Prev: [06/54] x86: Add memory modify constraints to xchg() and cmpxchg()
Next: [099/111] reiserfs: fix oops while creating privroot with selinux enabled
From: Greg KH on 11 Aug 2010 20:10 2.6.34-stable review patch. If anyone has any objections, please let us know. ------------------ From: NeilBrown <neilb(a)suse.de> commit e555190d82c0f58e825e3cbd9e6ebe2e7ac713bd upstream. When a raid1 array is configured to support write-behind on some devices, it normally only reads from other devices. If all devices are write-behind (because the rest have failed) it is possible for a read request to be serviced before a behind-write request, which would appear as data corruption. So when forced to read from a WriteMostly device, wait for any write-behind to complete, and don't start any more behind-writes. Signed-off-by: NeilBrown <neilb(a)suse.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)suse.de> --- drivers/md/bitmap.c | 4 +++- drivers/md/bitmap.h | 1 + drivers/md/raid1.c | 25 ++++++++++++++++++------- 3 files changed, 22 insertions(+), 8 deletions(-) --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1351,7 +1351,8 @@ void bitmap_endwrite(struct bitmap *bitm { if (!bitmap) return; if (behind) { - atomic_dec(&bitmap->behind_writes); + 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); } @@ -1675,6 +1676,7 @@ int bitmap_create(mddev_t *mddev) atomic_set(&bitmap->pending_writes, 0); init_waitqueue_head(&bitmap->write_wait); init_waitqueue_head(&bitmap->overflow_wait); + init_waitqueue_head(&bitmap->behind_wait); bitmap->mddev = mddev; --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -239,6 +239,7 @@ struct bitmap { atomic_t pending_writes; /* pending writes to the bitmap file */ wait_queue_head_t write_wait; wait_queue_head_t overflow_wait; + wait_queue_head_t behind_wait; struct sysfs_dirent *sysfs_can_clear; }; --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -866,6 +866,15 @@ static int make_request(struct request_q } mirror = conf->mirrors + rdisk; + if (test_bit(WriteMostly, &mirror->rdev->flags) && + bitmap) { + /* Reading from a write-mostly device must + * take care not to over-take any writes + * that are 'behind' + */ + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); + } r1_bio->read_disk = rdisk; read_bio = bio_clone(bio, GFP_NOIO); @@ -943,10 +952,14 @@ static int make_request(struct request_q set_bit(R1BIO_Degraded, &r1_bio->state); } - /* do behind I/O ? */ + /* do behind I/O ? + * Not if there are too many, or cannot allocate memory, + * or a reader on WriteMostly is waiting for behind writes + * to flush */ if (bitmap && (atomic_read(&bitmap->behind_writes) < mddev->bitmap_info.max_write_behind) && + !waitqueue_active(&bitmap->behind_wait) && (behind_pages = alloc_behind_pages(bio)) != NULL) set_bit(R1BIO_BehindIO, &r1_bio->state); @@ -2153,15 +2166,13 @@ static int stop(mddev_t *mddev) { conf_t *conf = mddev->private; struct bitmap *bitmap = mddev->bitmap; - int behind_wait = 0; /* wait for behind writes to complete */ - while (bitmap && atomic_read(&bitmap->behind_writes) > 0) { - behind_wait++; - printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop (%d)\n", mdname(mddev), behind_wait); - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_timeout(HZ); /* wait a second */ + if (bitmap && atomic_read(&bitmap->behind_writes) > 0) { + printk(KERN_INFO "raid1: behind writes in progress on device %s, waiting to stop.\n", mdname(mddev)); /* need to kick something here to make sure I/O goes? */ + wait_event(bitmap->behind_wait, + atomic_read(&bitmap->behind_writes) == 0); } raise_barrier(conf); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |