disk != d2) { sysfs_unlink_rdev(mddev, rdev); rdev->raid_disk = d2; @@ -2702,9 +2723,9 @@ static int raid1_reshape(mddev_t *mddev) return 0; } -static void raid1_quiesce(mddev_t *mddev, int state) +static void raid1_quiesce(struct mddev *mddev, int state) { - conf_t *conf = mddev->private; + struct r1conf *conf = mddev->private; switch(state) { case 2: /* wake for suspend */ @@ -2719,13 +2740,13 @@ static void raid1_quiesce(mddev_t *mddev, int state) } } -static void *raid1_takeover(mddev_t *mddev) +static void *raid1_takeover(struct mddev *mddev) { /* raid1 can take over: * raid5 with 2 devices, any layout or chunk size */ if (mddev->level == 5 && mddev->raid_disks == 2) { - conf_t *conf; + struct r1conf *conf; mddev->new_level = 1; mddev->new_layout = 0; mddev->new_chunk_sectors = 0; @@ -2737,7 +2758,7 @@ static void *raid1_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } -static struct mdk_personality raid1_personality = +static struct md_personality raid1_personality = { .name = "raid1", .level = 1, @@ -2775,3 +2796,5 @@ MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD"); MODULE_ALIAS("md-personality-3"); /* RAID1 */ MODULE_ALIAS("md-raid1"); MODULE_ALIAS("md-level-1"); + +module_param(max_queued_requests, int, S_IRUGO|S_IWUSR); diff --git a/drivers/md/raid1.h b/drivers/md/raid1.h index e0d676b48974..c732b6cce935 100644 --- a/drivers/md/raid1.h +++ b/drivers/md/raid1.h @@ -1,10 +1,8 @@ #ifndef _RAID1_H #define _RAID1_H -typedef struct mirror_info mirror_info_t; - struct mirror_info { - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t head_position; }; @@ -17,61 +15,82 @@ struct mirror_info { */ struct pool_info { - mddev_t *mddev; + struct mddev *mddev; int raid_disks; }; - -typedef struct r1bio_s r1bio_t; - -struct r1_private_data_s { - mddev_t *mddev; - mirror_info_t *mirrors; +struct r1conf { + struct mddev *mddev; + struct mirror_info *mirrors; int raid_disks; + + /* When choose the best device for a read (read_balance()) + * we try to keep sequential reads one the same device + * using 'last_used' and 'next_seq_sect' + */ int last_used; sector_t next_seq_sect; + /* During resync, read_balancing is only allowed on the part + * of the array that has been resynced. 'next_resync' tells us + * where that is. + */ + sector_t next_resync; + spinlock_t device_lock; + /* list of 'struct r1bio' that need to be processed by raid1d, + * whether to retry a read, writeout a resync or recovery + * block, or anything else. + */ struct list_head retry_list; - /* queue pending writes and submit them on unplug */ - struct bio_list pending_bio_list; - /* for use when syncing mirrors: */ + /* queue pending writes to be submitted on unplug */ + struct bio_list pending_bio_list; + int pending_count; + /* for use when syncing mirrors: + * We don't allow both normal IO and resync/recovery IO at + * the same time - resync/recovery can only happen when there + * is no other IO. So when either is active, the other has to wait. + * See more details description in raid1.c near raise_barrier(). + */ + wait_queue_head_t wait_barrier; spinlock_t resync_lock; int nr_pending; int nr_waiting; int nr_queued; int barrier; - sector_t next_resync; - int fullsync; /* set to 1 if a full sync is needed, - * (fresh device added). - * Cleared when a sync completes. - */ - int recovery_disabled; /* when the same as - * mddev->recovery_disabled - * we don't allow recovery - * to be attempted as we - * expect a read error - */ - wait_queue_head_t wait_barrier; + /* Set to 1 if a full sync is needed, (fresh device added). + * Cleared when a sync completes. + */ + int fullsync; + /* When the same as mddev->recovery_disabled we don't allow + * recovery to be attempted as we expect a read error. + */ + int recovery_disabled; + + + /* poolinfo contains information about the content of the + * mempools - it changes when the array grows or shrinks + */ struct pool_info *poolinfo; + mempool_t *r1bio_pool; + mempool_t *r1buf_pool; + /* temporary buffer to synchronous IO when attempting to repair + * a read error. + */ struct page *tmppage; - mempool_t *r1bio_pool; - mempool_t *r1buf_pool; /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct mdk_thread_s *thread; + struct md_thread *thread; }; -typedef struct r1_private_data_s conf_t; - /* * this is our 'private' RAID1 bio. * @@ -79,7 +98,7 @@ typedef struct r1_private_data_s conf_t; * for this RAID1 operation, and about their status: */ -struct r1bio_s { +struct r1bio { atomic_t remaining; /* 'have we finished' count, * used from IRQ handlers */ @@ -89,7 +108,7 @@ struct r1bio_s { sector_t sector; int sectors; unsigned long state; - mddev_t *mddev; + struct mddev *mddev; /* * original bio going to /dev/mdx */ @@ -148,6 +167,6 @@ struct r1bio_s { #define R1BIO_MadeGood 7 #define R1BIO_WriteError 8 -extern int md_raid1_congested(mddev_t *mddev, int bits); +extern int md_raid1_congested(struct mddev *mddev, int bits); #endif diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 0cd9672cf9cb..132c18ef8665 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -58,13 +58,19 @@ */ #define NR_RAID10_BIOS 256 -static void allow_barrier(conf_t *conf); -static void lower_barrier(conf_t *conf); +/* When there are this many requests queue to be written by + * the raid10 thread, we become 'congested' to provide back-pressure + * for writeback. + */ +static int max_queued_requests = 1024; + +static void allow_barrier(struct r10conf *conf); +static void lower_barrier(struct r10conf *conf); static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data) { - conf_t *conf = data; - int size = offsetof(struct r10bio_s, devs[conf->copies]); + struct r10conf *conf = data; + int size = offsetof(struct r10bio, devs[conf->copies]); /* allocate a r10bio with room for raid_disks entries in the bios array */ return kzalloc(size, gfp_flags); @@ -92,9 +98,9 @@ static void r10bio_pool_free(void *r10_bio, void *data) */ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) { - conf_t *conf = data; + struct r10conf *conf = data; struct page *page; - r10bio_t *r10_bio; + struct r10bio *r10_bio; struct bio *bio; int i, j; int nalloc; @@ -158,8 +164,8 @@ out_free_bio: static void r10buf_pool_free(void *__r10_bio, void *data) { int i; - conf_t *conf = data; - r10bio_t *r10bio = __r10_bio; + struct r10conf *conf = data; + struct r10bio *r10bio = __r10_bio; int j; for (j=0; j < conf->copies; j++) { @@ -175,7 +181,7 @@ static void r10buf_pool_free(void *__r10_bio, void *data) r10bio_pool_free(r10bio, conf); } -static void put_all_bios(conf_t *conf, r10bio_t *r10_bio) +static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio) { int i; @@ -187,28 +193,28 @@ static void put_all_bios(conf_t *conf, r10bio_t *r10_bio) } } -static void free_r10bio(r10bio_t *r10_bio) +static void free_r10bio(struct r10bio *r10_bio) { - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; put_all_bios(conf, r10_bio); mempool_free(r10_bio, conf->r10bio_pool); } -static void put_buf(r10bio_t *r10_bio) +static void put_buf(struct r10bio *r10_bio) { - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; mempool_free(r10_bio, conf->r10buf_pool); lower_barrier(conf); } -static void reschedule_retry(r10bio_t *r10_bio) +static void reschedule_retry(struct r10bio *r10_bio) { unsigned long flags; - mddev_t *mddev = r10_bio->mddev; - conf_t *conf = mddev->private; + struct mddev *mddev = r10_bio->mddev; + struct r10conf *conf = mddev->private; spin_lock_irqsave(&conf->device_lock, flags); list_add(&r10_bio->retry_list, &conf->retry_list); @@ -226,11 +232,11 @@ static void reschedule_retry(r10bio_t *r10_bio) * operation and are ready to return a success/failure code to the buffer * cache layer. */ -static void raid_end_bio_io(r10bio_t *r10_bio) +static void raid_end_bio_io(struct r10bio *r10_bio) { struct bio *bio = r10_bio->master_bio; int done; - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; if (bio->bi_phys_segments) { unsigned long flags; @@ -256,9 +262,9 @@ static void raid_end_bio_io(r10bio_t *r10_bio) /* * Update disk head position estimator based on IRQ completion info. */ -static inline void update_head_pos(int slot, r10bio_t *r10_bio) +static inline void update_head_pos(int slot, struct r10bio *r10_bio) { - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; conf->mirrors[r10_bio->devs[slot].devnum].head_position = r10_bio->devs[slot].addr + (r10_bio->sectors); @@ -267,7 +273,7 @@ static inline void update_head_pos(int slot, r10bio_t *r10_bio) /* * Find the disk number which triggered given bio */ -static int find_bio_disk(conf_t *conf, r10bio_t *r10_bio, +static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, struct bio *bio, int *slotp) { int slot; @@ -287,9 +293,9 @@ static int find_bio_disk(conf_t *conf, r10bio_t *r10_bio, static void raid10_end_read_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t *r10_bio = bio->bi_private; + struct r10bio *r10_bio = bio->bi_private; int slot, dev; - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; slot = r10_bio->read_slot; @@ -327,7 +333,7 @@ static void raid10_end_read_request(struct bio *bio, int error) } } -static void close_write(r10bio_t *r10_bio) +static void close_write(struct r10bio *r10_bio) { /* clear the bitmap if all writes complete successfully */ bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector, @@ -337,7 +343,7 @@ static void close_write(r10bio_t *r10_bio) md_write_end(r10_bio->mddev); } -static void one_write_done(r10bio_t *r10_bio) +static void one_write_done(struct r10bio *r10_bio) { if (atomic_dec_and_test(&r10_bio->remaining)) { if (test_bit(R10BIO_WriteError, &r10_bio->state)) @@ -355,10 +361,10 @@ static void one_write_done(r10bio_t *r10_bio) static void raid10_end_write_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t *r10_bio = bio->bi_private; + struct r10bio *r10_bio = bio->bi_private; int dev; int dec_rdev = 1; - conf_t *conf = r10_bio->mddev->private; + struct r10conf *conf = r10_bio->mddev->private; int slot; dev = find_bio_disk(conf, r10_bio, bio, &slot); @@ -433,7 +439,7 @@ static void raid10_end_write_request(struct bio *bio, int error) * sector offset to a virtual address */ -static void raid10_find_phys(conf_t *conf, r10bio_t *r10bio) +static void raid10_find_phys(struct r10conf *conf, struct r10bio *r10bio) { int n,f; sector_t sector; @@ -481,7 +487,7 @@ static void raid10_find_phys(conf_t *conf, r10bio_t *r10bio) BUG_ON(slot != conf->copies); } -static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev) +static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev) { sector_t offset, chunk, vchunk; @@ -522,7 +528,7 @@ static int raid10_mergeable_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *biovec) { - mddev_t *mddev = q->queuedata; + struct mddev *mddev = q->queuedata; sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); int max; unsigned int chunk_sectors = mddev->chunk_sectors; @@ -555,14 +561,14 @@ static int raid10_mergeable_bvec(struct request_queue *q, * FIXME: possibly should rethink readbalancing and do it differently * depending on near_copies / far_copies geometry. */ -static int read_balance(conf_t *conf, r10bio_t *r10_bio, int *max_sectors) +static int read_balance(struct r10conf *conf, struct r10bio *r10_bio, int *max_sectors) { const sector_t this_sector = r10_bio->sector; int disk, slot; int sectors = r10_bio->sectors; int best_good_sectors; sector_t new_distance, best_dist; - mdk_rdev_t *rdev; + struct md_rdev *rdev; int do_balance; int best_slot; @@ -677,15 +683,19 @@ retry: static int raid10_congested(void *data, int bits) { - mddev_t *mddev = data; - conf_t *conf = mddev->private; + struct mddev *mddev = data; + struct r10conf *conf = mddev->private; int i, ret = 0; + if ((bits & (1 << BDI_async_congested)) && + conf->pending_count >= max_queued_requests) + return 1; + if (mddev_congested(mddev, bits)) return 1; rcu_read_lock(); for (i = 0; i < conf->raid_disks && ret == 0; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); if (rdev && !test_bit(Faulty, &rdev->flags)) { struct request_queue *q = bdev_get_queue(rdev->bdev); @@ -696,7 +706,7 @@ static int raid10_congested(void *data, int bits) return ret; } -static void flush_pending_writes(conf_t *conf) +static void flush_pending_writes(struct r10conf *conf) { /* Any writes that have been queued but are awaiting * bitmap updates get flushed here. @@ -706,10 +716,12 @@ static void flush_pending_writes(conf_t *conf) if (conf->pending_bio_list.head) { struct bio *bio; bio = bio_list_get(&conf->pending_bio_list); + conf->pending_count = 0; spin_unlock_irq(&conf->device_lock); /* flush any pending bitmap writes to disk * before proceeding w/ I/O */ bitmap_unplug(conf->mddev->bitmap); + wake_up(&conf->wait_barrier); while (bio) { /* submit pending writes */ struct bio *next = bio->bi_next; @@ -743,7 +755,7 @@ static void flush_pending_writes(conf_t *conf) * lower_barrier when the particular background IO completes. */ -static void raise_barrier(conf_t *conf, int force) +static void raise_barrier(struct r10conf *conf, int force) { BUG_ON(force && !conf->barrier); spin_lock_irq(&conf->resync_lock); @@ -763,7 +775,7 @@ static void raise_barrier(conf_t *conf, int force) spin_unlock_irq(&conf->resync_lock); } -static void lower_barrier(conf_t *conf) +static void lower_barrier(struct r10conf *conf) { unsigned long flags; spin_lock_irqsave(&conf->resync_lock, flags); @@ -772,7 +784,7 @@ static void lower_barrier(conf_t *conf) wake_up(&conf->wait_barrier); } -static void wait_barrier(conf_t *conf) +static void wait_barrier(struct r10conf *conf) { spin_lock_irq(&conf->resync_lock); if (conf->barrier) { @@ -786,7 +798,7 @@ static void wait_barrier(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static void allow_barrier(conf_t *conf) +static void allow_barrier(struct r10conf *conf) { unsigned long flags; spin_lock_irqsave(&conf->resync_lock, flags); @@ -795,7 +807,7 @@ static void allow_barrier(conf_t *conf) wake_up(&conf->wait_barrier); } -static void freeze_array(conf_t *conf) +static void freeze_array(struct r10conf *conf) { /* stop syncio and normal IO and wait for everything to * go quiet. @@ -820,7 +832,7 @@ static void freeze_array(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static void unfreeze_array(conf_t *conf) +static void unfreeze_array(struct r10conf *conf) { /* reverse the effect of the freeze */ spin_lock_irq(&conf->resync_lock); @@ -830,11 +842,11 @@ static void unfreeze_array(conf_t *conf) spin_unlock_irq(&conf->resync_lock); } -static int make_request(mddev_t *mddev, struct bio * bio) +static int make_request(struct mddev *mddev, struct bio * bio) { - conf_t *conf = mddev->private; - mirror_info_t *mirror; - r10bio_t *r10_bio; + struct r10conf *conf = mddev->private; + struct mirror_info *mirror; + struct r10bio *r10_bio; struct bio *read_bio; int i; int chunk_sects = conf->chunk_mask + 1; @@ -842,7 +854,7 @@ static int make_request(mddev_t *mddev, struct bio * bio) const unsigned long do_sync = (bio->bi_rw & REQ_SYNC); const unsigned long do_fua = (bio->bi_rw & REQ_FUA); unsigned long flags; - mdk_rdev_t *blocked_rdev; + struct md_rdev *blocked_rdev; int plugged; int sectors_handled; int max_sectors; @@ -996,6 +1008,11 @@ read_again: /* * WRITE: */ + if (conf->pending_count >= max_queued_requests) { + md_wakeup_thread(mddev->thread); + wait_event(conf->wait_barrier, + conf->pending_count < max_queued_requests); + } /* first select target devices under rcu_lock and * inc refcount on their rdev. Record them by setting * bios[x] to bio @@ -1017,7 +1034,7 @@ retry_write: for (i = 0; i < conf->copies; i++) { int d = r10_bio->devs[i].devnum; - mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[d].rdev); + struct md_rdev *rdev = rcu_dereference(conf->mirrors[d].rdev); if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) { atomic_inc(&rdev->nr_pending); blocked_rdev = rdev; @@ -1129,6 +1146,7 @@ retry_write: atomic_inc(&r10_bio->remaining); spin_lock_irqsave(&conf->device_lock, flags); bio_list_add(&conf->pending_bio_list, mbio); + conf->pending_count++; spin_unlock_irqrestore(&conf->device_lock, flags); } @@ -1161,9 +1179,9 @@ retry_write: return 0; } -static void status(struct seq_file *seq, mddev_t *mddev) +static void status(struct seq_file *seq, struct mddev *mddev) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; int i; if (conf->near_copies < conf->raid_disks) @@ -1190,7 +1208,7 @@ static void status(struct seq_file *seq, mddev_t *mddev) * Don't consider the device numbered 'ignore' * as we might be about to remove it. */ -static int enough(conf_t *conf, int ignore) +static int enough(struct r10conf *conf, int ignore) { int first = 0; @@ -1209,10 +1227,10 @@ static int enough(conf_t *conf, int ignore) return 1; } -static void error(mddev_t *mddev, mdk_rdev_t *rdev) +static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; /* * If it is not operational, then we have already marked it as dead @@ -1246,10 +1264,10 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) mdname(mddev), conf->raid_disks - mddev->degraded); } -static void print_conf(conf_t *conf) +static void print_conf(struct r10conf *conf) { int i; - mirror_info_t *tmp; + struct