/* * raid10.c : Multiple Devices driver for Linux * * Copyright (C) 2000-2004 Neil Brown * * RAID-10 support for md. * * Base on code in raid1.c. See raid1.c for further copyright information. * * * 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/slab.h>#include <linux/delay.h>#include <linux/blkdev.h>#include <linux/module.h>#include <linux/seq_file.h>#include <linux/ratelimit.h>#include <linux/kthread.h>#include "md.h"#include "raid10.h"#include "raid0.h"#include "bitmap.h" /* * RAID10 provides a combination of RAID0 and RAID1 functionality. * The layout of data is defined by * chunk_size * raid_disks * near_copies (stored in low byte of layout) * far_copies (stored in second byte of layout) * far_offset (stored in bit 16 of layout ) * use_far_sets (stored in bit 17 of layout ) * * The data to be stored is divided into chunks using chunksize. Each device * is divided into far_copies sections. In each section, chunks are laid out * in a style similar to raid0, but near_copies copies of each chunk is stored * (each on a different drive). The starting device for each section is offset * near_copies from the starting device of the previous section. Thus there * are (near_copies * far_copies) of each chunk, and each is on a different * drive. near_copies and far_copies must be at least one, and their product * is at most raid_disks. * * If far_offset is true, then the far_copies are handled a bit differently. * The copies are still in different stripes, but instead of being very far * apart on disk, there are adjacent stripes. * * The far and offset algorithms are handled slightly differently if * 'use_far_sets' is true. In this case, the array's devices are grouped into * sets that are (near_copies * far_copies) in size. The far copied stripes * are still shifted by 'near_copies' devices, but this shifting stays confined * to the set rather than the entire array. This is done to improve the number * of device combinations that can fail without causing the array to fail. * Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk * on a device): * A B C D A B C D E * ... ... * D A B C E A B C D * Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s): * [A B] [C D] [A B] [C D E] * |...| |...| |...| | ... | * [B A] [D C] [B A] [E C D] */ /* * Number of guaranteed r10bios in case of extreme VM load: */#define NR_RAID10_BIOS 256 /* when we get a read error on a read-only array, we redirect to another * device without failing the first device, or trying to over-write to * correct the read error. To keep track of bad blocks on a per-bio * level, we store IO_BLOCKED in the appropriate 'bios' pointer */#define IO_BLOCKED ((struct bio *)1)/* When we successfully write to a known bad-block, we need to remove the * bad-block marking which must be done from process context. So we record * the success by setting devs[n].bio to IO_MADE_GOOD */#define IO_MADE_GOOD ((struct bio *)2) #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) /* When there are this many requests queued 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 int _enough(struct r10conf *conf, int previous, int ignore);static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *skipped);static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);static void end_reshape_write(struct bio *bio, int error);static void end_reshape(struct r10conf *conf); static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data){ 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);} static void r10bio_pool_free(void *r10_bio, void *data){ kfree(r10_bio);} /* Maximum size of each resync request */#define RESYNC_BLOCK_SIZE (64*1024)#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)/* amount of memory to reserve for resync requests */#define RESYNC_WINDOW (1024*1024)/* maximum number of concurrent requests, memory permitting */#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE) /* * When performing a resync, we need to read and compare, so * we need as many pages are there are copies. * When performing a recovery, we need 