diff options
Diffstat (limited to 'drivers/md/raid6main.c')
| -rw-r--r-- | drivers/md/raid6main.c | 2427 |
1 files changed, 0 insertions, 2427 deletions
diff --git a/drivers/md/raid6main.c b/drivers/md/raid6main.c deleted file mode 100644 index e53d2d96ea3..00000000000 --- a/drivers/md/raid6main.c +++ /dev/null @@ -1,2427 +0,0 @@ -/* - * raid6main.c : Multiple Devices driver for Linux - * Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman - * Copyright (C) 1999, 2000 Ingo Molnar - * Copyright (C) 2002, 2003 H. Peter Anvin - * - * RAID-6 management functions. This code is derived from raid5.c. - * Last merge from raid5.c bkcvs version 1.79 (kernel 2.6.1). - * - * Thanks to Penguin Computing for making the RAID-6 development possible - * by donating a test server! - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2, or (at your option) - * any later version. - * - * You should have received a copy of the GNU General Public License - * (for example /usr/src/linux/COPYING); if not, write to the Free - * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - */ - - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/highmem.h> -#include <linux/bitops.h> -#include <asm/atomic.h> -#include "raid6.h" - -#include <linux/raid/bitmap.h> - -/* - * Stripe cache - */ - -#define NR_STRIPES 256 -#define STRIPE_SIZE PAGE_SIZE -#define STRIPE_SHIFT (PAGE_SHIFT - 9) -#define STRIPE_SECTORS (STRIPE_SIZE>>9) -#define IO_THRESHOLD 1 -#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])) - -/* 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 - * a bio could span several devices. - * 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 - * 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 RAID6_DEBUG 0 /* Extremely verbose printk */ -#define RAID6_PARANOIA 1 /* Check spinlocks */ -#define RAID6_DUMPSTATE 0 /* Include stripe cache state in /proc/mdstat */ -#if RAID6_PARANOIA && defined(CONFIG_SMP) -# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock) -#else -# define CHECK_DEVLOCK() -#endif - -#define PRINTK(x...) ((void)(RAID6_DEBUG && printk(KERN_DEBUG x))) -#if RAID6_DEBUG -#undef inline -#undef __inline__ -#define inline -#define __inline__ -#endif - -#if !RAID6_USE_EMPTY_ZERO_PAGE -/* In .bss so it's zeroed */ -const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256))); -#endif - -static inline int raid6_next_disk(int disk, int raid_disks) -{ - disk++; - return (disk < raid_disks) ? disk : 0; -} - -static void print_raid6_conf (raid6_conf_t *conf); - -static void __release_stripe(raid6_conf_t *conf, struct stripe_head *sh) -{ - if (atomic_dec_and_test(&sh->count)) { - BUG_ON(!list_empty(&sh->lru)); - BUG_ON(atomic_read(&conf->active_stripes)==0); - if (test_bit(STRIPE_HANDLE, &sh->state)) { - if (test_bit(STRIPE_DELAYED, &sh->state)) - list_add_tail(&sh->lru, &conf->delayed_list); - else if (test_bit(STRIPE_BIT_DELAY, &sh->state) && - conf->seq_write == sh->bm_seq) - list_add_tail(&sh->lru, &conf->bitmap_list); - else { - clear_bit(STRIPE_BIT_DELAY, &sh->state); - list_add_tail(&sh->lru, &conf->handle_list); - } - md_wakeup_thread(conf->mddev->thread); - } else { - if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) { - atomic_dec(&conf->preread_active_stripes); - if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) - md_wakeup_thread(conf->mddev->thread); - } - list_add_tail(&sh->lru, &conf->inactive_list); - atomic_dec(&conf->active_stripes); - if (!conf->inactive_blocked || - atomic_read(&conf->active_stripes) < (conf->max_nr_stripes*3/4)) - wake_up(&conf->wait_for_stripe); - } - } -} -static void release_stripe(struct stripe_head *sh) -{ - raid6_conf_t *conf = sh->raid_conf; - unsigned long flags; - - spin_lock_irqsave(&conf->device_lock, flags); - __release_stripe(conf, sh); - spin_unlock_irqrestore(&conf->device_lock, flags); -} - -static inline void remove_hash(struct stripe_head *sh) -{ - PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector); - - hlist_del_init(&sh->hash); -} - -static inline void insert_hash(raid6_conf_t *conf, struct stripe_head *sh) -{ - struct hlist_head *hp = stripe_hash(conf, sh->sector); - - PRINTK("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(raid6_conf_t *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; - sh = list_entry(first, struct stripe_head, lru); - list_del_init(first); - remove_hash(sh); - atomic_inc(&conf->active_stripes); -out: - return sh; -} - -static void shrink_buffers(struct stripe_head *sh, int num) -{ - struct page *p; - int i; - - for (i=0; i<num ; i++) { - p = sh->dev[i].page; - if (!p) - continue; - sh->dev[i].page = NULL; - put_page(p); - } -} - -static int grow_buffers(struct stripe_head *sh, int num) -{ - int i; - - for (i=0; i<num; i++) { - struct page *page; - - if (!(page = alloc_page(GFP_KERNEL))) { - return 1; - } - sh->dev[i].page = page; - } - return 0; -} - -static void raid6_build_block (struct stripe_head *sh, int i); - -static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx) -{ - raid6_conf_t *conf = sh->raid_conf; - int disks = conf->raid_disks, i; - - BUG_ON(atomic_read(&sh->count) != 0); - BUG_ON(test_bit(STRIPE_HANDLE, &sh->state)); - - CHECK_DEVLOCK(); - PRINTK("init_stripe called, stripe %llu\n", - (unsigned long long)sh->sector); - - remove_hash(sh); - - sh->sector = sector; - sh->pd_idx = pd_idx; - sh->state = 0; - - for (i=disks; i--; ) { - struct r5dev *dev = &sh->dev[i]; - - if (dev->toread || dev->towrite || dev->written || - test_bit(R5_LOCKED, &dev->flags)) { - PRINTK("sector=%llx i=%d %p %p %p %d\n", - (unsigned long long)sh->sector, i, dev->toread, - dev->towrite, dev->written, - test_bit(R5_LOCKED, &dev->flags)); - BUG(); - } - dev->flags = 0; - raid6_build_block(sh, i); - } - insert_hash(conf, sh); -} - -static struct stripe_head *__find_stripe(raid6_conf_t *conf, sector_t sector) -{ - struct stripe_head *sh; - struct hlist_node *hn; - - CHECK_DEVLOCK(); - PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector); - hlist_for_each_entry (sh, hn, stripe_hash(conf, sector), hash) - if (sh->sector == sector) - return sh; - PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector); - return NULL; -} - -static void unplug_slaves(mddev_t *mddev); - -static struct stripe_head *get_active_stripe(raid6_conf_t *conf, sector_t sector, - int pd_idx, int noblock) -{ - struct stripe_head *sh; - - PRINTK("get_stripe, sector %llu\n", (unsigned long long)sector); - - spin_lock_irq(&conf->device_lock); - - do { - wait_event_lock_irq(conf->wait_for_stripe, - conf->quiesce == 0, - conf->device_lock, /* nothing */); - sh = __find_stripe(conf, sector); - if (!sh) { - if (!conf->inactive_blocked) - sh = get_free_stripe(conf); - if (noblock && sh == NULL) - break; - if (!sh) { - conf->inactive_blocked = 1; - wait_event_lock_irq(conf->wait_for_stripe, - !list_empty(&conf->inactive_list) && - (atomic_read(&conf->active_stripes) - < (conf->max_nr_stripes *3/4) - || !conf->inactive_blocked), - conf->device_lock, - unplug_slaves(conf->mddev); - ); - conf->inactive_blocked = 0; - } else - init_stripe(sh, sector, pd_idx); - } else { - if (atomic_read(&sh->count)) { - BUG_ON(!list_empty(&sh->lru)); - } else { - if (!test_bit(STRIPE_HANDLE, &sh->state)) - atomic_inc(&conf->active_stripes); - BUG_ON(list_empty(&sh->lru)); - list_del_init(&sh->lru); - } - } - } while (sh == NULL); - - if (sh) - atomic_inc(&sh->count); - - spin_unlock_irq(&conf->device_lock); - return sh; -} - -static int grow_one_stripe(raid6_conf_t *conf) -{ - struct stripe_head *sh; - sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL); - if (!sh) - return 0; - memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev)); - sh->raid_conf = conf; - spin_lock_init(&sh->lock); - - if (grow_buffers(sh, conf->raid_disks)) { - shrink_buffers(sh, conf->raid_disks); - kmem_cache_free(conf->slab_cache, sh); - return 0; - } - /* we just created an active stripe so... */ - atomic_set(&sh->count, 1); - atomic_inc(&conf->active_stripes); - INIT_LIST_HEAD(&sh->lru); - release_stripe(sh); - return 1; -} - -static int grow_stripes(raid6_conf_t *conf, int num) -{ - kmem_cache_t *sc; - int devs = conf->raid_disks; - - sprintf(conf->cache_name[0], "raid6/%s", mdname(conf->mddev)); - - sc = kmem_cache_create(conf->cache_name[0], - sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev), - 0, 0, NULL, NULL); - if (!sc) - return 1; - conf->slab_cache = sc; - while (num--) - if (!grow_one_stripe(conf)) - return 1; - return 0; -} - -static int drop_one_stripe(raid6_conf_t *conf) -{ - struct stripe_head *sh; - spin_lock_irq(&conf->device_lock); - sh = get_free_stripe(conf); - spin_unlock_irq(&conf->device_lock); - if (!sh) - return 0; - BUG_ON(atomic_read(&sh->count)); - shrink_buffers(sh, conf->raid_disks); - kmem_cache_free(conf->slab_cache, sh); - atomic_dec(&conf->active_stripes); - return 1; -} - -static void shrink_stripes(raid6_conf_t *conf) -{ - while (drop_one_stripe(conf)) - ; - - if (conf->slab_cache) - kmem_cache_destroy(conf->slab_cache); - conf->slab_cache = NULL; -} - -static int raid6_end_read_request(struct bio * bi, unsigned int bytes_done, - int error) -{ - struct stripe_head *sh = bi->bi_private; - raid6_conf_t *conf = sh->raid_conf; - int disks = conf->raid_disks, i; - int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); - - if (bi->bi_size) - return 1; - - for (i=0 ; i<disks; i++) - if (bi == &sh->dev[i].req) - break; - - PRINTK("end_read_request %llu/%d, count: %d, uptodate %d.\n", - (unsigned long long)sh->sector, i, atomic_read(&sh->count), - uptodate); - if (i == disks) { - BUG(); - return 0; - } - - if (uptodate) { -#if 0 - struct bio *bio; - unsigned long flags; - spin_lock_irqsave(&conf->device_lock, flags); - /* we can return a buffer if we bypassed the cache or - * if the top buffer is not in highmem. If there are - * multiple buffers, leave the extra work to - * handle_stripe - */ - buffer = sh->bh_read[i]; - if (buffer && - (!PageHighMem(buffer->b_page) - || buffer->b_page == bh->b_page ) - ) { - sh->bh_read[i] = buffer->b_reqnext; - buffer->b_reqnext = NULL; - } else - buffer = NULL; - spin_unlock_irqrestore(&conf->device_lock, flags); - if (sh->bh_page[i]==bh->b_page) - set_buffer_uptodate(bh); - if (buffer) { - if (buffer->b_page != bh->b_page) - memcpy(buffer->b_data, bh->b_data, bh->b_size); - buffer->b_end_io(buffer, 1); - } -#else - set_bit(R5_UPTODATE, &sh->dev[i].flags); -#endif - if (test_bit(R5_ReadError, &sh->dev[i].flags)) { - printk(KERN_INFO "raid6: read error corrected!!\n"); - clear_bit(R5_ReadError, &sh->dev[i].flags); - clear_bit(R5_ReWrite, &sh->dev[i].flags); - } - if (atomic_read(&conf->disks[i].rdev->read_errors)) - atomic_set(&conf->disks[i].rdev->read_errors, 0); - } else { - int retry = 0; - clear_bit(R5_UPTODATE, &sh->dev[i].flags); - atomic_inc(&conf->disks[i].rdev->read_errors); - if (conf->mddev->degraded) - printk(KERN_WARNING "raid6: read error not correctable.\n"); - else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) - /* Oh, no!!! */ - printk(KERN_WARNING "raid6: read error NOT corrected!!\n"); - else if (atomic_read(&conf->disks[i].rdev->read_errors) - > conf->max_nr_stripes) - printk(KERN_WARNING - "raid6: Too many read errors, failing device.\n"); - else - retry = 1; - if (retry) - set_bit(R5_ReadError, &sh->dev[i].flags); - else { - clear_bit(R5_ReadError, &sh->dev[i].flags); - clear_bit(R5_ReWrite, &sh->dev[i].flags); - md_error(conf->mddev, conf->disks[i].rdev); - } - } - rdev_dec_pending(conf->disks[i].rdev, conf->mddev); -#if 0 - /* must restore b_page before unlocking buffer... */ - if (sh->bh_page[i] != bh->b_page) { - bh->b_page = sh->bh_page[i]; - bh->b_data = page_address(bh->b_page); - clear_buffer_uptodate(bh); - } -#endif - clear_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(STRIPE_HANDLE, &sh->state); - release_stripe(sh); - return 0; -} - -static int raid6_end_write_request (struct bio *bi, unsigned int bytes_done, - int error) -{ - struct stripe_head *sh = bi->bi_private; - raid6_conf_t *conf = sh->raid_conf; - int disks = conf->raid_disks, i; - unsigned long flags; - int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags); - - if (bi->bi_size) - return 1; - - for (i=0 ; i<disks; i++) - if (bi == &sh->dev[i].req) - break; - - PRINTK("end_write_request %llu/%d, count %d, uptodate: %d.\n", - (unsigned long long)sh->sector, i, atomic_read(&sh->count), - uptodate); - if (i == disks) { - BUG(); - return 0; - } - - spin_lock_irqsave(&conf->device_lock, flags); - if (!uptodate) - md_error(conf->mddev, conf->disks[i].rdev); - - rdev_dec_pending(conf->disks[i].rdev, conf->mddev); - - clear_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(STRIPE_HANDLE, &sh->state); - __release_stripe(conf, sh); - spin_unlock_irqrestore(&conf->device_lock, flags); - return 0; -} - - -static sector_t compute_blocknr(struct stripe_head *sh, int i); - -static void raid6_build_block (struct stripe_head *sh, int i) -{ - struct r5dev *dev = &sh->dev[i]; - int pd_idx = sh->pd_idx; - int qd_idx = raid6_next_disk(pd_idx, sh->raid_conf->raid_disks); - - bio_init(&dev->req); - dev->req.bi_io_vec = &dev->vec; - dev->req.bi_vcnt++; - dev->req.bi_max_vecs++; - dev->vec.bv_page = dev->page; - dev->vec.bv_len = STRIPE_SIZE; - dev->vec.bv_offset = 0; - - dev->req.bi_sector = sh->sector; - dev->req.bi_private = sh; - - dev->flags = 0; - if (i != pd_idx && i != qd_idx) - dev->sector = compute_blocknr(sh, i); -} - -static void error(mddev_t *mddev, mdk_rdev_t *rdev) -{ - char b[BDEVNAME_SIZE]; - raid6_conf_t *conf = (raid6_conf_t *) mddev->private; - PRINTK("raid6: error called\n"); - - if (!test_bit(Faulty, &rdev->flags)) { - mddev->sb_dirty = 1; - if (test_bit(In_sync, &rdev->flags)) { - conf->working_disks--; - mddev->degraded++; - conf->failed_disks++; - clear_bit(In_sync, &rdev->flags); - /* - * if recovery was running, make sure it aborts. - */ - set_bit(MD_RECOVERY_ERR, &mddev->recovery); - } - set_bit(Faulty, &rdev->flags); - printk (KERN_ALERT - "raid6: Disk failure on %s, disabling device." - " Operation continuing on %d devices\n", - bdevname(rdev->bdev,b), conf->working_disks); - } -} - -/* - * Input: a 'big' sector number, - * Output: index of the data and parity disk, and the sector # in them. - */ -static sector_t raid6_compute_sector(sector_t r_sector, unsigned int raid_disks, - unsigned int data_disks, unsigned int * dd_idx, - unsigned int * pd_idx, raid6_conf_t *conf) -{ - long stripe; - unsigned long chunk_number; - unsigned int chunk_offset; - sector_t new_sector; - int sectors_per_chunk = conf->chunk_size >> 9; - - /* First compute the information on this sector */ - - /* - * Compute the chunk number and the sector offset inside the chunk - */ - chunk_offset = sector_div(r_sector, sectors_per_chunk); - chunk_number = r_sector; - if ( r_sector != chunk_number ) { - printk(KERN_CRIT "raid6: ERROR: r_sector = %llu, chunk_number = %lu\n", - (unsigned long long)r_sector, (unsigned long)chunk_number); - BUG(); - } - - /* - * Compute the stripe number - */ - stripe = chunk_number / data_disks; - - /* - * Compute the data disk and parity disk indexes inside the stripe - */ - *dd_idx = chunk_number % data_disks; - - /* - * Select the parity disk based on the user selected algorithm. - */ - - /**** FIX THIS ****/ - switch (conf->algorithm) { - case ALGORITHM_LEFT_ASYMMETRIC: - *pd_idx = raid_disks - 1 - (stripe % raid_disks); - if (*pd_idx == raid_disks-1) - (*dd_idx)++; /* Q D D D P */ - else if (*dd_idx >= *pd_idx) - (*dd_idx) += 2; /* D D P Q D */ - break; - case