mirror_info *tmp; printk(KERN_DEBUG "RAID10 conf printout:\n"); if (!conf) { @@ -1270,7 +1288,7 @@ static void print_conf(conf_t *conf) } } -static void close_sync(conf_t *conf) +static void close_sync(struct r10conf *conf) { wait_barrier(conf); allow_barrier(conf); @@ -1279,11 +1297,11 @@ static void close_sync(conf_t *conf) conf->r10buf_pool = NULL; } -static int raid10_spare_active(mddev_t *mddev) +static int raid10_spare_active(struct mddev *mddev) { int i; - conf_t *conf = mddev->private; - mirror_info_t *tmp; + struct r10conf *conf = mddev->private; + struct mirror_info *tmp; int count = 0; unsigned long flags; @@ -1309,9 +1327,9 @@ static int raid10_spare_active(mddev_t *mddev) } -static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) +static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; int err = -EEXIST; int mirror; int first = 0; @@ -1334,7 +1352,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) else mirror = first; for ( ; mirror <= last ; mirror++) { - mirror_info_t *p = &conf->mirrors[mirror]; + struct mirror_info *p = &conf->mirrors[mirror]; if (p->recovery_disabled == mddev->recovery_disabled) continue; if (!p->rdev) @@ -1355,6 +1373,7 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) } p->head_position = 0; + p->recovery_disabled = mddev->recovery_disabled - 1; rdev->raid_disk = mirror; err = 0; if (rdev->saved_raid_disk != mirror) @@ -1368,12 +1387,12 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) return err; } -static int raid10_remove_disk(mddev_t *mddev, int number) +static int raid10_remove_disk(struct mddev *mddev, int number) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; int err = 0; - mdk_rdev_t *rdev; - mirror_info_t *p = conf->mirrors+ number; + struct md_rdev *rdev; + struct mirror_info *p = conf->mirrors+ number; print_conf(conf); rdev = p->rdev; @@ -1411,8 +1430,8 @@ abort: static void end_sync_read(struct bio *bio, int error) { - r10bio_t *r10_bio = bio->bi_private; - conf_t *conf = r10_bio->mddev->private; + struct r10bio *r10_bio = bio->bi_private; + struct r10conf *conf = r10_bio->mddev->private; int d; d = find_bio_disk(conf, r10_bio, bio, NULL); @@ -1439,9 +1458,9 @@ static void end_sync_read(struct bio *bio, int error) } } -static void end_sync_request(r10bio_t *r10_bio) +static void end_sync_request(struct r10bio *r10_bio) { - mddev_t *mddev = r10_bio->mddev; + struct mddev *mddev = r10_bio->mddev; while (atomic_dec_and_test(&r10_bio->remaining)) { if (r10_bio->master_bio == NULL) { @@ -1455,7 +1474,7 @@ static void end_sync_request(r10bio_t *r10_bio) md_done_sync(mddev, s, 1); break; } else { - r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio; + struct r10bio *r10_bio2 = (struct r10bio *)r10_bio->master_bio; if (test_bit(R10BIO_MadeGood, &r10_bio->state) || test_bit(R10BIO_WriteError, &r10_bio->state)) reschedule_retry(r10_bio); @@ -1469,9 +1488,9 @@ static void end_sync_request(r10bio_t *r10_bio) static void end_sync_write(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - r10bio_t *r10_bio = bio->bi_private; - mddev_t *mddev = r10_bio->mddev; - conf_t *conf = mddev->private; + struct r10bio *r10_bio = bio->bi_private; + struct mddev *mddev = r10_bio->mddev; + struct r10conf *conf = mddev->private; int d; sector_t first_bad; int bad_sectors; @@ -1509,9 +1528,9 @@ static void end_sync_write(struct bio *bio, int error) * We check if all blocks are in-sync and only write to blocks that * aren't in sync */ -static void sync_request_write(mddev_t *mddev, r10bio_t *r10_bio) +static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; int i, first; struct bio *tbio, *fbio; @@ -1609,7 +1628,7 @@ done: * The second for writing. * */ -static void fix_recovery_read_error(r10bio_t *r10_bio) +static void fix_recovery_read_error(struct r10bio *r10_bio) { /* We got a read error during recovery. * We repeat the read in smaller page-sized sections. @@ -1618,8 +1637,8 @@ static void fix_recovery_read_error(r10bio_t *r10_bio) * If a read fails, record a bad block on both old and * new devices. */ - mddev_t *mddev = r10_bio->mddev; - conf_t *conf = mddev->private; + struct mddev *mddev = r10_bio->mddev; + struct r10conf *conf = mddev->private; struct bio *bio = r10_bio->devs[0].bio; sector_t sect = 0; int sectors = r10_bio->sectors; @@ -1629,7 +1648,7 @@ static void fix_recovery_read_error(r10bio_t *r10_bio) while (sectors) { int s = sectors; - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t addr; int ok; @@ -1663,7 +1682,7 @@ static void fix_recovery_read_error(r10bio_t *r10_bio) if (rdev != conf->mirrors[dw].rdev) { /* need bad block on destination too */ - mdk_rdev_t *rdev2 = conf->mirrors[dw].rdev; + struct md_rdev *rdev2 = conf->mirrors[dw].rdev; addr = r10_bio->devs[1].addr + sect; ok = rdev_set_badblocks(rdev2, addr, s, 0); if (!ok) { @@ -1688,9 +1707,9 @@ static void fix_recovery_read_error(r10bio_t *r10_bio) } } -static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio) +static void recovery_request_write(struct mddev *mddev, struct r10bio *r10_bio) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; int d; struct bio *wbio; @@ -1719,7 +1738,7 @@ static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio) * since the last recorded read error. * */ -static void check_decay_read_errors(mddev_t *mddev, mdk_rdev_t *rdev) +static void check_decay_read_errors(struct mddev *mddev, struct md_rdev *rdev) { struct timespec cur_time_mon; unsigned long hours_since_last; @@ -1750,7 +1769,7 @@ static void check_decay_read_errors(mddev_t *mddev, mdk_rdev_t *rdev) atomic_set(&rdev->read_errors, read_errors >> hours_since_last); } -static int r10_sync_page_io(mdk_rdev_t *rdev, sector_t sector, +static int r10_sync_page_io(struct md_rdev *rdev, sector_t sector, int sectors, struct page *page, int rw) { sector_t first_bad; @@ -1778,11 +1797,11 @@ static int r10_sync_page_io(mdk_rdev_t *rdev, sector_t sector, * 3. Performs writes following reads for array synchronising. */ -static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio) +static void fix_read_error(struct r10conf *conf, struct mddev *mddev, struct r10bio *r10_bio) { int sect = 0; /* Offset from r10_bio->sector */ int sectors = r10_bio->sectors; - mdk_rdev_t*rdev; + struct md_rdev*rdev; int max_read_errors = atomic_read(&mddev->max_corr_read_errors); int d = r10_bio->devs[r10_bio->read_slot].devnum; @@ -1983,12 +2002,12 @@ static int submit_bio_wait(int rw, struct bio *bio) return test_bit(BIO_UPTODATE, &bio->bi_flags); } -static int narrow_write_error(r10bio_t *r10_bio, int i) +static int narrow_write_error(struct r10bio *r10_bio, int i) { struct bio *bio = r10_bio->master_bio; - mddev_t *mddev = r10_bio->mddev; - conf_t *conf = mddev->private; - mdk_rdev_t *rdev = conf->mirrors[r10_bio->devs[i].devnum].rdev; + struct mddev *mddev = r10_bio->mddev; + struct r10conf *conf = mddev->private; + struct md_rdev *rdev = conf->mirrors[r10_bio->devs[i].devnum].rdev; /* bio has the data to be written to slot 'i' where * we just recently had a write error. * We repeatedly clone the bio and trim down to one block, @@ -2040,13 +2059,13 @@ static int narrow_write_error(r10bio_t *r10_bio, int i) return ok; } -static void handle_read_error(mddev_t *mddev, r10bio_t *r10_bio) +static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio) { int slot = r10_bio->read_slot; int mirror = r10_bio->devs[slot].devnum; struct bio *bio; - conf_t *conf = mddev->private; - mdk_rdev_t *rdev; + struct r10conf *conf = mddev->private; + struct md_rdev *rdev; char b[BDEVNAME_SIZE]; unsigned long do_sync; int max_sectors; @@ -2139,7 +2158,7 @@ read_more: generic_make_request(bio); } -static void handle_write_completed(conf_t *conf, r10bio_t *r10_bio) +static void handle_write_completed(struct r10conf *conf, struct r10bio *r10_bio) { /* Some sort of write request has finished and it * succeeded in writing where we thought there was a @@ -2148,7 +2167,7 @@ static void handle_write_completed(conf_t *conf, r10bio_t *r10_bio) * a bad block. */ int m; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (test_bit(R10BIO_IsSync, &r10_bio->state) || test_bit(R10BIO_IsRecover, &r10_bio->state)) { @@ -2200,11 +2219,11 @@ static void handle_write_completed(conf_t *conf, r10bio_t *r10_bio) } } -static void raid10d(mddev_t *mddev) +static void raid10d(struct mddev *mddev) { - r10bio_t *r10_bio; + struct r10bio *r10_bio; unsigned long flags; - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; struct list_head *head = &conf->retry_list; struct blk_plug plug; @@ -2220,7 +2239,7 @@ static void raid10d(mddev_t *mddev) spin_unlock_irqrestore(&conf->device_lock, flags); break; } - r10_bio = list_entry(head->prev, r10bio_t, retry_list); + r10_bio = list_entry(head->prev, struct r10bio, retry_list); list_del(head->prev); conf->nr_queued--; spin_unlock_irqrestore(&conf->device_lock, flags); @@ -2252,7 +2271,7 @@ static void raid10d(mddev_t *mddev) } -static int init_resync(conf_t *conf) +static int init_resync(struct r10conf *conf) { int buffs; @@ -2297,11 +2316,11 @@ static int init_resync(conf_t *conf) * */ -static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, +static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) { - conf_t *conf = mddev->private; - r10bio_t *r10_bio; + struct r10conf *conf = mddev->private; + struct r10bio *r10_bio; struct bio *biolist = NULL, *bio; sector_t max_sector, nr_sectors; int i; @@ -2393,7 +2412,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, for (i=0 ; i<conf->raid_disks; i++) { int still_degraded; - r10bio_t *rb2; + struct r10bio *rb2; sector_t sect; int must_sync; int any_working; @@ -2453,7 +2472,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int k; int d = r10_bio->devs[j].devnum; sector_t from_addr, to_addr; - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t sector, first_bad; int bad_sectors; if (!conf->mirrors[d].rdev || @@ -2547,8 +2566,8 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, } if (biolist == NULL) { while (r10_bio) { - r10bio_t *rb2 = r10_bio; - r10_bio = (r10bio_t*) rb2->master_bio; + struct r10bio *rb2 = r10_bio; + r10_bio = (struct r10bio*) rb2->master_bio; rb2->master_bio = NULL; put_buf(rb2); } @@ -2714,10 +2733,10 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, } static sector_t -raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks) +raid10_size(struct mddev *mddev, sector_t sectors, int raid_disks) { sector_t size; - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; if (!raid_disks) raid_disks = conf->raid_disks; @@ -2733,9 +2752,9 @@ raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks) } -static conf_t *setup_conf(mddev_t *mddev) +static struct r10conf *setup_conf(struct mddev *mddev) { - conf_t *conf = NULL; + struct r10conf *conf = NULL; int nc, fc, fo; sector_t stride, size; int err = -EINVAL; @@ -2760,7 +2779,7 @@ static conf_t *setup_conf(mddev_t *mddev) } err = -ENOMEM; - conf = kzalloc(sizeof(conf_t), GFP_KERNEL); + conf = kzalloc(sizeof(struct r10conf), GFP_KERNEL); if (!conf) goto out; @@ -2836,12 +2855,12 @@ static conf_t *setup_conf(mddev_t *mddev) return ERR_PTR(err); } -static int run(mddev_t *mddev) +static int run(struct mddev *mddev) { - conf_t *conf; + struct r10conf *conf; int i, disk_idx, chunk_size; - mirror_info_t *disk; - mdk_rdev_t *rdev; + struct mirror_info *disk; + struct md_rdev *rdev; sector_t size; /* @@ -2913,6 +2932,7 @@ static int run(mddev_t *mddev) if (disk->rdev) conf->fullsync = 1; } + disk->recovery_disabled = mddev->recovery_disabled - 1; } if (mddev->recovery_cp != MaxSector) @@ -2966,9 +2986,9 @@ out: return -EIO; } -static int stop(mddev_t *mddev) +static int stop(struct mddev *mddev) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; raise_barrier(conf, 0); lower_barrier(conf); @@ -2983,9 +3003,9 @@ static int stop(mddev_t *mddev) return 0; } -static void raid10_quiesce(mddev_t *mddev, int state) +static void raid10_quiesce(struct mddev *mddev, int state) { - conf_t *conf = mddev->private; + struct r10conf *conf = mddev->private; switch(state) { case 1: @@ -2997,10 +3017,10 @@ static void raid10_quiesce(mddev_t *mddev, int state) } } -static void *raid10_takeover_raid0(mddev_t *mddev) +static void *raid10_takeover_raid0(struct mddev *mddev) { - mdk_rdev_t *rdev; - conf_t *conf; + struct md_rdev *rdev; + struct r10conf *conf; if (mddev->degraded > 0) { printk(KERN_ERR "md/raid10:%s: Error: degraded raid0!\n", @@ -3029,17 +3049,17 @@ static void *raid10_takeover_raid0(mddev_t *mddev) return conf; } -static void *raid10_takeover(mddev_t *mddev) +static void *raid10_takeover(struct mddev *mddev) { - struct raid0_private_data *raid0_priv; + struct r0conf *raid0_conf; /* raid10 can take over: * raid0 - providing it has only two drives */ if (mddev->level == 0) { /* for raid0 takeover only one zone is supported */ - raid0_priv = mddev->private; - if (raid0_priv->nr_strip_zones > 1) { + raid0_conf = mddev->private; + if (raid0_conf->nr_strip_zones > 1) { printk(KERN_ERR "md/raid10:%s: cannot takeover raid 0" " with more than one zone.\n", mdname(mddev)); @@ -3050,7 +3070,7 @@ static void *raid10_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } -static struct mdk_personality raid10_personality = +static struct md_personality raid10_personality = { .name = "raid10", .level = 10, @@ -3086,3 +3106,5 @@ MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD"); MODULE_ALIAS("md-personality-9"); /* RAID10 */ MODULE_ALIAS("md-raid10"); MODULE_ALIAS("md-level-10"); + +module_param(max_queued_requests, int, S_IRUGO|S_IWUSR); diff --git a/drivers/md/raid10.h b/drivers/md/raid10.h index 79cb52a0d4a2..7facfdf841f4 100644 --- a/drivers/md/raid10.h +++ b/drivers/md/raid10.h @@ -1,10 +1,8 @@ #ifndef _RAID10_H #define _RAID10_H -typedef struct mirror_info mirror_info_t; - struct mirror_info { - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t head_position; int recovery_disabled; /* matches * mddev->recovery_disabled @@ -13,11 +11,9 @@ struct mirror_info { */ }; -typedef struct r10bio_s r10bio_t; - -struct r10_private_data_s { - mddev_t *mddev; - mirror_info_t *mirrors; +struct r10conf { + struct mddev *mddev; + struct mirror_info *mirrors; int raid_disks; spinlock_t device_lock; @@ -46,7 +42,7 @@ struct r10_private_data_s { struct list_head retry_list; /* queue pending writes and submit them on unplug */ struct bio_list pending_bio_list; - + int pending_count; spinlock_t resync_lock; int nr_pending; @@ -68,11 +64,9 @@ struct r10_private_data_s { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct mdk_thread_s *thread; + struct md_thread *thread; }; -typedef struct r10_private_data_s conf_t; - /* * this is our 'private' RAID10 bio. * @@ -80,14 +74,14 @@ typedef struct r10_private_data_s conf_t; * for this RAID10 operation, and about their status: */ -struct r10bio_s { +struct r10bio { atomic_t remaining; /* 'have we finished' count, * used from IRQ handlers */ sector_t sector; /* virtual sector number */ int sectors; unsigned long state; - mddev_t *mddev; + struct mddev *mddev; /* * original bio going to /dev/mdx */ diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index ac5e8b57e50f..f6fe053a5bed 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -70,7 +70,11 @@ #define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head)) #define HASH_MASK (NR_HASH - 1) -#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])) +static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect) +{ + int hash = (sect >> STRIPE_SHIFT) & HASH_MASK; + return &conf->stripe_hashtbl[hash]; +} /* bio's attached to a stripe+device for I/O are linked together in bi_sector * order without overlap. There may be several bio's per stripe+device, and @@ -78,24 +82,17 @@ * When walking this list for a particular stripe+device, we must never proceed * beyond a bio that extends past this device, as the next bio might no longer * be valid. - * This macro is used to determine the 'next' bio in the list, given the sector + * This function is used to determine the 'next' bio in the list, given the sector * of the current stripe+device */ -#define r5_next_bio(bio, sect) ( ( (bio)->bi_sector + ((bio)->bi_size>>9) < sect + STRIPE_SECTORS) ? (bio)->bi_next : NULL) -/* - * The following can be used to debug the driver - */ -#define RAID5_PARANOIA 1 -#if RAID5_PARANOIA && defined(CONFIG_SMP) -# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock) -#else -# define CHECK_DEVLOCK() -#endif - -#ifdef DEBUG -#define inline -#define __inline__ -#endif +static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector) +{ + int sectors = bio->bi_size >> 9; + if (bio->bi_sector + sectors < sector + STRIPE_SECTORS) + return bio->bi_next; + else + return NULL; +} /* * We maintain a biased count of active stripes in the bottom 16 bits of @@ -183,7 +180,7 @@ static void return_io(struct bio *return_bi) } } -static void print_raid5_conf (raid5_conf_t *conf); +static void print_raid5_conf (struct r5conf *conf); static int stripe_operations_active(struct stripe_head *sh) { @@ -192,7 +189,7 @@ static int stripe_operations_active(struct stripe_head *sh) test_bit(STRIPE_COMPUTE_RUN, &sh->state); } -static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) +static void __release_stripe(struct r5conf *conf, struct stripe_head *sh) { if (atomic_dec_and_test(&sh->count)) { BUG_ON(!list_empty(&sh->lru)); @@ -228,7 +225,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh) static void release_stripe(struct stripe_head *sh) { - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; unsigned long flags; spin_lock_irqsave(&conf->device_lock, flags); @@ -244,25 +241,23 @@ static inline void remove_hash(struct stripe_head *sh) hlist_del_init(&sh->hash); } -static inline void insert_hash(raid5_conf_t *conf, struct stripe_head *sh) +static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh) { struct hlist_head *hp = stripe_hash(conf, sh->sector); pr_debug("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector); - CHECK_DEVLOCK(); hlist_add_head(&sh->hash, hp); } /* find an idle stripe, make sure it is unhashed, and return it. */ -static struct stripe_head *get_free_stripe(raid5_conf_t *conf) +static struct stripe_head *get_free_stripe(struct r5conf *conf) { struct stripe_head *sh = NULL; struct list_head *first; - CHECK_DEVLOCK(); if (list_empty(&conf->inactive_list)) goto out; first = conf->inactive_list.next; @@ -306,19 +301,18 @@ static int grow_buffers(struct stripe_head *sh) } static void raid5_build_block(struct stripe_head *sh, int i, int previous); -static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous, +static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous, struct stripe_head *sh); static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) { - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int i; BUG_ON(atomic_read(&sh->count) != 0); BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); BUG_ON(stripe_operations_active(sh)); - CHECK_DEVLOCK(); pr_debug("init_stripe called, stripe %llu\n", (unsigned long long)sh->sector); @@ -348,13 +342,12 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int previous) insert_hash(conf, sh); } -static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, +static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector, short generation) { struct stripe_head *sh; struct hlist_node *hn; - CHECK_DEVLOCK(); pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector); hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash) if (sh->sector == sector && sh->generation == generation) @@ -376,7 +369,7 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, * of the two sections, and some non-in_sync devices may * be insync in the section most affected by failed devices. */ -static int has_failed(raid5_conf_t *conf) +static int has_failed(struct r5conf *conf) { int degraded; int i; @@ -386,7 +379,7 @@ static int has_failed(raid5_conf_t *conf) rcu_read_lock(); degraded = 0; for (i = 0; i < conf->previous_raid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded++; else if (test_bit(In_sync, &rdev->flags)) @@ -410,7 +403,7 @@ static int has_failed(raid5_conf_t *conf) rcu_read_lock(); degraded = 0; for (i = 0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev); + struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev); if (!rdev || test_bit(Faulty, &rdev->flags)) degraded++; else if (test_bit(In_sync, &rdev->flags)) @@ -431,7 +424,7 @@ static int has_failed(raid5_conf_t *conf) } static struct stripe_head * -get_active_stripe(raid5_conf_t *conf, sector_t sector, +get_active_stripe(struct r5conf *conf, sector_t sector, int previous, int noblock, int noquiesce) { struct stripe_head *sh; @@ -491,7 +484,7 @@ raid5_end_write_request(struct bio *bi, int error); static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) { - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int i, disks = sh->disks; might_sleep(); @@ -499,7 +492,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) for (i = disks; i--; ) { int rw; struct bio *bi; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) { if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags)) rw = WRITE_FUA; @@ -650,7 +643,7 @@ static void ops_complete_biofill(void *stripe_head_ref) { struct stripe_head *sh = stripe_head_ref; struct bio *return_bi = NULL; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int i; pr_debug("%s: stripe %llu\n", __func__, @@ -695,7 +688,7 @@ static void ops_complete_biofill(void *stripe_head_ref) static void ops_run_biofill(struct stripe_head *sh) { struct dma_async_tx_descriptor *tx = NULL; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; struct async_submit_ctl submit; int i; @@ -1246,7 +1239,7 @@ static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request) { int overlap_clear = 0, i, disks = sh->disks; struct dma_async_tx_descriptor *tx = NULL; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int level = conf->level; struct raid5_percpu *percpu; unsigned long cpu; @@ -1337,7 +1330,7 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request) #define raid_run_ops __raid_run_ops #endif -static int grow_one_stripe(raid5_conf_t *conf) +static int grow_one_stripe(struct r5conf *conf) { struct stripe_head *sh; sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL); @@ -1362,7 +1355,7 @@ static int grow_one_stripe(raid5_conf_t *conf) return 1; } -static int grow_stripes(raid5_conf_t *conf, int num) +static int grow_stripes(struct r5conf *conf, int num) { struct kmem_cache *sc; int devs = max(conf->raid_disks, conf->previous_raid_disks); @@ -1411,7 +1404,7 @@ static size_t scribble_len(int num) return len; } -static int resize_stripes(raid5_conf_t *conf, int newsize) +static int resize_stripes(struct r5conf *conf, int newsize) { /* Make all the stripes able to hold 'newsize' devices. * New slots in each stripe get 'page' set to a new page. @@ -1556,7 +1549,7 @@ static int resize_stripes(raid5_conf_t *conf, int newsize) return err; } -static int drop_one_stripe(raid5_conf_t *conf) +static int drop_one_stripe(struct r5conf *conf) { struct stripe_head *sh; @@ -1572,7 +1565,7 @@ static int drop_one_stripe(raid5_conf_t *conf) return 1; } -static void shrink_stripes(raid5_conf_t *conf) +static void shrink_stripes(struct r5conf *conf) { while (drop_one_stripe(conf)) ; @@ -1585,11 +1578,11 @@ static void shrink_stripes(raid5_conf_t *conf) static void raid5_end_read_request(struct bio * bi, int error) { struct stripe_head *sh = bi->bi_private; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int disks = sh->disks, i; int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); char b[BDEVNAME_SIZE]; - mdk_rdev_t *rdev; + struct md_rdev *rdev; for (i=0 ; i<disks; i++) @@ -1672,7 +1665,7 @@ static void raid5_end_read_request(struct bio * bi, int error) static void raid5_end_write_request(struct bio *bi, int error) { struct stripe_head *sh = bi->bi_private; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int disks = sh->disks, i; int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); sector_t first_bad; @@ -1726,10 +1719,10 @@ static void raid5_build_block(struct stripe_head *sh, int i, int previous) dev->sector = compute_blocknr(sh, i, previous); } -static void error(mddev_t *mddev, mdk_rdev_t *rdev) +static void error(struct mddev *mddev, struct md_rdev *rdev) { char b[BDEVNAME_SIZE]; - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; pr_debug("raid456: error called\n"); if (test_and_clear_bit(In_sync, &rdev->flags)) { @@ -1758,7 +1751,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev) * Input: a 'big' sector number, * Output: index of the data and parity disk, and the sector # in them. */ -static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, +static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, int previous, int *dd_idx, struct stripe_head *sh) { @@ -1963,7 +1956,7 @@ static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector, static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous) { - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int raid_disks = sh->disks; int data_disks = raid_disks - conf->max_degraded; sector_t new_sector = sh->sector, check; @@ -2088,7 +2081,7 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, int rcw, int expand) { int i, pd_idx = sh->pd_idx, disks = sh->disks; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int level = conf->level; if (rcw) { @@ -2173,7 +2166,7 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s, static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite) { struct bio **bip; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int firstwrite=0; pr_debug("adding bi b#%llu to stripe s#%llu\n", @@ -2235,9 +2228,9 @@ static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, in return 0; } -static void