2 bios, one for read, * one for write (we recover only one drive per r10buf) * */static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data){ struct r10conf *conf = data; struct page *page; struct r10bio *r10_bio; struct bio *bio; int i, j; int nalloc; r10_bio = r10bio_pool_alloc(gfp_flags, conf); if (!r10_bio) return NULL; if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) || test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery)) nalloc = conf->copies; /* resync */ else nalloc = 2; /* recovery */ /* * Allocate bios. */ for (j = nalloc ; j-- ; ) { bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); if (!bio) goto out_free_bio; r10_bio->devs[j].bio = bio; if (!conf->have_replacement) continue; bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); if (!bio) goto out_free_bio; r10_bio->devs[j].repl_bio = bio; } /* * Allocate RESYNC_PAGES data pages and attach them * where needed. */ for (j = 0 ; j < nalloc; j++) { struct bio *rbio = r10_bio->devs[j].repl_bio; bio = r10_bio->devs[j].bio; for (i = 0; i < RESYNC_PAGES; i++) { if (j > 0 && !test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery)) { /* we can share bv_page's during recovery * and reshape */ struct bio *rbio = r10_bio->devs[0].bio; page = rbio->bi_io_vec[i].bv_page; get_page(page); } else page = alloc_page(gfp_flags); if (unlikely(!page)) goto out_free_pages; bio->bi_io_vec[i].bv_page = page; if (rbio) rbio->bi_io_vec[i].bv_page = page; } } return r10_bio; out_free_pages: for ( ; i > 0 ; i--) safe_put_page(bio->bi_io_vec[i-1].bv_page); while (j--) for (i = 0; i < RESYNC_PAGES ; i++) safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page); j = 0;out_free_bio: for ( ; j < nalloc; j++) { if (r10_bio->devs[j].bio) bio_put(r10_bio->devs[j].bio); if (r10_bio->devs[j].repl_bio) bio_put(r10_bio->devs[j].repl_bio); } r10bio_pool_free(r10_bio, conf); return NULL;} static void r10buf_pool_free(void *__r10_bio, void *data){ int i; struct r10conf *conf = data; struct r10bio *r10bio = __r10_bio; int j; for (j=0; j < conf->copies; j++) { struct bio *bio = r10bio->devs[j].bio; if (bio) { for (i = 0; i < RESYNC_PAGES; i++) { safe_put_page(bio->bi_io_vec[i].bv_page); bio->bi_io_vec[i].bv_page = NULL; } bio_put(bio); } bio = r10bio->devs[j].repl_bio; if (bio) bio_put(bio); } r10bio_pool_free(r10bio, conf);} static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio){ int i; for (i = 0; i < conf->copies; i++) { struct bio **bio = & r10_bio->devs[i].bio; if (!BIO_SPECIAL(*bio)) bio_put(*bio); *bio = NULL; bio = &r10_bio->devs[i].repl_bio; if (r10_bio->read_slot < 0 && !BIO_SPECIAL(*bio)) bio_put(*bio); *bio = NULL; }} static void free_r10bio(struct r10bio *r10_bio){ struct r10conf *conf = r10_bio->mddev->private; put_all_bios(conf, r10_bio); mempool_free(r10_bio, conf->r10bio_pool);} static void put_buf(struct r10bio *r10_bio){ struct r10conf *conf = r10_bio->mddev->private; mempool_free(r10_bio, conf->r10buf_pool); lower_barrier(conf);} static void reschedule_retry(struct r10bio *r10_bio){ unsigned long flags; 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); conf->nr_queued ++; spin_unlock_irqrestore(&conf->device_lock, flags); /* wake up frozen array... */ wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread);} /* * raid_end_bio_io() is called when we have finished servicing a mirrored * operation and are ready to return a success/failure code to the buffer * cache layer. */static void raid_end_bio_io(struct r10bio *r10_bio){ struct bio *bio = r10_bio->master_bio; int done; struct r10conf *conf = r10_bio->mddev->private; if (bio->bi_phys_segments) { unsigned long flags; spin_lock_irqsave(&conf->device_lock, flags); bio->bi_phys_segments--; done = (bio->bi_phys_segments == 0); spin_unlock_irqrestore(&conf->device_lock, flags); } else done = 1; if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) clear_bit(BIO_UPTODATE, &bio->bi_flags); if (done) { bio_endio(bio, 0); /* * Wake up any possible resync thread that waits for the device * to go idle. */ allow_barrier(conf); } free_r10bio(r10_bio);} /* * Update disk head position estimator based on IRQ completion info. */static inline void update_head_pos(int slot, struct r10bio *r10_bio){ struct r10conf *conf = r10_bio->mddev->private; conf->mirrors[r10_bio->devs[slot].devnum].head_position = r10_bio->devs[slot].addr + (r10_bio->sectors);} /* * Find the disk number which triggered given bio */static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, struct bio *bio, int *slotp, int *replp){ int slot; int repl = 0; for (slot = 0; slot < conf->copies; slot++) { if (r10_bio->devs[slot].bio == bio) break; if (r10_bio->devs[slot].repl_bio == bio) { repl = 1; break; } } BUG_ON(slot == conf->copies); update_head_pos(slot, r10_bio); if (slotp) *slotp = slot; if (replp) *replp = repl; return r10_bio->devs[slot].devnum;} static void raid10_end_read_request(struct bio *bio, int error){ int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r10bio *r10_bio = bio->bi_private; int slot, dev; struct md_rdev *rdev; struct r10conf *conf = r10_bio->mddev->private; slot = r10_bio->read_slot; dev = r10_bio->devs[slot].devnum; rdev = r10_bio->devs[slot].rdev; /* * this branch is our 'one mirror IO has finished' event handler: */ update_head_pos(slot, r10_bio); if (uptodate) { /* * Set R10BIO_Uptodate in our master bio, so that * we will return a good error code to the higher * levels even if IO on some other mirrored buffer fails. * * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. */ set_bit(R10BIO_Uptodate, &r10_bio->state); } else { /* If all other devices that store this block have * failed, we want to return the error upwards rather * than fail the last device. Here we redefine * "uptodate" to mean "Don't want to retry" */ if (!_enough(conf, test_bit(R10BIO_Previous, &r10_bio->state), rdev->raid_disk)) uptodate = 1; } if (uptodate) { raid_end_bio_io(r10_bio); rdev_dec_pending(rdev, conf->mddev); } else { /* * oops, read error - keep the refcount on the rdev */ char b[BDEVNAME_SIZE]; printk_ratelimited(KERN_ERR "md/raid10:%s: %s: rescheduling sector %llu\n", mdname(conf->mddev), bdevname(rdev->bdev, b), (unsigned long long)r10_bio->sector); set_bit(R10BIO_ReadError, &r10_bio->state); reschedule_retry(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, r10_bio->sectors, !test_bit(R10BIO_Degraded, &r10_bio->state), 0); md_write_end(r10_bio->mddev);} 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)) reschedule_retry(r10_bio); else { close_write(r10_bio); if (test_bit(R10BIO_MadeGood, &r10_bio->state)) reschedule_retry(r10_bio); else raid_end_bio_io(r10_bio); } }} static void raid10_end_write_request(struct bio *bio, int error){ int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r10bio *r10_bio = bio->bi_private; int dev; int dec_rdev = 1; struct r10conf *conf = r10_bio->mddev->private; int slot, repl; struct md_rdev *rdev = NULL; dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); if (repl) rdev = conf->mirrors[dev].replacement; if (!rdev) { smp_rmb(); repl = 0; rdev = conf->mirrors[dev].rdev; } /* * this branch is our 'one mirror IO has finished' event handler: */ if (!uptodate) { if (repl) /* Never record new bad blocks to replacement, * just fail it. */ md_error(rdev->mddev, rdev); else { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); set_bit(R10BIO_WriteError, &r10_bio->state); dec_rdev = 0; } } else { /* * Set R10BIO_Uptodate in our master bio, so that * we will return a good error code for to the higher * levels even if IO on some other mirrored buffer fails. * * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. */ sector_t first_bad; int bad_sectors; /* * Do not set R10BIO_Uptodate if the current device is * rebuilding or Faulty. This is because we cannot use * such device for properly reading the data back (we could * potentially use it, if the current write would have felt * before rdev->recovery_offset, but for simplicity we don't * check this here. */ if (test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags))Lines 1–500 of 4762. Load more
