Set the underlying block device "read only" and silently discard writes to the device at the block layer. This allows the block device queue to drain quickly for controlled failback of the device. At one time it was required to avoid crashes in the JBD layer during failover, but it may also be possible to just allow the inflight IO to complete and have Lustre handle this more gracefully. Index: linux-2.6.22.5/block/ll_rw_blk.c =================================================================== --- linux-2.6.22.5.orig/block/ll_rw_blk.c +++ linux-2.6.22.5/block/ll_rw_blk.c @@ -3101,6 +3101,8 @@ static inline int should_fail_request(st #endif /* CONFIG_FAIL_MAKE_REQUEST */ +int dev_check_rdonly(struct block_device *bdev); + /** * generic_make_request: hand a buffer to its device driver for I/O * @bio: The bio describing the location in memory and on the device. @@ -3185,6 +3187,12 @@ end_io: if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags))) goto end_io; + /* this is cfs's dev_rdonly check */ + if (bio->bi_rw == WRITE && + dev_check_rdonly(bio->bi_bdev)) { + bio_endio(bio, bio->bi_size, 0); + break; + } if (should_fail_request(bio)) goto end_io; @@ -3850,6 +3858,91 @@ void swap_io_context(struct io_context * *ioc2 = temp; } EXPORT_SYMBOL(swap_io_context); + /* + * Debug code for turning block devices "read-only" (will discard writes + * silently). This is for filesystem crash/recovery testing. + */ +struct deventry { + dev_t dev; + struct deventry *next; +}; + +static struct deventry *devlist = NULL; +static spinlock_t devlock = SPIN_LOCK_UNLOCKED; + +int dev_check_rdonly(struct block_device *bdev) +{ + struct deventry *cur; + if (!bdev) return 0; + spin_lock(&devlock); + cur = devlist; + while(cur) { + if (bdev->bd_dev == cur->dev) { + spin_unlock(&devlock); + return 1; + } + cur = cur->next; + } + spin_unlock(&devlock); + return 0; +} + +void dev_set_rdonly(struct block_device *bdev) +{ + struct deventry *newdev, *cur; + + if (!bdev) + return; + newdev = kmalloc(sizeof(struct deventry), GFP_KERNEL); + if (!newdev) + return; + + spin_lock(&devlock); + cur = devlist; + while(cur) { + if (bdev->bd_dev == cur->dev) { + spin_unlock(&devlock); + kfree(newdev); + return; + } + cur = cur->next; + } + newdev->dev = bdev->bd_dev; + newdev->next = devlist; + devlist = newdev; + spin_unlock(&devlock); + printk(KERN_WARNING "Turning device %s (%#x) read-only\n", + bdev->bd_disk ? bdev->bd_disk->disk_name : "", bdev->bd_dev); +} + +void dev_clear_rdonly(struct block_device *bdev) +{ + struct deventry *cur, *last = NULL; + if (!bdev) return; + spin_lock(&devlock); + cur = devlist; + while(cur) { + if (bdev->bd_dev == cur->dev) { + if (last) + last->next = cur->next; + else + devlist = cur->next; + spin_unlock(&devlock); + kfree(cur); + printk(KERN_WARNING "Removing read-only on %s (%#x)\n", + bdev->bd_disk ? bdev->bd_disk->disk_name : + "unknown block", bdev->bd_dev); + return; + } + last = cur; + cur = cur->next; + } + spin_unlock(&devlock); +} + +EXPORT_SYMBOL(dev_set_rdonly); +EXPORT_SYMBOL(dev_clear_rdonly); +EXPORT_SYMBOL(dev_check_rdonly); /* * sysfs parts below Index: linux-2.6.22.5/fs/block_dev.c =================================================================== --- linux-2.6.22.5.orig/fs/block_dev.c +++ linux-2.6.22.5/fs/block_dev.c @@ -1294,6 +1294,7 @@ static int __blkdev_put(struct block_dev if (bdev != bdev->bd_contains) victim = bdev->bd_contains; bdev->bd_contains = NULL; + dev_clear_rdonly(bdev); } unlock_kernel(); mutex_unlock(&bdev->bd_mutex); Index: linux-2.6.22.5/include/linux/fs.h =================================================================== --- linux-2.6.22.5.orig/include/linux/fs.h +++ linux-2.6.22.5/include/linux/fs.h @@ -1744,6 +1744,10 @@ struct bio; extern void submit_bio(int, struct bio *); extern int bdev_read_only(struct block_device *); #endif +#define HAVE_CLEAR_RDONLY_ON_PUT +extern void dev_set_rdonly(struct block_device *bdev); +extern int dev_check_rdonly(struct block_device *bdev); +extern void dev_clear_rdonly(struct block_device *bdev); extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int);