end_reshape(raid5_conf_t *conf); +static void end_reshape(struct r5conf *conf); -static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous, +static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous, struct stripe_head *sh) { int sectors_per_chunk = @@ -2254,7 +2247,7 @@ static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous, } static void -handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh, +handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks, struct bio **return_bi) { @@ -2264,7 +2257,7 @@ handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh, int bitmap_end = 0; if (test_bit(R5_ReadError, &sh->dev[i].flags)) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; rcu_read_lock(); rdev = rcu_dereference(conf->disks[i].rdev); if (rdev && test_bit(In_sync, &rdev->flags)) @@ -2359,7 +2352,7 @@ handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh, } static void -handle_failed_sync(raid5_conf_t *conf, struct stripe_head *sh, +handle_failed_sync(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s) { int abort = 0; @@ -2378,7 +2371,7 @@ handle_failed_sync(raid5_conf_t *conf, struct stripe_head *sh, * refcounting of rdevs is not needed */ for (i = 0; i < conf->raid_disks; i++) { - mdk_rdev_t *rdev = conf->disks[i].rdev; + struct md_rdev *rdev = conf->disks[i].rdev; if (!rdev || test_bit(Faulty, &rdev->flags) || test_bit(In_sync, &rdev->flags)) @@ -2508,7 +2501,7 @@ static void handle_stripe_fill(struct stripe_head *sh, * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but * never LOCKED, so we don't need to test 'failed' directly. */ -static void handle_stripe_clean_event(raid5_conf_t *conf, +static void handle_stripe_clean_event(struct r5conf *conf, struct stripe_head *sh, int disks, struct bio **return_bi) { int i; @@ -2553,7 +2546,7 @@ static void handle_stripe_clean_event(raid5_conf_t *conf, md_wakeup_thread(conf->mddev->thread); } -static void handle_stripe_dirtying(raid5_conf_t *conf, +static void handle_stripe_dirtying(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks) @@ -2655,7 +2648,7 @@ static void handle_stripe_dirtying(raid5_conf_t *conf, schedule_reconstruction(sh, s, rcw == 0, 0); } -static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh, +static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks) { struct r5dev *dev = NULL; @@ -2743,7 +2736,7 @@ static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh, } -static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh, +static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, struct stripe_head_state *s, int disks) { @@ -2906,7 +2899,7 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh, } } -static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh) +static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh) { int i; @@ -2985,7 +2978,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh) static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) { - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int disks = sh->disks; struct r5dev *dev; int i; @@ -3002,7 +2995,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) rcu_read_lock(); spin_lock_irq(&conf->device_lock); for (i=disks; i--; ) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t first_bad; int bad_sectors; int is_bad = 0; @@ -3069,7 +3062,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) } } else if (test_bit(In_sync, &rdev->flags)) set_bit(R5_Insync, &dev->flags); - else { + else if (!test_bit(Faulty, &rdev->flags)) { /* in sync if before recovery_offset */ if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) set_bit(R5_Insync, &dev->flags); @@ -3109,7 +3102,7 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) static void handle_stripe(struct stripe_head *sh) { struct stripe_head_state s; - raid5_conf_t *conf = sh->raid_conf; + struct r5conf *conf = sh->raid_conf; int i; int prexor; int disks = sh->disks; @@ -3341,7 +3334,7 @@ finish: if (s.handle_bad_blocks) for (i = disks; i--; ) { - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct r5dev *dev = &sh->dev[i]; if (test_and_clear_bit(R5_WriteError, &dev->flags)) { /* We own a safe reference to the rdev */ @@ -3380,7 +3373,7 @@ finish: clear_bit(STRIPE_ACTIVE, &sh->state); } -static void raid5_activate_delayed(raid5_conf_t *conf) +static void raid5_activate_delayed(struct r5conf *conf) { if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) { while (!list_empty(&conf->delayed_list)) { @@ -3396,7 +3389,7 @@ static void raid5_activate_delayed(raid5_conf_t *conf) } } -static void activate_bit_delay(raid5_conf_t *conf) +static void activate_bit_delay(struct r5conf *conf) { /* device_lock is held */ struct list_head head; @@ -3410,9 +3403,9 @@ static void activate_bit_delay(raid5_conf_t *conf) } } -int md_raid5_congested(mddev_t *mddev, int bits) +int md_raid5_congested(struct mddev *mddev, int bits) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; /* No difference between reads and writes. Just check * how busy the stripe_cache is @@ -3431,7 +3424,7 @@ EXPORT_SYMBOL_GPL(md_raid5_congested); static int raid5_congested(void *data, int bits) { - mddev_t *mddev = data; + struct mddev *mddev = data; return mddev_congested(mddev, bits) || md_raid5_congested(mddev, bits); @@ -3444,7 +3437,7 @@ static int raid5_mergeable_bvec(struct request_queue *q, struct bvec_merge_data *bvm, struct bio_vec *biovec) { - mddev_t *mddev = q->queuedata; + struct mddev *mddev = q->queuedata; sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev); int max; unsigned int chunk_sectors = mddev->chunk_sectors; @@ -3464,7 +3457,7 @@ static int raid5_mergeable_bvec(struct request_queue *q, } -static int in_chunk_boundary(mddev_t *mddev, struct bio *bio) +static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) { sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev); unsigned int chunk_sectors = mddev->chunk_sectors; @@ -3480,7 +3473,7 @@ static int in_chunk_boundary(mddev_t *mddev, struct bio *bio) * add bio to the retry LIFO ( in O(1) ... we are in interrupt ) * later sampled by raid5d. */ -static void add_bio_to_retry(struct bio *bi,raid5_conf_t *conf) +static void add_bio_to_retry(struct bio *bi,struct r5conf *conf) { unsigned long flags; @@ -3494,7 +3487,7 @@ static void add_bio_to_retry(struct bio *bi,raid5_conf_t *conf) } -static struct bio *remove_bio_from_retry(raid5_conf_t *conf) +static struct bio *remove_bio_from_retry(struct r5conf *conf) { struct bio *bi; @@ -3527,10 +3520,10 @@ static struct bio *remove_bio_from_retry(raid5_conf_t *conf) static void raid5_align_endio(struct bio *bi, int error) { struct bio* raid_bi = bi->bi_private; - mddev_t *mddev; - raid5_conf_t *conf; + struct mddev *mddev; + struct r5conf *conf; int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); - mdk_rdev_t *rdev; + struct md_rdev *rdev; bio_put(bi); @@ -3574,12 +3567,12 @@ static int bio_fits_rdev(struct bio *bi) } -static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio) +static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int dd_idx; struct bio* align_bi; - mdk_rdev_t *rdev; + struct md_rdev *rdev; if (!in_chunk_boundary(mddev, raid_bio)) { pr_debug("chunk_aligned_read : non aligned\n"); @@ -3652,7 +3645,7 @@ static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio) * head of the hold_list has changed, i.e. the head was promoted to the * handle_list. */ -static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf) +static struct stripe_head *__get_priority_stripe(struct r5conf *conf) { struct stripe_head *sh; @@ -3695,9 +3688,9 @@ static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf) return sh; } -static int make_request(mddev_t *mddev, struct bio * bi) +static int make_request(struct mddev *mddev, struct bio * bi) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int dd_idx; sector_t new_sector; sector_t logical_sector, last_sector; @@ -3855,9 +3848,9 @@ static int make_request(mddev_t *mddev, struct bio * bi) return 0; } -static sector_t raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks); +static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks); -static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped) +static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *skipped) { /* reshaping is quite different to recovery/resync so it is * handled quite separately ... here. @@ -3868,7 +3861,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped * As the reads complete, handle_stripe will copy the data * into the destination stripe and release that stripe. */ - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; struct stripe_head *sh; sector_t first_sector, last_sector; int raid_disks = conf->previous_raid_disks; @@ -4075,9 +4068,9 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped } /* FIXME go_faster isn't used */ -static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster) +static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; struct stripe_head *sh; sector_t max_sector = mddev->dev_sectors; sector_t sync_blocks; @@ -4162,7 +4155,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski return STRIPE_SECTORS; } -static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) +static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio) { /* We may not be able to submit a whole bio at once as there * may not be enough stripe_heads available. @@ -4234,10 +4227,10 @@ static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio) * During the scan, completed stripes are saved for us by the interrupt * handler, so that they will not have to wait for our next wakeup. */ -static void raid5d(mddev_t *mddev) +static void raid5d(struct mddev *mddev) { struct stripe_head *sh; - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int handled; struct blk_plug plug; @@ -4301,9 +4294,9 @@ static void raid5d(mddev_t *mddev) } static ssize_t -raid5_show_stripe_cache_size(mddev_t *mddev, char *page) +raid5_show_stripe_cache_size(struct mddev *mddev, char *page) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (conf) return sprintf(page, "%d\n", conf->max_nr_stripes); else @@ -4311,9 +4304,9 @@ raid5_show_stripe_cache_size(mddev_t *mddev, char *page) } int -raid5_set_cache_size(mddev_t *mddev, int size) +raid5_set_cache_size(struct mddev *mddev, int size) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int err; if (size <= 16 || size > 32768) @@ -4337,9 +4330,9 @@ raid5_set_cache_size(mddev_t *mddev, int size) EXPORT_SYMBOL(raid5_set_cache_size); static ssize_t -raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len) +raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; unsigned long new; int err; @@ -4362,9 +4355,9 @@ raid5_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR, raid5_store_stripe_cache_size); static ssize_t -raid5_show_preread_threshold(mddev_t *mddev, char *page) +raid5_show_preread_threshold(struct mddev *mddev, char *page) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (conf) return sprintf(page, "%d\n", conf->bypass_threshold); else @@ -4372,9 +4365,9 @@ raid5_show_preread_threshold(mddev_t *mddev, char *page) } static ssize_t -raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len) +raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; unsigned long new; if (len >= PAGE_SIZE) return -EINVAL; @@ -4396,9 +4389,9 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold, raid5_store_preread_threshold); static ssize_t -stripe_cache_active_show(mddev_t *mddev, char *page) +stripe_cache_active_show(struct mddev *mddev, char *page) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (conf) return sprintf(page, "%d\n", atomic_read(&conf->active_stripes)); else @@ -4420,9 +4413,9 @@ static struct attribute_group raid5_attrs_group = { }; static sector_t -raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks) +raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (!sectors) sectors = mddev->dev_sectors; @@ -4435,7 +4428,7 @@ raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks) return sectors * (raid_disks - conf->max_degraded); } -static void raid5_free_percpu(raid5_conf_t *conf) +static void raid5_free_percpu(struct r5conf *conf) { struct raid5_percpu *percpu; unsigned long cpu; @@ -4457,7 +4450,7 @@ static void raid5_free_percpu(raid5_conf_t *conf) free_percpu(conf->percpu); } -static void free_conf(raid5_conf_t *conf) +static void free_conf(struct r5conf *conf) { shrink_stripes(conf); raid5_free_percpu(conf); @@ -4470,7 +4463,7 @@ static void free_conf(raid5_conf_t *conf) static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, void *hcpu) { - raid5_conf_t *conf = container_of(nfb, raid5_conf_t, cpu_notify); + struct r5conf *conf = container_of(nfb, struct r5conf, cpu_notify); long cpu = (long)hcpu; struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu); @@ -4505,7 +4498,7 @@ static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action, } #endif -static int raid5_alloc_percpu(raid5_conf_t *conf) +static int raid5_alloc_percpu(struct r5conf *conf) { unsigned long cpu; struct page *spare_page; @@ -4547,11 +4540,11 @@ static int raid5_alloc_percpu(raid5_conf_t *conf) return err; } -static raid5_conf_t *setup_conf(mddev_t *mddev) +static struct r5conf *setup_conf(struct mddev *mddev) { - raid5_conf_t *conf; + struct r5conf *conf; int raid_disk, memory, max_disks; - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct disk_info *disk; if (mddev->new_level != 5 @@ -4583,7 +4576,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) return ERR_PTR(-EINVAL); } - conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL); + conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL); if (conf == NULL) goto abort; spin_lock_init(&conf->device_lock); @@ -4598,6 +4591,7 @@ static raid5_conf_t *setup_conf(mddev_t *mddev) atomic_set(&conf->preread_active_stripes, 0); atomic_set(&conf->active_aligned_reads, 0); conf->bypass_threshold = BYPASS_THRESHOLD; + conf->recovery_disabled = mddev->recovery_disabled - 1; conf->raid_disks = mddev->raid_disks; if (mddev->reshape_position == MaxSector) @@ -4712,12 +4706,12 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded return 0; } -static int run(mddev_t *mddev) +static int run(struct mddev *mddev) { - raid5_conf_t *conf; + struct r5conf *conf; int working_disks = 0; int dirty_parity_disks = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; sector_t reshape_offset = 0; if (mddev->recovery_cp != MaxSector) @@ -4942,18 +4936,16 @@ static int run(mddev_t *mddev) return 0; abort: md_unregister_thread(&mddev->thread); - if (conf) { - print_raid5_conf(conf); - free_conf(conf); - } + print_raid5_conf(conf); + free_conf(conf); mddev->private = NULL; printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev)); return -EIO; } -static int stop(mddev_t *mddev) +static int stop(struct mddev *mddev) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; md_unregister_thread(&mddev->thread); if (mddev->queue) @@ -4964,44 +4956,9 @@ static int stop(mddev_t *mddev) return 0; } -#ifdef DEBUG -static void print_sh(struct seq_file *seq, struct stripe_head *sh) -{ - int i; - - seq_printf(seq, "sh %llu, pd_idx %d, state %ld.\n", - (unsigned long long)sh->sector, sh->pd_idx, sh->state); - seq_printf(seq, "sh %llu, count %d.\n", - (unsigned long long)sh->sector, atomic_read(&sh->count)); - seq_printf(seq, "sh %llu, ", (unsigned long long)sh->sector); - for (i = 0; i < sh->disks; i++) { - seq_printf(seq, "(cache%d: %p %ld) ", - i, sh->dev[i].page, sh->dev[i].flags); - } - seq_printf(seq, "\n"); -} - -static void printall(struct seq_file *seq, raid5_conf_t *conf) +static void status(struct seq_file *seq, struct mddev *mddev) { - struct stripe_head *sh; - struct hlist_node *hn; - int i; - - spin_lock_irq(&conf->device_lock); - for (i = 0; i < NR_HASH; i++) { - hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) { - if (sh->raid_conf != conf) - continue; - print_sh(seq, sh); - } - } - spin_unlock_irq(&conf->device_lock); -} -#endif - -static void status(struct seq_file *seq, mddev_t *mddev) -{ - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int i; seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level, @@ -5012,13 +4969,9 @@ static void status(struct seq_file *seq, mddev_t *mddev) conf->disks[i].rdev && test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_"); seq_printf (seq, "]"); -#ifdef DEBUG - seq_printf (seq, "\n"); - printall(seq, conf); -#endif } -static void print_raid5_conf (raid5_conf_t *conf) +static void print_raid5_conf (struct r5conf *conf) { int i; struct disk_info *tmp; @@ -5042,10 +4995,10 @@ static void print_raid5_conf (raid5_conf_t *conf) } } -static int raid5_spare_active(mddev_t *mddev) +static int raid5_spare_active(struct mddev *mddev) { int i; - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; struct disk_info *tmp; int count = 0; unsigned long flags; @@ -5067,11 +5020,11 @@ static int raid5_spare_active(mddev_t *mddev) return count; } -static int raid5_remove_disk(mddev_t *mddev, int number) +static int raid5_remove_disk(struct mddev *mddev, int number) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int err = 0; - mdk_rdev_t *rdev; + struct md_rdev *rdev; struct disk_info *p = conf->disks + number; print_raid5_conf(conf); @@ -5110,9 +5063,9 @@ abort: return err; } -static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) +static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int err = -EEXIST; int disk; struct disk_info *p; @@ -5153,7 +5106,7 @@ static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev) return err; } -static int raid5_resize(mddev_t *mddev, sector_t sectors) +static int raid5_resize(struct mddev *mddev, sector_t sectors) { /* no resync is happening, and there is enough space * on all devices, so we can resize. @@ -5180,7 +5133,7 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors) return 0; } -static int check_stripe_cache(mddev_t *mddev) +static int check_stripe_cache(struct mddev *mddev) { /* Can only proceed if there are plenty of stripe_heads. * We need a minimum of one full stripe,, and for sensible progress @@ -5190,7 +5143,7 @@ static int check_stripe_cache(mddev_t *mddev) * If the chunk size is greater, user-space should request more * stripe_heads first. */ - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4 > conf->max_nr_stripes || ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4 @@ -5204,9 +5157,9 @@ static int check_stripe_cache(mddev_t *mddev) return 1; } -static int check_reshape(mddev_t *mddev) +static int check_reshape(struct mddev *mddev) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (mddev->delta_disks == 0 && mddev->new_layout == mddev->layout && @@ -5236,10 +5189,10 @@ static int check_reshape(mddev_t *mddev) return resize_stripes(conf, conf->raid_disks + mddev->delta_disks); } -static int raid5_start_reshape(mddev_t *mddev) +static int raid5_start_reshape(struct mddev *mddev) { - raid5_conf_t *conf = mddev->private; - mdk_rdev_t *rdev; + struct r5conf *conf = mddev->private; + struct md_rdev *rdev; int spares = 0; unsigned long flags; @@ -5353,7 +5306,7 @@ static int raid5_start_reshape(mddev_t *mddev) /* This is called from the reshape thread and should make any * changes needed in 'conf' */ -static void end_reshape(raid5_conf_t *conf) +static void end_reshape(struct r5conf *conf) { if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) { @@ -5380,9 +5333,9 @@ static void end_reshape(raid5_conf_t *conf) /* This is called from the raid5d thread with mddev_lock held. * It makes config changes to the device. */ -static void raid5_finish_reshape(mddev_t *mddev) +static void raid5_finish_reshape(struct mddev *mddev) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) { @@ -5401,7 +5354,7 @@ static void raid5_finish_reshape(mddev_t *mddev) for (d = conf->raid_disks ; d < conf->raid_disks - mddev->delta_disks; d++) { - mdk_rdev_t *rdev = conf->disks[d].rdev; + struct md_rdev *rdev = conf->disks[d].rdev; if (rdev && raid5_remove_disk(mddev, d) == 0) { sysfs_unlink_rdev(mddev, rdev); rdev->raid_disk = -1; @@ -5415,9 +5368,9 @@ static void raid5_finish_reshape(mddev_t *mddev) } } -static void raid5_quiesce(mddev_t *mddev, int state) +static void raid5_quiesce(struct mddev *mddev, int state) { - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; switch(state) { case 2: /* resume for a suspend */ @@ -5451,20 +5404,20 @@ static void raid5_quiesce(mddev_t *mddev, int state) } -static void *raid45_takeover_raid0(mddev_t *mddev, int level) +static void *raid45_takeover_raid0(struct mddev *mddev, int level) { - struct raid0_private_data *raid0_priv = mddev->private; + struct r0conf *raid0_conf = mddev->private; sector_t sectors; /* for raid0 takeover only one zone is supported */ - if (raid0_priv->nr_strip_zones > 1) { + if (raid0_conf->nr_strip_zones > 1) { printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n", mdname(mddev)); return ERR_PTR(-EINVAL); } - sectors = raid0_priv->strip_zone[0].zone_end; - sector_div(sectors, raid0_priv->strip_zone[0].nb_dev); + sectors = raid0_conf->strip_zone[0].zone_end; + sector_div(sectors, raid0_conf->strip_zone[0].nb_dev); mddev->dev_sectors = sectors; mddev->new_level = level; mddev->new_layout = ALGORITHM_PARITY_N; @@ -5478,7 +5431,7 @@ static void *raid45_takeover_raid0(mddev_t *mddev, int level) } -static void *raid5_takeover_raid1(mddev_t *mddev) +static void *raid5_takeover_raid1(struct mddev *mddev) { int chunksect; @@ -5505,7 +5458,7 @@ static void *raid5_takeover_raid1(mddev_t *mddev) return setup_conf(mddev); } -static void *raid5_takeover_raid6(mddev_t *mddev) +static void *raid5_takeover_raid6(struct mddev *mddev) { int new_layout; @@ -5539,14 +5492,14 @@ static void *raid5_takeover_raid6(mddev_t *mddev) } -static int raid5_check_reshape(mddev_t *mddev) +static int raid5_check_reshape(struct mddev *mddev) { /* For a 2-drive array, the layout and chunk size can be changed * immediately as not restriping is needed. * For larger arrays we record the new value - after validation * to be used by a reshape pass. */ - raid5_conf_t *conf = mddev->private; + struct r5conf *conf = mddev->private; int new_chunk = mddev->new_chunk_sectors; if (mddev->new_layout >= 0 && !algorithm_valid_raid5(mddev->new_layout)) @@ -5579,7 +5532,7 @@ static int raid5_check_reshape(mddev_t *mddev) return check_reshape(mddev); } -static int raid6_check_reshape(mddev_t *mddev) +static int raid6_check_reshape(struct mddev *mddev) { int new_chunk = mddev->new_chunk_sectors; @@ -5599,7 +5552,7 @@ static int raid6_check_reshape(mddev_t *mddev) return check_reshape(mddev); } -static void *raid5_takeover(mddev_t *mddev) +static void *raid5_takeover(struct mddev *mddev) { /* raid5 can take over: * raid0 - if there is only one strip zone - make it a raid4 layout @@ -5622,7 +5575,7 @@ static void *raid5_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } -static void *raid4_takeover(mddev_t *mddev) +static void *raid4_takeover(struct mddev *mddev) { /* raid4 can take over: * raid0 - if there is only one strip zone @@ -5639,9 +5592,9 @@ static void *raid4_takeover(mddev_t *mddev) return ERR_PTR(-EINVAL); } -static struct mdk_personality raid5_personality; +static struct md_personality raid5_personality; -static void *raid6_takeover(mddev_t *mddev) +static void *raid6_takeover(struct mddev *mddev) { /* Currently can only take over a raid5. We map the * personality to an equivalent raid6 personality @@ -5688,7 +5641,7 @@ static void *raid6_takeover(mddev_t *mddev) } -static struct mdk_personality raid6_personality = +static struct md_personality raid6_personality = { .name = "raid6", .level = 6, @@ -5710,7 +5663,7 @@ static struct mdk_personality raid6_personality = .quiesce = raid5_quiesce, .takeover = raid6_takeover, }; -static struct mdk_personality raid5_personality = +static struct md_personality raid5_personality = { .name = "raid5", .level = 5, @@ -5733,7 +5686,7 @@ static struct mdk_personality raid5_personality = .takeover = raid5_takeover, }; -static struct mdk_personality raid4_personality = +static struct md_personality raid4_personality = { .name = "raid4", .level = 4, diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index 11b9566184b2..e10c5531f9c5 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -197,7 +197,7 @@ enum reconstruct_states { struct stripe_head { struct hlist_node hash; struct list_head lru; /* inactive_list or handle_list */ - struct raid5_private_data *raid_conf; + struct r5conf *raid_conf; short generation; /* increments with every * reshape */ sector_t sector; /* sector of this row */ @@ -248,7 +248,7 @@ struct stripe_head_state { unsigned long ops_request; struct bio *return_bi; - mdk_rdev_t *blocked_rdev; + struct md_rdev *blocked_rdev; int handle_bad_blocks; }; @@ -344,12 +344,12 @@ enum { struct disk_info { - mdk_rdev_t *rdev; + struct md_rdev *rdev; }; -struct raid5_private_data { +struct r5conf { struct hlist_head *stripe_hashtbl; - mddev_t *mddev; + struct mddev *mddev; struct disk_info *spare; int chunk_sectors; int level, algorithm; @@ -436,11 +436,9 @@ struct raid5_private_data { /* When taking over an array from a different personality, we store * the new thread here until we fully activate the array. */ - struct mdk_thread_s *thread; + struct md_thread *thread; }; -typedef struct raid5_private_data raid5_conf_t; - /* * Our supported algorithms */ @@ -503,7 +501,7 @@ static inline int algorithm_is_DDF(int layout) return layout >= 8 && layout <= 10; } -extern int md_raid5_congested(mddev_t *mddev, int bits); -extern void md_raid5_kick_device(raid5_conf_t *conf); -extern int raid5_set_cache_size(mddev_t *mddev, int size); +extern int md_raid5_congested(struct mddev *mddev, int bits); +extern void md_raid5_kick_device(struct r5conf *conf); +extern int raid5_set_cache_size(struct mddev *mddev, int size); #endif |