/* * raid10.c : Multiple Devices driver for Linux * * Copyright (C) 2000-2004 Neil Brown * * RAID-10 support for md. * * Base on code in raid1.c. See raid1.c for further copyright information. * * * 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/slab.h> #include <linux/delay.h> #include <linux/blkdev.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/ratelimit.h> #include <linux/kthread.h> #include "md.h" #include "raid10.h" #include "raid0.h" #include "bitmap.h" /* * RAID10 provides a combination of RAID0 and RAID1 functionality. * The layout of data is defined by * chunk_size * raid_disks * near_copies (stored in low byte of layout) * far_copies (stored in second byte of layout) * far_offset (stored in bit 16 of layout ) * use_far_sets (stored in bit 17 of layout ) * * The data to be stored is divided into chunks using chunksize. Each device * is divided into far_copies sections. In each section, chunks are laid out * in a style similar to raid0, but near_copies copies of each chunk is stored * (each on a different drive). The starting device for each section is offset * near_copies from the starting device of the previous section. Thus there * are (near_copies * far_copies) of each chunk, and each is on a different * drive. near_copies and far_copies must be at least one, and their product * is at most raid_disks. * * If far_offset is true, then the far_copies are handled a bit differently. * The copies are still in different stripes, but instead of being very far * apart on disk, there are adjacent stripes. * * The far and offset algorithms are handled slightly differently if * 'use_far_sets' is true. In this case, the array's devices are grouped into * sets that are (near_copies * far_copies) in size. The far copied stripes * are still shifted by 'near_copies' devices, but this shifting stays confined * to the set rather than the entire array. This is done to improve the number * of device combinations that can fail without causing the array to fail. * Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk * on a device): * A B C D A B C D E * ... ... * D A B C E A B C D * Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s): * [A B] [C D] [A B] [C D E] * |...| |...| |...| | ... | * [B A] [D C] [B A] [E C D] */ /* * Number of guaranteed r10bios in case of extreme VM load: */ #define NR_RAID10_BIOS 256 /* when we get a read error on a read-only array, we redirect to another * device without failing the first device, or trying to over-write to * correct the read error. To keep track of bad blocks on a per-bio * level, we store IO_BLOCKED in the appropriate 'bios' pointer */ #define IO_BLOCKED ((struct bio *)1) /* When we successfully write to a known bad-block, we need to remove the * bad-block marking which must be done from process context. So we record * the success by setting devs[n].bio to IO_MADE_GOOD */ #define IO_MADE_GOOD ((struct bio *)2) #define BIO_SPECIAL(bio) ((unsigned long)bio <= 2) /* When there are this many requests queued 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 int _enough(struct r10conf *conf, int previous, int ignore); static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *skipped); static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio); static void end_reshape_write(struct bio *bio, int error); static void end_reshape(struct r10conf *conf); static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data) { 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); } static void r10bio_pool_free(void *r10_bio, void *data) { kfree(r10_bio); } /* Maximum size of each resync request */ #define RESYNC_BLOCK_SIZE (64*1024) #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE) /* amount of memory to reserve for resync requests */ #define RESYNC_WINDOW (1024*1024) /* maximum number of concurrent requests, memory permitting */ #define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE) /* * When performing a resync, we need to read and compare, so * we need as many pages are there are copies. * When performing a recovery, we need 2 bios, one