ALGORITHM_RIGHT_ASYMMETRIC: - *pd_idx = stripe % raid_disks; - if (*pd_idx == raid_disks-1) - (*dd_idx)++; /* Q D D D P */ - else if (*dd_idx >= *pd_idx) - (*dd_idx) += 2; /* D D P Q D */ - break; - case ALGORITHM_LEFT_SYMMETRIC: - *pd_idx = raid_disks - 1 - (stripe % raid_disks); - *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks; - break; - case ALGORITHM_RIGHT_SYMMETRIC: - *pd_idx = stripe % raid_disks; - *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks; - break; - default: - printk (KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); - } - - PRINTK("raid6: chunk_number = %lu, pd_idx = %u, dd_idx = %u\n", - chunk_number, *pd_idx, *dd_idx); - - /* - * Finally, compute the new sector number - */ - new_sector = (sector_t) stripe * sectors_per_chunk + chunk_offset; - return new_sector; -} - - -static sector_t compute_blocknr(struct stripe_head *sh, int i) -{ - raid6_conf_t *conf = sh->raid_conf; - int raid_disks = conf->raid_disks, data_disks = raid_disks - 2; - sector_t new_sector = sh->sector, check; - int sectors_per_chunk = conf->chunk_size >> 9; - sector_t stripe; - int chunk_offset; - int chunk_number, dummy1, dummy2, dd_idx = i; - sector_t r_sector; - int i0 = i; - - chunk_offset = sector_div(new_sector, sectors_per_chunk); - stripe = new_sector; - if ( new_sector != stripe ) { - printk(KERN_CRIT "raid6: ERROR: new_sector = %llu, stripe = %lu\n", - (unsigned long long)new_sector, (unsigned long)stripe); - BUG(); - } - - switch (conf->algorithm) { - case ALGORITHM_LEFT_ASYMMETRIC: - case ALGORITHM_RIGHT_ASYMMETRIC: - if (sh->pd_idx == raid_disks-1) - i--; /* Q D D D P */ - else if (i > sh->pd_idx) - i -= 2; /* D D P Q D */ - break; - case ALGORITHM_LEFT_SYMMETRIC: - case ALGORITHM_RIGHT_SYMMETRIC: - if (sh->pd_idx == raid_disks-1) - i--; /* Q D D D P */ - else { - /* D D P Q D */ - if (i < sh->pd_idx) - i += raid_disks; - i -= (sh->pd_idx + 2); - } - break; - default: - printk (KERN_CRIT "raid6: unsupported algorithm %d\n", - conf->algorithm); - } - - PRINTK("raid6: compute_blocknr: pd_idx = %u, i0 = %u, i = %u\n", sh->pd_idx, i0, i); - - chunk_number = stripe * data_disks + i; - r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset; - - check = raid6_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf); - if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) { - printk(KERN_CRIT "raid6: compute_blocknr: map not correct\n"); - return 0; - } - return r_sector; -} - - - -/* - * Copy data between a page in the stripe cache, and one or more bion - * The page could align with the middle of the bio, or there could be - * several bion, each with several bio_vecs, which cover part of the page - * Multiple bion are linked together on bi_next. There may be extras - * at the end of this list. We ignore them. - */ -static void copy_data(int frombio, struct bio *bio, - struct page *page, - sector_t sector) -{ - char *pa = page_address(page); - struct bio_vec *bvl; - int i; - int page_offset; - - if (bio->bi_sector >= sector) - page_offset = (signed)(bio->bi_sector - sector) * 512; - else - page_offset = (signed)(sector - bio->bi_sector) * -512; - bio_for_each_segment(bvl, bio, i) { - int len = bio_iovec_idx(bio,i)->bv_len; - int clen; - int b_offset = 0; - - if (page_offset < 0) { - b_offset = -page_offset; - page_offset += b_offset; - len -= b_offset; - } - - if (len > 0 && page_offset + len > STRIPE_SIZE) - clen = STRIPE_SIZE - page_offset; - else clen = len; - - if (clen > 0) { - char *ba = __bio_kmap_atomic(bio, i, KM_USER0); - if (frombio) - memcpy(pa+page_offset, ba+b_offset, clen); - else - memcpy(ba+b_offset, pa+page_offset, clen); - __bio_kunmap_atomic(ba, KM_USER0); - } - if (clen < len) /* hit end of page */ - break; - page_offset += len; - } -} - -#define check_xor() do { \ - if (count == MAX_XOR_BLOCKS) { \ - xor_block(count, STRIPE_SIZE, ptr); \ - count = 1; \ - } \ - } while(0) - -/* Compute P and Q syndromes */ -static void compute_parity(struct stripe_head *sh, int method) -{ - raid6_conf_t *conf = sh->raid_conf; - int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = conf->raid_disks, count; - struct bio *chosen; - /**** FIX THIS: This could be very bad if disks is close to 256 ****/ - void *ptrs[disks]; - - qd_idx = raid6_next_disk(pd_idx, disks); - d0_idx = raid6_next_disk(qd_idx, disks); - - PRINTK("compute_parity, stripe %llu, method %d\n", - (unsigned long long)sh->sector, method); - - switch(method) { - case READ_MODIFY_WRITE: - BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */ - case RECONSTRUCT_WRITE: - for (i= disks; i-- ;) - if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) { - chosen = sh->dev[i].towrite; - sh->dev[i].towrite = NULL; - - if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags)) - wake_up(&conf->wait_for_overlap); - - BUG_ON(sh->dev[i].written); - sh->dev[i].written = chosen; - } - break; - case CHECK_PARITY: - BUG(); /* Not implemented yet */ - } - - for (i = disks; i--;) - if (sh->dev[i].written) { - sector_t sector = sh->dev[i].sector; - struct bio *wbi = sh->dev[i].written; - while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) { - copy_data(1, wbi, sh->dev[i].page, sector); - wbi = r5_next_bio(wbi, sector); - } - - set_bit(R5_LOCKED, &sh->dev[i].flags); - set_bit(R5_UPTODATE, &sh->dev[i].flags); - } - -// switch(method) { -// case RECONSTRUCT_WRITE: -// case CHECK_PARITY: -// case UPDATE_PARITY: - /* Note that unlike RAID-5, the ordering of the disks matters greatly. */ - /* FIX: Is this ordering of drives even remotely optimal? */ - count = 0; - i = d0_idx; - do { - ptrs[count++] = page_address(sh->dev[i].page); - if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags)) - printk("block %d/%d not uptodate on parity calc\n", i,count); - i = raid6_next_disk(i, disks); - } while ( i != d0_idx ); -// break; -// } - - raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs); - - switch(method) { - case RECONSTRUCT_WRITE: - set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); - set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags); - set_bit(R5_LOCKED, &sh->dev[pd_idx].flags); - set_bit(R5_LOCKED, &sh->dev[qd_idx].flags); - break; - case UPDATE_PARITY: - set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags); - set_bit(R5_UPTODATE, &sh->dev[qd_idx].flags); - break; - } -} - -/* Compute one missing block */ -static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero) -{ - raid6_conf_t *conf = sh->raid_conf; - int i, count, disks = conf->raid_disks; - void *ptr[MAX_XOR_BLOCKS], *p; - int pd_idx = sh->pd_idx; - int qd_idx = raid6_next_disk(pd_idx, disks); - - PRINTK("compute_block_1, stripe %llu, idx %d\n", - (unsigned long long)sh->sector, dd_idx); - - if ( dd_idx == qd_idx ) { - /* We're actually computing the Q drive */ - compute_parity(sh, UPDATE_PARITY); - } else { - ptr[0] = page_address(sh->dev[dd_idx].page); - if (!nozero) memset(ptr[0], 0, STRIPE_SIZE); - count = 1; - for (i = disks ; i--; ) { - if (i == dd_idx || i == qd_idx) - continue; - p = page_address(sh->dev[i].page); - if (test_bit(R5_UPTODATE, &sh->dev[i].flags)) - ptr[count++] = p; - else - printk("compute_block() %d, stripe %llu, %d" - " not present\n", dd_idx, - (unsigned long long)sh->sector, i); - - check_xor(); - } - if (count != 1) - xor_block(count, STRIPE_SIZE, ptr); - if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags); - else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags); - } -} - -/* Compute two missing blocks */ -static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2) -{ - raid6_conf_t *conf = sh->raid_conf; - int i, count, disks = conf->raid_disks; - int pd_idx = sh->pd_idx; - int qd_idx = raid6_next_disk(pd_idx, disks); - int d0_idx = raid6_next_disk(qd_idx, disks); - int