for read, * one for write (we recover only one drive per r10buf) * */ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data) { struct r10conf *conf = data; struct page *page; struct r10bio *r10_bio; struct bio *bio; int i, j; int nalloc; r10_bio = r10bio_pool_alloc(gfp_flags, conf); if (!r10_bio) return NULL; if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) || test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery)) nalloc = conf->copies; /* resync */ else nalloc = 2; /* recovery */ /* * Allocate bios. */ for (j = nalloc ; j-- ; ) { bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); if (!bio) goto out_free_bio; r10_bio->devs[j].bio = bio; if (!conf->have_replacement) continue; bio = bio_kmalloc(gfp_flags, RESYNC_PAGES); if (!bio) goto out_free_bio; r10_bio->devs[j].repl_bio = bio; } /* * Allocate RESYNC_PAGES data pages and attach them * where needed. */ for (j = 0 ; j < nalloc; j++) { struct bio *rbio = r10_bio->devs[j].repl_bio; bio = r10_bio->devs[j].bio; for (i = 0; i < RESYNC_PAGES; i++) { if (j > 0 && !test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery)) { /* we can share bv_page's during recovery * and reshape */ struct bio *rbio = r10_bio->devs[0].bio; page = rbio->bi_io_vec[i].bv_page; get_page(page); } else page = alloc_page(gfp_flags); if (unlikely(!page)) goto out_free_pages; bio->bi_io_vec[i].bv_page = page; if (rbio) rbio->bi_io_vec[i].bv_page = page; } } return r10_bio; out_free_pages: for ( ; i > 0 ; i--) safe_put_page(bio->bi_io_vec[i-1].bv_page); while (j--) for (i = 0; i < RESYNC_PAGES ; i++) safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page); j = 0; out_free_bio: for ( ; j < nalloc; j++) { if (r10_bio->devs[j].bio) bio_put(r10_bio->devs[j].bio); if (r10_bio->devs[j].repl_bio) bio_put(r10_bio->devs[j].repl_bio); } r10bio_pool_free(r10_bio, conf); return NULL; } static void r10buf_pool_free(void *__r10_bio, void *data) { int i; struct r10conf *conf = data; struct r10bio *r10bio = __r10_bio; int j; for (j=0; j < conf->copies; j++) { struct bio *bio = r10bio->devs[j].bio; if (bio) { for (i = 0; i < RESYNC_PAGES; i++) { safe_put_page(bio->bi_io_vec[i].bv_page); bio->bi_io_vec[i].bv_page = NULL; } bio_put(bio); } bio = r10bio->devs[j].repl_bio; if (bio) bio_put(bio); } r10bio_pool_free(r10bio, conf); } static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio) { int i; for (i = 0; i < conf->copies; i++) { struct bio **bio = & r10_bio->devs[i].bio; if (!BIO_SPECIAL(*bio)) bio_put(*bio); *bio = NULL; bio = &r10_bio->devs[i].repl_bio; if (r10_bio->read_slot < 0 && !BIO_SPECIAL(*bio)) bio_put(*bio); *bio = NULL; } } static void free_r10bio(struct r10bio *r10_bio) { struct r10conf *conf = r10_bio->mddev->private; put_all_bios(conf, r10_bio); mempool_free(r10_bio, conf->r10bio_pool); } static void put_buf(struct r10bio *r10_bio) { struct r10conf *conf = r10_bio->mddev->private; mempool_free(r10_bio, conf->r10buf_pool); lower_barrier(conf); } static void reschedule_retry(struct r10bio *r10_bio) { unsigned long flags; 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); conf->nr_queued ++; spin_unlock_irqrestore(&conf->device_lock, flags); /* wake up frozen array... */ wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); } /* * raid_end_bio_io() is called when we have finished servicing a mirrored * operation and are ready to return a success/failure code to the buffer * cache layer. */ static void raid_end_bio_io(struct r10bio *r10_bio) { struct bio *bio = r10_bio->master_bio; int done; struct r10conf *conf = r10_bio->mddev->private; if (bio->bi_phys_segments) { unsigned long flags; spin_lock_irqsave(&conf->device_lock, flags); bio->bi_phys_segments--; done = (bio->bi_phys_segments == 0); spin_unlock_irqrestore(&conf->device_lock, flags); } else done = 1; if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) clear_bit(BIO_UPTODATE, &bio->bi_flags); if (done) { bio_endio(bio, 0); /* * Wake up any possible resync thread that waits for the device * to go idle. */ allow_barrier(conf); } free_r10bio(r10_bio); } /* * Update