faila, failb; - - /* faila and failb are disk numbers relative to d0_idx */ - /* pd_idx become disks-2 and qd_idx become disks-1 */ - faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx; - failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx; - - BUG_ON(faila == failb); - if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; } - - PRINTK("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n", - (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb); - - if ( failb == disks-1 ) { - /* Q disk is one of the missing disks */ - if ( faila == disks-2 ) { - /* Missing P+Q, just recompute */ - compute_parity(sh, UPDATE_PARITY); - return; - } else { - /* We're missing D+Q; recompute D from P */ - compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0); - compute_parity(sh, UPDATE_PARITY); /* Is this necessary? */ - return; - } - } - - /* We're missing D+P or D+D; build pointer table */ - { - /**** FIX THIS: This could be very bad if disks is close to 256 ****/ - void *ptrs[disks]; - - count = 0; - i = d0_idx; - do { - ptrs[count++] = page_address(sh->dev[i].page); - i = raid6_next_disk(i, disks); - if (i != dd_idx1 && i != dd_idx2 && - !test_bit(R5_UPTODATE, &sh->dev[i].flags)) - printk("compute_2 with missing block %d/%d\n", count, i); - } while ( i != d0_idx ); - - if ( failb == disks-2 ) { - /* We're missing D+P. */ - raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs); - } else { - /* We're missing D+D. */ - raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs); - } - - /* Both the above update both missing blocks */ - set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags); - set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags); - } -} - - -/* - * Each stripe/dev can have one or more bion attached. - * toread/towrite point to the first in a chain. - * The bi_next chain must be in order. - */ -static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite) -{ - struct bio **bip; - raid6_conf_t *conf = sh->raid_conf; - int firstwrite=0; - - PRINTK("adding bh b#%llu to stripe s#%llu\n", - (unsigned long long)bi->bi_sector, - (unsigned long long)sh->sector); - - - spin_lock(&sh->lock); - spin_lock_irq(&conf->device_lock); - if (forwrite) { - bip = &sh->dev[dd_idx].towrite; - if (*bip == NULL && sh->dev[dd_idx].written == NULL) - firstwrite = 1; - } else - bip = &sh->dev[dd_idx].toread; - while (*bip && (*bip)->bi_sector < bi->bi_sector) { - if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector) - goto overlap; - bip = &(*bip)->bi_next; - } - if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9)) - goto overlap; - - BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next); - if (*bip) - bi->bi_next = *bip; - *bip = bi; - bi->bi_phys_segments ++; - spin_unlock_irq(&conf->device_lock); - spin_unlock(&sh->lock); - - PRINTK("added bi b#%llu to stripe s#%llu, disk %d.\n", - (unsigned long long)bi->bi_sector, - (unsigned long long)sh->sector, dd_idx); - - if (conf->mddev->bitmap && firstwrite) { - sh->bm_seq = conf->seq_write; - bitmap_startwrite(conf->mddev->bitmap, sh->sector, - STRIPE_SECTORS, 0); - set_bit(STRIPE_BIT_DELAY, &sh->state); - } - - if (forwrite) { - /* check if page is covered */ - sector_t sector = sh->dev[dd_idx].sector; - for (bi=sh->dev[dd_idx].towrite; - sector < sh->dev[dd_idx].sector + STRIPE_SECTORS && - bi && bi->bi_sector <= sector; - bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) { - if (bi->bi_sector + (bi->bi_size>>9) >= sector) - sector = bi->bi_sector + (bi->bi_size>>9); - } - if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS) - set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags); - } - return 1; - - overlap: - set_bit(R5_Overlap, &sh->dev[dd_idx].flags); - spin_unlock_irq(&conf->device_lock); - spin_unlock(&sh->lock); - return 0; -} - - -static int page_is_zero(struct page *p) -{ - char *a = page_address(p); - return ((*(u32*)a) == 0 && - memcmp(a, a+4, STRIPE_SIZE-4)==0); -} -/* - * handle_stripe - do things to a stripe. - * - * We lock the stripe and then examine the state of various bits - * to see what needs to be done. - * Possible results: - * return some read request which now have data - * return some write requests which are safely on disc - * schedule a read on some buffers - * schedule a write of some buffers - * return confirmation of parity correctness - * - * Parity calculations are done inside the stripe lock - * buffers are taken off read_list or write_list, and bh_cache buffers - * get BH_Lock set before the stripe lock is released. - * - */ - -static void handle_stripe(struct stripe_head *sh, struct page *tmp_page) -{ - raid6_conf_t *conf = sh->raid_conf; - int disks = conf->raid_disks; - struct bio *return_bi= NULL; - struct bio *bi; - int i; - int syncing; - int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0; - int non_overwrite = 0; - int failed_num[2] = {0, 0}; - struct r5dev *dev, *pdev, *qdev; - int pd_idx = sh->pd_idx; - int qd_idx = raid6_next_disk(pd_idx, disks); - int p_failed, q_failed; - - PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d, qd_idx=%d\n", - (unsigned long long)sh->sector, sh->state, atomic_read(&sh->count), - pd_idx, qd_idx); - - spin_lock(&sh->lock); - clear_bit(STRIPE_HANDLE, &sh->state); - clear_bit(STRIPE_DELAYED, &sh->state); - - syncing = test_bit(STRIPE_SYNCING, &sh->state); - /* Now to look around and see what can be done */ - - rcu_read_lock(); - for (i=disks; i--; ) { - mdk_rdev_t *rdev; - dev = &sh->dev[i]; - clear_bit(R5_Insync, &dev->flags); - - PRINTK("check %d: state 0x%lx read %p write %p written %p\n", - i, dev->flags, dev->toread, dev->towrite, dev->written); - /* maybe we can reply to a read */ - if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) { - struct bio *rbi, *rbi2; - PRINTK("Return read for disc %d\n", i); - spin_lock_irq(&conf->device_lock); - rbi = dev->toread; - dev->toread = NULL; - if (test_and_clear_bit(R5_Overlap, &dev->flags)) - wake_up(&conf->wait_for_overlap); - spin_unlock_irq(&conf->device_lock); - while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) { - copy_data(0, rbi, dev->page, dev->sector); - rbi2 = r5_next_bio(rbi, dev->sector); - spin_lock_irq(&conf->device_lock); - if (--rbi->bi_phys_segments == 0) { - rbi->bi_next = return_bi; - return_bi = rbi; - } - spin_unlock_irq(&conf->device_lock); - rbi = rbi2; - } - } - - /* now count some things */ - if (test_bit(R5_LOCKED, &dev->flags)) locked++; - if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++; - - - if (dev->toread) to_read++; - if (dev->towrite) { - to_write++; - if (!test_bit(R5_OVERWRITE, &dev->flags)) - non_overwrite++; - } - if (dev->written) written++; - rdev = rcu_dereference(conf->disks[i].rdev); - if (!rdev || !test_bit(In_sync, &rdev->flags)) { - /* The ReadError flag will just be confusing now */ - clear_bit(R5_ReadError, &dev->flags); - clear_bit(R5_ReWrite, &dev->flags); - } - if (!rdev || !test_bit(In_sync, &rdev->flags) - || test_bit(R5_ReadError, &dev->flags)) { - if ( failed < 2 ) - failed_num[failed] = i; - failed++; - } else - set_bit(R5_Insync, &dev->flags); - } - rcu_read_unlock(); - PRINTK("locked=%d uptodate=%d to_read=%d" - " to_write=%d failed=%d failed_num=%d,%d\n", - locked, uptodate, to_read, to_write, failed, - failed_num[0], failed_num[1]); - /* check if the array has lost >2 devices and, if so, some requests might - * need to be failed - */ - if (failed > 2 && to_read+to_write+written) { - for (i=disks; i--; ) { - int bitmap_end = 0; - - if (test_bit(R5_ReadError, &sh->dev[i].flags)) { - mdk_rdev_t *rdev; - rcu_read_lock(); - rdev = rcu_dereference(conf->disks[i].rdev); - if (rdev && test_bit(In_sync, &rdev->flags)) - /* multiple read failures in one stripe */ - md_error(conf->mddev, rdev); - rcu_re |