disk head position estimator based on IRQ completion info. */ static inline void update_head_pos(int slot, struct r10bio *r10_bio) { struct r10conf *conf = r10_bio->mddev->private; conf->mirrors[r10_bio->devs[slot].devnum].head_position = r10_bio->devs[slot].addr + (r10_bio->sectors); } /* * Find the disk number which triggered given bio */ static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio, struct bio *bio, int *slotp, int *replp) { int slot; int repl = 0; for (slot = 0; slot < conf->copies; slot++) { if (r10_bio->devs[slot].bio == bio) break; if (r10_bio->devs[slot].repl_bio == bio) { repl = 1; break; } } BUG_ON(slot == conf->copies); update_head_pos(slot, r10_bio); if (slotp) *slotp = slot; if (replp) *replp = repl; return r10_bio->devs[slot].devnum; } static void raid10_end_read_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r10bio *r10_bio = bio->bi_private; int slot, dev; struct md_rdev *rdev; struct r10conf *conf = r10_bio->mddev->private; slot = r10_bio->read_slot; dev = r10_bio->devs[slot].devnum; rdev = r10_bio->devs[slot].rdev; /* * this branch is our 'one mirror IO has finished' event handler: */ update_head_pos(slot, r10_bio); if (uptodate) { /* * Set R10BIO_Uptodate in our master bio, so that * we will return a good error code to the higher * levels even if IO on some other mirrored buffer fails. * * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. */ set_bit(R10BIO_Uptodate, &r10_bio->state); } else { /* If all other devices that store this block have * failed, we want to return the error upwards rather * than fail the last device. Here we redefine * "uptodate" to mean "Don't want to retry" */ if (!_enough(conf, test_bit(R10BIO_Previous, &r10_bio->state), rdev->raid_disk)) uptodate = 1; } if (uptodate) { raid_end_bio_io(r10_bio); rdev_dec_pending(rdev, conf->mddev); } else { /* * oops, read error - keep the refcount on the rdev */ char b[BDEVNAME_SIZE]; printk_ratelimited(KERN_ERR "md/raid10:%s: %s: rescheduling sector %llu\n", mdname(conf->mddev), bdevname(rdev->bdev, b), (unsigned long long)r10_bio->sector); set_bit(R10BIO_ReadError, &r10_bio->state); reschedule_retry(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, r10_bio->sectors, !test_bit(R10BIO_Degraded, &r10_bio->state), 0); md_write_end(r10_bio->mddev); } 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)) reschedule_retry(r10_bio); else { close_write(r10_bio); if (test_bit(R10BIO_MadeGood, &r10_bio->state)) reschedule_retry(r10_bio); else raid_end_bio_io(r10_bio); } } } static void raid10_end_write_request(struct bio *bio, int error) { int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct r10bio *r10_bio = bio->bi_private; int dev; int dec_rdev = 1; struct r10conf *conf = r10_bio->mddev->private; int slot, repl; struct md_rdev *rdev = NULL; dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl); if (repl) rdev = conf->mirrors[dev].replacement; if (!rdev) { smp_rmb(); repl = 0; rdev = conf->mirrors[dev].rdev; } /* * this branch is our 'one mirror IO has finished' event handler: */ if (!uptodate) { if (repl) /* Never record new bad blocks to replacement, * just fail it. */ md_error(rdev->mddev, rdev); else { set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); set_bit(R10BIO_WriteError, &r10_bio->state); dec_rdev = 0; } } else { /* * Set R10BIO_Uptodate in our master bio, so that * we will return a good error code for to the higher * levels even if IO on some other mirrored buffer fails. * * The 'master' represents the composite IO operation to * user-side. So if something waits for IO, then it will * wait for the 'master' bio. */ sector_t first_bad; int bad_sectors; /* * Do not set R10BIO_Uptodate if the current device is * rebuilding or Faulty. This is because we cannot use * such device for properly reading the data back (we could * potentially use it, if the current write would have felt * before rdev->recovery_offset, but for simplicity we don't * check this here. */ if (test_bit(In_sync, &rdev->flags) && !test_bit(Faulty, &rdev->flags))